diff --git a/.env.sample b/.env.sample
index 4b0f09c32..975096bba 100644
--- a/.env.sample
+++ b/.env.sample
@@ -1,6 +1,7 @@
 DEBUG=True
-PIXL_DICOM_TRANSFER_TIMEOUT=120
-PIXL_QUERY_TIMEOUT=120
+PIXL_DICOM_TRANSFER_TIMEOUT=240
+PIXL_QUERY_TIMEOUT=10
+CLI_RETRY_SECONDS=300
 
 # PIXL PostgreSQL instance
 PIXL_DB_HOST=postgres
@@ -9,14 +10,6 @@ PIXL_DB_USER=pixl
 PIXL_DB_PASSWORD=
 SKIP_ALEMBIC=false
 
-# EMAP UDS
-EMAP_UDS_HOST=
-EMAP_UDS_PORT=
-EMAP_UDS_NAME=
-EMAP_UDS_USER=
-EMAP_UDS_PASSWORD=
-EMAP_UDS_SCHEMA_NAME=
-
 # Exposed ports
 HASHER_API_PORT=
 POSTGRES_PORT=
@@ -52,11 +45,12 @@ ORTHANC_RAW_AE_TITLE=
 ORTHANC_AUTOROUTE_RAW_TO_ANON=true
 ORTHANC_RAW_MAXIMUM_STORAGE_SIZE= // MB
 ORTHANC_RAW_JOB_HISTORY_SIZE=100
-ORTHANC_RAW_CONCURRENT_JOBS=5
+ORTHANC_CONCURRENT_JOBS=20
 ORTHANC_RAW_RECORD_HEADERS=
 ORTHANC_RAW_HEADER_LOG_PATH=
 
 # PIXL Orthanc anon instance
+ORTHANC_ANON_URL=http://orthanc-anon:8042
 ORTHANC_ANON_USERNAME=
 ORTHANC_ANON_PASSWORD=
 ORTHANC_ANON_AE_TITLE=
@@ -67,11 +61,17 @@ STUDY_TIME_OFFSET=
 LOCAL_SALT_VALUE=PIXL
 
 
-# UCVNAQR DICOM node information
-VNAQR_AE_TITLE=
-VNAQR_DICOM_PORT=
-VNAQR_IP_ADDR=
-VNAQR_MODALITY=UCVNAQR
+# UCPRIMARYQR DICOM node information
+PRIMARY_DICOM_SOURCE_AE_TITLE=
+PRIMARY_DICOM_SOURCE_PORT=
+PRIMARY_DICOM_SOURCE_IP_ADDR=
+PRIMARY_DICOM_SOURCE_MODALITY=UCPRIMARYQR
+
+# UCSECONDARYQR DICOM node information - commented out vars are optional
+#SECONDARY_DICOM_SOURCE_AE_TITLE=
+#SECONDARY_DICOM_SOURCE_PORT=
+#SECONDARY_DICOM_SOURCE_IP_ADDR=
+SECONDARY_DICOM_SOURCE_MODALITY=UCSECONDARYQR
 
 # DICOMweb endpoint
 AZ_DICOM_ENDPOINT_NAME=
@@ -88,9 +88,7 @@ RABBITMQ_USERNAME=
 RABBITMQ_PASSWORD=
 
 # Imaging extraction API
-PIXL_DICOM_TRANSFER_TIMEOUT=240
-PIXL_QUERY_TIMEOUT=10
-PIXL_MAX_MESSAGES_IN_FLIGHT=50
+PIXL_MAX_MESSAGES_IN_FLIGHT=5
 
 # Project configs directory
 PROJECT_CONFIGS_DIR=projects/configs
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
new file mode 100644
index 000000000..88370c408
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -0,0 +1,43 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+name: Bug Report
+description: Have you got a bug? Please report it here!
+projects: [ "SAFEHR-data/13" ]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        A clear and concise description of what the bug is. Please use a short, concise title for the bug and elaborate here
+  - type: textarea
+    id: actual_behaviour
+    attributes:
+      label: What happened?
+      description: A clear and concise description of what actually happens.
+      placeholder: "If you have a code sample, error messages, stack traces, please provide it here as well"
+    validations:
+      required: false
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output (optional)
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+    validations:
+      required: false 
+  - type: textarea
+    id: expected_behaviour
+    attributes:
+      label: What did you expect? (optional)
+      description: A clear and concise description of what you expected to happen.
+    validations:
+      required: false
diff --git a/.github/ISSUE_TEMPLATE/feature_request.yaml b/.github/ISSUE_TEMPLATE/feature_request.yaml
new file mode 100644
index 000000000..65dde0108
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/feature_request.yaml
@@ -0,0 +1,51 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+name: Feature Request
+description: Submit a proposal/request for a new feature
+projects: [ "SAFEHR-data/13" ]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        A clear and concise description of the feature proposal
+  - type: textarea
+    id: motivation
+    attributes:
+      label: Motivation
+      description: Please outline the motivation for the proposal. 
+      placeholder: "Is your feature request related to a problem? e.g., I'm always frustrated when [...]. If this is related to another GitHub issue, please link here too"
+    validations:
+      required: true
+  - type: textarea
+    id: pitch
+    attributes:
+      label: Pitch
+      description: A clear and concise description of what you want to happen.
+    validations:
+      required: false
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternatives
+      description: A clear and concise description of any alternative solutions or features you've considered, if any.
+      placeholder:
+    validations:
+      required: false
+  - type: textarea
+    id: additional_context
+    attributes:
+      label: Additional context
+      description: Add any other context or screenshots about the feature request here.
+    validations:
+      required: false
diff --git a/.github/ISSUE_TEMPLATE/voxl.yml b/.github/ISSUE_TEMPLATE/voxl.yml
index c3012d0ca..9fa8da48b 100644
--- a/.github/ISSUE_TEMPLATE/voxl.yml
+++ b/.github/ISSUE_TEMPLATE/voxl.yml
@@ -13,7 +13,7 @@
 #  limitations under the License.
 name: VOXL story
 description: Create a new story or task for VOXL
-projects: [ "UCLH-Foundry/13" ]
+projects: [ "SAFEHR-data/13" ]
 body:
   - type: markdown
     attributes:
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
new file mode 100644
index 000000000..bdf4d2add
--- /dev/null
+++ b/.github/pull_request_template.md
@@ -0,0 +1,28 @@
+<!-- Replace {issue_number} with the issue that will be closed after merging this PR -->
+## Description
+Fixes #{issue_number}: A few words or sentences describing the changes proposed in this pull request (PR).
+
+## Type of change
+Please delete options accordingly to the description.
+
+<!-- Write an `x` in all the boxes that apply -->
+- [ ] Bug fix (non-breaking change which fixes an issue)
+- [ ] New feature (non-breaking change which adds functionality)
+- [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
+- [ ] This change requires a documentation update
+
+
+### Suggested Checklist
+<!-- You do not need to complete all the items by the time you submit the pull request, but most likely the changes will only be merged if all the tasks are done. -->
+
+<!-- Write an `x` in all the boxes that apply -->
+- [ ] I have performed a self-review of my own code.
+- [ ] I have made corresponding changes to the documentation.
+- [ ] My changes generate no new warnings.
+- [ ] I have commented my code, particularly in hard-to-understand areas.
+- [ ] I have passed on my local host device. (see further details at the [CONTRIBUTING](https://github.com/SAFEHR-data/PIXL/blob/main/CONTRIBUTING.md#local-testing) document)
+- [ ] Make sure your branch is up-to-date with main branch. See [CONTRIBUTING](https://github.com/SAFEHR-data/PIXL/blob/main/CONTRIBUTING.md) for a general example to syncronise your branch with the `main` branch.
+- [ ] I have requested review to this PR.
+- [ ] I have addressed and marked as resolved all the review comments in my PR.
+- [ ] Finally, I have selected `squash and merge`
+
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index f0f592a2e..f95ad02ef 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -17,6 +17,7 @@ on:
     push:
         branches:
             - main
+            - "renovate/**"
     pull_request:
     workflow_dispatch:
 
@@ -27,14 +28,14 @@ concurrency:
 
 jobs:
     lint:
-        runs-on: ubuntu-22.04
+        runs-on: ubuntu-24.04
         timeout-minutes: 5
         steps:
             - name: Checkout
-              uses: actions/checkout@v4
+              uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
 
             - name: Run pre-commit
-              uses: pre-commit/action@v3.0.1
+              uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
               with:
                   extra_args: --all-files
 
@@ -45,18 +46,18 @@ jobs:
                   docker compose config --quiet
 
     test:
-        runs-on: ubuntu-22.04
+        runs-on: ubuntu-24.04
         timeout-minutes: 30
         strategy:
             fail-fast: false # run all tests if even if one fails
             matrix:
-                package_dir: [pixl_core, hasher, pixl_dcmd, cli, pixl_export, pixl_imaging]
+                package_dir: [pixl_core, hasher, pixl_dcmd, cli, pixl_export, pixl_imaging, pytest-pixl]
 
         steps:
-            - uses: actions/checkout@v4
+            - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
 
             - name: Init Python
-              uses: actions/setup-python@v5
+              uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
               with:
                   python-version: "3.11"
                   cache: "pip"
@@ -70,14 +71,14 @@ jobs:
 
             - name: Run tests and generate coverage report
               working-directory: ${{ matrix.package_dir }}
-              run: pytest --cov --cov-report=xml
+              run: COV_CORE_SOURCE=src COV_CORE_CONFIG=.coveragerc COV_CORE_DATAFILE=.coverage.eager pytest --cov=src --cov-append --cov-report=xml --cov-report=term-missing
               env:
                   ENV: test
                   AZURE_KEY_VAULT_NAME: test
                   AZURE_KEY_VAULT_SECRET_NAME: test
 
             - name: Upload coverage reports to Codecov
-              uses: codecov/codecov-action@v4.2.0
+              uses: codecov/codecov-action@7f8b4b4bde536c465e797be725718b88c5d95e0e # v5.1.1
               with:
                   directory: ${{ matrix.package_dir }}
               env:
@@ -85,13 +86,13 @@ jobs:
 
     system-test:
         if: ${{ ! github.event.pull_request.draft || contains(github.event.pull_request.title, '[force-system-test]') }}
-        runs-on: ubuntu-22.04
+        runs-on: ubuntu-24.04
         timeout-minutes: 30
         steps:
-            - uses: actions/checkout@v4
-            - uses: docker/setup-buildx-action@v3
+            - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+            - uses: docker/setup-buildx-action@c47758b77c9736f4b2ef4073d4d51994fabfe349 # v3
             - name: Init Python
-              uses: actions/setup-python@v5
+              uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5
               with:
                   python-version: "3.11"
                   cache: "pip"
@@ -131,23 +132,54 @@ jobs:
                   ./run-system-test.sh coverage
                   echo FINISHED SYSTEM TEST SCRIPT
 
-            - name: Dump export-api docker logs for debugging
+            - name: Dump queue docker logs for debugging
               if: ${{ failure() }}
               run: |
-                  docker logs -t system-test-export-api-1 2>&1
+                  docker logs -t system-test-queue-1 2>&1
 
-            - name: Dump orthanc-anon docker logs for debugging
+            - name: Dump postgres docker logs for debugging
               if: ${{ failure() }}
               run: |
-                  docker logs -t system-test-orthanc-anon-1 2>&1
+                  docker logs -t system-test-postgres-1 2>&1
 
             - name: Dump imaging-api docker logs for debugging
               if: ${{ failure() }}
               run: |
                   docker logs -t system-test-imaging-api-1 2>&1
 
+            - name: Dump orthanc-raw docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-orthanc-raw-1 2>&1
+
+            - name: Dump orthanc-anon docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-orthanc-anon-1 2>&1
+
+            - name: Dump hasher-api docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-hasher-api-1 2>&1
+
+            - name: Dump export-api docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-export-api-1 2>&1
+
+            - name: Dump VNA docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-vna-qr-1 2>&1
+
+            - name: Dump DICOMWeb docker logs for debugging
+              if: ${{ failure() }}
+              run: |
+                  docker logs -t system-test-dicomweb-server-1 2>&1
+
+
             - name: Upload coverage reports to Codecov
-              uses: codecov/codecov-action@v4.2.0
+              uses: codecov/codecov-action@7f8b4b4bde536c465e797be725718b88c5d95e0e # v5.1.1
               with:
                 directory: test
               env:
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index cd91f08da..720ba6df4 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -14,7 +14,7 @@
 ---
 repos:
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.3.3
+      rev: v0.5.5
       hooks:
           - id: ruff-format
           - id: ruff
@@ -22,7 +22,7 @@ repos:
                 - --fix
 
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.9.0
+      rev: v1.11.1
       hooks:
           - id: mypy
             entry: mypy .
@@ -30,12 +30,21 @@ repos:
             pass_filenames: false
             additional_dependencies:
                 [
-                    "mypy==1.9.0",
+                    "mypy==1.11.1",
                     "types-PyYAML",
                     "types-requests",
                     "types-python-slugify",
                     "types-psycopg2",
                 ]
+    - repo: https://github.com/python-jsonschema/check-jsonschema
+      rev: 0.28.6
+      hooks:
+        # Schemas taken from https://www.schemastore.org/json/
+        - id: check-jsonschema
+          name: "Validate GitHub issue templates"
+          files: ^\.github/ISSUE_TEMPLATE/.*\.yml$
+          exclude: ^\.github/ISSUE_TEMPLATE/config\.yml$
+          args: ["--verbose", "--schemafile", "schemas/github-issue-forms.json"]
 
     - repo: local
       hooks:
diff --git a/.renovaterc.json5 b/.renovaterc.json5
new file mode 100644
index 000000000..ed970c527
--- /dev/null
+++ b/.renovaterc.json5
@@ -0,0 +1,37 @@
+{
+  $schema: "https://docs.renovatebot.com/renovate-schema.json",
+  extends: [
+    "github>UCL-ARC/.github//renovate/default-config.json",
+    ":assignAndReview(team:arc-dev)",
+    "group:allNonMajor"
+  ],
+  customDatasources: {
+    dicomSpec: {
+      defaultRegistryUrlTemplate: "https://dicom.nema.org/medical/dicom",
+      format: "html",
+    },
+  },
+  customManagers: [
+    {
+      customType: "regex",
+      description: "Update DICOM Spec edition used for validation",
+      fileMatch: [
+        "orthanc/orthanc-anon/plugin/download_dicom_spec.py",
+        "pixl_dcmd/src/pixl_dcmd/main.py",
+      ],
+      matchStrings: [
+        'edition\\s?=\\s?"(?<currentValue>.*?)"\n',
+        '.*\\(edition\\s?=\\s?"(?<currentValue>.*?)"\\)\n',
+      ],
+      depNameTemplate: "dicomSpec",
+      datasourceTemplate: "custom.dicomSpec",
+    },
+  ],
+  packageRules: [
+    {
+      matchDatasources: ["custom.dicomSpec"],
+      extractVersion: "/medical/dicom/(?<version>\\d{4}[a-z])/",
+      versioning: "loose",
+    }
+  ]
+}
diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md
new file mode 100644
index 000000000..d6e177944
--- /dev/null
+++ b/CODE_OF_CONDUCT.md
@@ -0,0 +1,77 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to make participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, sex characteristics, gender identity and expression,
+level of experience, education, socio-economic status, nationality, personal
+appearance, race, religion, or sexual identity and orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+  advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies within all project spaces, and it also applies when
+an individual is representing the project or its community in public spaces.
+Examples of representing a project or community include using an official
+project e-mail address, posting via an official social media account, or acting
+as an appointed representative at an online or offline event. Representation of
+a project may be further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team opening a [new issue](https://github.com/SAFEHR-data/PIXL/issues/new/choose). 
+All complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see
+https://www.contributor-covenant.org/faq
+
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
new file mode 100644
index 000000000..3fd071858
--- /dev/null
+++ b/CONTRIBUTING.md
@@ -0,0 +1,78 @@
+# Contributing to `PIXL`.
+
+👍🎉 First off, thanks for taking the time to contribute! 🎉👍
+
+When contributing to this repository, please first discuss the change you wish to make via issue, instant message in clara-agx chatbox, or any other method with the owners of this repository before making a change. 
+Please note we have a [code of conduct](CODE_OF_CONDUCT.md), please follow it in all your interactions with the project.
+
+## :octocat: Setting up project locally. 
+1. Generate your SSH keys as suggested [here](https://docs.github.com/en/github/authenticating-to-github/generating-a-new-ssh-key-and-adding-it-to-the-ssh-agent)
+2. Clone the repository by typing (or copying) the following lines in a terminal
+```
+git clone git@github.com:SAFEHR-data/PIXL.git
+```
+
+## New issues
+* Open an issue (bug report, feature request, or something is not working): https://github.com/SAFEHR-data/PIXL/issues/new/choose 
+* Workflow for issue management 
+```mermaid
+  flowchart TD;
+      Z[Bug Reported] -->A[...];  
+      A[Bug resolution] -->B(Testing OK?);
+      B--Yes-->C[Prepare commit];
+      B--No-->D[Reopen issue];
+      D----> A[Bug resolution];
+      C ----> E[Request Review];
+      E ----> F[Commit changes];
+      F --> H[Merge PR and close issue]
+```  
+
+## Committing and pushing changes 
+The following commands are typed or copied via command line. 
+Altenatively, you can use the features of your integrated development environment (pycharm, code, vim, etc).
+
+1. Clone this repo 
+```
+git clone git@github.com:SAFEHR-data/PIXL.git
+``` 
+2. Create new branch `{FEATURE_BRANCH_NAME}` using issue number `{ISSUE_NUMBER}`
+```
+git checkout -b ISSUE_NUMBER-FEATURE_BRANCH_NAME #(e.g. `git checkout -b 422-my-feature-branch`)
+```
+3. Commit changes and push to your branch
+```
+git add .
+git commit -m 'short message #ISSUE_NUMBER' #(e.g. git commit -m 'adding a message to my feature branch #422' 
+git push origin ISSUENUMBER-branch-name
+```
+4. Submit a Pull Request against the `main` branch. 
+
+## Pull Request (PR) and merge to `main` branch
+1. Select branch that contain your commits.
+2. Click `Compare and pull request` and create PR for the associated branch.
+3. Type a title and description of your PR and create PR
+4. Please keep your PR in sync with the base branch.
+It is recommended that you use [Squashing and merging a long-running branch](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/incorporating-changes-from-a-pull-request/about-pull-request-merges#squashing-and-merging-a-long-running-branch).
+Otherwise, you have the option to rebase your `{ISSUE_NUMBER-FEATURE_BRANCH_NAME}` branch with the base branch (e.g. `main`).
+```
+git checkout main
+git pull origin main
+git checkout ISSUE_NUMBER-FEATURE_BRANCH #(e.g. git checkout 422-my-feature-branch)
+git fetch
+git merge main
+git push --force origin FEATURE_BRANCH
+```
+5. Run `pre-commit run -a` to tidy up code and documentation (this is also tested in [CI](https://github.com/SAFEHR-data/PIXL/blob/main/.github/workflows/main.yml)).
+6. If you are developing in your local host, please check that your code is properly tested with `pytest` (this is also tested in [CI](https://github.com/SAFEHR-data/PIXL/blob/main/.github/workflows/main.yml)).
+7. Request a PR review.
+See [collaborating-with-pull-requests](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests) for further details.
+8. Once your PRs has been approved, procced to merge it to main. See [Merging a pull request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/incorporating-changes-from-a-pull-request/merging-a-pull-request)
+9. Delete and remove your merged branch   
+9.1 You can navigate branches in https://github.com/SAFEHR-data/PIXL/branches and removed merged branches by clickling :wastebasket: icon.    
+9.2 Alternatively, you can delete your local and merged branches using the following commands:     
+```
+#Local git clear
+git branch --merged | grep -v '\*\|master\|main\|develop' | xargs -n 1 git branch -d
+#Remote git clear
+git branch -r --merged | grep -v '\*\|master\|main\|develop' | sed 's/origin\///' | xargs -n 1 git push --delete origin
+```
diff --git a/README.md b/README.md
index 597e63b53..e9a30860d 100644
--- a/README.md
+++ b/README.md
@@ -1,42 +1,38 @@
-[![pixl-ci](https://github.com/UCLH-Foundry/PIXL/actions/workflows/main.yml/badge.svg)](https://github.com/UCLH-Foundry/PIXL/actions/workflows/main.yml)
-[![codecov](https://codecov.io/gh/UCLH-Foundry/PIXL/graph/badge.svg?token=99CHF3ZCAW)](https://codecov.io/gh/UCLH-Foundry/PIXL)
+[![pixl-ci](https://github.com/SAFEHR-data/PIXL/actions/workflows/main.yml/badge.svg)](https://github.com/SAFEHR-data/PIXL/actions/workflows/main.yml)
+[![codecov](https://codecov.io/gh/SAFEHR-data/PIXL/graph/badge.svg?token=99CHF3ZCAW)](https://codecov.io/gh/SAFEHR-data/PIXL)
 
 # PIXL
 
 PIXL Image eXtraction Laboratory
 
 `PIXL` is a system for extracting, linking and de-identifying DICOM imaging data, structured EHR data and free-text data from radiology reports at UCLH.
-Please see the [rolling-skeleton]([https://github.com/UCLH-Foundry/the-rolling-skeleton=](https://github.com/UCLH-Foundry/the-rolling-skeleton/blob/main/docs/design/100-day-design.md)) for more details.
+Please see the [rolling-skeleton]([https://github.com/SAFEHR-data/the-rolling-skeleton=](https://github.com/SAFEHR-data/the-rolling-skeleton/blob/main/docs/design/100-day-design.md)) for more details.
 
-PIXL is intended run on one of the [GAE](https://github.com/UCLH-Foundry/Book-of-FlowEHR/blob/main/glossary.md#gaes)s and comprises
+PIXL is intended run on one of the [GAE (General Application Environments)](https://github.com/SAFEHR-data/Book-of-FlowEHR/blob/main/glossary.md#gaes)s and comprises
 several services orchestrated by [Docker Compose](https://docs.docker.com/compose/).
 
-To get access to the GAE, [see the documentation on Slab](https://uclh.slab.com/posts/gae-access-7hkddxap)
+To get access to the GAE, [see the documentation on Slab](https://uclh.slab.com/posts/gae-access-7hkddxap). 
+Please request access to Slab and add further details in a [new blank issue](https://github.com/SAFEHR-data/PIXL/issues/new).
 
-## Development
-
-[Follow the developer setup instructions](./docs/setup/developer.md).
+## Installation
 
-Before raising a PR, make sure to **run the tests** for the PIXL module you have been working on .
-In addition, make sure to [have `pre-commit` installed](/docs/setup/developer.md#linting) to
-automatically check your code before committing.
-
-You can run all tests from the root of the repo with:
+Install the PIXL Python modules by running the following commands from the top-level `PIXL/` directory:
 
 ```shell
-pytest
+python -m pip install -e pixl_core/
+python -m pip install -e cli/
 ```
 
-The `pytest.ini` file in the root of the repo contains the configuration for running all tests at once.
+Note, the CLI currently [needs to be installed in editable mode](https://github.com/SAFEHR-data/PIXL/issues/318).
 
-We run [pre-commit](https://pre-commit.com/) as part of the GitHub Actions CI. To install and run it locally, do:
+## Development
 
-```shell
-pip install pre-commit
-pre-commit install
-```
+[Follow the developer setup instructions](./docs/setup/developer.md).
+
+Before raising a PR, make sure to **run the tests** for every PIXL module, not just the one you
+have been working on. In addition, make sure to [have `pre-commit` installed](/docs/setup/developer.md#linting)
+to automatically check your code before committing.
 
-The configuration can be found in [`.pre-commit-config.yml`](./.pre-commit-config.yaml)
 
 ## Design
 
@@ -83,7 +79,10 @@ HTTP API to export files (parquet and DICOM) from UCLH to endpoints.
 
 HTTP API to process messages from the `imaging` queue and populate the raw orthanc instance with images from PACS/VNA.
 
-## Setup
+## Setup `PIXL` in GAE
+
+<details>
+  <summary>Click here to expand steps and configurations</summary>
 
 ### 0. [UCLH infrastructure setup](./docs/setup/uclh-infrastructure-setup.md)
 
@@ -139,10 +138,12 @@ To configure a new project, follow these steps:
     >[!NOTE]
     > The project slug should match the [slugify](https://github.com/un33k/python-slugify)-ed project name in the `extract_summary.json` log file!
 
-2. [Open a PR in PIXL](https://github.com/UCLH-Foundry/PIXL/compare) to merge the new project config into `main`
+2. [Open a PR in PIXL](https://github.com/SAFEHR-data/PIXL/compare) to merge the new project config into `main`
 
 #### The config YAML file
 
+<details><summary>The config YAML file</summary>
+<p>
 The configuration file defines:
 
 - Project name: the `<project-slug>` name of the Project
@@ -174,13 +175,19 @@ The configuration file defines:
   [parquet files](./docs/file_types/parquet_files.md). We currently support the following endpoints:
     - `"none"`: no upload
     - `"ftps"`: a secure FTP server (for both _DICOM_ and _parquet_ files)
+    - `"dicomweb"`: a DICOMweb server (for _DICOM_ files only).
+      Requires the `DICOMWEB_*` environment variables to be set in `.env`
+    - `"xnat"`: an [XNAT](https://www.xnat.org/) instance (for _DICOM_ files only)
     <!-- - `"azure"`: a secure Azure Dicom web service (for both _DICOM_ and _parquet_ files) -->
     <!--   Requires the `AZURE_*` environment variables to be set in `.env` -->
-    <!-- - `"dicomweb"`: a DICOMweb server (for _DICOM_ files only) -->
-    <!--   Requires the `DICOMWEB_*` environment variables to be set in `.env` -->
+</p>
+</details> 
 
 #### Project secrets
 
+<details><summary>Project secrets</summary>
+<p>
+
 Any credentials required for uploading the project's results should be stored in an **Azure Key Vault**
 (set up instructions below).
 PIXL will query this key vault for the required secrets at runtime. This requires the following
@@ -206,15 +213,22 @@ This kevyault is configured with the following environment variables:
 - `HASHER_API_AZ_KEY_VAULT_NAME` the name of the key vault, used to connect to the correct key vault
 
 See the [hasher documentation](./hasher/README.md) for more information.
+</p>
+</details> 
+
+</details>
 
-## Run
+## Run `PIXL` in GAE
+
+<details>
+  <summary>Click here to view detailed steps</summary>
 
 ### Start
 
 From the _PIXL_ directory:
 
-```bash
-bin/pixldc pixl_dev up
+```shell
+pixl dc up
 ```
 
 Once the services are running, you can interact with the services using the [`pixl` CLI](./cli/README.md).
@@ -223,10 +237,13 @@ Once the services are running, you can interact with the services using the [`pi
 
 From the _PIXL_ directory:
 
-```bash
-bin/pixldc pixl_dev down
+```shell
+pixl dc down  # --volumes to remove all data volumes
 ```
 
+</details>
+
+
 ## Analysis
 
 The number of DICOM instances in the raw Orthanc instance can be accessed from
@@ -292,3 +309,11 @@ be uploaded to the FTP server at the following path:
 FTPROOT/PROJECT_SLUG/EXTRACT_DATETIME/parquet/radiology/radiology.parquet
 ..............................................omop/public/*.parquet
 ```
+
+## :octocat: Cloning repository
+* Generate your SSH keys as suggested [here](https://docs.github.com/en/github/authenticating-to-github/generating-a-new-ssh-key-and-adding-it-to-the-ssh-agent)
+* Clone the repository by typing (or copying) the following lines in a terminal
+```
+git clone git@github.com:SAFEHR-data/PIXL.git
+```
+
diff --git a/bin/pixldc b/bin/pixldc
deleted file mode 100755
index 578588071..000000000
--- a/bin/pixldc
+++ /dev/null
@@ -1,66 +0,0 @@
-#!/usr/bin/env python3
-#  Copyright (c) University College London Hospitals NHS Foundation Trust
-#
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
-"""A wrapper around docker compose that sets the correct directory and environment"""
-
-import argparse
-import os
-import sys
-from pathlib import Path
-
-from loguru import logger
-
-ALLOWED_PROJECT_NAMES = ["pixl_dev", "pixl_test", "pixl_prod"]
-parser = argparse.ArgumentParser(description="Wrapper around docker compose for pixl")
-parser.add_argument("--debug", action="store_true", help="print debugging for this wrapper")
-parser.add_argument(
-    "project",
-    choices=ALLOWED_PROJECT_NAMES,
-    help="Which project to run this docker compose command on",
-)
-parser.add_argument("command", help="Which docker compose command to run")
-args, unknown_args = parser.parse_known_args()
-
-logging_level = "INFO" if not args.debug else "DEBUG"
-logger.remove()  # Remove all handlers
-logger.add(sys.stderr, level=logging_level)
-
-BIN_DIR = Path(__file__).parent.absolute()
-os.chdir(BIN_DIR)
-PROJECT_DIR = BIN_DIR.parent.absolute()
-COMPOSE_FILE = PROJECT_DIR / "docker-compose.yml"
-
-# The first arg is necessary even if it looks repetitive! Equivalent to bash's $0.
-docker_args = [
-    "docker",
-    "compose",
-    "--file",
-    COMPOSE_FILE,
-    "--project-name",
-    args.project,
-    args.command,
-]
-
-# up gets these options for free
-if args.command == "up":
-    docker_args.extend(["--remove-orphans", "--abort-on-container-exit", "--build"])
-
-# add on the user's extra args
-docker_args.extend(unknown_args)
-
-logger.debug("args = {}", args)
-logger.debug("extra args = {}", unknown_args)
-logger.debug("about to run with docker: {}", docker_args)
-
-os.execvp("docker", docker_args)  # noqa: S606, S607 this is what the previous script was doing
diff --git a/cli/README.md b/cli/README.md
index 77847c3f8..374c358bd 100644
--- a/cli/README.md
+++ b/cli/README.md
@@ -1,40 +1,38 @@
 # PIXL Driver + Command line interface
 
 The PIXL CLI driver provides functionality to populate a queue with messages containing information
-required to run electronic health queries against the EMAP star database and the VNA image system.
+required to run electronic health queries against the VNA image system.
 Once a set of queues are populated the consumers can be started, updated and the system extractions
 stopped cleanly.
 
 ## Prerequisites
-
-`PIXL CLI` requires Python version 3.10.
-
-Running the tests requires [docker](https://docs.docker.com/get-docker/) to be installed.
-
-## Installation
-
-We recommend installing in a project specific virtual environment created using a environment
+* Python version 3.11 (matching python versions in [pixl-ci](../.github/workflows/main.yml) and [dev](../docs/setup/developer.md#installation-of-pixl-modules)).
+* [Docker](https://docs.docker.com/get-docker/) with version `>=27.0.3`
+* [Docker Compose](https://docs.docker.com/compose/install/#installation-scenarios) with version `>=v2.28.1-desktop.1`
+* We recommend installing PIXL project in specific virtual environment using a environment
 management tool such as [conda](https://docs.conda.io/en/latest/) or
-[virtualenv](https://virtualenv.pypa.io/en/latest/).
-
-Then install in editable mode by running
+[virtualenv](https://virtualenv.pypa.io/en/latest/). 
+See detailed instructions [here](../docs/setup/developer.md#setting-up-python-virtual-environment)
 
+## Installation
+Activate your python virtual environment and install `PIXL` project in editable mode by running
 ```bash
-pip install -e ../pixl_core/ -e .
+python -m pip install -e ../pixl_core -e .
 ```
 
 ## Usage
 
-> **Note** The `rabbitmq`, `export-api` and `imaging-api` services must be started prior to using the CLI
-> This is typically done by spinning up the necessary Docker containers through `docker compose`.
-> For convenience, we provide the [`bin/pixldc`](../bin/pixldc) script to spin up the relevant
-> services in production.
+**Note** The `rabbitmq`, `export-api` and `imaging-api` services must be started prior to using the CLI
+This is done by spinning up the necessary Docker containers through `docker compose`.
+For convenience, we provide the `pixl dc` command, which acts as a wrapper for `docker compose`,
+but takes care of some of the configuration for you.
 
 See the commands and subcommands with
 
 ```bash
 pixl --help
 ```
+
 ### Configuration
 
 The `rabbitmq` and `postgres` services are configured by setting the following environment variables
@@ -65,7 +63,7 @@ where the `*_RATE` variables set the default querying rate for the message queue
 
 ### Running the pipeline
 
-Populate queue for Imaging
+Populate queue for Imaging using parquet files:
 
 ```bash
 pixl populate </path/to/parquet_dir>
@@ -83,6 +81,16 @@ parquet_dir
     └── PROCEDURE_OCCURRENCE.parquet
 ```
 
+Alternatively, the queue can be populated based on records in CSV files:
+
+```bash
+pixl populate <path/to/file.csv>
+```
+
+One advantage of using a CSV file is that multiple projects can be listed
+for export in the file. Using the parquet format, in contrast, only supports
+exporting a single project per call to `pixl populate`.
+
 Extraction will start automatically after populating the queues.  If granular
 customisation of the rate per queue is required or a queue should not be started
 then supply the argument `--no-start` and use `pixl start...` to launch
@@ -101,43 +109,36 @@ Stop Imaging extraction
 pixl stop
 ```
 
-## Development
+### High-priority messages
 
-The CLI is created using [click](https://click.palletsprojects.com/en/8.0.x/), and curently provides
-the following commands:
+By default, messages will be sent to the queue with the lowest priority (1).
 
-```sh
-$ pixl --help
-Usage: pixl [OPTIONS] COMMAND [ARGS]...
-
-  PIXL command line interface
-
-Options:
-  --debug / --no-debug
-  --help                Show this message and exit.
-
-Commands:
-  extract-radiology-reports  Export processed radiology reports to...
-  kill                       Stop all the PIXL services
-  populate                   Populate a (set of) queue(s) from a parquet...
-  start                      Start consumers for a set of queues
-  status                     Get the status of the PIXL consumers
-  stop                       Stop extracting data
-  update                     Update one or a list of consumers with a...
+To send to the queue with a different priority, you can use the `--priority` argument to
+`populate`:
+
+```bash
+pixl populate --priority 5 <path/to/file.csv>
 ```
 
-Install locally in editable mode with the development and testing dependencies by running
+`priority` must be an integer between 1 and 5, with 5 being the highest priority.
 
+## Development
+### Help commands
+The CLI is created using [click](https://click.palletsprojects.com/en/8.0.x/). To see which commands
+are currently available, you can use the `pixl --help` command:
+
+### Local installation
+Activate your python environment and install project locally in editable mode with the development and testing dependencies by running
 ```bash
-pip install -e ../pixl_core/ -e .[test]
+python -m pip install -e ../pixl_core -e ../pytest-pixl -e ".[test]" -e ".[dev]"
 ```
 
 ### Running tests
-
 The CLI tests require a running instance of the `rabbitmq` service, for which we provide a
 `docker-compose` [file](./tests/docker-compose.yml). The service is automatically started by the
 `run_containers` _pytest_ fixture. So to run the tests, run
 
 ```bash
-pytest
+pytest -vs tests #for all tests
+pytest -vs tests/test_docker_commands.py #e.g., for particular tests
 ```
diff --git a/cli/pyproject.toml b/cli/pyproject.toml
index 638daee06..4b7888a5d 100644
--- a/cli/pyproject.toml
+++ b/cli/pyproject.toml
@@ -1,26 +1,24 @@
 [project]
 name = "pixl_cli"
-version = "0.0.4"
+version = "0.2.0rc0"
 authors = [{ name = "PIXL authors" }]
 description = "PIXL command line interface"
 readme = "README.md"
 requires-python = ">=3.10"
 classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "core",
-    "click==8.1.3",
+    "core==0.2.0rc0",
+    "click==8.1.7",
+    "tqdm==4.67.1",
 ]
 
 [project.optional-dependencies]
 test = [
-    "pytest==7.4.*",
-    "pytest-mock==3.12.*",
-    "pytest-pixl"
+    "core[test]==0.2.0rc0",
+    "pytest-mock==3.14.*",
 ]
 dev = [
-    "mypy",
-    "pre-commit",
-    "ruff",
+    "core[dev]==0.2.0rc0",
 ]
 
 [project.scripts]
@@ -29,3 +27,19 @@ pixl = "pixl_cli.main:cli"
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
+
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
diff --git a/cli/src/pixl_cli/_config.py b/cli/src/pixl_cli/_config.py
index a5dab35ec..7a4f578cc 100644
--- a/cli/src/pixl_cli/_config.py
+++ b/cli/src/pixl_cli/_config.py
@@ -68,7 +68,11 @@ def base_url(self) -> str:
 
 def api_config_for_queue(queue_name: str) -> APIConfig:
     """Configuration for an API associated with a queue"""
-    api_name = f"{queue_name}_api"
+    api_name = {
+        "export": "export_api",
+        "imaging-primary": "imaging_api",
+        "imaging-secondary": "imaging_api",
+    }[queue_name]
 
     if api_name not in API_CONFIGS:
         msg = (
diff --git a/cli/src/pixl_cli/_database.py b/cli/src/pixl_cli/_database.py
index cc8ecd0b7..4c9c6e197 100644
--- a/cli/src/pixl_cli/_database.py
+++ b/cli/src/pixl_cli/_database.py
@@ -16,9 +16,9 @@
 
 from typing import cast
 
+import pandas as pd
 from core.db.models import Extract, Image
-from core.patient_queue.message import Message
-from sqlalchemy import URL, create_engine
+from sqlalchemy import URL, create_engine, not_, select
 from sqlalchemy.orm import Session, sessionmaker
 
 from pixl_cli._config import SERVICE_SETTINGS
@@ -37,88 +37,123 @@
 engine = create_engine(url)
 
 
-def filter_exported_or_add_to_db(messages: list[Message], project_slug: str) -> list[Message]:
+def filter_exported_or_add_to_db(messages_df: pd.DataFrame) -> pd.DataFrame:
     """
-    Filter exported images for this project, and adds missing extract or images to database.
+    Filter exported images for multiple projects, and adds missing extract and images to database.
 
     :param messages: Initial messages to filter if they already exist
-    :param project_slug: project slug to query on
-    :return messages that have not been exported
+    :return DataFrame of messages that have not been exported
     """
     PixlSession = sessionmaker(engine)
     with PixlSession() as pixl_session, pixl_session.begin():
-        extract, extract_created = _get_or_create_project(project_slug, pixl_session)
-
-        return _filter_exported_messages(
-            extract, messages, pixl_session, extract_created=extract_created
-        )
-
+        messages_dfs = [
+            _filter_exported_or_add_to_db_for_project(
+                pixl_session, project_messages_df, project_slug
+            )
+            for project_slug, project_messages_df in messages_df.groupby("project_name")
+        ]
+    return pd.concat(messages_dfs)
+
+
+def _filter_exported_or_add_to_db_for_project(
+    session: Session, messages_df: pd.DataFrame, project_slug: str
+) -> pd.DataFrame:
+    """
+    Filter exported images for this project, and adds missing extract and images to database.
 
-def _get_or_create_project(project_slug: str, session: Session) -> tuple[Extract, bool]:
-    existing_extract = session.query(Extract).filter(Extract.slug == project_slug).one_or_none()
-    if existing_extract:
-        return existing_extract, False
-    new_extract = Extract(slug=project_slug)
-    session.add(new_extract)
-    return new_extract, True
+    :param session: SQLAlchemy session
+    :param messages: Initial messages to filter if they already exist
+    :param project_slug: project slug to query on
+    :return DataFrame of messages that have not been exported for this project
+    """
+    extract = session.query(Extract).filter(Extract.slug == project_slug).one_or_none()
+    if extract:
+        db_images_df = all_images_for_project(project_slug)
+        missing_images_df = _filter_existing_images(messages_df, db_images_df)
+        messages_df = _filter_exported_messages(messages_df, db_images_df)
+    else:
+        # We need to add the extract to the database and retrive it again so
+        # we can access extract.extract_id (needed by session.bulk_save_objects(images))
+        session.add(Extract(slug=project_slug))
+        extract = session.query(Extract).filter(Extract.slug == project_slug).one_or_none()
+        missing_images_df = messages_df
+
+    _add_images_to_session(extract, missing_images_df, session)
+
+    return messages_df
+
+
+def _filter_existing_images(
+    messages_df: pd.DataFrame,
+    images_df: pd.DataFrame,
+) -> pd.DataFrame:
+    # DataFrame indices must batch when using df.isin (or df.index.isin)
+    # So we re-index the DataFrames to match on the columns we want to compare
+    messages_df_reindexed = messages_df.set_index(["accession_number", "mrn", "study_date"])
+    images_df_reindexed = images_df.set_index(["accession_number", "mrn", "study_date"])
+    keep_indices = ~messages_df_reindexed.index.isin(images_df_reindexed.index)
+    return messages_df[keep_indices]
 
 
 def _filter_exported_messages(
-    extract: Extract, messages: list[Message], session: Session, *, extract_created: bool
-) -> list[Message]:
-    output_messages = []
-    for message in messages:
-        _, image_exported = _get_image_and_check_exported(
-            extract, message, session, extract_created=extract_created
-        )
-        if not image_exported:
-            output_messages.append(message)
-    return output_messages
-
-
-def _get_image_and_check_exported(
-    extract: Extract, message: Message, session: Session, *, extract_created: bool
-) -> tuple[Image, bool]:
-    if extract_created:
-        new_image = _add_new_image_to_session(extract, message, session)
-        return new_image, False
-
-    existing_image = (
-        session.query(Image)
-        .filter(
-            Image.extract == extract,
-            Image.accession_number == message.accession_number,
-            Image.mrn == message.mrn,
-            Image.study_date == message.study_date,
-        )
-        .one_or_none()
+    messages_df: pd.DataFrame,
+    images_df: pd.DataFrame,
+) -> pd.DataFrame:
+    merged = messages_df.merge(
+        images_df,
+        on=["accession_number", "mrn", "study_date"],
+        how="left",
+        validate="one_to_one",
+        suffixes=(None, None),
     )
+    keep_indices = merged["exported_at"].isna().to_numpy()
+    return merged[keep_indices][messages_df.columns]
+
+
+def _add_images_to_session(extract: Extract, images_df: pd.DataFrame, session: Session) -> None:
+    images = []
+    for _, row in images_df.iterrows():
+        new_image = Image(
+            accession_number=row["accession_number"],
+            study_date=row["study_date"],
+            mrn=row["mrn"],
+            study_uid=row["study_uid"],
+            extract=extract,
+            extract_id=extract.extract_id,
+            pseudo_patient_id=row["pseudo_patient_id"],
+        )
+        images.append(new_image)
+    session.bulk_save_objects(images)
 
-    if existing_image:
-        if existing_image.exported_at is not None:
-            return existing_image, True
-        return existing_image, False
-
-    new_image = _add_new_image_to_session(extract, message, session)
-    return new_image, False
 
+def all_images_for_project(project_slug: str) -> pd.DataFrame:
+    """Given a project, get all images in the DB for that project."""
+    PixlSession = sessionmaker(engine)
 
-def _add_new_image_to_session(extract: Extract, message: Message, session: Session) -> Image:
-    new_image = Image(
-        accession_number=message.accession_number,
-        study_date=message.study_date,
-        mrn=message.mrn,
-        extract=extract,
+    query = (
+        select(Image.accession_number, Image.study_date, Image.mrn, Image.exported_at)
+        .join(Extract)
+        .where(Extract.slug == project_slug)
     )
-    session.add(new_image)
-    return new_image
+    with PixlSession() as session:
+        return pd.read_sql(
+            sql=query,
+            con=session.bind,
+        )
 
 
-def images_for_project(project_slug: str) -> list[Image]:
-    """Given a project, get all images in the DB for that project."""
+def exported_images_for_project(project_slug: str) -> list[Image]:
+    """
+    Given a project, get all images in the DB for that project
+    that have not yet been exported.
+    """
     PixlSession = sessionmaker(engine)
     with PixlSession() as session:
         return cast(
             list[Image],
-            session.query(Image).join(Extract).filter(Extract.slug == project_slug).all(),
+            session.query(Image)
+            .join(Extract)
+            .filter(Extract.slug == project_slug)
+            .filter(not_(Image.exported_at.is_(None)))
+            .all(),
         )
diff --git a/cli/src/pixl_cli/_docker_commands.py b/cli/src/pixl_cli/_docker_commands.py
new file mode 100644
index 000000000..ba9406be1
--- /dev/null
+++ b/cli/src/pixl_cli/_docker_commands.py
@@ -0,0 +1,73 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+import shutil
+import subprocess
+from pathlib import Path
+from typing import Optional
+
+import click
+from decouple import config
+from loguru import logger
+
+PIXL_ROOT = Path(__file__).parents[3].resolve()
+
+
+# Required to allow passing unkown options to docker-compose
+# https://click.palletsprojects.com/en/8.1.x/advanced/#forwarding-unknown-options
+@click.command(context_settings={"ignore_unknown_options": True})
+@click.argument("args", nargs=-1, type=click.UNPROCESSED)
+def dc(args: tuple[str]) -> None:
+    """Wrapper around docker compose for PIXL"""
+    # Construct the docker-compose arguments based on subcommand
+    docker_args = list(args)
+
+    if "up" in args:
+        docker_args = [*args, "--wait", "--build", "--remove-orphans"]
+    if "down" in args:
+        docker_args = _check_down_args(args)
+
+    run_docker_compose(docker_args, working_dir=PIXL_ROOT)
+
+
+def _check_down_args(args: tuple[str, ...]) -> list:
+    """Stop all the PIXL services"""
+    if config("ENV") == "prod" and "--volumes" in args:
+        click.secho("WARNING: Attempting to remove volumes in production.", fg="yellow")
+        if not click.confirm("Are you sure you want to remove the volumes?"):
+            click.secho("Running 'docker compose down' without removing volumes.", fg="blue")
+            return [arg for arg in args if arg != "--volumes"]
+    return list(args)
+
+
+def run_docker_compose(args: list, working_dir: Optional[Path]) -> None:
+    """Wrapper to run docker-compose through the CLI."""
+    docker_cmd = shutil.which("docker")
+
+    if not docker_cmd:
+        err_msg = "docker not found in $PATH. Please make sure it's installed."
+        raise FileNotFoundError(err_msg)
+
+    pixl_env = config("ENV")
+
+    docker_args = [
+        docker_cmd,
+        "compose",
+        "--project-name",
+        f"pixl_{pixl_env}",
+        *args,
+    ]
+    logger.info("Running docker compose with: {}, from {}", docker_args, working_dir)
+
+    subprocess.run(docker_args, check=True, cwd=working_dir)  # noqa: S603
diff --git a/cli/src/pixl_cli/_io.py b/cli/src/pixl_cli/_io.py
index 9336e9125..39bff743b 100644
--- a/cli/src/pixl_cli/_io.py
+++ b/cli/src/pixl_cli/_io.py
@@ -16,13 +16,14 @@
 from __future__ import annotations
 
 import json
-from datetime import UTC, datetime
+from datetime import datetime
+from enum import StrEnum, auto
 from pathlib import Path
 from typing import TYPE_CHECKING
 
+import numpy as np
 import pandas as pd
 from core.exports import ParquetExport
-from core.patient_queue.message import Message
 from loguru import logger
 
 if TYPE_CHECKING:
@@ -53,104 +54,78 @@ def copy_parquet_return_logfile_fields(resources_path: Path) -> tuple[str, datet
     return project_name_slug, extract_generated_timestamp
 
 
-def messages_from_csv(filepath: Path) -> list[Message]:
+def read_patient_info(resources_path: Path) -> pd.DataFrame:
+    """
+    Read patient information from a CSV file or parquet files within directory structure.
+    :param resources_path: Path for CSV file or parquet directory containing private and public
+    :return: DataFrame with patient information
+    """
+    if resources_path.is_file() and resources_path.suffix == ".csv":
+        messages_df = _load_csv(resources_path)
+    else:
+        messages_df = _load_parquet(resources_path)
+
+    messages_df = messages_df.sort_values(by=["project_name", "study_date"])
+    messages_df = messages_df.drop_duplicates(
+        subset=["project_name", "mrn", "accession_number", "study_date"]
+    )
+
+    if len(messages_df) == 0:
+        msg = f"Failed to find any messages in {resources_path}"
+        raise ValueError(msg)
+
+    logger.info("Created {} messages from {}", len(messages_df), resources_path)
+
+    return messages_df
+
+
+def _load_csv(filepath: Path) -> pd.DataFrame:
     """
     Reads patient information from CSV and transforms that into messages.
     :param filepath: Path for CSV file to be read
     """
-    expected_col_names = [
-        "procedure_id",
-        "mrn",
-        "accession_number",
-        "project_name",
-        "extract_generated_timestamp",
-        "study_date",
-    ]
-
     # First line is column names
     messages_df = pd.read_csv(filepath, header=0, dtype=str)
+    messages_df = _map_columns(messages_df, MAP_CSV_TO_MESSAGE_KEYS)
+    _raise_if_column_names_not_found(messages_df, [col.name for col in DF_COLUMNS])
+    messages_df["pseudo_patient_id"] = messages_df["pseudo_patient_id"].replace(np.nan, None)
+
+    # Parse non string columns
+    messages_df["procedure_occurrence_id"] = messages_df["procedure_occurrence_id"].astype(int)
+    messages_df["study_date"] = pd.to_datetime(
+        messages_df["study_date"], format="%Y-%m-%d", errors="raise"
+    ).dt.date
+    messages_df["extract_generated_timestamp"] = pd.to_datetime(
+        messages_df["extract_generated_timestamp"],
+        format="%Y-%m-%dT%H:%M:%SZ",
+        errors="raise",
+        utc=True,
+    )
 
-    _raise_if_column_names_not_found(messages_df, expected_col_names)
-
-    (
-        procedure_id_col_name,
-        mrn_col_name,
-        acc_num_col_name,
-        project_col_name,
-        extract_col_name,
-        dt_col_name,
-    ) = expected_col_names
-
-    messages = []
-    for _, row in messages_df.iterrows():
-        message = Message(
-            mrn=row[mrn_col_name],
-            accession_number=row[acc_num_col_name],
-            study_date=datetime.strptime(row[dt_col_name], "%d/%m/%Y %H:%M")
-            .replace(tzinfo=UTC)
-            .date(),
-            procedure_occurrence_id=row[procedure_id_col_name],
-            project_name=row[project_col_name],
-            extract_generated_timestamp=datetime.strptime(
-                row[extract_col_name], "%d/%m/%Y %H:%M"
-            ).replace(tzinfo=UTC),
-        )
-        messages.append(message)
-
-    if len(messages) == 0:
-        msg = f"Failed to find any messages in {filepath}"
-        raise ValueError(msg)
-
-    logger.info("Created {} messages from {}", len(messages), filepath)
-    return messages
+    return messages_df
 
 
-def messages_from_parquet(
-    dir_path: Path, project_name: str, extract_generated_timestamp: datetime
-) -> list[Message]:
+def _load_parquet(
+    dir_path: Path,
+) -> pd.DataFrame:
     """
     Reads patient information from parquet files within directory structure
-    and transforms that into messages.
+    and transforms that into a DataFrame
 
     :param dir_path: Path for parquet directory containing private and public
-    :param project_name: Name of the project, should be a slug, so it can match the export directory
-    :param extract_generated_timestamp: Datetime that OMOP ES ran the extract
-    files
     """
     public_dir = dir_path / "public"
     private_dir = dir_path / "private"
 
-    cohort_data = _check_and_parse_parquet(private_dir, public_dir)
-    cohort_data_mapped = _map_columns(cohort_data)
+    messages_df = _check_and_parse_parquet(private_dir, public_dir)
+    messages_df = _map_columns(messages_df, MAP_PARQUET_TO_MESSAGE_KEYS)
 
-    messages = []
-    for _, row in cohort_data_mapped.iterrows():
-        message = Message(
-            project_name=project_name,
-            extract_generated_timestamp=extract_generated_timestamp,
-            **{column: row[column] for column in MAP_PARQUET_TO_MESSAGE_KEYS.values()},
-        )
-        messages.append(message)
-
-    if len(messages) == 0:
-        msg = f"Failed to find any messages in {dir_path}"
-        raise ValueError(msg)
+    project_name, extract_generated_timestamp = copy_parquet_return_logfile_fields(dir_path)
+    messages_df["project_name"] = project_name
+    messages_df["extract_generated_timestamp"] = extract_generated_timestamp
+    messages_df["pseudo_patient_id"] = None
 
-    logger.info("Created {} messages from {}", len(messages), dir_path)
-    return messages
-
-
-MAP_PARQUET_TO_MESSAGE_KEYS = {
-    "PrimaryMrn": "mrn",
-    "AccessionNumber": "accession_number",
-    "procedure_date": "study_date",
-    "procedure_occurrence_id": "procedure_occurrence_id",
-}
-
-
-def _map_columns(input_df: pd.DataFrame) -> pd.DataFrame:
-    _raise_if_column_names_not_found(input_df, list(MAP_PARQUET_TO_MESSAGE_KEYS.keys()))
-    return input_df.rename(MAP_PARQUET_TO_MESSAGE_KEYS, axis=1)
+    return messages_df
 
 
 def _check_and_parse_parquet(private_dir: Path, public_dir: Path) -> pd.DataFrame:
@@ -169,24 +144,42 @@ def _check_and_parse_parquet(private_dir: Path, public_dir: Path) -> pd.DataFram
     # joining data together
     people_procedures = people.merge(procedure, on="person_id")
     people_procedures_accessions = people_procedures.merge(accessions, on="procedure_occurrence_id")
-    return people_procedures_accessions[~people_procedures_accessions["AccessionNumber"].isna()]
 
+    # Filter out any rows where accession number is NA or an empty string
+    return people_procedures_accessions[
+        ~people_procedures_accessions["AccessionNumber"].isna()
+        & (people_procedures_accessions["AccessionNumber"] != "")
+    ]
 
-def make_radiology_linker_table(parquet_dir: Path, images: list[Image]) -> pd.DataFrame:
-    """
-    Make a table linking the OMOP procedure_occurrence_id to the hashed image/study ID.
-    :param parquet_dir: location of OMOP extract
-                        (this gives us: procedure_occurrence_id <-> mrn+accession mapping)
-    :param images: the images already processed by PIXL, from the DB
-                        (this gives us: mrn+accession <-> hashed ID)
-    """
-    public_dir = parquet_dir / "public"
-    private_dir = parquet_dir / "private"
-    people_procedures_accessions = _map_columns(_check_and_parse_parquet(private_dir, public_dir))
 
-    images_df = pd.DataFrame.from_records([vars(im) for im in images])
-    merged = people_procedures_accessions.merge(images_df, on=("mrn", "accession_number"))
-    return merged[["procedure_occurrence_id", "hashed_identifier"]]
+class DF_COLUMNS(StrEnum):  # noqa: N801
+    procedure_occurrence_id = auto()
+    mrn = auto()
+    accession_number = auto()
+    project_name = auto()
+    extract_generated_timestamp = auto()
+    study_date = auto()
+    study_uid = auto()
+    pseudo_patient_id = auto()
+
+
+MAP_CSV_TO_MESSAGE_KEYS = {
+    "procedure_id": "procedure_occurrence_id",
+    "participant_id": "pseudo_patient_id",
+}
+
+
+MAP_PARQUET_TO_MESSAGE_KEYS = {
+    "PrimaryMrn": "mrn",
+    "AccessionNumber": "accession_number",
+    "procedure_date": "study_date",
+    "StudyUid_X": "study_uid",
+}
+
+
+def _map_columns(input_df: pd.DataFrame, columns: dict) -> pd.DataFrame:
+    _raise_if_column_names_not_found(input_df, list(columns.keys()))
+    return input_df.rename(columns, axis=1)
 
 
 def _raise_if_column_names_not_found(
@@ -202,3 +195,23 @@ def _raise_if_column_names_not_found(
                 f"column names"
             )
             raise ValueError(msg)
+
+
+def make_radiology_linker_table(parquet_dir: Path, images: list[Image]) -> pd.DataFrame:
+    """
+    Make a table linking the OMOP procedure_occurrence_id to the pseudo image/study ID.
+    :param parquet_dir: location of OMOP extract
+                        (this gives us: procedure_occurrence_id <-> mrn+accession mapping)
+    :param images: the images already processed by PIXL, from the DB
+                        (this gives us: mrn+accession <-> pseudo_study_uid)
+    """
+    public_dir = parquet_dir / "public"
+    private_dir = parquet_dir / "private"
+    people_procedures_accessions = _map_columns(
+        _check_and_parse_parquet(private_dir, public_dir),
+        MAP_PARQUET_TO_MESSAGE_KEYS,
+    )
+
+    images_df = pd.DataFrame.from_records([vars(im) for im in images])
+    merged = people_procedures_accessions.merge(images_df, on=("mrn", "accession_number"))
+    return merged[["procedure_occurrence_id", "pseudo_study_uid"]]
diff --git a/cli/src/pixl_cli/_message_processing.py b/cli/src/pixl_cli/_message_processing.py
new file mode 100644
index 000000000..254ae0c77
--- /dev/null
+++ b/cli/src/pixl_cli/_message_processing.py
@@ -0,0 +1,158 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Processing of messages and interaction with rabbitmq."""
+
+from __future__ import annotations
+
+from time import sleep
+from typing import TYPE_CHECKING
+
+import pandas as pd
+import tqdm
+from core.patient_queue._base import PixlBlockingInterface
+from core.patient_queue.message import Message
+from core.patient_queue.producer import PixlProducer
+from decouple import config
+from loguru import logger
+
+from pixl_cli._config import SERVICE_SETTINGS
+from pixl_cli._database import exported_images_for_project, filter_exported_or_add_to_db
+
+if TYPE_CHECKING:
+    import pandas as pd
+
+
+def messages_from_df(
+    df: pd.DataFrame,
+) -> list[Message]:
+    """
+    Reads patient information from a DataFrame and transforms that into messages.
+
+    :param messages_df: DataFrame containing patient information
+    """
+    messages = []
+    for _, row in df.iterrows():
+        message = Message(
+            mrn=row["mrn"],
+            accession_number=row["accession_number"],
+            study_uid=row["study_uid"],
+            study_date=row["study_date"],
+            procedure_occurrence_id=row["procedure_occurrence_id"],
+            project_name=row["project_name"],
+            extract_generated_timestamp=row["extract_generated_timestamp"].to_pydatetime(),
+        )
+        messages.append(message)
+
+    return messages
+
+
+def retry_until_export_count_is_unchanged(
+    messages_df: pd.DataFrame,
+    num_retries: int,
+    queues_to_populate: list[str],
+    messages_priority: int,
+) -> None:
+    """Retry populating messages until there is no change in the number of exported studies."""
+    last_exported_count = 0
+
+    # wait PIXL_DICOM_TRANSFER_TIMEOUT seconds if CLI_RETRY_SECONDS is not defined
+    total_wait_seconds = config("PIXL_DICOM_TRANSFER_TIMEOUT", default=300, cast=int)
+    total_wait_seconds = config("CLI_RETRY_SECONDS", default=total_wait_seconds, cast=int)
+    wait_to_display = f"{total_wait_seconds //60} minutes"
+    if total_wait_seconds % 60:
+        wait_to_display = f"{total_wait_seconds //60} minutes & {total_wait_seconds % 60} seconds"
+
+    logger.info(
+        "Retrying extraction every {} until no new extracts are found, max retries: {}",
+        wait_to_display,
+        num_retries,
+    )
+    for i in range(1, num_retries + 1):
+        _wait_for_queues_to_empty(queues_to_populate)
+        logger.info("Waiting {} for new extracts to be found", wait_to_display)
+        for _ in tqdm.tqdm(
+            range(total_wait_seconds), desc="Waiting for series to be fully processed"
+        ):
+            sleep(1)
+
+        images = (
+            [
+                exported_images_for_project(project_name)
+                for project_name in messages_df["project_name"].unique()
+            ]
+            if messages_df["project_name"].size
+            else [[]]
+        )
+        new_last_exported_count = sum([len(project_images) for project_images in images])
+        if new_last_exported_count == last_exported_count:
+            logger.info(
+                "{} studies exported, didn't change between retries",
+                new_last_exported_count,
+            )
+            return
+        logger.info(
+            "{} studies exported, retrying extraction {}/{}",
+            new_last_exported_count - last_exported_count,
+            i,
+            num_retries,
+        )
+        last_exported_count = new_last_exported_count
+        populate_queue_and_db(queues_to_populate, messages_df, messages_priority=messages_priority)
+
+
+def _wait_for_queues_to_empty(queues_to_populate: list[str]) -> None:
+    logger.info("Waiting for rabbitmq queues to be empty")
+    message_count = _message_count(queues_to_populate)
+    while message_count != 0:
+        logger.debug(f"{message_count=}, sleeping for a minute")
+        sleep(60)
+        message_count = _message_count(queues_to_populate)
+    logger.info("Queues are empty")
+
+
+def _message_count(queues_to_populate: list[str]) -> int:
+    # We don't want to modify the queues we're populating, but if we're populating imaging-primary
+    # we also need to wait for imaging-secondary to be empty
+    queues_to_count = set(queues_to_populate)
+    if "imaging-primary" in queues_to_populate:
+        queues_to_count.add("imaging-secondary")
+
+    messages_in_queues = 0
+    for queue in queues_to_count:
+        with PixlBlockingInterface(queue_name=queue, **SERVICE_SETTINGS["rabbitmq"]) as rabbitmq:
+            messages_in_queues += rabbitmq.message_count
+
+    return messages_in_queues
+
+
+def populate_queue_and_db(
+    queues: list[str], messages_df: pd.DataFrame, messages_priority: int
+) -> list[Message]:
+    """
+    Populate queues with messages,
+    for imaging queue update the database and filter out exported studies.
+    """
+    output_messages = []
+    for queue in queues:
+        # For imaging, we don't want to query again for images that have already been exported
+        if "imaging" in queue and len(messages_df):
+            logger.info("Filtering out exported images and uploading new ones to the database")
+            messages_df = filter_exported_or_add_to_db(messages_df)
+
+        messages = messages_from_df(messages_df)
+        with PixlProducer(queue_name=queue, **SERVICE_SETTINGS["rabbitmq"]) as producer:
+            producer.publish(messages, priority=messages_priority)
+        output_messages.extend(messages)
+
+    return output_messages
diff --git a/cli/src/pixl_cli/main.py b/cli/src/pixl_cli/main.py
index 62be7fb7b..97dbafdc3 100644
--- a/cli/src/pixl_cli/main.py
+++ b/cli/src/pixl_cli/main.py
@@ -18,7 +18,6 @@
 import json
 import os
 import sys
-from operator import attrgetter
 from pathlib import Path
 from typing import Any, Optional
 
@@ -30,19 +29,24 @@
 from loguru import logger
 
 from pixl_cli._config import SERVICE_SETTINGS, api_config_for_queue
-from pixl_cli._database import filter_exported_or_add_to_db, images_for_project
+from pixl_cli._database import exported_images_for_project
+from pixl_cli._docker_commands import dc
 from pixl_cli._io import (
     HOST_EXPORT_ROOT_DIR,
-    copy_parquet_return_logfile_fields,
     make_radiology_linker_table,
-    messages_from_csv,
-    messages_from_parquet,
     project_info,
+    read_patient_info,
+)
+from pixl_cli._message_processing import (
+    populate_queue_and_db,
+    retry_until_export_count_is_unchanged,
 )
 
 # localhost needs to be added to the NO_PROXY environment variables on GAEs
 os.environ["NO_PROXY"] = os.environ["no_proxy"] = "localhost"
 
+PIXL_ROOT = Path(__file__).parents[3].resolve()
+
 
 @click.group()
 @click.option("--debug/--no-debug", default=False)
@@ -53,6 +57,9 @@ def cli(*, debug: bool) -> None:
     logger.add(sys.stderr, level=logging_level)
 
 
+cli.add_command(dc)
+
+
 @cli.command()
 @click.option(
     "--error",
@@ -68,10 +75,10 @@ def cli(*, debug: bool) -> None:
     type=click.Path(exists=True),
     help="Path to the sample env file",
 )
-def check_env(*, error: bool, sample_env_file: click.Path) -> None:
+def check_env(*, error: bool, sample_env_file: Path) -> None:
     """Check that all variables from .env.sample are set either in .env or in environ"""
     if not sample_env_file:
-        sample_env_file = Path(__file__).parents[3] / ".env.sample"
+        sample_env_file = PIXL_ROOT / ".env.sample"
     sample_config = RepositoryEnv(sample_env_file)
     for key in sample_config.data:
         try:
@@ -83,9 +90,12 @@ def check_env(*, error: bool, sample_env_file: click.Path) -> None:
 
 
 @cli.command()
+@click.argument(
+    "parquet-path", required=True, type=click.Path(path_type=Path, exists=True, file_okay=True)
+)
 @click.option(
     "--queues",
-    default="imaging",
+    default="imaging-primary",
     show_default=True,
     help="Comma seperated list of queues to populate with messages generated from the "
     "input file(s)",
@@ -103,11 +113,29 @@ def check_env(*, error: bool, sample_env_file: click.Path) -> None:
     default=None,
     help="Rate at which to process items from a queue (in items per second).",
 )
-@click.argument(
-    "parquet-path", required=True, type=click.Path(path_type=Path, exists=True, file_okay=True)
+@click.option(
+    "--num-retries",
+    "num_retries",
+    type=int,
+    show_default=True,
+    default=5,
+    help="Number of retries to attempt before giving up, 5 minute wait inbetween",
+)
+@click.option(
+    "--priority",
+    "priority",
+    show_default=True,
+    default=1,
+    help="Priority of the messages, from 1 (lowest) to 5 (highest)",
 )
-def populate(
-    parquet_path: Path, *, queues: str, start_processing: bool, rate: Optional[float]
+def populate(  # noqa: PLR0913 - too many args
+    parquet_path: Path,
+    *,
+    queues: str,
+    rate: Optional[float],
+    num_retries: int,
+    start_processing: bool,
+    priority: int,
 ) -> None:
     """
     Populate a (set of) queue(s) from a parquet file directory
@@ -123,26 +151,21 @@ def populate(
             │   └── PROCEDURE_OCCURRENCE.parquet
             └── extract_summary.json
     """
+    queues_to_populate = queues.split(",")
     if start_processing:
-        _start_or_update_extract(queues=queues.split(","), rate=rate)
-
-    logger.info("Populating queue(s) {} from {}", queues, parquet_path)
-    if parquet_path.is_file() and parquet_path.suffix == ".csv":
-        messages = messages_from_csv(parquet_path)
+        _start_or_update_extract(queues=queues_to_populate, rate=rate)
     else:
-        project_name, omop_es_datetime = copy_parquet_return_logfile_fields(parquet_path)
-        messages = messages_from_parquet(parquet_path, project_name, omop_es_datetime)
+        logger.info("Starting to process messages disabled, setting `--num-retries` to 0")
+        num_retries = 0
 
-    for queue in queues.split(","):
-        sorted_messages = sorted(messages, key=attrgetter("study_date"))
-        # For imaging, we don't want to query again for images that have already been exported
-        if queue == "imaging" and messages:
-            logger.info("Filtering out exported images and uploading new ones to the database")
-            sorted_messages = filter_exported_or_add_to_db(
-                sorted_messages, messages[0].project_name
-            )
-        with PixlProducer(queue_name=queue, **SERVICE_SETTINGS["rabbitmq"]) as producer:
-            producer.publish(sorted_messages)
+    logger.info("Populating queue(s) {} from {}", queues_to_populate, parquet_path)
+    messages_df = read_patient_info(parquet_path)
+
+    populate_queue_and_db(queues_to_populate, messages_df, messages_priority=priority)
+    if num_retries != 0:
+        retry_until_export_count_is_unchanged(
+            messages_df, num_retries, queues_to_populate, messages_priority=priority
+        )
 
 
 @cli.command()
@@ -165,7 +188,7 @@ def export_patient_data(parquet_dir: Path, timeout: int) -> None:
     project_name_raw, omop_es_datetime = project_info(parquet_dir)
     export = ParquetExport(project_name_raw, omop_es_datetime, HOST_EXPORT_ROOT_DIR)
 
-    images = images_for_project(export.project_slug)
+    images = exported_images_for_project(export.project_slug)
     linker_data = make_radiology_linker_table(parquet_dir, images)
     export.export_radiology_linker(linker_data)
 
@@ -189,7 +212,7 @@ def export_patient_data(parquet_dir: Path, timeout: int) -> None:
 @cli.command()
 @click.option(
     "--queues",
-    default="imaging",
+    default="imaging-primary",
     show_default=True,
     help="Comma seperated list of queues to start consuming from",
 )
@@ -211,7 +234,7 @@ def start(queues: str, rate: Optional[float]) -> None:
 @cli.command()
 @click.option(
     "--queues",
-    default="imaging",
+    default="imaging-primary",
     show_default=True,
     help="Comma seperated list of queues to update the consume rate of",
 )
@@ -264,7 +287,7 @@ def _update_extract_rate(queue_name: str, rate: Optional[float]) -> None:
 @cli.command()
 @click.option(
     "--queues",
-    default="imaging",
+    default="imaging-primary",
     show_default=True,
     help="Comma seperated list of queues to consume messages from",
 )
@@ -300,7 +323,7 @@ def kill() -> None:
 @cli.command()
 @click.option(
     "--queues",
-    default="imaging",
+    default="imaging-primary",
     show_default=True,
     help="Comma seperated list of queues to consume messages from",
 )
@@ -314,7 +337,7 @@ def _get_extract_rate(queue_name: str) -> str:
     """
     Get the extraction rate in items per second from a queue
 
-    :param queue_name: Name of the queue to get the extract rate for (e.g. imaging)
+    :param queue_name: Name of the queue to get the extract rate for (e.g. imaging-primary)
     :return: The extract rate in items per seconds
 
     Throws a RuntimeError if the status code is not 200.
diff --git a/cli/tests/conftest.py b/cli/tests/conftest.py
index 53c192771..3218387ae 100644
--- a/cli/tests/conftest.py
+++ b/cli/tests/conftest.py
@@ -15,37 +15,56 @@
 
 from __future__ import annotations
 
+import datetime
 import os
 from pathlib import Path
+from typing import TYPE_CHECKING
+from zoneinfo import ZoneInfo
 
+import pandas as pd
 import pytest
 from core.db.models import Base, Extract, Image
+from core.patient_queue.message import Message
+from core.patient_queue.producer import PixlProducer
 from sqlalchemy import Engine, create_engine
 from sqlalchemy.orm import Session, sessionmaker
 
+if TYPE_CHECKING:
+    from collections.abc import Generator
+    from unittest.mock import Mock
+
+
+# Load environment variables from test .env file
+with (Path(__file__).parents[2] / "test/.env").open() as f:
+    for line in f.readlines():
+        if "=" in line:
+            key, value = line.strip().split("=")
+            os.environ[key] = value
+
+# Set the remaining environment variables
 os.environ["PROJECT_CONFIGS_DIR"] = str(Path(__file__).parents[2] / "projects/configs")
 
-# Set the necessary environment variables
-os.environ["PIXL_EXPORT_API_HOST"] = "localhost"
-os.environ["PIXL_EXPORT_API_PORT"] = "7006"
+os.environ["EXPORT_AZ_CLIENT_ID"] = "export client id"
+os.environ["EXPORT_AZ_CLIENT_PASSWORD"] = "export client password"
+os.environ["EXPORT_AZ_TENANT_ID"] = "export tenant id"
+os.environ["EXPORT_AZ_KEY_VAULT_NAME"] = "export key vault name"
 
-os.environ["PIXL_IMAGING_API_HOST"] = "localhost"
-os.environ["PIXL_IMAGING_API_RATE"] = "1"
-os.environ["PIXL_IMAGING_API_PORT"] = "7007"
+os.environ["HASHER_API_AZ_CLIENT_ID"] = "hasher client id"
+os.environ["HASHER_API_AZ_CLIENT_PASSWORD"] = "hasher client password"
+os.environ["HASHER_API_AZ_TENANT_ID"] = "hasher tenant id"
+os.environ["HASHER_API_AZ_KEY_VAULT_NAME"] = "hasher key vault name"
 
-os.environ["RABBITMQ_HOST"] = "localhost"
-os.environ["RABBITMQ_USERNAME"] = "rabbitmq_username"
-os.environ["RABBITMQ_PASSWORD"] = "rabbitmq_password"  # noqa: S105
-os.environ["RABBITMQ_PORT"] = "7008"
+os.environ["ORTHANC_RAW_JOB_HISTORY_SIZE"] = "100"
+os.environ["ORTHANC_CONCURRENT_JOBS"] = "20"
 
-os.environ["PIXL_DB_USER"] = "pixl_db_username"
-os.environ["PIXL_DB_PASSWORD"] = "pixl_db_password"  # noqa: S105
-os.environ["POSTGRES_HOST"] = "locahost"
-os.environ["POSTGRES_PORT"] = "7001"
-os.environ["PIXL_DB_NAME"] = "pixl"
+os.environ["AZ_DICOM_ENDPOINT_NAME"] = "dicom endpoint name"
+os.environ["AZ_DICOM_ENDPOINT_URL"] = "dicom endpoint url"
+os.environ["AZ_DICOM_ENDPOINT_TOKEN"] = "dicom endpoint token"
+os.environ["AZ_DICOM_ENDPOINT_CLIENT_ID"] = "dicom endpoint client id"
+os.environ["AZ_DICOM_ENDPOINT_CLIENT_SECRET"] = "dicom endpoint client secret"
+os.environ["AZ_DICOM_ENDPOINT_TENANT_ID"] = "dicom endpoint tenant id"
 
-os.environ["ORTHANC_ANON_USERNAME"] = "orthanc"
-os.environ["ORTHANC_ANON_PASSWORD"] = "orthanc"  # noqa: S105, hardcoded password
+os.environ["TZ"] = "Europe/London"
 
 
 @pytest.fixture(autouse=True)
@@ -90,7 +109,7 @@ def db_engine(monkeymodule) -> Engine:
 
 
 @pytest.fixture()
-def db_session(db_engine) -> Session:
+def db_session(db_engine) -> Generator[Session]:
     """
     Creates a session for interacting with an in memory database.
 
@@ -106,3 +125,127 @@ def db_session(db_engine) -> Session:
         session.query(Extract).delete()
         yield session
     session.close()
+
+
+STUDY_DATE = datetime.date.fromisoformat("2023-01-01")
+
+
+def _make_message(
+    project_name: str,
+    accession_number: str,
+    mrn: str,
+    study_uid: str,
+) -> Message:
+    return Message(
+        project_name=project_name,
+        accession_number=accession_number,
+        mrn=mrn,
+        study_uid=study_uid,
+        study_date=STUDY_DATE,
+        procedure_occurrence_id=1,
+        extract_generated_timestamp=datetime.datetime.now(tz=ZoneInfo(os.environ["TZ"])),
+    )
+
+
+@pytest.fixture()
+def example_messages() -> list[Message]:
+    """Test input data."""
+    return [
+        _make_message(
+            project_name="i-am-a-project", accession_number="123", mrn="mrn", study_uid="1.2.3"
+        ),
+        _make_message(
+            project_name="i-am-a-project", accession_number="234", mrn="mrn", study_uid="2.3.4"
+        ),
+        _make_message(
+            project_name="i-am-a-project", accession_number="345", mrn="mrn", study_uid="3.4.5"
+        ),
+    ]
+
+
+@pytest.fixture()
+def example_messages_df(example_messages):
+    """Test input data in a DataFrame."""
+    messages_df = pd.DataFrame.from_records([vars(im) for im in example_messages])
+    messages_df["pseudo_patient_id"] = None
+    return messages_df
+
+
+@pytest.fixture()
+def example_messages_multiple_projects() -> list[Message]:
+    """Test input data."""
+    return [
+        _make_message(
+            project_name="i-am-a-project", accession_number="123", mrn="mrn", study_uid="1.2.3"
+        ),
+        _make_message(
+            project_name="i-am-a-project", accession_number="234", mrn="mrn", study_uid="2.3.4"
+        ),
+        _make_message(
+            project_name="i-am-a-project", accession_number="345", mrn="mrn", study_uid="3.4.5"
+        ),
+        _make_message(
+            project_name="i-am-another-project",
+            accession_number="123",
+            mrn="mrn",
+            study_uid="1.2.3",
+        ),
+        _make_message(
+            project_name="i-am-another-project",
+            accession_number="234",
+            mrn="mrn",
+            study_uid="2.3.4",
+        ),
+        _make_message(
+            project_name="i-am-another-project",
+            accession_number="345",
+            mrn="mrn",
+            study_uid="3.4.5",
+        ),
+    ]
+
+
+@pytest.fixture()
+def example_messages_multiple_projects_df(example_messages_multiple_projects) -> pd.DataFrame:
+    """Test input data."""
+    messages_df = pd.DataFrame.from_records([vars(im) for im in example_messages_multiple_projects])
+    messages_df["pseudo_patient_id"] = None
+    return messages_df
+
+
+@pytest.fixture()
+def rows_in_session(db_session) -> Session:
+    """Insert a test row for each table, returning the session for use in tests."""
+    extract = Extract(slug="i-am-a-project")
+
+    image_exported = Image(
+        accession_number="123",
+        study_date=STUDY_DATE,
+        mrn="mrn",
+        study_uid="1.2.3",
+        extract=extract,
+        extract_id=extract.extract_id,
+        exported_at=datetime.datetime.now(ZoneInfo(os.environ["TZ"])),
+    )
+    image_not_exported = Image(
+        accession_number="234",
+        study_date=STUDY_DATE,
+        mrn="mrn",
+        study_uid="2.3.4",
+        extract=extract,
+        extract_id=extract.extract_id,
+    )
+    with db_session:
+        db_session.add_all([extract, image_exported, image_not_exported])
+        db_session.commit()
+
+    return db_session
+
+
+@pytest.fixture()
+def mock_publisher(mocker) -> Generator[Mock, None, None]:
+    """Patched publisher that does nothing, returns MagicMock of the publish method."""
+    mocker.patch.object(PixlProducer, "__init__", return_value=None)
+    mocker.patch.object(PixlProducer, "__enter__", return_value=PixlProducer)
+    mocker.patch.object(PixlProducer, "__exit__")
+    return mocker.patch.object(PixlProducer, "publish")
diff --git a/cli/tests/test_check_env.py b/cli/tests/test_check_env.py
index 057997f29..f4a8b44f1 100644
--- a/cli/tests/test_check_env.py
+++ b/cli/tests/test_check_env.py
@@ -15,7 +15,9 @@
 
 from pathlib import Path
 
+import pytest
 from click.testing import CliRunner
+from decouple import UndefinedValueError
 from pixl_cli.main import check_env
 
 SAMPLE_ENV_FILE = Path(__file__).parents[2] / ".env.sample"
@@ -28,7 +30,7 @@ def test_check_env():
     - current test env file matches the sample env file
     """
     runner = CliRunner()
-    result = runner.invoke(check_env)
+    result = runner.invoke(check_env, args=["--error"])
     assert result.exit_code == 0
 
 
@@ -40,5 +42,9 @@ def test_check_env_fails(tmp_path):
     tmp_sample_env_file.write_text("NONEXISTENT_VARIABLE=")
 
     runner = CliRunner()
-    result = runner.invoke(check_env, str(tmp_sample_env_file))
-    assert result.exit_code != 0
+    with pytest.raises(UndefinedValueError, match="not found"):
+        runner.invoke(
+            check_env,
+            args=["--error", "--sample-env-file", tmp_sample_env_file],
+            catch_exceptions=False,
+        )
diff --git a/cli/tests/test_database.py b/cli/tests/test_database.py
deleted file mode 100644
index 9e2fe3dcb..000000000
--- a/cli/tests/test_database.py
+++ /dev/null
@@ -1,118 +0,0 @@
-#  Copyright (c) University College London Hospitals NHS Foundation Trust
-#
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
-
-"""Test database interaction methods for the cli."""
-
-import datetime
-
-import pytest
-from core.db.models import Extract, Image
-from core.patient_queue.message import Message
-from pixl_cli._database import filter_exported_or_add_to_db
-from sqlalchemy.orm import Session
-
-STUDY_DATE = datetime.date.fromisoformat("2023-01-01")
-
-
-def _make_message(project_name: str, accession_number: str, mrn: str) -> Message:
-    return Message(
-        project_name=project_name,
-        accession_number=accession_number,
-        mrn=mrn,
-        study_date=STUDY_DATE,
-        procedure_occurrence_id=1,
-        extract_generated_timestamp=datetime.datetime.now(tz=datetime.UTC),
-    )
-
-
-@pytest.fixture()
-def example_messages():
-    """Test input data."""
-    return [
-        _make_message(project_name="i-am-a-project", accession_number="123", mrn="mrn"),
-        _make_message(project_name="i-am-a-project", accession_number="234", mrn="mrn"),
-        _make_message(project_name="i-am-a-project", accession_number="345", mrn="mrn"),
-    ]
-
-
-@pytest.fixture()
-def rows_in_session(db_session) -> Session:
-    """Insert a test row for each table, returning the session for use in tests."""
-    extract = Extract(slug="i-am-a-project")
-
-    image_exported = Image(
-        accession_number="123",
-        study_date=STUDY_DATE,
-        mrn="mrn",
-        extract=extract,
-        exported_at=datetime.datetime.now(tz=datetime.UTC),
-    )
-    image_not_exported = Image(
-        accession_number="234",
-        study_date=STUDY_DATE,
-        mrn="mrn",
-        extract=extract,
-    )
-    with db_session:
-        db_session.add_all([extract, image_exported, image_not_exported])
-        db_session.commit()
-
-    return db_session
-
-
-def test_project_doesnt_exist(example_messages, db_session):
-    """If project doesn't exist, no filtering and then project & messages saved to database"""
-    output = filter_exported_or_add_to_db(example_messages, "i-am-a-project")
-    assert output == example_messages
-    extract = db_session.query(Extract).one()
-    images = db_session.query(Image).filter(Image.extract == extract).all()
-    assert len(images) == len(example_messages)
-
-
-def test_first_image_exported(example_messages, rows_in_session):
-    """
-    GIVEN 3 messages, where one has been exported, the second has been saved to db but not exported
-    WHEN the messages are filtered
-    THEN the first message that has an exported_at value should not be in the filtered list
-        and all images should be saved to the database
-    """
-    output = filter_exported_or_add_to_db(example_messages, "i-am-a-project")
-    assert len(output) == len(example_messages) - 1
-    assert [x for x in output if x.accession_number == "123"] == []
-    extract = rows_in_session.query(Extract).one()
-    images = rows_in_session.query(Image).filter(Image.extract == extract).all()
-    assert len(images) == len(example_messages)
-
-
-def test_new_extract_with_overlapping_images(example_messages, rows_in_session):
-    """
-    GIVEN messages from a new extract, two have been saved to the database with another extract
-    WHEN the messages are filtered
-    THEN all messages should be returned and all new images should be added
-    """
-    new_project_name = "new-project"
-    for message in example_messages:
-        message.project_name = new_project_name
-
-    output = filter_exported_or_add_to_db(example_messages, new_project_name)
-
-    # none filtered out
-    assert len(output) == len(example_messages)
-    # all new batch of images saved
-    extract = rows_in_session.query(Extract).filter(Extract.slug == new_project_name).one()
-    images = rows_in_session.query(Image).filter(Image.extract == extract).all()
-    assert len(images) == len(example_messages)
-    # other extract and images still in database
-    assert len(rows_in_session.query(Extract).all()) > 1
-    assert len(rows_in_session.query(Image).all()) > len(example_messages)
diff --git a/cli/tests/test_database_cli_interaction.py b/cli/tests/test_database_cli_interaction.py
new file mode 100644
index 000000000..efd4f147b
--- /dev/null
+++ b/cli/tests/test_database_cli_interaction.py
@@ -0,0 +1,76 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""Test database interaction methods for the cli."""
+
+from core.db.models import Extract, Image
+from pandas.testing import assert_frame_equal
+from pixl_cli._database import exported_images_for_project, filter_exported_or_add_to_db
+
+
+def test_project_doesnt_exist(example_messages_df, db_session):
+    """If project doesn't exist, no filtering and then project & messages saved to database"""
+    output = filter_exported_or_add_to_db(example_messages_df)
+    assert_frame_equal(output, example_messages_df)
+    extract = db_session.query(Extract).one()
+    images = db_session.query(Image).filter(Image.extract == extract).all()
+    assert len(images) == len(example_messages_df)
+
+
+def test_first_image_exported(example_messages_df, rows_in_session):
+    """
+    GIVEN 3 messages, where one has been exported, the second has been saved to db but not exported
+    WHEN the messages are filtered
+    THEN the first message that has an exported_at value should not be in the filtered list
+        and all images should be saved to the database
+    """
+    output = filter_exported_or_add_to_db(example_messages_df)
+    assert len(output) == len(example_messages_df) - 1
+    assert "123" not in output.accession_number.to_numpy()
+    extract = rows_in_session.query(Extract).one()
+    images = rows_in_session.query(Image).filter(Image.extract == extract).all()
+    assert len(images) == len(example_messages_df)
+
+
+def test_new_extract_with_overlapping_images(example_messages_df, rows_in_session):
+    """
+    GIVEN messages from a new extract, two have been saved to the database with another extract
+    WHEN the messages are filtered
+    THEN all messages should be returned and all new images should be added
+    """
+    new_project_name = "new-project"
+    example_messages_df["project_name"] = new_project_name
+
+    output = filter_exported_or_add_to_db(example_messages_df)
+
+    # none filtered out
+    assert len(output) == len(example_messages_df)
+    # all new batch of images saved
+    extract = rows_in_session.query(Extract).filter(Extract.slug == new_project_name).one()
+    images = rows_in_session.query(Image).filter(Image.extract == extract).all()
+    assert len(images) == len(example_messages_df)
+    # other extract and images still in database
+    assert len(rows_in_session.query(Extract).all()) > 1
+    assert len(rows_in_session.query(Image).all()) > len(example_messages_df)
+
+
+def test_processed_images_for_project(rows_in_session):
+    """
+    GIVEN a project with 3 images in the database, only one of which is exported
+    WHEN the processed_images_for_project function is called
+    THEN only the exported images are returned
+    """
+    processed = exported_images_for_project("i-am-a-project")
+    assert len(processed) == 1
+    assert processed[0].accession_number == "123"
diff --git a/cli/tests/test_docker_commands.py b/cli/tests/test_docker_commands.py
new file mode 100644
index 000000000..a9590fa8f
--- /dev/null
+++ b/cli/tests/test_docker_commands.py
@@ -0,0 +1,61 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Docker commands tests"""
+
+import pytest
+from click.testing import CliRunner
+from pixl_cli.main import PIXL_ROOT, cli
+
+
+@pytest.fixture(autouse=True)
+def _change_working_directory(monkeypatch) -> None:
+    """
+    Change the working directory to the PIXL root directory.
+    This is required to spin up the docker containers.
+    """
+    monkeypatch.setenv("ENV", "test")
+    monkeypatch.chdir(PIXL_ROOT)
+
+
+@pytest.fixture()
+def default_args() -> list[str]:
+    """Default arguments for the docker commands."""
+    return ["--dry-run", "--env-file=test/.env"]
+
+
+def test_pixl_up_works(default_args):
+    """Test that pixl up works and attempts to spin up docker containers."""
+    runner = CliRunner()
+    result = runner.invoke(cli, args=["dc", *default_args, "up"])
+    assert result.exit_code == 0
+
+
+def test_pixl_down_works(default_args):
+    """Test that pixl up works and attempts to spin up docker containers."""
+    runner = CliRunner()
+    result = runner.invoke(cli, args=["dc", *default_args, "down"])
+    assert result.exit_code == 0
+
+
+def test_pixl_down_warns_on_volumes(monkeypatch, default_args):
+    """Test that a warning is displayed when attempting to remove volumes in production."""
+    monkeypatch.setenv("ENV", "prod")
+
+    runner = CliRunner()
+    result = runner.invoke(cli, args=["dc", *default_args, "down", "--volumes"])
+
+    assert result.exit_code == 0
+    assert "WARNING: Attempting to remove volumes in production." in result.output
+    assert "Are you sure you want to remove the volumes?" in result.output
+    assert "Running 'docker compose down' without removing volumes." in result.output
diff --git a/cli/tests/test_io.py b/cli/tests/test_io.py
index e02aeedcb..18b50b00d 100644
--- a/cli/tests/test_io.py
+++ b/cli/tests/test_io.py
@@ -19,17 +19,19 @@
 
 import pytest
 from core.db.models import Extract, Image
-from pixl_cli._io import make_radiology_linker_table, messages_from_csv
+from pixl_cli._io import make_radiology_linker_table, read_patient_info
+from pydicom.uid import generate_uid
 
 
 def test_message_from_csv_raises_for_malformed_input(tmpdir):
     """Test that messages_from_csv raises for malformed input."""
     # Create a CSV file with the wrong column names
     csv_file = tmpdir.join("malformed.csv")
-    csv_file.write("procedure_id,mrn,accession_number,extract_generated_timestamp,study_date\n")
-    csv_file.write("1,123,1234,01/01/2021 00:00,01/01/2021\n")
+    with csv_file.open("w") as f:
+        f.write("procedure_id,mrn,accession_number,extract_generated_timestamp,study_date\n")
+        f.write("1,123,1234,01/01/2021 00:00,01/01/2021\n")
     with pytest.raises(ValueError, match=".*expected to have at least.*"):
-        messages_from_csv(csv_file)
+        read_patient_info(Path(csv_file))
 
 
 def test_make_radiology_linker_table(omop_resources: Path):
@@ -43,28 +45,28 @@ def test_make_radiology_linker_table(omop_resources: Path):
             accession_number="AA12345601",
             study_date=date(1, 1, 1),
             mrn="987654321",
-            hashed_identifier="test_hashed_id_1",
+            pseudo_study_uid=generate_uid(entropy_srcs=["test_pseudo_id_1"]),
             extract=extract,
         ),
         Image(
             accession_number="AA12345605",
             study_date=date(1, 1, 1),
             mrn="987654321",
-            hashed_identifier="test_hashed_id_2",
+            pseudo_study_uid=generate_uid(entropy_srcs=["test_pseudo_id_2"]),
             extract=extract,
         ),
         Image(
             accession_number="different_should_ignore",
             study_date=date(1, 1, 1),
             mrn="987654321",
-            hashed_identifier="should_never_see_1",
+            pseudo_study_uid=generate_uid(entropy_srcs=["should_never_see_1"]),
             extract=extract,
         ),
         Image(
             accession_number="AA12345605",
             study_date=date(1, 1, 1),
             mrn="different_should_ignore",
-            hashed_identifier="should_never_see_2",
+            pseudo_study_uid=generate_uid(entropy_srcs=["should_never_see_2"]),
             extract=extract,
         ),
     ]
@@ -73,8 +75,8 @@ def test_make_radiology_linker_table(omop_resources: Path):
     po_col = linker_df["procedure_occurrence_id"]
     row_po_4 = linker_df[po_col == 4].iloc[0]
     row_po_5 = linker_df[po_col == 5].iloc[0]
-    assert row_po_4.hashed_identifier == "test_hashed_id_1"
-    assert row_po_5.hashed_identifier == "test_hashed_id_2"
+    assert row_po_4.pseudo_study_uid == generate_uid(entropy_srcs=["test_pseudo_id_1"])
+    assert row_po_5.pseudo_study_uid == generate_uid(entropy_srcs=["test_pseudo_id_2"])
 
     assert linker_df.shape[0] == 2
-    assert set(linker_df.columns) == {"procedure_occurrence_id", "hashed_identifier"}
+    assert set(linker_df.columns) == {"procedure_occurrence_id", "pseudo_study_uid"}
diff --git a/cli/tests/test_message_processing.py b/cli/tests/test_message_processing.py
new file mode 100644
index 000000000..dbd473486
--- /dev/null
+++ b/cli/tests/test_message_processing.py
@@ -0,0 +1,100 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""Test message processing module."""
+
+import os
+from collections.abc import Generator
+from unittest.mock import Mock
+
+import pytest
+from _pytest.monkeypatch import MonkeyPatch
+from core.patient_queue.producer import PixlProducer
+from pixl_cli._message_processing import retry_until_export_count_is_unchanged
+
+
+@pytest.fixture()
+def _zero_message_count(monkeypatch: MonkeyPatch) -> None:
+    """Ensure that message count is always zero, so that we don't have to deal with rabbitmq"""
+    monkeypatch.setattr("pixl_cli._message_processing._message_count", lambda _: 0)
+
+
+@pytest.fixture()
+def mock_publisher(mocker) -> Generator[Mock, None, None]:
+    """Patched publisher that does nothing, returns MagicMock of the publish method."""
+    mocker.patch.object(PixlProducer, "__init__", return_value=None)
+    mocker.patch.object(PixlProducer, "__enter__", return_value=PixlProducer)
+    mocker.patch.object(PixlProducer, "__exit__")
+    return mocker.patch.object(PixlProducer, "publish")
+
+
+@pytest.mark.usefixtures("_zero_message_count")
+def test_no_retry_if_none_exported(example_messages_df, db_session, mock_publisher):
+    """
+    GIVEN no images have been exported before starting, and num_retries set to 5
+    WHEN rabbitmq messages set to zero and no messages are published to queue
+    THEN populate_queue_and_db should never be called
+    """
+    os.environ["CLI_RETRY_SECONDS"] = "1"
+
+    retry_until_export_count_is_unchanged(
+        example_messages_df,
+        num_retries=5,
+        queues_to_populate=["imaging-primary"],
+        messages_priority=1,
+    )
+
+    mock_publisher.assert_not_called()
+
+
+@pytest.mark.usefixtures("_zero_message_count")
+def test_retry_with_image_exported_and_no_change(
+    example_messages_df, rows_in_session, mock_publisher
+):
+    """
+    GIVEN one image already has been exported, and num_retries set to 5
+    WHEN rabbitmq messages set to zero and no messages are published to queue
+    THEN populate_queue_and_db should be called once
+    """
+    os.environ["CLI_RETRY_SECONDS"] = "1"
+
+    retry_until_export_count_is_unchanged(
+        example_messages_df,
+        num_retries=5,
+        queues_to_populate=["imaging-primary"],
+        messages_priority=1,
+    )
+
+    mock_publisher.assert_called_once()
+
+
+@pytest.mark.usefixtures("_zero_message_count")
+def test_retry_with_image_exported_and_no_change_multiple_projects(
+    example_messages_multiple_projects_df, rows_in_session, mock_publisher
+):
+    """
+    GIVEN one image across two projects has been exported, and num_retries set to 5
+    WHEN rabbitmq messages set to zero and no messages are published to queue
+    THEN populate_queue_and_db should be called once
+    """
+    os.environ["CLI_RETRY_SECONDS"] = "1"
+
+    retry_until_export_count_is_unchanged(
+        example_messages_multiple_projects_df,
+        num_retries=5,
+        queues_to_populate=["imaging-primary"],
+        messages_priority=1,
+    )
+
+    mock_publisher.assert_called_once()
diff --git a/cli/tests/test_messages_from_files.py b/cli/tests/test_messages_from_files.py
new file mode 100644
index 000000000..ca6c7339a
--- /dev/null
+++ b/cli/tests/test_messages_from_files.py
@@ -0,0 +1,190 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Unit tests for reading cohorts from parquet files."""
+
+from __future__ import annotations
+
+import datetime
+from typing import TYPE_CHECKING
+
+from core.db.models import Image
+from core.patient_queue.message import Message
+from pixl_cli._io import read_patient_info
+from pixl_cli._message_processing import messages_from_df, populate_queue_and_db
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+def test_messages_from_csv(omop_resources: Path) -> None:
+    """
+    Given a csv with a single dataset.
+    When the messages are generated from the directory
+    Then one message should be generated
+    """
+    # Arrange
+    test_csv = omop_resources / "test.csv"
+    messages_df = read_patient_info(test_csv)
+    # Act
+    messages = messages_from_df(messages_df)
+    # Assert
+    assert all(isinstance(msg, Message) for msg in messages)
+
+    expected_messages = [
+        Message(
+            procedure_occurrence_id=0,
+            mrn="patient_identifier",
+            accession_number="123456789",
+            study_uid="1.2.3.4.5.6.7.8",
+            project_name="ms-pinpoint-test",
+            extract_generated_timestamp=datetime.datetime.fromisoformat("2023-01-01T00:01:00Z"),
+            study_date=datetime.date.fromisoformat("2022-01-01"),
+        ),
+    ]
+    assert messages == expected_messages
+
+
+def test_messages_from_csv_multiple_projects(
+    omop_resources: Path, rows_in_session, mock_publisher
+) -> None:
+    """
+    GIVEN the database has a single Export entity, with one exported Image, one un-exported Image,
+    WHEN we parse a file with two projects, each with the same 3 images
+      where one project has already exported one of the images
+      and the other project has not exported any images
+    THEN the database should have 6 Images, with 5 messages returned.
+    """
+    input_file = omop_resources / "multiple_projects.csv"
+    messages_df = read_patient_info(input_file)
+    messages = populate_queue_and_db(["imaging-primary"], messages_df, messages_priority=1)
+
+    # Database has 6 rows now
+    images_in_db = rows_in_session.query(Image).all()
+    assert len(images_in_db) == 6
+    # Exported image filtered out
+    assert len(messages) == 5
+
+
+def test_messages_from_parquet(omop_resources: Path) -> None:
+    """
+    Given a valid OMOP ES extract with 4 procedures, two of which are x-rays.
+    When the messages are generated from the directory and the output of logfile parsing
+    Then two messages should be generated
+    """
+    # Arrange
+    omop_parquet_dir = omop_resources / "omop"
+    messages_df = read_patient_info(omop_parquet_dir)
+    # Act
+    messages = messages_from_df(messages_df)
+    # Assert
+    assert all(isinstance(msg, Message) for msg in messages)
+
+    expected_messages = [
+        Message(
+            mrn="987654321",
+            accession_number="AA12345601",
+            study_uid="1.3.6.1.4.1.14519.5.2.1.99.1071.12985477682660597455732044031486",
+            study_date=datetime.date.fromisoformat("2020-05-23"),
+            procedure_occurrence_id=4,
+            project_name="test-extract-uclh-omop-cdm",
+            extract_generated_timestamp=datetime.datetime.fromisoformat("2023-12-07T14:08:58"),
+        ),
+        Message(
+            mrn="987654321",
+            accession_number="AA12345605",
+            study_uid="1.2.276.0.7230010.3.1.2.929116473.1.1710754859.579485",
+            study_date=datetime.date.fromisoformat("2020-05-23"),
+            procedure_occurrence_id=5,
+            project_name="test-extract-uclh-omop-cdm",
+            extract_generated_timestamp=datetime.datetime.fromisoformat("2023-12-07T14:08:58"),
+        ),
+    ]
+
+    assert messages == expected_messages
+
+
+def test_batch_upload(omop_resources: Path, rows_in_session, mock_publisher) -> None:
+    """
+    GIVEN the database has a single Export entity, with one exported Image, one unexported Image
+    WHEN we parse a file with the two existing images and one new image with no participant_ids
+    THEN the database should have 3 images, and returned messages excludes the exported image.
+    """
+    input_file = omop_resources / "batch_input.csv"
+    messages_df = read_patient_info(input_file)
+    messages = populate_queue_and_db(["imaging-primary"], messages_df, messages_priority=1)
+
+    # Database has 3 rows now
+    images_in_db: list[Image] = rows_in_session.query(Image).all()
+    assert len(images_in_db) == 3
+    # Exported image filtered out
+    assert len(messages) == 2
+
+
+def test_duplicate_upload(omop_resources: Path, rows_in_session, mock_publisher) -> None:
+    """
+    GIVEN the database has a single Export entity, with one exported Image, one un-exported Image
+    WHEN we parse a file with duplicated entries the two existing images and one new image
+    THEN the database should have 3 Images, with two message returned.
+    """
+    input_file = omop_resources / "duplicate_input.csv"
+    messages_df = read_patient_info(input_file)
+    messages = populate_queue_and_db(["imaging-primary"], messages_df, messages_priority=1)
+
+    # Database has 3 rows now
+    images_in_db = rows_in_session.query(Image).all()
+    assert len(images_in_db) == 3
+    # Exported and duplicate messages filtered out
+    assert len(messages) == 2
+
+
+def test_upload_with_participant_id(omop_resources: Path, db_session, mock_publisher) -> None:
+    """
+    GIVEN the database is empty,
+    WHEN we parse a file with the images that have participant_ids,
+    THEN the database should have 3 images and the `pseudo_patient_id`s in the database should
+    math the participant_ids in the CSV file.
+    """
+    input_file = omop_resources / "participant_id.csv"
+    messages_df = read_patient_info(input_file)
+    messages = populate_queue_and_db(["imaging-primary"], messages_df, messages_priority=1)
+
+    # Database has 3 rows now
+    images_in_db: list[Image] = db_session.query(Image).all()
+    assert len(images_in_db) == 3
+    # A message per image
+    assert len(messages) == 3
+    # Pseudo_patient_id for new image is same as participant_ids in CSV file
+    assert images_in_db[0].pseudo_patient_id == "AAA00"
+    assert images_in_db[1].pseudo_patient_id == "BBB11"
+    assert images_in_db[2].pseudo_patient_id == "CCC22"
+
+
+def test_upload_with_no_participant_id(omop_resources: Path, db_session, mock_publisher) -> None:
+    """
+    GIVEN the database is empty,
+    WHEN we parse a file with images that do not have participant_ids,
+    THEN the database should have 3 images and the `pseudo_patient_id`s should be `None` in the
+    database.
+    """
+    input_file = omop_resources / "batch_input.csv"
+    messages_df = read_patient_info(input_file)
+    messages = populate_queue_and_db(["imaging-primary"], messages_df, messages_priority=1)
+
+    # Database has 3 rows now
+    images_in_db: list[Image] = db_session.query(Image).all()
+    assert len(images_in_db) == 3
+    # A message per image
+    assert len(messages) == 3
+    # Pseudo_patient_id for new image is same as participant_ids in CSV file
+    assert all(image.pseudo_patient_id is None for image in images_in_db)
diff --git a/cli/tests/test_messages_from_parquet.py b/cli/tests/test_messages_from_parquet.py
deleted file mode 100644
index a56bd3941..000000000
--- a/cli/tests/test_messages_from_parquet.py
+++ /dev/null
@@ -1,91 +0,0 @@
-#  Copyright (c) University College London Hospitals NHS Foundation Trust
-#
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
-"""Unit tests for reading cohorts from parquet files."""
-
-from __future__ import annotations
-
-import datetime
-from typing import TYPE_CHECKING
-
-from core.patient_queue.message import Message
-from pixl_cli._io import (
-    copy_parquet_return_logfile_fields,
-    messages_from_csv,
-    messages_from_parquet,
-)
-
-if TYPE_CHECKING:
-    from pathlib import Path
-
-
-def test_messages_from_csv(omop_resources: Path) -> None:
-    """
-    Given a csv with a single dataset.
-    When the messages are generated from the directory
-    Then one message should be generated
-    """
-    # Arrange
-    test_csv = omop_resources / "test.csv"
-    # Act
-    messages = messages_from_csv(test_csv)
-    # Assert
-    assert all(isinstance(msg, Message) for msg in messages)
-
-    expected_messages = [
-        Message(
-            mrn="patient_identifier",
-            accession_number="123456789",
-            study_date=datetime.date.fromisoformat("2022-01-01"),
-            procedure_occurrence_id="0",
-            project_name="ms-pinpoint-test",
-            extract_generated_timestamp=datetime.datetime(2022, 1, 1, 0, 1, tzinfo=datetime.UTC),
-        ),
-    ]
-    assert messages == expected_messages
-
-
-def test_messages_from_parquet(omop_resources: Path) -> None:
-    """
-    Given a valid OMOP ES extract with 4 procedures, two of which are x-rays.
-    When the messages are generated from the directory and the output of logfile parsing
-    Then two messages should be generated
-    """
-    # Arrange
-    omop_parquet_dir = omop_resources / "omop"
-    project_name, omop_es_datetime = copy_parquet_return_logfile_fields(omop_parquet_dir)
-    # Act
-    messages = messages_from_parquet(omop_parquet_dir, project_name, omop_es_datetime)
-    # Assert
-    assert all(isinstance(msg, Message) for msg in messages)
-
-    expected_messages = [
-        Message(
-            mrn="987654321",
-            accession_number="AA12345601",
-            study_date=datetime.date.fromisoformat("2020-05-23"),
-            procedure_occurrence_id=4,
-            project_name="test-extract-uclh-omop-cdm",
-            extract_generated_timestamp=datetime.datetime.fromisoformat("2023-12-07T14:08:58"),
-        ),
-        Message(
-            mrn="987654321",
-            accession_number="AA12345605",
-            study_date=datetime.date.fromisoformat("2020-05-23"),
-            procedure_occurrence_id=5,
-            project_name="test-extract-uclh-omop-cdm",
-            extract_generated_timestamp=datetime.datetime.fromisoformat("2023-12-07T14:08:58"),
-        ),
-    ]
-
-    assert messages == expected_messages
diff --git a/cli/tests/test_populate.py b/cli/tests/test_populate.py
index 3a279a043..86b48e364 100644
--- a/cli/tests/test_populate.py
+++ b/cli/tests/test_populate.py
@@ -13,11 +13,13 @@
 #  limitations under the License.
 """Patient queue tests"""
 
+# ruff: noqa: SLF001 allow accessing of private members for mocking
+
 from __future__ import annotations
 
 from typing import TYPE_CHECKING
 
-import pixl_cli.main
+import pixl_cli._message_processing
 from click.testing import CliRunner
 from core.patient_queue.producer import PixlProducer
 from pixl_cli.main import populate
@@ -39,7 +41,7 @@ def __exit__(self, *args: object, **kwargs) -> None:
         """Context exit point."""
         return
 
-    def publish(self, messages: list[Message]) -> None:  # noqa: ARG002 don't access messages
+    def publish(self, messages: list[Message], priority: int) -> None:  # noqa: ARG002 don't access messages or priority
         """Dummy method for publish."""
         return
 
@@ -51,9 +53,12 @@ def test_populate_queue_parquet(
     omop_parquet_dir = str(omop_resources / "omop")
     runner = CliRunner()
 
-    monkeypatch.setattr(pixl_cli.main, "PixlProducer", MockProducer)
+    monkeypatch.setattr(pixl_cli._message_processing, "PixlProducer", MockProducer)
 
-    result = runner.invoke(populate, args=[omop_parquet_dir, "--queues", queue_name, "--no-start"])
+    result = runner.invoke(
+        populate,
+        args=[omop_parquet_dir, "--queues", queue_name, "--no-start", "--num-retries", "0"],
+    )
     assert result.exit_code == 0
 
 
@@ -65,12 +70,17 @@ def test_populate_queue_and_start(
     runner = CliRunner()
 
     mocked_start = mocker.patch("pixl_cli.main._start_or_update_extract")
-    monkeypatch.setattr(pixl_cli.main, "PixlProducer", MockProducer)
+    monkeypatch.setattr(pixl_cli._message_processing, "PixlProducer", MockProducer)
 
-    result = runner.invoke(populate, args=[omop_parquet_dir, "--queues", queue_name, "--no-start"])
+    result = runner.invoke(
+        populate,
+        args=[omop_parquet_dir, "--queues", queue_name, "--no-start", "--num-retries", "0"],
+    )
     assert result.exit_code == 0
     mocked_start.assert_not_called()
 
-    result = runner.invoke(populate, args=[omop_parquet_dir, "--queues", queue_name])
+    result = runner.invoke(
+        populate, args=[omop_parquet_dir, "--queues", queue_name, "--num-retries", "0"]
+    )
     assert result.exit_code == 0
     mocked_start.assert_called_with(queues=queue_name.split(","), rate=None)
diff --git a/docker-compose.yml b/docker-compose.yml
index 21770d113..996853e28 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -31,6 +31,7 @@ x-build-args-common: &build-args-common
 x-pixl-common-env: &pixl-common-env
     DEBUG: ${DEBUG}
     LOG_LEVEL: ${LOG_LEVEL}
+    TZ: ${TZ:-Europe/London}
 
 x-pixl-rabbit-mq: &pixl-rabbit-mq
     RABBITMQ_HOST: "queue" # Name of the queue service
@@ -38,14 +39,6 @@ x-pixl-rabbit-mq: &pixl-rabbit-mq
     RABBITMQ_USERNAME: ${RABBITMQ_USERNAME}
     RABBITMQ_PASSWORD: ${RABBITMQ_PASSWORD}
 
-x-emap-db: &emap-db
-    EMAP_UDS_HOST: ${EMAP_UDS_HOST}
-    EMAP_UDS_PORT: ${EMAP_UDS_PORT}
-    EMAP_UDS_NAME: ${EMAP_UDS_NAME}
-    EMAP_UDS_USER: ${EMAP_UDS_USER}
-    EMAP_UDS_PASSWORD: ${EMAP_UDS_PASSWORD}
-    EMAP_UDS_SCHEMA_NAME: ${EMAP_UDS_SCHEMA_NAME}
-
 x-pixl-db: &pixl-db
     PIXL_DB_HOST: ${PIXL_DB_HOST}
     PIXL_DB_PORT: ${PIXL_DB_PORT}
@@ -114,10 +107,12 @@ services:
             target: pixl_orthanc_anon
             args:
                 <<: *build-args-common
+                ORTHANC_CONCURRENT_JOBS: ${ORTHANC_CONCURRENT_JOBS}
         platform: linux/amd64
         command: /run/secrets
+        restart: always
         environment:
-            <<: [*proxy-common, *pixl-common-env, *azure-keyvault]
+            <<: [*pixl-db, *proxy-common, *pixl-common-env, *azure-keyvault]
             ORTHANC_NAME: "PIXL: Anon"
             ORTHANC_USERNAME: ${ORTHANC_ANON_USERNAME}
             ORTHANC_PASSWORD: ${ORTHANC_ANON_PASSWORD}
@@ -126,19 +121,18 @@ services:
             ORTHANC_RAW_AE_TITLE: ${ORTHANC_RAW_AE_TITLE}
             ORTHANC_RAW_DICOM_PORT: "4242"
             ORTHANC_RAW_HOSTNAME: "orthanc-raw"
+            ORTHANC_RAW_URL: ${ORTHANC_RAW_URL}
+            ORTHANC_RAW_USERNAME: ${ORTHANC_RAW_USERNAME}
+            ORTHANC_RAW_PASSWORD: ${ORTHANC_RAW_PASSWORD}
+            PIXL_DICOM_TRANSFER_TIMEOUT: ${PIXL_DICOM_TRANSFER_TIMEOUT}
+            PIXL_MAX_MESSAGES_IN_FLIGHT: ${PIXL_MAX_MESSAGES_IN_FLIGHT}
             # For the export API
             ORTHANC_ANON_URL: "http://localhost:8042"
             ORTHANC_ANON_USERNAME: ${ORTHANC_ANON_USERNAME}
             ORTHANC_ANON_PASSWORD: ${ORTHANC_ANON_PASSWORD}
-            PIXL_DB_HOST: ${PIXL_DB_HOST}
-            PIXL_DB_PORT: ${PIXL_DB_PORT}
-            PIXL_DB_NAME: ${PIXL_DB_NAME}
-            PIXL_DB_USER: ${PIXL_DB_USER}
-            PIXL_DB_PASSWORD: ${PIXL_DB_PASSWORD}
             DICOM_WEB_PLUGIN_ENABLED: ${ENABLE_DICOM_WEB}
             HASHER_API_AZ_NAME: "hasher-api"
             HASHER_API_PORT: 8000
-            HTTP_TIMEOUT: ${ORTHANC_ANON_HTTP_TIMEOUT}
             AZ_DICOM_ENDPOINT_NAME: ${AZ_DICOM_ENDPOINT_NAME}
             AZ_DICOM_ENDPOINT_URL: ${AZ_DICOM_ENDPOINT_URL}
             AZ_DICOM_ENDPOINT_TOKEN: ${AZ_DICOM_ENDPOINT_TOKEN}
@@ -156,7 +150,6 @@ services:
             - type: volume
               source: orthanc-anon-data
               target: /var/lib/orthanc/db
-            - ${PWD}/orthanc/orthanc-anon/config:/run/secrets:ro
             - ${PWD}/projects/configs:/${PROJECT_CONFIGS_DIR:-/projects/configs}:ro
         networks:
             - pixl-net
@@ -176,7 +169,6 @@ services:
             retries: 2
             interval: 3s
             timeout: 2s
-        restart: "no"
 
     orthanc-raw:
         build:
@@ -187,7 +179,8 @@ services:
                 <<: *build-args-common
                 ORTHANC_RAW_MAXIMUM_STORAGE_SIZE: ${ORTHANC_RAW_MAXIMUM_STORAGE_SIZE}
                 ORTHANC_RAW_JOB_HISTORY_SIZE: ${ORTHANC_RAW_JOB_HISTORY_SIZE}
-                ORTHANC_RAW_CONCURRENT_JOBS: ${ORTHANC_RAW_CONCURRENT_JOBS}
+                ORTHANC_CONCURRENT_JOBS: ${ORTHANC_CONCURRENT_JOBS}
+                PIXL_DICOM_TRANSFER_TIMEOUT: ${PIXL_DICOM_TRANSFER_TIMEOUT}
         platform: linux/amd64
         command: /run/secrets
         environment:
@@ -196,12 +189,14 @@ services:
             ORTHANC_USERNAME: ${ORTHANC_RAW_USERNAME}
             ORTHANC_PASSWORD: ${ORTHANC_RAW_PASSWORD}
             ORTHANC_RAW_AE_TITLE: ${ORTHANC_RAW_AE_TITLE}
-            ORTHANC_AUTOROUTE_RAW_TO_ANON: ${ORTHANC_AUTOROUTE_RAW_TO_ANON}
             ORTHANC_RAW_RECORD_HEADERS: ${ORTHANC_RAW_RECORD_HEADERS}
             ORTHANC_RAW_HEADER_LOG_PATH: ${ORTHANC_RAW_HEADER_LOG_PATH}
-            VNAQR_AE_TITLE: ${VNAQR_AE_TITLE}
-            VNAQR_DICOM_PORT: ${VNAQR_DICOM_PORT}
-            VNAQR_IP_ADDR: ${VNAQR_IP_ADDR}
+            PRIMARY_DICOM_SOURCE_AE_TITLE: ${PRIMARY_DICOM_SOURCE_AE_TITLE}
+            PRIMARY_DICOM_SOURCE_PORT: ${PRIMARY_DICOM_SOURCE_PORT}
+            PRIMARY_DICOM_SOURCE_IP_ADDR: ${PRIMARY_DICOM_SOURCE_IP_ADDR}
+            SECONDARY_DICOM_SOURCE_AE_TITLE: ${SECONDARY_DICOM_SOURCE_AE_TITLE:-$PRIMARY_DICOM_SOURCE_AE_TITLE}
+            SECONDARY_DICOM_SOURCE_PORT: ${SECONDARY_DICOM_SOURCE_PORT:-$PRIMARY_DICOM_SOURCE_PORT}
+            SECONDARY_DICOM_SOURCE_IP_ADDR: ${SECONDARY_DICOM_SOURCE_IP_ADDR:-$PRIMARY_DICOM_SOURCE_IP_ADDR}
             ORTHANC_ANON_AE_TITLE: ${ORTHANC_ANON_AE_TITLE}
             ORTHANC_ANON_DICOM_PORT: "4242"
             ORTHANC_ANON_HOSTNAME: "orthanc-anon"
@@ -231,15 +226,16 @@ services:
             retries: 10
             interval: 3s
             timeout: 2s
-        restart: "no"
+        restart: "always"
 
     queue:
-        image: rabbitmq:3.12.9-management
+        image: rabbitmq:3.13.7-management@sha256:1c32767bb8f7afb93fe99b890c05a250936bc2836fa3fd0154058f3953207095
         hostname: queue-host
         environment:
             RABBITMQ_DEFAULT_USER: ${RABBITMQ_USERNAME}
             RABBITMQ_DEFAULT_PASS: ${RABBITMQ_PASSWORD}
             RABBITMQ_NODENAME: "rabbit@queue-host"
+            TZ: ${TZ:-Europe/London}
         healthcheck:
             test: rabbitmq-diagnostics -q check_running
             interval: 30s
@@ -265,7 +261,6 @@ services:
             <<:
                 [
                     *pixl-db,
-                    *emap-db,
                     *proxy-common,
                     *pixl-common-env,
                     *pixl-rabbit-mq,
@@ -276,6 +271,9 @@ services:
             ORTHANC_ANON_PASSWORD: ${ORTHANC_ANON_PASSWORD}
             PROJECT_CONFIGS_DIR: /${PROJECT_CONFIGS_DIR:-/projects/configs}
             PIXL_MAX_MESSAGES_IN_FLIGHT: ${PIXL_MAX_MESSAGES_IN_FLIGHT}
+            HTTP_TIMEOUT: ${PIXL_DICOM_TRANSFER_TIMEOUT}
+            XNAT_OVERWRITE: ${XNAT_OVERWRITE}
+            XNAT_DESTINATION: ${XNAT_DESTINATION}
         env_file:
             - ./docker/common.env
         depends_on:
@@ -314,6 +312,8 @@ services:
                 condition: service_healthy
             orthanc-raw:
                 condition: service_healthy
+            orthanc-anon:
+                condition: service_healthy
         healthcheck:
             interval: 10s
             timeout: 30s
@@ -326,7 +326,16 @@ services:
             ORTHANC_RAW_USERNAME: ${ORTHANC_RAW_USERNAME}
             ORTHANC_RAW_PASSWORD: ${ORTHANC_RAW_PASSWORD}
             ORTHANC_RAW_AE_TITLE: ${ORTHANC_RAW_AE_TITLE}
-            VNAQR_MODALITY: ${VNAQR_MODALITY}
+            ORTHANC_AUTOROUTE_RAW_TO_ANON: ${ORTHANC_AUTOROUTE_RAW_TO_ANON}
+            PRIMARY_DICOM_SOURCE_MODALITY: ${PRIMARY_DICOM_SOURCE_MODALITY}
+            PRIMARY_DICOM_SOURCE_AE_TITLE: ${PRIMARY_DICOM_SOURCE_AE_TITLE}
+            SECONDARY_DICOM_SOURCE_MODALITY: ${SECONDARY_DICOM_SOURCE_MODALITY}
+            SECONDARY_DICOM_SOURCE_AE_TITLE: ${SECONDARY_DICOM_SOURCE_AE_TITLE:-$PRIMARY_DICOM_SOURCE_AE_TITLE}
+            ORTHANC_ANON_URL: ${ORTHANC_ANON_URL}
+            ORTHANC_ANON_USERNAME: ${ORTHANC_ANON_USERNAME}
+            ORTHANC_ANON_PASSWORD: ${ORTHANC_ANON_PASSWORD}
+            ORTHANC_ANON_AE_TITLE: ${ORTHANC_ANON_AE_TITLE}
+            ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT: ${ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT}
             SKIP_ALEMBIC: ${SKIP_ALEMBIC}
             PIXL_DB_HOST: ${PIXL_DB_HOST}
             PIXL_DB_PORT: ${PIXL_DB_PORT}
@@ -351,7 +360,7 @@ services:
             POSTGRES_USER: ${PIXL_DB_USER}
             POSTGRES_PASSWORD: ${PIXL_DB_PASSWORD}
             POSTGRES_DB: ${PIXL_DB_NAME}
-            PGTZ: Europe/London
+            PGTZ: ${TZ:-Europe/London}
         env_file:
             - ./docker/common.env
         command: postgres -c 'config_file=/etc/postgresql/postgresql.conf'
@@ -362,7 +371,7 @@ services:
         ports:
             - "${POSTGRES_PORT}:5432"
         healthcheck:
-            test: ["CMD", "pg_isready", "-U", "${PIXL_DB_USER}"]
+            test: ["CMD", "pg_isready", "-U", "${PIXL_DB_USER}", "--dbname", "${PIXL_DB_NAME}"]
             interval: 10s
             timeout: 30s
             retries: 5
diff --git a/docker/orthanc/Dockerfile b/docker/orthanc/Dockerfile
index 1d85f8e1b..a78503428 100644
--- a/docker/orthanc/Dockerfile
+++ b/docker/orthanc/Dockerfile
@@ -11,15 +11,14 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-FROM orthancteam/orthanc:24.3.3 AS pixl_orthanc_base
+FROM orthancteam/orthanc:24.7.3@sha256:57a3d037729897331027ddc00c12695b50f1effbbf805f855396f3d0248d2d5f AS pixl_orthanc_base
 SHELL ["/bin/bash", "-o", "pipefail", "-e", "-u", "-x", "-c"]
 
-
 # Create a virtual environment, recommended since python 3.11 and Debian bookworm based images
 # where you get a warning when installing system-wide packages.
 RUN export DEBIAN_FRONTEND=noninteractive && \
     apt-get update && \
-    apt-get install --yes --no-install-recommends python3-venv
+    apt-get install --yes --no-install-recommends python3-venv tzdata
 RUN python3 -m venv /.venv
 
 # Install curl for now, but try to remove this dependency
@@ -48,11 +47,13 @@ COPY ./orthanc/orthanc-raw/plugin/pixl.py /etc/orthanc/pixl.py
 # Orthanc can't substitute environment veriables as integers so copy and replace before running
 ARG ORTHANC_RAW_MAXIMUM_STORAGE_SIZE
 ARG ORTHANC_RAW_JOB_HISTORY_SIZE
-ARG ORTHANC_RAW_CONCURRENT_JOBS
+ARG ORTHANC_CONCURRENT_JOBS
+ARG PIXL_DICOM_TRANSFER_TIMEOUT
 COPY ./orthanc/orthanc-raw/config /run/secrets
 RUN sed -i "s/\${ORTHANC_RAW_MAXIMUM_STORAGE_SIZE}/${ORTHANC_RAW_MAXIMUM_STORAGE_SIZE:-0}/g" /run/secrets/orthanc.json
 RUN sed -i "s/\${ORTHANC_RAW_JOB_HISTORY_SIZE}/${ORTHANC_RAW_JOB_HISTORY_SIZE:-100}/g" /run/secrets/orthanc.json
-RUN sed -i "s/\${ORTHANC_RAW_CONCURRENT_JOBS}/${ORTHANC_RAW_CONCURRENT_JOBS:-5}/g" /run/secrets/orthanc.json
+RUN sed -i "s/\${ORTHANC_CONCURRENT_JOBS}/${ORTHANC_CONCURRENT_JOBS:-5}/g" /run/secrets/orthanc.json
+RUN sed -i "s/\${ORTHANC_RAW_STABLE_SECONDS}/${PIXL_DICOM_TRANSFER_TIMEOUT:-600}/g" /run/secrets/orthanc.json
 
 ENV PYTHONPATH=/.venv/lib64/python3.11/site-packages/
 
@@ -60,3 +61,12 @@ FROM pixl_orthanc_base AS pixl_orthanc_anon
 COPY ./orthanc/orthanc-anon/plugin/pixl.py /etc/orthanc/pixl.py
 
 ENV PYTHONPATH=/.venv/lib64/python3.11/site-packages/
+COPY ./orthanc/orthanc-anon/plugin/download_dicom_spec.py /etc/orthanc/download_dicom_spec.py
+RUN --mount=type=cache,target=/root/.cache \
+    python3 /etc/orthanc/download_dicom_spec.py
+
+ARG ORTHANC_CONCURRENT_JOBS
+COPY ./orthanc/orthanc-anon/config /run/secrets
+
+RUN sed -i "s/\${ORTHANC_CONCURRENT_JOBS}/${ORTHANC_CONCURRENT_JOBS:-5}/g" /run/secrets/orthanc.json
+
diff --git a/docker/pixl-python/Dockerfile b/docker/pixl-python/Dockerfile
index f730168c3..84f188c57 100644
--- a/docker/pixl-python/Dockerfile
+++ b/docker/pixl-python/Dockerfile
@@ -11,7 +11,7 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-FROM python:3.11.7-slim-bullseye AS pixl_python_base
+FROM python:3.12.4-slim-bullseye@sha256:26ce493641ad3b1c8a6202117c31340c7bbb2dc126f1aeee8ea3972730a81dc6 AS pixl_python_base
 SHELL ["/bin/bash", "-o", "pipefail", "-e", "-u", "-x", "-c"]
 
 ARG TEST="false"
@@ -25,7 +25,9 @@ RUN export DEBIAN_FRONTEND=noninteractive && \
         libpq-dev \
         curl \
         gnupg \
-        locales
+        locales \
+        tzdata
+
 RUN sed -i '/en_GB.UTF-8/s/^# //g' /etc/locale.gen && locale-gen
 RUN  apt-get autoremove && apt-get clean && rm -rf /var/lib/apt/lists/*
 
diff --git a/docker/postgres/Dockerfile b/docker/postgres/Dockerfile
index 8888138cc..bf615f6e8 100644
--- a/docker/postgres/Dockerfile
+++ b/docker/postgres/Dockerfile
@@ -11,12 +11,12 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-FROM postgres:16-bookworm
+FROM postgres:16-bookworm@sha256:5620f242bbc0e17478556102327e7efcf60ab48de3607c9e0ea98800841785ec
 
 # OS setup
 RUN export DEBIAN_FRONTEND=noninteractive && \
     apt-get update && \
-    apt-get install --yes --no-install-recommends procps ca-certificates locales python3 python3-pip python3.11-venv && \
+    apt-get install --yes --no-install-recommends procps ca-certificates locales python3 python3-pip python3.11-venv tzdata && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 RUN sed -i '/en_GB.UTF-8/s/^# //g' /etc/locale.gen && locale-gen
diff --git a/docs/design/bigger_picture.md b/docs/design/bigger_picture.md
index 06e643d85..27750abbf 100644
--- a/docs/design/bigger_picture.md
+++ b/docs/design/bigger_picture.md
@@ -1,5 +1,7 @@
 # The bigger picture
 
-The [System design for linkage and export of imaging and EHR data](https://github.com/UCLH-Foundry/the-rolling-skeleton/blob/main/docs/design/system-design.md)
+The [System design for linkage and export of imaging and EHR data](https://github.com/SAFEHR-data/the-rolling-skeleton/blob/main/docs/design/system-design.md)
 document in `the-rolling-skeleton` repository provides an overview of the overall system
 architecture and the components that make up the system that PIXL is part of.
+
+Please request access to the `the-rolling-skeleton` repository and add further details in a [new blank issue](https://github.com/SAFEHR-data/PIXL/issues/new).
\ No newline at end of file
diff --git a/docs/design/diagrams/pixl-multi-project-config.drawio b/docs/design/diagrams/pixl-multi-project-config.drawio
index 62a6f07ac..1bdb84394 100644
--- a/docs/design/diagrams/pixl-multi-project-config.drawio
+++ b/docs/design/diagrams/pixl-multi-project-config.drawio
@@ -10,7 +10,7 @@
         <mxCell id="KNKUc1UJHXEjSF4-eD5e-1" value="&lt;h2&gt;Config template&lt;/h2&gt;" style="shape=hexagon;perimeter=hexagonPerimeter2;whiteSpace=wrap;html=1;fixedSize=1;fillColor=#e1d5e7;strokeColor=#9673a6;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
           <mxGeometry x="70" y="90" width="120" height="80" as="geometry" />
         </mxCell>
-        <mxCell id="KNKUc1UJHXEjSF4-eD5e-2" value="&lt;pre&gt;&lt;span style=&quot;font-style: normal;&quot;&gt;UCLH-Foundry/PIXL&lt;/span&gt;&lt;/pre&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=1;points=[];autosize=1;strokeColor=none;fillColor=none;fontFamily=Courier New;fontStyle=2;movable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
+        <mxCell id="KNKUc1UJHXEjSF4-eD5e-2" value="&lt;pre&gt;&lt;span style=&quot;font-style: normal;&quot;&gt;SAFEHR-data/PIXL&lt;/span&gt;&lt;/pre&gt;" style="text;html=1;align=center;verticalAlign=middle;resizable=1;points=[];autosize=1;strokeColor=none;fillColor=none;fontFamily=Courier New;fontStyle=2;movable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
           <mxGeometry x="55" y="50" width="150" height="50" as="geometry" />
         </mxCell>
         <mxCell id="KNKUc1UJHXEjSF4-eD5e-53" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;curved=1;dashed=1;dashPattern=12 12;endArrow=none;endFill=0;entryX=1;entryY=0;entryDx=0;entryDy=0;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" source="KNKUc1UJHXEjSF4-eD5e-3" target="KNKUc1UJHXEjSF4-eD5e-51" edge="1">
@@ -25,7 +25,7 @@
         <mxCell id="KNKUc1UJHXEjSF4-eD5e-3" value="&lt;pre style=&quot;font-size: 15px;&quot;&gt;my_project.toml&lt;/pre&gt;" style="rounded=1;whiteSpace=wrap;html=1;fontSize=15;fillColor=#dae8fc;strokeColor=#6c8ebf;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
           <mxGeometry x="260" y="95" width="140" height="70" as="geometry" />
         </mxCell>
-        <mxCell id="KNKUc1UJHXEjSF4-eD5e-5" value="&lt;pre&gt;UCLH-Foundry/PIXL&lt;/pre&gt;" style="swimlane;whiteSpace=wrap;html=1;fillColor=#d5e8d4;strokeColor=#82b366;container=1;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
+        <mxCell id="KNKUc1UJHXEjSF4-eD5e-5" value="&lt;pre&gt;SAFEHR-data/PIXL&lt;/pre&gt;" style="swimlane;whiteSpace=wrap;html=1;fillColor=#d5e8d4;strokeColor=#82b366;container=1;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1">
           <mxGeometry x="610" y="40" width="200" height="150" as="geometry" />
         </mxCell>
         <mxCell id="KNKUc1UJHXEjSF4-eD5e-11" value="" style="group;movable=1;resizable=1;rotatable=1;deletable=1;editable=1;locked=0;connectable=1;" parent="1" vertex="1" connectable="0">
diff --git a/docs/file_types/parquet_files.md b/docs/file_types/parquet_files.md
index 3fd9a7df5..8b56234e1 100644
--- a/docs/file_types/parquet_files.md
+++ b/docs/file_types/parquet_files.md
@@ -3,7 +3,7 @@
 ## OMOP-ES files
 
 From
-[OMOP-ES](https://github.com/UCLH-Foundry/the-rolling-skeleton/blob/main/docs/design/100-day-design.md#data-flow-through-components)
+[OMOP-ES](https://github.com/SAFEHR-data/the-rolling-skeleton/blob/main/docs/design/100-day-design.md#data-flow-through-components)
 we receive parquet files defining the data we need to export. These input files appear as 2 groups:
 
 1. **Public** parquet files: have had identifiers removed and replaced with a sequential ID for the
@@ -22,7 +22,7 @@ parquet file.
 ## Radiology linker table
 
 An output parquet file named `IMAGE_LINKER.parquet` that defines the connection between the
-OMOP procedure_occurrence_id for the current extract and the hashed image/study ID.
+OMOP procedure_occurrence_id for the current extract and the pseudo image/study ID.
 The procedure_occurrence_id can get renumbered from extract to extract.
 
 See method `make_radiology_linker_table` for more.
@@ -42,10 +42,8 @@ implemented and documented in [`pixl_core`](../../pixl_core/README.md#uploading-
 
 Various _parquet_ files are provided throughout the repo to enable unit and system testing:
 
-- `cli/tests/resources/omop/` contains public and private parquet files together with an
-  `extract_summary.json` file to mimic the input received from OMOP-ES for the unit tests. (This directory is identical to that below and should be deleted at some point).
 - `test/resources/omop/` contains public and private parquet files together with an
-  `extract_summary.json` file to mimic the input received from OMOP-ES for the system tests
+  `extract_summary.json` file to mimic the input received from OMOP-ES for the system tests and cli unit tests
 
 During the system test, a `radiology.parquet` file is generated and temporarily stored in
 `projects/exports/test-extract-uclh-omop-cdm/latest/radiology/radiology.parquet` to check the successful
diff --git a/docs/services/pixl_database.md b/docs/services/pixl_database.md
index c30be5213..24058d9b5 100644
--- a/docs/services/pixl_database.md
+++ b/docs/services/pixl_database.md
@@ -2,7 +2,7 @@
 
 PIXL uses a [postgres database](../../postgres/README.md) to
 
-- Add hashed identifiers along with the originals for DICOM images (in `pixl_dcmd`)
+- Add pseudo identifiers along with the originals for DICOM images (in `pixl_dcmd`)
 - Keep track of the export status of imaging (in `core.uploader`) studies and the projects they are used in
 
 Note that the pipeline will not process any studies for a project that have already been exported.
diff --git a/docs/setup/azure-keyvault.md b/docs/setup/azure-keyvault.md
index 6ba6c180d..ed91884aa 100644
--- a/docs/setup/azure-keyvault.md
+++ b/docs/setup/azure-keyvault.md
@@ -1,6 +1,6 @@
 # Azure Keyvault setup
 
-_This is done for the \_UCLH_DIF\_ `dev` tenancy, will need to be done once in the _UCLHAZ_ `prod`
+_This is done for the \_UCLH_DIF\_ `dev` tenancy, will need to be done once in the __UCLHSDE__ `prod`
 tenancy when ready to deploy to production._
 
 This Key Vault and secret must persist any infrastructure changes so should be separate from disposable
diff --git a/docs/setup/developer.md b/docs/setup/developer.md
index 3c4a15681..07f13c9c0 100644
--- a/docs/setup/developer.md
+++ b/docs/setup/developer.md
@@ -1,21 +1,111 @@
 # Developer setup
 
+## Setting up `Python` Virtual Environment (VE)
+
+### Using conda
+```
+conda create -n "pixlVE" python=3.11  pip -c conda-forge --yes
+conda activate pixlVE
+conda list -n pixlVE #to check installed packages
+conda deactivate #to deactivate VE 
+conda remove -n pixlVE --all #to remove pixlVE environment 
+```
+
+### Using python virtual environment `venv`
+You require `python3-venv` to setup your `venv`. See further details [here](https://docs.python.org/3/library/venv.html).
+```
+# Create path for venv
+cd $HOME
+mkdir pixlVE
+cd pixlVE
+# Create virtual environment
+python3 -m venv pixlVE
+source pixlVE/bin/activate
+```
+
+## Docker requirements 
+Most modules require `docker` and `docker-compose` to be installed to run tests.
+* [Docker](https://docs.docker.com/get-docker/) with version `>=27.0.3`
+* [Docker Compose](https://docs.docker.com/compose/install/#installation-scenarios) with version `>=v2.28.1-desktop.1`
+
+## Installation of `PIXL` modules
+
+You can install all PIXL Python modules by running the following commands from the `PIXL/` directory:
+
+```shell
+python -m pip install -e "pixl_core/[dev]"
+python -m pip install -e "pytest-pixl/[dev,test]"
+python -m pip install -e "pixl_core/[test]"
+python -m pip install -e "cli/[dev,test]"
+python -m pip install -e "pixl_imaging/[dev,test]"
+python -m pip install -e "pixl_dcmd/[dev,test]"
+python -m pip install -e "pixl_export/[dev,test]"
+python -m pip install -e "hasher/[dev,test]"
+```
+
 See each service's README for instructions for individual developing and testing instructions.
-Most modules require [`docker`](https://docs.docker.com/desktop/) and `docker-compose` to be installed to run tests.
 
-For Python development we use [ruff](https://docs.astral.sh/ruff/) and [mypy](https://mypy.readthedocs.io/)
-alongside [pytest](https://www.pytest.org/).
-There is support (sometimes through plugins) for these tools in most IDEs & editors.
+## Testing
+
+### Module-level testing
+
+Once you have installed each module, you can run the tests for a module using the `pytest` command, e.g.
+
+```shell
+cd pixl_core/
+pytest
+```
+
+Alternatively, you can run most of the module-level tests from the root of the repo with:
+
+```shell
+pytest #to test all tests `testpaths` pytest.ini
+```
+
+The `pytest.ini` file in the root of the repo contains the configuration for running most of the module-level tests at once.
+However, `pixl_dcmd` and `hasher` have `conftests.py` files that clash, so only `pixl_dcmd` is included as a `testpath` in the
+top-level `pytest.ini`. You will therefore need to run tests for `hasher` from the `hasher` directory.
+
+
+#### Enabling default Docker socket for testing `pixl_core`
+
+We have tests in `pixl_core` for uploading DICOM to XNAT as an endpoint. These tests use
+[`xnat4tests`](https://github.com/Australian-Imaging-Service/xnat4tests) to spin up a docker container running XNAT.
+
+`xnat4tests` requires you to allow the Docker daemon to listen for Docker Engine API requests via the default
+socket. This is because `xnat4tests` set up the XNAT Container Service for launching other containers that run
+analysis pipelines.
+
+If you are using Docker Desktop, you will need to enable Docker to listen on the default socket by going to
+`Settings > Advanced` and checking the box `Allow the default Docker socket to be used`.
+
+If your are running Docker Engine on Linux, listening on this socket should be
+[enabled by default](https://docs.docker.com/reference/cli/dockerd/#daemon-socket-option).
+
+
+### Integration tests
+
+There are also integration tests in `PIXL/test/` directory that can be run using the `PIXL/test/run-system-test.sh`. See the
+[integration test docs](test/README.md) for more info.
+
+
+### Workflow
 
 Before raising a PR, make sure to **run all tests** for each PIXL module
-and not just the component you have been working on as this will help us catch unintentional regressions without spending GH actions minutes :-)
+and not just the component you have been working on as this will help us catch unintentional regressions without spending GH actions minutes.
+
 
 ## Linting
 
+For Python development we use [ruff](https://docs.astral.sh/ruff/) and [mypy](https://mypy.readthedocs.io/)
+alongside [pytest](https://www.pytest.org/).
+There is support (sometimes through plugins) for these tools in most IDEs & editors.
+
+
 We run [pre-commit](https://pre-commit.com/) as part of the GitHub Actions CI. To install and run it locally, do:
 
 ```shell
-pip install pre-commit
+python -m pip install pre-commit
 pre-commit install
 ```
 
diff --git a/hasher/README.md b/hasher/README.md
index 9a96754cd..3119a298f 100644
--- a/hasher/README.md
+++ b/hasher/README.md
@@ -27,7 +27,7 @@ It is assumed you have a Python virtual environment configured using a tool like
 Install `hasher` locally with:
 
 ```shell
-pip install -e .
+python -m pip install -e .
 ```
 
 ### Setup
diff --git a/hasher/pyproject.toml b/hasher/pyproject.toml
index 85773286d..51c5626e4 100644
--- a/hasher/pyproject.toml
+++ b/hasher/pyproject.toml
@@ -1,24 +1,28 @@
 [project]
 name = "hasher"
-version = "0.0.1"
+version = "0.2.0rc0"
 authors = [{ name = "PIXL authors" }]
 description = "Service to securely hash identifiers"
 readme = "README.md"
 requires-python = ">=3.10"
 classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "core",
-    "azure-identity==1.12.0",
+    "core==0.2.0rc0",
+    "azure-identity==1.19.0",
     "azure-keyvault==4.2.0",
-    "fastapi==0.109.1",
-    "hypothesis==6.56.0",
-    "requests==2.31.0",
-    "uvicorn==0.23.2",
+    "fastapi==0.115.6",
+    "hypothesis==6.122.3",
+    "requests==2.32.3",
+    "uvicorn==0.32.1",
 ]
 
 [project.optional-dependencies]
-test = ["pytest==7.4.*", "httpx==0.24.*"]
-dev = ["mypy", "pre-commit", "ruff"]
+test = [
+    "core[test]==0.2.0rc0",
+]
+dev = [
+    "core[dev]==0.2.0rc0",
+]
 
 [build-system]
 requires = ["setuptools>=61.0"]
@@ -30,3 +34,19 @@ extend = "../ruff.toml"
 [tool.ruff.lint.extend-per-file-ignores]
 "./tests/**" = ["D1"]
 "./src/hasher/endpoints.py" = ["D103"]
+
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
diff --git a/hasher/tests/conftest.py b/hasher/tests/conftest.py
index aa587ab32..e57f9d988 100644
--- a/hasher/tests/conftest.py
+++ b/hasher/tests/conftest.py
@@ -18,7 +18,7 @@
 import pytest
 
 os.environ["LOG_LEVEL"] = "DEBUG"
-os.environ["AZURE_KEY_VAULT_SECRET_NAME"] = "test-key"  # noqa: S105, hardcoded secret
+os.environ["AZURE_KEY_VAULT_SECRET_NAME"] = "test-key"
 os.environ["LOCAL_SALT_VALUE"] = "pixl_salt"
 
 
diff --git a/orthanc/orthanc-anon/README.md b/orthanc/orthanc-anon/README.md
index e336ee58b..bef1b3f58 100644
--- a/orthanc/orthanc-anon/README.md
+++ b/orthanc/orthanc-anon/README.md
@@ -37,6 +37,9 @@ secrets. Orthanc interprets all `.json` files in the `/run/secrets` mount as con
 - The anonymisation is carried out by an Orthanc Python plugin [pixl.py](./plugin/pixl.py). This
 plugin uses the [pixl_dcmd](../../pixl_dcmd/) package to apply the anonymisation scheme (and that
 in turn uses [Kitware Dicom Anonymizer](https://github.com/KitwareMedical/dicom-anonymizer))
+- Environmental variables:
+  - `PIXL_DICOM_TRANSFER_TIMEOUT` is used as the timeout for any REST API requests made from
+        orthanc-anon
 
 ### Step 1
 
diff --git a/orthanc/orthanc-anon/config/orthanc.json b/orthanc/orthanc-anon/config/orthanc.json
index 8b85b47a3..e848006db 100644
--- a/orthanc/orthanc-anon/config/orthanc.json
+++ b/orthanc/orthanc-anon/config/orthanc.json
@@ -1,7 +1,4 @@
 {
-  "Dictionary": {
-    "000d,1001": ["LO", "UCLHPIXLProjectName", 1, 1, "UCLH PIXL"]
-  },
   "Name" : "${ORTHANC_NAME}",
   "RemoteAccessAllowed" : true,
   "RegisteredUsers": {
@@ -13,14 +10,19 @@
   // doubling them, or replaced by forward slashes "/".
   "StorageDirectory" : "/var/lib/orthanc/db",
 
+  // overwrite instances with the same UID if we get them for a second time
+  "OverwriteInstances" : true,
+
   // Limit the maximum number of instances
   "MaximumPatientCount": 200,
-
+  "MaximumStorageMode" : "Recycle",
   // Path to the directory that holds the SQLite index (if unset, the
   // value of StorageDirectory is used). This index could be stored on
   // a RAM-drive or a SSD device for performance reasons.
   "IndexDirectory" : "/var/lib/orthanc/db",
 
+  "ConcurrentJobs" : ${ORTHANC_CONCURRENT_JOBS}, // replaced in Dockerfile because its an integer
+
   // To enable plugins:
   "Plugins" : [ "/usr/share/orthanc/plugins" ],
   "PythonScript" : "/etc/orthanc/pixl.py",
diff --git a/cli/src/pixl_cli/_utils.py b/orthanc/orthanc-anon/plugin/download_dicom_spec.py
similarity index 53%
rename from cli/src/pixl_cli/_utils.py
rename to orthanc/orthanc-anon/plugin/download_dicom_spec.py
index d7b390f84..04e4f3f4d 100644
--- a/cli/src/pixl_cli/_utils.py
+++ b/orthanc/orthanc-anon/plugin/download_dicom_spec.py
@@ -1,4 +1,4 @@
-#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#  Copyright (c) 2022 University College London Hospitals NHS Foundation Trust
 #
 #  Licensed under the Apache License, Version 2.0 (the "License");
 #  you may not use this file except in compliance with the License.
@@ -11,22 +11,15 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-from __future__ import annotations
+"""Download the DICOM spec with dicom-validator."""
 
 from pathlib import Path
 
+from dicom_validator.spec_reader.edition_reader import EditionReader
 
-def clear_file(filepath: Path) -> None:
-    """Clear the contents of a file"""
-    filepath.open("w").close()
-
-
-def string_is_non_empty(string: str) -> bool:
-    """Does a string have more than just spaces and newlines?"""
-    return len(string.split()) > 0
-
-
-def remove_file_if_it_exists(filepath: Path) -> None:
-    """If a file exists remove it"""
-    if filepath.exists():
-        Path.unlink(filepath)
+edition = "2024e"
+download_path = str(Path.home() / "dicom-validator")
+edition_reader = EditionReader(download_path)
+destination = edition_reader.get_revision(edition, recreate_json=False)
+json_path = Path(destination, "json")
+EditionReader.load_dicom_info(json_path)
diff --git a/orthanc/orthanc-anon/plugin/pixl.py b/orthanc/orthanc-anon/plugin/pixl.py
index 13e66b200..a9d10c641 100644
--- a/orthanc/orthanc-anon/plugin/pixl.py
+++ b/orthanc/orthanc-anon/plugin/pixl.py
@@ -26,26 +26,39 @@
 import sys
 import threading
 import traceback
+from concurrent.futures import ThreadPoolExecutor
 from io import BytesIO
 from time import sleep
 from typing import TYPE_CHECKING, cast
+from zipfile import ZipFile
 
+import pydicom
 import requests
-from core.exceptions import PixlDiscardError
+from core.exceptions import PixlDiscardError, PixlSkipInstanceError
+from core.project_config.pixl_config_model import load_project_config
 from decouple import config
 from loguru import logger
 from pydicom import dcmread
 
 import orthanc
-from pixl_dcmd.main import anonymise_dicom, should_exclude_series, write_dataset_to_bytes
+from pixl_dcmd.main import (
+    anonymise_dicom_and_update_db,
+    write_dataset_to_bytes,
+)
 
 if TYPE_CHECKING:
     from typing import Any
 
+    from core.project_config.pixl_config_model import PixlConfig
+
 ORTHANC_USERNAME = config("ORTHANC_USERNAME")
 ORTHANC_PASSWORD = config("ORTHANC_PASSWORD")
 ORTHANC_URL = "http://localhost:8042"
 
+ORTHANC_RAW_USERNAME = config("ORTHANC_RAW_USERNAME")
+ORTHANC_RAW_PASSWORD = config("ORTHANC_RAW_PASSWORD")
+ORTHANC_RAW_URL = "http://orthanc-raw:8042"
+
 EXPORT_API_URL = "http://export-api:8000"
 
 # Set up logging as main entry point
@@ -57,6 +70,12 @@
 
 logger.warning("Running logging at level {}", logging_level)
 
+# Set up a thread pool executor for non-blocking calls to Orthanc
+max_workers = config("PIXL_MAX_MESSAGES_IN_FLIGHT", cast=int)
+executor = ThreadPoolExecutor(max_workers=max_workers)
+
+logger.info("Using {} threads for processing", max_workers)
+
 
 def AzureAccessToken() -> str:
     """
@@ -149,28 +168,7 @@ def AzureDICOMTokenRefresh() -> None:
     return None
 
 
-def Send(study_id: str) -> None:
-    """
-    Send the resource to the appropriate destination.
-    Throws an exception if the image has already been exported.
-    """
-    msg = f"Sending {study_id}"
-    logger.debug(msg)
-    notify_export_api_of_readiness(study_id)
-
-
-def notify_export_api_of_readiness(study_id: str):
-    """
-    Tell export-api that our data is ready and it should download it from us and upload
-    as appropriate
-    """
-    url = EXPORT_API_URL + "/export-dicom-from-orthanc"
-    payload = {"study_id": study_id}
-    response = requests.post(url, json=payload, timeout=30)
-    response.raise_for_status()
-
-
-def should_auto_route() -> bool:
+def should_export() -> bool:
     """
     Checks whether ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT environment variable is
     set to true or false
@@ -186,19 +184,14 @@ def _azure_available() -> bool:
 
 def OnChange(changeType, level, resource):  # noqa: ARG001
     """
-    - If a study is stable and if should_auto_route returns true
-    then notify the export API that it should perform the upload of DICOM data.
-    - If orthanc has started then start a timer to refresh the Azure token every 30 seconds
-    - If orthanc has stopped then cancel the timer
+    - If `should_export` returns `false`, the do nothing
+    - Otherwise:
+        - If orthanc has started then start a timer to refresh the Azure token every 30 seconds
+        - If orthanc has stopped then cancel the timer
     """
-    if not should_auto_route():
+    if not should_export():
         return
 
-    if changeType == orthanc.ChangeType.STABLE_STUDY:
-        msg = f"Stable study: {resource}"
-        logger.info(msg)
-        Send(resource)
-
     if changeType == orthanc.ChangeType.ORTHANC_STARTED and _azure_available():
         orthanc.LogWarning("Starting the scheduler")
         AzureDICOMTokenRefresh()
@@ -214,42 +207,195 @@ def OnHeartBeat(output, uri, **request) -> Any:  # noqa: ARG001
     output.AnswerBuffer("OK\n", "text/plain")
 
 
-def ReceivedInstanceCallback(receivedDicom: bytes, origin: str) -> Any:
-    """Modifies a DICOM instance received by Orthanc and applies anonymisation."""
-    if origin == orthanc.InstanceOrigin.REST_API:
-        orthanc.LogWarning("DICOM instance received from the REST API")
-    elif origin == orthanc.InstanceOrigin.DICOM_PROTOCOL:
-        orthanc.LogWarning("DICOM instance received from the DICOM protocol")
+def ImportStudiesFromRaw(output, uri, **request):  # noqa: ARG001
+    """
+    Import studies from Orthanc Raw.
+
+    Offload to a thread pool executor to avoid blocking the Orthanc main thread.
+    """
+    payload = json.loads(request["body"])
+    study_resource_ids = payload["ResourceIDs"]
+    study_uids = payload["StudyInstanceUIDs"]
+    project_name = payload["ProjectName"]
 
-    # It's important that as much code in this handler as possible is inside this "try" block.
-    # This ensures we discard the image if anything goes wrong in the anonymisation process.
-    # If the handler raises an exception the pre-anon image will be kept.
-    try:
-        return _process_dicom_instance(receivedDicom)
-    except Exception:  # noqa: BLE001
-        orthanc.LogError("Failed to anonymize instance due to\n" + traceback.format_exc())
-        return orthanc.ReceivedInstanceAction.DISCARD, None
+    for study_resource_id, study_uid in zip(study_resource_ids, study_uids, strict=False):
+        executor.submit(_import_study_from_raw, study_resource_id, study_uid, project_name)
 
+    response = json.dumps({"Message": "Ok"})
+    output.AnswerBuffer(response, "application/json")
 
-def _process_dicom_instance(receivedDicom: bytes) -> tuple[orthanc.ReceivedInstanceAction, None]:
-    # Read the bytes as DICOM/
-    dataset = dcmread(BytesIO(receivedDicom))
 
-    # Do before anonymisation in case someone decides to delete the
-    # Series Description tag as part of anonymisation.
-    if should_exclude_series(dataset):
-        orthanc.LogWarning("DICOM instance discarded due to its series description")
-        return orthanc.ReceivedInstanceAction.DISCARD, None
+def _import_study_from_raw(study_resource_id: str, study_uid: str, project_name: str) -> None:
+    """
+    Import a study from Orthanc Raw.
 
-    # Attempt to anonymise and drop the study if any exceptions occur
-    try:
-        anonymise_dicom(dataset)
-        return orthanc.ReceivedInstanceAction.MODIFY, write_dataset_to_bytes(dataset)
-    except PixlDiscardError as error:
-        logger.debug("Skipping instance: {}", error)
-        return orthanc.ReceivedInstanceAction.DISCARD, None
+    Args:
+        study_resource_id: Resource ID of the study in Orthanc Raw
+        study_uid: Corresponding StudyInstanceUID
+        project_name: Name of the project
+
+    - Pull a study from Orthanc Raw based on its resource ID
+    - Iterate over instances and anonymise them
+    - Re-upload the study via the dicom-web api
+    - Notify the PIXL export-api to send the study the to relevant endpoint for the project
+
+    """
+    zipped_study_bytes = get_study_zip_archive_from_raw(resource_id=study_resource_id)
+
+    with ZipFile(zipped_study_bytes) as zipped_study:
+        try:
+            anonymised_instances_bytes, anonymised_study_uid = _anonymise_study_instances(
+                zipped_study=zipped_study,
+                study_uid=study_uid,
+                project_name=project_name,
+            )
+        except PixlDiscardError as discard:
+            logger.warning("Failed to anonymize study {}: {}", study_uid, discard)
+        except Exception:  # noqa: BLE001
+            logger.exception("Failed to anonymize study: {} ", study_uid)
+            return
+
+    _upload_instances(anonymised_instances_bytes)
+
+    if not should_export():
+        logger.debug("Not exporting study {} as auto-routing is disabled", anonymised_study_uid)
+        return
+
+    anonymised_study_resource_id = _get_study_resource_id(anonymised_study_uid)
+    logger.debug(
+        "Notify export API to retrieve study resource. Original UID {} Anon UID: {}",
+        study_uid,
+        anonymised_study_uid,
+    )
+    send_study(study_id=anonymised_study_resource_id, project_name=project_name)
+
+
+def get_study_zip_archive_from_raw(resource_id: str) -> BytesIO:
+    """Download zip archive of study resource from Orthanc Raw."""
+    query = f"{ORTHANC_RAW_URL}/studies/{resource_id}/archive"
+    response = requests.get(
+        query,
+        auth=(config("ORTHANC_RAW_USERNAME"), config("ORTHANC_RAW_PASSWORD")),
+        timeout=config("PIXL_DICOM_TRANSFER_TIMEOUT", default=180, cast=int),
+    )
+    response.raise_for_status()
+    logger.debug("Downloaded data for resource {} from Orthanc Raw", resource_id)
+    return BytesIO(response.content)
+
+
+def _get_study_resource_id(study_uid: str) -> str:
+    """
+    Get the resource ID for an existing study based on its StudyInstanceUID.
+
+    Returns None if there are no resources with the given StudyInstanceUID.
+    Returns the resource ID if there is a single resource with the given StudyInstanceUID.
+    Returns None if there are multiple resources with the given StudyInstanceUID and deletes
+    the studies.
+    """
+    data = json.dumps(
+        {
+            "Level": "Study",
+            "Query": {
+                "StudyInstanceUID": study_uid,
+            },
+        }
+    )
+    study_resource_ids = json.loads(orthanc.RestApiPost("/tools/find", data))
+    if not study_resource_ids:
+        message = f"No study found with StudyInstanceUID {study_uid}"
+        raise ValueError(message)
+    if len(study_resource_ids) > 1:
+        message = f"Multiple studies found with StudyInstanceUID {study_uid}"
+        raise ValueError(message)
+
+    return study_resource_ids[0]
+
+
+def _anonymise_study_instances(
+    zipped_study: ZipFile, study_uid: str, project_name: str
+) -> tuple[list[bytes], str]:
+    """
+    Iterate over all instances and anonymise them.
+
+    Skip an instance if a PixlSkipInstanceError is raised during anonymisation.
+
+    Return a list of the bytes of anonymised instances, and the anonymised StudyInstanceUID.
+    """
+    config = load_project_config(project_name)
+    anonymised_instances_bytes = []
+    logger.debug("Zipped study infolist: {}", zipped_study.infolist())
+    for file_info in zipped_study.infolist():
+        with zipped_study.open(file_info) as file:
+            logger.debug("Reading file {}", file)
+            dataset = dcmread(file)
+
+            logger.info("Anonymising file: {} for study: {}", file, study_uid)
+            try:
+                anonymised_instances_bytes.append(_anonymise_dicom_instance(dataset, config))
+            except PixlSkipInstanceError as e:
+                logger.warning(
+                    "Skipping instance {} for study {}: {}",
+                    dataset[0x0008, 0x0018].value,
+                    study_uid,
+                    e,
+                )
+            else:
+                anonymised_study_uid = dataset[0x0020, 0x000D].value
+
+    if not anonymised_instances_bytes:
+        message = f"All instances have been skipped for study {study_uid}"
+        raise PixlDiscardError(message)
+
+    logger.success("Finished anonymising file: {} for study: {}", file, study_uid)
+    return anonymised_instances_bytes, anonymised_study_uid
+
+
+def _anonymise_dicom_instance(dataset: pydicom.Dataset, config: PixlConfig) -> bytes:
+    """Anonymise a DICOM instance."""
+    anonymise_dicom_and_update_db(dataset, config=config)
+    return write_dataset_to_bytes(dataset)
+
+
+def _upload_instances(instances_bytes: list[bytes]) -> None:
+    """Upload instances to Orthanc"""
+    files = []
+    for index, dicom_bytes in enumerate(instances_bytes):
+        files.append(("file", (f"instance{index}.dcm", dicom_bytes, "application/dicom")))
+
+    # Using requests as doing:
+    # `upload_response = orthanc.RestApiPost(f"/instances", anonymised_files)`
+    # gives an error BadArgumentType error (orthanc.RestApiPost seems to only accept json)
+    upload_response = requests.post(
+        url=f"{ORTHANC_URL}/instances",
+        auth=(ORTHANC_USERNAME, ORTHANC_PASSWORD),
+        files=files,
+        timeout=config("PIXL_DICOM_TRANSFER_TIMEOUT", default=180, cast=int),
+    )
+    upload_response.raise_for_status()
+
+
+def send_study(study_id: str, project_name: str) -> None:
+    """
+    Send the resource to the appropriate destination.
+    Throws an exception if the image has already been exported.
+    """
+    msg = f"Sending {study_id}"
+    logger.debug(msg)
+    notify_export_api_of_readiness(study_id, project_name)
+
+
+def notify_export_api_of_readiness(study_id: str, project_name: str) -> None:
+    """
+    Tell export-api that our data is ready and it should download it from us and upload
+    as appropriate
+    """
+    url = EXPORT_API_URL + "/export-dicom-from-orthanc"
+    payload = {"study_id": study_id, "project_name": project_name}
+    timeout: float = config("HTTP_TIMEOUT", default=30, cast=float)
+    response = requests.post(url, json=payload, timeout=timeout)
+    response.raise_for_status()
 
 
 orthanc.RegisterOnChangeCallback(OnChange)
-orthanc.RegisterReceivedInstanceCallback(ReceivedInstanceCallback)
 orthanc.RegisterRestCallback("/heart-beat", OnHeartBeat)
+orthanc.RegisterRestCallback("/import-from-raw", ImportStudiesFromRaw)
diff --git a/orthanc/orthanc-raw/README.md b/orthanc/orthanc-raw/README.md
index 0b603f18f..eec29a5a0 100644
--- a/orthanc/orthanc-raw/README.md
+++ b/orthanc/orthanc-raw/README.md
@@ -16,8 +16,8 @@ The following assumptions are made:
 - There is a PostgreSQL database available (currently [defined in
 `pixl_core`](../../pixl_core/README.md)) to store the Index data within Orthanc (or it will become
 available shortly when the service is started).
-- The IP, port and AE Title for the VNA Q/R target have been provided, and the reciprocal details
-for this instance have been shared with the PACS team.
+- The IPs, ports and AE Titles for the primary (VNA) and secondary (PACS) Q/R targets have been provided,
+  and the reciprocal details for this instance have been shared with the PACS team.
 - There is sufficient local storage for the `orthanc-raw-data` volume.
 
 ### Configuration
@@ -26,8 +26,8 @@ for this instance have been shared with the PACS team.
   - `ORTHANC_RAW_MAXIMUM_STORAGE_SIZE` to limit the storage size
   - `ORTHANC_RAW_JOB_HISTORY_SIZE` has been increased so that while there is concurrent processing,
     the job should always exist for being able to query its status
-  - `ORTHANC_RAW_CONCURRENT_JOBS` has been increased to allow for more concurrent transfers from
-    the VNA to orthanc raw.  
+  - `ORTHANC_CONCURRENT_JOBS` has been increased to allow for more concurrent transfers from
+    the VNA to orthanc raw.
 - All configuration is driven through customised JSON config files stored in the [config](./config/)
 directory.
 - The files are populated with values from environment variables and injected into the container as
@@ -41,7 +41,7 @@ secrets. Orthanc interprets all `.json` files in the `/run/secrets` mount as con
 
 ### Step 1
 
-Save credentials `.env` for the PACS/VNA Q/R target, postgreSQL and 'Orthanc anon'.
+Save credentials `.env` for the VNA (primary) and PACS (secondary) Q/R targets, postgreSQL and 'Orthanc anon'.
 ```
 # PIXL PostgreSQL instance
 PIXL_DB_HOST=
@@ -62,10 +62,15 @@ ORTHANC_RAW_AE_TITLE=
 # PIXL Orthanc anon instance
 ORTHANC_ANON_AE_TITLE=
 
-# UCVNAQR DICOM node information
-VNAQR_AE_TITLE=
-VNAQR_DICOM_PORT=
-VNAQR_IP_ADDR=
+# UCPRIMARYQR DICOM node information
+PRIMARY_DICOM_SOURCE_AE_TITLE=
+PRIMARY_DICOM_SOURCE_PORT=
+PRIMARY_DICOM_SOURCE_IP_ADDR=
+
+# UCSECONDARYQR DICOM node information
+SECONDARY_DICOM_SOURCE_AE_TITLE=
+SECONDARY_DICOM_SOURCE_PORT=
+SECONDARY_DICOM_SOURCE_IP_ADDR=
 ```
 
 ### Step 2
diff --git a/orthanc/orthanc-raw/config/dicom.json b/orthanc/orthanc-raw/config/dicom.json
index beb41a9c7..f1288a693 100644
--- a/orthanc/orthanc-raw/config/dicom.json
+++ b/orthanc/orthanc-raw/config/dicom.json
@@ -2,10 +2,10 @@
   "DicomAet" : "${ORTHANC_RAW_AE_TITLE}",
 
   "DicomModalities" : {
-    "UCVNAQR" : {
-      "AET" : "${VNAQR_AE_TITLE}",
-      "Port" : "${VNAQR_DICOM_PORT}",
-      "Host" : "${VNAQR_IP_ADDR}",
+    "UCPRIMARYQR" : {
+      "AET" : "${PRIMARY_DICOM_SOURCE_AE_TITLE}",
+      "Port" : "${PRIMARY_DICOM_SOURCE_PORT}",
+      "Host" : "${PRIMARY_DICOM_SOURCE_IP_ADDR}",
       "Manufacturer" : "Generic",
       "AllowEcho" : true,
       "AllowFind" : false,
@@ -16,7 +16,23 @@
       "AllowStorageCommitment" : false,
       "AllowTranscoding" : true,
       "UseDicomTls" : false,
-      "Timeout" : 60
+      "Timeout" : 120
+    },
+    "UCSECONDARYQR" : {
+      "AET" : "${SECONDARY_DICOM_SOURCE_AE_TITLE}",
+      "Port" : "${SECONDARY_DICOM_SOURCE_PORT}",
+      "Host" : "${SECONDARY_DICOM_SOURCE_IP_ADDR}",
+      "Manufacturer" : "Generic",
+      "AllowEcho" : true,
+      "AllowFind" : false,
+      "AllowFindWorklist" : false,
+      "AllowGet"  : false,
+      "AllowMove" : false,
+      "AllowStore" : true,
+      "AllowStorageCommitment" : false,
+      "AllowTranscoding" : true,
+      "UseDicomTls" : false,
+      "Timeout" : 120
     },
     "PIXL-Anon" : {
       "AET" : "${ORTHANC_ANON_AE_TITLE}",
@@ -32,7 +48,7 @@
       "AllowStorageCommitment" : false,
       "AllowTranscoding" : true,
       "UseDicomTls" : false,
-      "Timeout" : 60
+      "Timeout" : 120
     }
   },
 
@@ -86,6 +102,11 @@
   // modality initiating a DICOM connection (as listed in the
   // "DicomModalities" option above). If this option is set to
   // "false", Orthanc only checks the AET of the remote modality.
-  "DicomCheckModalityHost" : false
+  "DicomCheckModalityHost" : false,
+
+  // Overwrite instances with the same UID
+  // This allows us to set the project name tag in-place without modifying the
+  //StudyInstanceUID, SeriesInstanceUID, and SOPInstanceUID
+  "OverwriteInstance": true
 
 }
diff --git a/orthanc/orthanc-raw/config/orthanc.json b/orthanc/orthanc-raw/config/orthanc.json
index 498f86de1..b53374e30 100644
--- a/orthanc/orthanc-raw/config/orthanc.json
+++ b/orthanc/orthanc-raw/config/orthanc.json
@@ -1,6 +1,5 @@
 {
   "Dictionary": {
-    "000d,1001": ["LO", "UCLHPIXLProjectName", 1, 1, "UCLH PIXL"]
   },
   "DefaultPrivateCreator" : "UCLH PIXL",
   "Name" : "${ORTHANC_NAME}",
@@ -20,15 +19,46 @@
   "MaximumStorageMode" : "Recycle",
   // Enable concurrency
   "JobsHistorySize": ${ORTHANC_RAW_JOB_HISTORY_SIZE}, // replaced in Dockerfile because its an integer
-  "ConcurrentJobs" : ${ORTHANC_RAW_CONCURRENT_JOBS}, // replaced in Dockerfile because its an integer
+  "ConcurrentJobs" : ${ORTHANC_CONCURRENT_JOBS}, // replaced in Dockerfile because its an integer
   // overwrite instances with the same UID if we get them for a second time
   "OverwriteInstances" : true,
   // Path to the directory that holds the SQLite index (if unset, the
   // value of StorageDirectory is used). This index could be stored on
   // a RAM-drive or a SSD device for performance reasons.
   //"IndexDirectory" : "/var/lib/orthanc/db"
+    "StableAge" : ${ORTHANC_RAW_STABLE_SECONDS},
+  // Defines the number of threads that are used to execute each type of
+  // jobs (for the jobs that can be parallelized).
+  // A value of "0" indicates to use all the available CPU logical cores
+  "JobsEngineThreadsCount" : {
+    "ResourceModification": 1  // for /anonymize, /modify
+  },
+
+  // Whether to save the jobs into the Orthanc database. If this
+  // option is set to "true", the pending/running/completed jobs are
+  // automatically reloaded from the database if Orthanc is stopped
+  // then restarted (except if the "--no-jobs" command-line argument
+  // is specified). This option should be set to "false" if multiple
+  // Orthanc servers are using the same database (e.g. if PostgreSQL
+  // or MariaDB/MySQL is used).
+  "SaveJobs" : false,
+
+  "DicomScpTimeout" : 120,
+
+  // Main Dicom tags that are already stored.
+  // see https://orthanc.uclouvain.be/book/faq/main-dicom-tags.html 
+  // (new in Orthanc 1.11.0)
+  // Sequences tags are not supported.
+"ExtraMainDicomTags" : {
+    "Instance" : [
+      "SOPClassUID"
+    ],
+    "Series" : [],
+    "Study": [],
+    "Patient": []
+  },
 
-  // To enable plugins:
+// To enable plugins:
   "Plugins" : [ "/usr/share/orthanc/plugins" ],
   "PythonScript" : "/etc/orthanc/pixl.py",
   "PythonVerbose" : false,
diff --git a/orthanc/orthanc-raw/plugin/pixl.py b/orthanc/orthanc-raw/plugin/pixl.py
index c3b3e6936..22f8265ff 100644
--- a/orthanc/orthanc-raw/plugin/pixl.py
+++ b/orthanc/orthanc-raw/plugin/pixl.py
@@ -15,27 +15,19 @@
 Facilitates routing of stable studies from orthanc-raw to orthanc-anon
 
 This module provides:
--OnChange: route stable studies and if auto-routing enabled
--should_auto_route: checks whether auto-routing is enabled
 -OnHeartBeat: extends the REST API
 """
 
 from __future__ import annotations
 
-import json
 import os
 import sys
-import traceback
-from io import BytesIO
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
-from core.dicom_tags import DICOM_TAG_PROJECT_NAME, add_private_tag
 from decouple import config
 from loguru import logger
-from pydicom import dcmread
 
 import orthanc
-from pixl_dcmd.main import write_dataset_to_bytes
 from pixl_dcmd.tagrecording import record_dicom_headers
 
 if TYPE_CHECKING:
@@ -51,39 +43,17 @@
 logger.warning("Running logging at level {}", logging_level)
 
 
-def OnChange(changeType, level, resourceId):  # noqa: ARG001
-    """
-    # Taken from:
-    # https://book.orthanc-server.com/plugins/python.html#auto-routing-studies
-    This routes any stable study to a modality named PIXL-Anon if
-    should_auto_route returns true
-    """
-    if changeType == orthanc.ChangeType.STABLE_STUDY and should_auto_route():
-        logger.debug("Sending study: {}", resourceId)
-        # Although this can throw, since we have nowhere to report errors
-        # back to (eg. an HTTP client), don't try to handle anything here.
-        # The client will have to detect that it hasn't happened and retry.
-        orthanc_anon_store_study(resourceId)
-
-
-def orthanc_anon_store_study(resource_id):
-    """Call the API to send the specified resource (study) to the orthanc anon server."""
-    # RestApiPost raises an orthanc.OrthancException if it fails
-    orthanc.RestApiPost("/modalities/PIXL-Anon/store", resource_id)
-    orthanc.LogInfo(f"Successfully sent study to anon modality: {resource_id}")
-
-
 def OnHeartBeat(output, uri, **request):  # noqa: ARG001
     """Extends the REST API by registering a new route in the REST API"""
     orthanc.LogWarning("OK")
     output.AnswerBuffer("OK\n", "text/plain")
 
 
-def ReceivedInstanceCallback(receivedDicom: bytes, origin: str) -> Any:
+def ReceivedInstanceCallback(receivedDicom: bytes, origin: str) -> Any:  # noqa: ARG001
     """Optionally record headers from the received DICOM instance."""
     if should_record_headers():
         record_dicom_headers(receivedDicom)
-    return modify_dicom_tags(receivedDicom, origin)
+    return orthanc.ReceivedInstanceAction.KEEP_AS_IS, None
 
 
 def should_record_headers() -> bool:
@@ -94,99 +64,5 @@ def should_record_headers() -> bool:
     return os.environ.get("ORTHANC_RAW_RECORD_HEADERS", "false").lower() == "true"
 
 
-def should_auto_route():
-    """
-    Checks whether ORTHANC_AUTOROUTE_RAW_TO_ANON environment variable is
-    set to true or false
-    """
-    return os.environ.get("ORTHANC_AUTOROUTE_RAW_TO_ANON", "false").lower() == "true"
-
-
-def modify_dicom_tags(receivedDicom: bytes, origin: str) -> Any:
-    """
-    A new incoming DICOM file needs to have the project name private tag added here, so
-    that the API will later allow us to edit it.
-    However, we don't know its correct value at this point, so just create it with an obvious
-    placeholder value.
-    """
-    if origin != orthanc.InstanceOrigin.DICOM_PROTOCOL:
-        # don't keep resetting the tag values if this was triggered by an API call!
-        logger.trace("doing nothing as change triggered by API")
-        return orthanc.ReceivedInstanceAction.KEEP_AS_IS, None
-    dataset = dcmread(BytesIO(receivedDicom))
-    # See the orthanc.json config file for where this tag is given a nickname
-    # The private block is the first free block >= 0x10.
-    # We can't directly control it, but the orthanc config requires it to be
-    # hardcoded to 0x10
-    # https://dicom.nema.org/dicom/2013/output/chtml/part05/sect_7.8.html
-
-    # Add project name as private tag, at this point, the value is unknown
-    private_block = add_private_tag(dataset, DICOM_TAG_PROJECT_NAME)
-
-    logger.debug("added new private block starting at 0x{:04x}", private_block.block_start)
-    return orthanc.ReceivedInstanceAction.MODIFY, write_dataset_to_bytes(dataset)
-
-
-def log_and_return_http(
-    output, http_code: int, http_message: str, log_message: Optional[str] = None
-):
-    """
-    Log and make an HTTP response in case of success or failure. For failure, log
-    a stack/exception trace as well.
-
-    :param output: the orthanc output object as given to the callback function
-    :param http_code: HTTP code to return
-    :param http_message: message to return in HTTP body
-    :param log_message: message to log, if different to http_message.
-                        If None, do not log at all if success
-    """
-    http_json_str = json.dumps({"Message": http_message})
-    if http_code == 200:  # noqa: PLR2004
-        if log_message:
-            orthanc.LogInfo(log_message)
-        output.AnswerBuffer(http_json_str, "application/json")
-    else:
-        orthanc.LogWarning(f"{log_message or http_message}:\n{traceback.format_exc()}")
-        # length needed in bytes not chars
-        output.SendHttpStatus(http_code, http_json_str, len(http_json_str.encode()))
-
-
-def SendResourceToAnon(output, uri, **request):  # noqa: ARG001
-    """Send an existing study to the anon modality"""
-    orthanc.LogWarning(f"Received request to send study to anon modality: {request}")
-    if not should_auto_route():
-        log_and_return_http(
-            output,
-            200,
-            "Auto-routing is not enabled",
-            f"Auto-routing is not enabled, dropping request {request}",
-        )
-        return
-    try:
-        body = json.loads(request["body"])
-        resource_id = body["ResourceId"]
-    except (json.decoder.JSONDecodeError, KeyError):
-        err_str = "Body needs to be JSON with key ResourceId"
-        log_and_return_http(output, 400, err_str)
-    except:
-        err_str = "Other error decoding request"
-        log_and_return_http(output, 500, err_str)
-        raise
-
-    try:
-        orthanc_anon_store_study(resource_id)
-    except orthanc.OrthancException:
-        err_str = "Failed contacting downstream server"
-        log_and_return_http(output, 502, err_str)
-    except:
-        err_str = "Misc error sending study to anon"
-        log_and_return_http(output, 500, err_str)
-        raise
-    else:
-        log_and_return_http(output, 200, "OK")
-
-
-orthanc.RegisterOnChangeCallback(OnChange)
 orthanc.RegisterReceivedInstanceCallback(ReceivedInstanceCallback)
 orthanc.RegisterRestCallback("/heart-beat", OnHeartBeat)
-orthanc.RegisterRestCallback("/send-to-anon", SendResourceToAnon)
diff --git a/pixl_core/README.md b/pixl_core/README.md
index 25e803d78..8116ba49e 100644
--- a/pixl_core/README.md
+++ b/pixl_core/README.md
@@ -10,21 +10,25 @@ Specifically, it defines:
 - The [RabbitMQ queue](#patient-queue) implementation shared by the Imaging API and any other APIs
 - The PIXL `postgres` internal database for storing exported images and extracts from the messages
   processed by the CLI driver
-- The [`ParquetExport`](./src/core/exports.py) class for exporting OMOP and EMAP extracts to
+- The [`ParquetExport`](./src/core/exports.py) class for exporting OMOP extracts to
   parquet files
-- Handling of [uploads over FTPS](./src/core/upload.py), used to transfer images and parquet files
+- Pydantic models for [project configuration](./src/core/project_config/pixl_config_model.py)
+- [Secrets management](./src/core/project_config/secrets.py) via an Azure Key Vault.
+- Handling of [uploads over FTPS](./src/core/uploader/_ftps.py), used to transfer images and parquet files
   to the DSH (Data Safe Haven)
+- [Uploading DICOM files to a DICOMWeb server](./src/core/uploader/_dicomweb.py)
+- [Uploading DICOM files to XNAT](./src/core/uploader/_xnat.py)
 
 ## Installation
 
 ```bash
-pip install -e .
+python -m pip install -e .
 ```
 
 ## Testing
 
 ```bash
-pip install -e .[test] && pip install -e ../pytest-pixl
+python -m pip install -e ../pytest-pixl -e ".[test]"
 pytest
 ```
 
@@ -59,9 +63,9 @@ is geared towards stability. The asynchronous mode of transferring messages is a
 it is based on the [asyncio event loop](https://docs.python.org/3/library/asyncio-eventloop.html).
 
 We set the maximum number of message which can be being processed at once using the `PIXL_MAX_MESSAGES_IN_FLIGHT`
-variable in the `.env` file. Chest X-rays take about 5 seconds to return so the default of 100 allows for
-a maximum of 20 messages per second. The VNA should be able to cope with 12-15 per second, so this allows
-our rate limiting to fit within this range.
+variable in the `.env` file. The VNA allows for 5 DICOM transfers at a single point in time, so the default is 5.
+We recommend allowing more concurrent jobs using `ORTHANC_CONCURRENT_JOBS`, to allow for resource modification
+and export of stable DICOM to orthanc-anon while still pulling from the VNA.
 
 ### OMOP ES files
 
@@ -104,11 +108,11 @@ The `project_config` module provides the functionality to handle
 ## Uploading to an FTPS server
 
 The `core.uploader` module implements functionality to upload DICOM images and parquet files to
-several destinations. This requires the following environment variables to be set:
+several destinations.
 
 The `Uploader` abstract class provides a consistent interface for uploading files. Child classes
 such as the `FTPSUploader` implement the actual upload functionality. The credentials required for
-uploading are queried from an **Azure Keyvault** instance (implemented in `_secrets.py`), for which
+uploading are queried from an **Azure Keyvault** instance (implemented in `core.project_config.secrets`), for which
 the setup instructions are in the [top-level README](../README.md#project-secrets)
 
 When an extract is ready to be published to the DSH, the PIXL pipeline will upload the **Public**
@@ -161,3 +165,72 @@ so we can have different (or no) endpoints for different projects.
 For [testing](../test/README.md) we set up an additional Orthanc server that acts as a DICOMweb server,
 using the vanilla Orthanc Docker image with the DICOMWeb plugin enabled.
 
+## Uploading to an XNAT instance
+
+PIXL also supports sending DICOM images to an [XNAT](https://www.xnat.org/) instance.
+
+The `XNATUploader` class in `core.uploader._xnat` handles downloading anonymised images from Orthanc and
+sending to XNAT. [XNATPy](https://xnat.readthedocs.io/en/latest/) is used to upload the
+data to XNAT using the
+[`DICOM-zip` Import Handler](https://wiki.xnat.org/xnat-api/image-session-import-service-api#ImageSessionImportServiceAPI-SelectAnImportHandler).
+
+To use XNAT as an endpoint, first:
+
+- a user will need to be created on the XNAT instance to perform the upload with PIXL
+- a project will need to be created on the XNAT instance. It is assumed the user created for uploading
+  data does not have admin permissions to create new projects
+
+### XNAT endpoint Configuration
+
+Configuration for XNAT as an endpoint is done by storing the following secrets in an Azure Key Vault:
+
+```bash
+"${az_prefix}--xnat--host"  # hostname for the XNAT instance
+"${az_prefix}--xnat--username"  # username of user to perform upload
+"${az_prefix}--xnat--password"  # password of user to perform upload
+"${az_prefix}--xnat--port"  # port for connecting to the XNAT instance
+```
+
+where `az_prefix` is either the project slug or is defined in the [project configuration file](../template_config.yaml)
+as `azure_kv_alias`.
+
+> Note
+>
+> The project name defined in the configuration file **must** match the
+> [XNAT Project ID](https://wiki.xnat.org/documentation/creating-and-managing-projects). If the project name does
+> not match the XNAT Project ID, the upload will fail.
+
+The following environment variables must also be set to determine the XNAT destination and how to handle conflicts
+with existing session and series data:
+
+`"XNAT_DESTINATION"`:
+
+- if `"/archive"`, will send data straight to the archive
+- if `"/prearchive"`, will send data to the [prearchive](https://wiki.xnat.org/documentation/using-the-prearchive)
+  for manual review before archiving
+
+`"XNAT_OVERWRITE"`:
+
+- if `"none"`, will error if the session already exists. Upon error, data will be sent to the prearchive,
+  even if `XNAT_DESTINATION` is `/archive`
+- if `"append"`, will append the data to an existing session or create a new one if it doesn't exist.
+        If there is a conflict with existing series, an error will be raised.
+- if `"delete"`, will append the data to an existing session or create a new one if it doesn't exist.
+        If there is a conflict with existing series, the existing series will be overwritten.
+
+### XNAT testing setup
+
+For unit testing, we use [`xnat4tests`](https://github.com/Australian-Imaging-Service/xnat4tests) to spin up an XNAT
+instance in a Docker container.
+
+Secrets are not used for these unit testing. Instead, the following environment variables are used to configure XNAT for testing:
+
+- `"XNAT_HOST"`
+- `"XNAT_USER_NAME"`
+- `"XNAT_PASSWORD"`
+- `"XNAT_PORT"`
+
+Note, it can take several minutes for the server to start up.
+
+Once the server has started, you can log in by visiting `http://localhost:8080` with the username and password set
+in the `XNAT_USER_NAME` and `XNAT_PASSWORD` environment variables.
diff --git a/pixl_core/pyproject.toml b/pixl_core/pyproject.toml
index 05f958918..e57aa6881 100644
--- a/pixl_core/pyproject.toml
+++ b/pixl_core/pyproject.toml
@@ -1,40 +1,47 @@
 [project]
 name = "core"
-version = "0.0.1"
+version = "0.2.0rc0"
 authors = [{ name = "PIXL core functionality" }]
 description = ""
 readme = "README.md"
 requires-python = ">=3.9"
 classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "azure-identity==1.12.0",
+    "aio_pika==9.5.3",
+    "azure-identity==1.19.0",
     "azure-keyvault==4.2.0",
-    "fastapi==0.109.1",
-    "token-bucket==0.3.0",
-    "python-decouple==3.6",
+    "fastapi==0.115.6",
+    "jsonpickle==4.0.0",
+    "loguru==0.7.3",
+    "pandas==2.2.3",
+    "pika==1.3.2",
+    "psycopg2-binary==2.9.10",
+    "pyarrow==18.1.0",
+    "pydantic==2.10.3",
+    "python-decouple==3.8",
     "python-slugify==8.0.4",
-    "pika==1.3.1",
-    "aio_pika==8.2.4",
-    "requests==2.31.0",
-    "jsonpickle==3.0.2",
-    "loguru==0.7.2",
-    "sqlalchemy==2.0.24",
-    "psycopg2-binary==2.9.9",
-    "pandas==2.2.1",
-    "pyarrow==14.0.1",
-    "PyYAML==6.0.1",
-    "pydantic==2.6.3",
+    "PyYAML==6.0.2",
+    "requests==2.32.3",
+    "sqlalchemy==2.0.36",
+    "token-bucket==0.3.0",
+    "xnat==0.6.2",
 ]
 
 [project.optional-dependencies]
 test = [
-    "pytest==7.4.2",
-    "pytest-cov==5.0.0",
-    "pytest-asyncio==0.21.1",
-    "httpx==0.24.*",
-    "pytest-pixl",
+    "httpx==0.28.*",
+    "pytest==8.3.4",
+    "pytest-asyncio==0.24.0",
+    "pytest-check==2.4.1",
+    "pytest-cov==6.0.0",
+    "pytest-pixl==0.2.0rc0",
+    "xnat4tests==0.3.12",
+]
+dev = [
+    "mypy",
+    "pre-commit",
+    "ruff",
 ]
-dev = ["mypy", "pre-commit", "ruff"]
 
 [build-system]
 requires = ["setuptools>=61.0"]
@@ -61,6 +68,7 @@ exclude_also = [
     "if 0:",
     "if __name__ == .__main__.:",
     "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
     "class .*\\bProtocol\\):",
     "@(abc\\.)?abstractmethod",
-]
\ No newline at end of file
+]
diff --git a/pixl_core/src/core/db/models.py b/pixl_core/src/core/db/models.py
index ed330b833..e45fc4e53 100644
--- a/pixl_core/src/core/db/models.py
+++ b/pixl_core/src/core/db/models.py
@@ -52,15 +52,17 @@ class Image(Base):
     accession_number: Mapped[str]
     study_date: Mapped[Date] = mapped_column(Date())
     mrn: Mapped[str]
-    hashed_identifier: Mapped[Optional[str]]
+    study_uid: Mapped[Optional[str]]
+    pseudo_study_uid: Mapped[Optional[str]]
     exported_at: Mapped[DateTime] = mapped_column(DateTime(timezone=True), nullable=True)
     extract: Mapped[Extract] = relationship()
     extract_id: Mapped[int] = mapped_column(ForeignKey("extract.extract_id"))
+    pseudo_patient_id: Mapped[Optional[str]]
 
     def __repr__(self) -> str:
         """Nice representation for printing."""
         return (
             f"<{self.__class__.__name__} "
-            f"{self.image_id=} {self.accession_number=} {self.mrn=} "
-            f"{self.hashed_identifier} {self.extract_id}>"
+            f"{self.image_id=} {self.accession_number=} {self.mrn=} {self.study_uid=}"
+            f"{self.pseudo_study_uid} {self.extract_id}>"
         ).replace(" self.", " ")
diff --git a/pixl_core/src/core/db/queries.py b/pixl_core/src/core/db/queries.py
index 617ea4e4c..1801cb2a5 100644
--- a/pixl_core/src/core/db/queries.py
+++ b/pixl_core/src/core/db/queries.py
@@ -34,28 +34,28 @@
 engine = create_engine(url)
 
 
-def have_already_exported_image(image_hashed_id: str) -> bool:
+def have_already_exported_image(pseudo_study_uid: str) -> bool:
     """Check if the given image has already been exported."""
     PixlSession = sessionmaker(engine)
     with PixlSession() as pixl_session, pixl_session.begin():
-        existing_image = _query_existing_image(pixl_session, image_hashed_id)
+        existing_image = _query_existing_image(pixl_session, pseudo_study_uid)
         return existing_image.exported_at is not None
 
 
-def update_exported_at(hashed_value: str, date_time: datetime) -> None:
+def update_exported_at(pseudo_study_uid: str, date_time: datetime) -> None:
     """Update the `exported_at` field for an image in the PIXL database"""
     PixlSession = sessionmaker(engine)
     with PixlSession() as pixl_session, pixl_session.begin():
-        existing_image = _query_existing_image(pixl_session, hashed_value)
+        existing_image = _query_existing_image(pixl_session, pseudo_study_uid)
         existing_image.exported_at = date_time
         pixl_session.add(existing_image)
 
 
-def _query_existing_image(pixl_session: Session, hashed_value: str) -> Image:
+def _query_existing_image(pixl_session: Session, pseudo_study_uid: str) -> Image:
     existing_image: Image = (
         pixl_session.query(Image)
         .filter(
-            Image.hashed_identifier == hashed_value,
+            Image.pseudo_study_uid == pseudo_study_uid,
         )
         .one()
     )
diff --git a/pixl_core/src/core/dicom_tags.py b/pixl_core/src/core/dicom_tags.py
index 6f370481a..8f6d6ca81 100644
--- a/pixl_core/src/core/dicom_tags.py
+++ b/pixl_core/src/core/dicom_tags.py
@@ -53,7 +53,7 @@ class PrivateDicomTag:
     # LO = Long string max 64
     # https://dicom.nema.org/medical/dicom/current/output/chtml/part05/sect_6.2.html
     vr: str
-    unknown_value: Optional[str] = "__pixl_unknown_value__"
+    unknown_value: Optional[str | bytes] = "__pixl_unknown_value__"
 
     def acceptable_private_block(self, actual_private_block: int) -> bool:
         """
@@ -68,19 +68,8 @@ def acceptable_private_block(self, actual_private_block: int) -> bool:
         return self.required_private_block == actual_private_block
 
 
-DICOM_TAG_PROJECT_NAME = PrivateDicomTag(
-    group_id=0x000D,
-    required_private_block=0x10,
-    offset_id=0x01,
-    creator_string="UCLH PIXL",
-    tag_nickname="UCLHPIXLProjectName",
-    vr="LO",  # LO = Long string max 64
-    unknown_value="__pixl_unknown_value__",
-)
-
-
 def add_private_tag(
-    dataset: Dataset, private_tag: PrivateDicomTag, value: Optional[str] = None
+    dataset: Dataset, private_tag: PrivateDicomTag, value: Optional[str | bytes] = None
 ) -> PrivateBlock:
     """
     Add a private tag to an existing DICOM dataset.
diff --git a/pixl_core/src/core/exceptions.py b/pixl_core/src/core/exceptions.py
index 2f4c38024..63b06b7e8 100644
--- a/pixl_core/src/core/exceptions.py
+++ b/pixl_core/src/core/exceptions.py
@@ -24,5 +24,17 @@ class PixlDiscardError(RuntimeError):
     """
 
 
+class PixlSkipInstanceError(RuntimeError):
+    """Study instance should be ignored."""
+
+
 class PixlRequeueMessageError(RuntimeError):
     """Requeue PIXL message."""
+
+
+class PixlOutOfHoursError(Exception):
+    """Nack and requeue PIXL message."""
+
+
+class PixlStudyNotInPrimaryArchiveError(Exception):
+    """Study not in primary archive."""
diff --git a/pixl_core/src/core/patient_queue/_base.py b/pixl_core/src/core/patient_queue/_base.py
index 9cc40b0dd..aa9c19922 100644
--- a/pixl_core/src/core/patient_queue/_base.py
+++ b/pixl_core/src/core/patient_queue/_base.py
@@ -21,7 +21,7 @@
 
 
 class PixlQueueInterface:
-    def __init__(  # noqa: PLR0913
+    def __init__(
         self,
         queue_name: str,
         host: str = "localhost",
@@ -65,7 +65,11 @@ def __enter__(self) -> Any:
 
             if self._channel is None or self._channel.is_closed:
                 self._channel = self._connection.channel()
-            self._queue = self._channel.queue_declare(queue=self.queue_name, durable=True)
+            self._queue = self._channel.queue_declare(
+                queue=self.queue_name,
+                durable=True,
+                arguments={"x-max-priority": 5},
+            )
 
         logger.debug("Connected to {}", self.queue_name)
         return self
diff --git a/pixl_core/src/core/patient_queue/message.py b/pixl_core/src/core/patient_queue/message.py
index a6cdfc3be..f6d9d3f35 100644
--- a/pixl_core/src/core/patient_queue/message.py
+++ b/pixl_core/src/core/patient_queue/message.py
@@ -28,10 +28,11 @@
 
 @dataclass
 class Message:
-    """Class to represent a message containing the relevant information for a study."""
+    """Representation of a RabbitMQ message containing the information to identify a DICOM study."""
 
     mrn: str
     accession_number: str
+    study_uid: str
     study_date: date
     procedure_occurrence_id: int
     project_name: str
@@ -40,7 +41,9 @@ class Message:
     @property
     def identifier(self) -> str:
         """Identifier for message"""
-        return f"Message({self.mrn=} {self.accession_number=})".replace("self.", "")
+        return f"Message({self.mrn=} {self.accession_number=} {self.study_uid=})".replace(
+            "self.", ""
+        )
 
     def serialise(self, *, deserialisable: bool = True) -> bytes:
         """
diff --git a/pixl_core/src/core/patient_queue/producer.py b/pixl_core/src/core/patient_queue/producer.py
index 9e36d4912..f46c00774 100644
--- a/pixl_core/src/core/patient_queue/producer.py
+++ b/pixl_core/src/core/patient_queue/producer.py
@@ -30,10 +30,11 @@
 class PixlProducer(PixlBlockingInterface):
     """Generic publisher for RabbitMQ"""
 
-    def publish(self, messages: list[Message]) -> None:
+    def publish(self, messages: list[Message], priority: int) -> None:
         """
         Sends a list of serialised messages to a queue.
         :param messages: list of messages to be sent to queue
+        :param priority: priority of the messages, from 1 (lowest) to 5 (highest)
         """
         logger.info("Publishing {} messages to queue: {}", len(messages), self.queue_name)
         if len(messages) > 0:
@@ -43,9 +44,14 @@ def publish(self, messages: list[Message]) -> None:
                     exchange="",
                     routing_key=self.queue_name,
                     body=serialised_msg,
-                    properties=BasicProperties(delivery_mode=DeliveryMode.Persistent),
+                    properties=BasicProperties(
+                        delivery_mode=DeliveryMode.Persistent,
+                        priority=priority,
+                    ),
+                )
+                logger.debug(
+                    "Message {} published to queue {} with priority", msg, self.queue_name, priority
                 )
-                logger.debug("Message {} published to queue {}", msg, self.queue_name)
         else:
             logger.warning("List of messages is empty so nothing will be published to queue.")
 
diff --git a/pixl_core/src/core/patient_queue/subscriber.py b/pixl_core/src/core/patient_queue/subscriber.py
index 7be2141e0..dd43737c1 100644
--- a/pixl_core/src/core/patient_queue/subscriber.py
+++ b/pixl_core/src/core/patient_queue/subscriber.py
@@ -22,9 +22,15 @@
 import aio_pika
 from decouple import config
 
-from core.exceptions import PixlDiscardError, PixlRequeueMessageError
+from core.exceptions import (
+    PixlDiscardError,
+    PixlOutOfHoursError,
+    PixlRequeueMessageError,
+    PixlStudyNotInPrimaryArchiveError,
+)
 from core.patient_queue._base import PixlQueueInterface
 from core.patient_queue.message import deserialise
+from core.patient_queue.producer import PixlProducer
 
 if TYPE_CHECKING:
     from collections.abc import Awaitable, Callable
@@ -45,6 +51,7 @@ def __init__(
         self,
         queue_name: str,
         token_bucket: TokenBucket,
+        token_bucket_key: str,
         callback: Callable[[Message], Awaitable[None]],
     ) -> None:
         """
@@ -53,6 +60,7 @@ def __init__(
         """
         super().__init__(queue_name=queue_name)
         self.token_bucket = token_bucket
+        self.token_bucket_key = token_bucket_key
         self._callback = callback
 
     @property
@@ -67,23 +75,50 @@ async def __aenter__(self) -> Self:
         max_in_flight = config("PIXL_MAX_MESSAGES_IN_FLIGHT", cast=int)
         logger.info("Pika will consume up to {} messages concurrently", max_in_flight)
         await self._channel.set_qos(prefetch_count=max_in_flight)
-        self._queue = await self._channel.declare_queue(self.queue_name, durable=True)
+        self._queue = await self._channel.declare_queue(
+            self.queue_name,
+            durable=True,
+            arguments={"x-max-priority": 5},
+        )
         return self
 
     async def _process_message(self, message: AbstractIncomingMessage) -> None:
-        if not self.token_bucket.has_token:
+        if not self.token_bucket.has_token(key=self.token_bucket_key):
             await asyncio.sleep(1)
             await message.reject(requeue=True)
             return
 
         pixl_message: Message = deserialise(message.body)
-        logger.info("Starting message {}", pixl_message.identifier)
+        logger.debug("Picked up from queue: {}", pixl_message.identifier)
         try:
             await self._callback(pixl_message)
         except PixlRequeueMessageError as requeue:
             logger.trace("Requeue message: {} from {}", pixl_message.identifier, requeue)
             await asyncio.sleep(1)
             await message.reject(requeue=True)
+        except PixlStudyNotInPrimaryArchiveError as discard:
+            logger.info(
+                "Discard message: {} from {}. Sending to secondary imaging queue with priority {}.",
+                pixl_message.identifier,
+                discard,
+                message.priority,
+            )
+            await asyncio.sleep(1)
+            await message.reject(requeue=False)
+            with PixlProducer(
+                queue_name="imaging-secondary",
+                host=config("RABBITMQ_HOST"),
+                port=config("RABBITMQ_PORT", cast=int),
+                username=config("RABBITMQ_USERNAME"),
+                password=config("RABBITMQ_PASSWORD"),
+            ) as producer:
+                producer.publish([pixl_message], priority=message.priority)
+        except PixlOutOfHoursError as nack_requeue:
+            logger.trace(
+                "Nack and requeue message: {} from {}", pixl_message.identifier, nack_requeue
+            )
+            await asyncio.sleep(10)
+            await message.nack(requeue=True)
         except PixlDiscardError as exception:
             logger.warning("Failed message {}: {}", pixl_message.identifier, exception)
             await (
diff --git a/pixl_core/src/core/project_config/pixl_config_model.py b/pixl_core/src/core/project_config/pixl_config_model.py
index 2ae5a5305..407daee61 100644
--- a/pixl_core/src/core/project_config/pixl_config_model.py
+++ b/pixl_core/src/core/project_config/pixl_config_model.py
@@ -20,8 +20,8 @@
 from pathlib import Path
 from typing import Any, Optional
 
-import yaml  # type: ignore [import-untyped]
-from decouple import Config, RepositoryEmpty, RepositoryEnv  # type: ignore [import-untyped]
+import yaml
+from decouple import Config, RepositoryEmpty, RepositoryEnv
 from loguru import logger
 from pydantic import BaseModel, field_validator
 
@@ -38,19 +38,19 @@ def load_project_config(project_slug: str) -> PixlConfig | Any:
     Project needs to have a corresponding yaml file in the `$PROJECT_CONFIGS_DIR` directory.
     """
     configpath = Path(config("PROJECT_CONFIGS_DIR")) / f"{project_slug}.yaml"
-    logger.debug("Loading config for {} from {}", project_slug, configpath)
     try:
-        return _load_and_validate(configpath)
+        return load_config_and_validate(configpath)
     except FileNotFoundError as error:
         msg = f"No config for {project_slug}. Please submit PR and redeploy."
         raise PixlDiscardError(msg) from error
 
 
-def _load_and_validate(filename: Path) -> PixlConfig | Any:
+def load_config_and_validate(filename: Path) -> PixlConfig | Any:
     """
     Load configuration from a yaml file.
     :param filename: Path to the yaml file
     """
+    logger.debug("Loading config from {}", filename)
     yaml_data = yaml.safe_load(filename.read_text())
     return PixlConfig.model_validate(yaml_data)
 
@@ -65,7 +65,7 @@ class TagOperationFiles(BaseModel):
     """Tag operations files for a project. At least a base file is required."""
 
     base: list[Path]
-    manufacturer_overrides: Optional[Path]
+    manufacturer_overrides: Optional[list[Path]]
 
     @field_validator("base")
     @classmethod
@@ -87,16 +87,24 @@ def _valid_tag_operations(cls, tag_ops_files: list[str]) -> list[Path]:
 
     @field_validator("manufacturer_overrides")
     @classmethod
-    def _valid_manufacturer_overrides(cls, tags_file: str) -> Optional[Path]:
-        if not tags_file:
+    def _valid_manufacturer_overrides(cls, tag_files: list[str]) -> Optional[list[Path]]:
+        if not tag_files:
             return None
 
-        tags_file_path = Path(config("PROJECT_CONFIGS_DIR")) / "tag-operations" / tags_file
-        # Pydantic does not appear to automatically check if the file exists
-        if not tags_file_path.exists():
-            # For pydantic, you must raise a ValueError (or AssertionError)
-            raise ValueError from FileNotFoundError(tags_file_path)
-        return tags_file_path
+        tag_file_paths = []
+        for tag_file in tag_files:
+            tag_file_path = (
+                Path(config("PROJECT_CONFIGS_DIR"))
+                / "tag-operations"
+                / "manufacturer-overrides"
+                / tag_file
+            )
+            # Pydantic does not appear to automatically check if the file exists
+            if not tag_file_path.exists():
+                # For pydantic, you must raise a ValueError (or AssertionError)
+                raise ValueError from FileNotFoundError(tag_file_path)
+            tag_file_paths.append(tag_file_path)
+        return tag_file_paths
 
 
 class _DestinationEnum(str, Enum):
@@ -105,6 +113,7 @@ class _DestinationEnum(str, Enum):
     none = "none"
     ftps = "ftps"
     dicomweb = "dicomweb"
+    xnat = "xnat"
 
 
 class _Destination(BaseModel):
@@ -114,8 +123,8 @@ class _Destination(BaseModel):
     @field_validator("parquet")
     @classmethod
     def valid_parquet_destination(cls, v: str) -> str:
-        if v == "dicomweb":
-            msg = "Parquet destination cannot be dicomweb"
+        if v in ("dicomweb", "xnat"):
+            msg = f"Parquet destination cannot be {v}"
             raise ValueError(msg)
         return v
 
diff --git a/pixl_core/src/core/project_config/tag_operations.py b/pixl_core/src/core/project_config/tag_operations.py
index 6f7f3707e..d7ec56d60 100644
--- a/pixl_core/src/core/project_config/tag_operations.py
+++ b/pixl_core/src/core/project_config/tag_operations.py
@@ -40,12 +40,12 @@ def load_tag_operations(pixl_config: PixlConfig) -> TagOperations:
     :param pixl_config: Project configuration
     """
     base = [_load_scheme(f) for f in pixl_config.tag_operation_files.base]
-    manufacturer_overrides = None
+    manufacturer_overrides = []
 
     if pixl_config.tag_operation_files.manufacturer_overrides:
-        manufacturer_overrides = _load_scheme(
-            pixl_config.tag_operation_files.manufacturer_overrides
-        )
+        for override_file in pixl_config.tag_operation_files.manufacturer_overrides:
+            override_dict = _load_scheme(override_file)
+            manufacturer_overrides.append(override_dict)
 
     return TagOperations(base=base, manufacturer_overrides=manufacturer_overrides)
 
@@ -61,7 +61,7 @@ class TagOperations(BaseModel):
     """
 
     base: list[list[dict]]
-    manufacturer_overrides: Optional[list[dict]]
+    manufacturer_overrides: Optional[list[list[dict]]]
 
     @field_validator("base")
     @classmethod
@@ -77,19 +77,20 @@ def _valid_base_tags(cls, base_tags: list[list[dict]]) -> list[list[dict]]:
     @field_validator("manufacturer_overrides")
     @classmethod
     def _valid_manufacturer_overrides(
-        cls, manufacturer_overrides: Optional[list[dict]]
-    ) -> Optional[list[dict]]:
+        cls, manufacturer_overrides: Optional[list[list[dict]]]
+    ) -> Optional[list[list[dict]]]:
         if manufacturer_overrides is None:
             return None
-        if not isinstance(manufacturer_overrides, list):
-            msg = "Tags must be a list of dictionaries."
-            raise TypeError(msg)
-        for override in manufacturer_overrides:
-            if "manufacturer" not in override or "tags" not in override:
-                msg = "Manufacturer overrides must have 'manufacturer' and 'tags' keys."
-                raise ValueError(msg)
-            for tag in override["tags"]:
-                _check_tag_format(tag)
+        for manufacturer_override in manufacturer_overrides:
+            if not isinstance(manufacturer_override, list):
+                msg = "Tags must be a list of dictionaries."
+                raise TypeError(msg)
+            for override in manufacturer_override:
+                if "manufacturer" not in override or "tags" not in override:
+                    msg = "Manufacturer overrides must have 'manufacturer' and 'tags' keys."
+                    raise ValueError(msg)
+                for tag in override["tags"]:
+                    _check_tag_format(tag)
 
         return manufacturer_overrides
 
diff --git a/pixl_core/src/core/token_buffer/tokens.py b/pixl_core/src/core/token_buffer/tokens.py
index d570d162c..027ea44d6 100644
--- a/pixl_core/src/core/token_buffer/tokens.py
+++ b/pixl_core/src/core/token_buffer/tokens.py
@@ -14,6 +14,8 @@
 #  limitations under the License.
 from __future__ import annotations
 
+import typing
+
 import token_bucket as tb
 
 
@@ -22,19 +24,20 @@ class TokenBucket(tb.Limiter):
     Rate limitation is governed by the existence of tokens in a bucket, whereby the
     bucket is refilled every second. As long as a token can be retrieved, an item can
     be downloaded. Should there be no more tokens inside the bucket, the request is
-    added back into the queue. Note that the Limiter object can operate the rate on
+    added back into the queue.
+
+    Note that the Limiter object can operate the rate on
     different "streams", which are specified by a string object, also called key. This
-    key has been hard coded here to "pixl" as we do not expect the token bucket to be
-    responsible for more than one stream at this point in time.
+    key has been hard coded here to accept one of two values: 'primary' or 'secondary',
+    representing two different streams.
     """
 
-    key = b"pixl"
+    _keys: typing.ClassVar = ["primary", "secondary"]
 
     def __init__(
         self,
         rate: float = 5,
         capacity: int = 5,
-        storage: tb.StorageBase = None,
     ) -> None:
         """
         Uses the token bucket implementation from `Falconry`
@@ -46,18 +49,19 @@ def __init__(
         :param storage: Type of storage used to hold the tokens
         """
         self._zero_rate = False
-        storage = tb.MemoryStorage()
 
         if rate == 0:
             rate = 1  # tb.Limiter does not allow zero rates, so keep track...
             self._zero_rate = True
 
-        super().__init__(rate=rate, capacity=capacity, storage=storage)
+        super().__init__(rate=rate, capacity=capacity, storage=tb.MemoryStorage())
 
-    @property
-    def has_token(self) -> bool:
-        """Does this token bucket have a token?"""
-        return not self._zero_rate and bool(self.consume(self.key))
+    def has_token(self, key: str) -> bool:
+        """Does this token bucket have a token for the given key?"""
+        if key not in self._keys:
+            message = f"Key must be one of {self._keys}, not '{key}'"
+            raise ValueError(message)
+        return not self._zero_rate and bool(self.consume(key))
 
     @property
     def rate(self) -> float:
diff --git a/pixl_core/src/core/uploader/__init__.py b/pixl_core/src/core/uploader/__init__.py
index 6d4be3568..b87bc9d00 100644
--- a/pixl_core/src/core/uploader/__init__.py
+++ b/pixl_core/src/core/uploader/__init__.py
@@ -29,6 +29,7 @@
 
 from ._dicomweb import DicomWebUploader
 from ._ftps import FTPSUploader
+from ._xnat import XNATUploader
 
 if TYPE_CHECKING:
     from core.uploader.base import Uploader
@@ -37,7 +38,11 @@
 # Intenitonally defined in __init__.py to avoid circular imports
 def get_uploader(project_slug: str) -> Uploader:
     """Uploader Factory, returns uploader instance based on destination."""
-    choices: dict[str, type[Uploader]] = {"ftps": FTPSUploader, "dicomweb": DicomWebUploader}
+    choices: dict[str, type[Uploader]] = {
+        "ftps": FTPSUploader,
+        "dicomweb": DicomWebUploader,
+        "xnat": XNATUploader,
+    }
     project_config = load_project_config(project_slug)
     destination = project_config.destination.dicom
 
diff --git a/pixl_core/src/core/uploader/_dicomweb.py b/pixl_core/src/core/uploader/_dicomweb.py
index 90e35e057..90603395d 100644
--- a/pixl_core/src/core/uploader/_dicomweb.py
+++ b/pixl_core/src/core/uploader/_dicomweb.py
@@ -17,7 +17,7 @@
 from __future__ import annotations
 
 import json
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
 
 import requests
 from decouple import config  # type: ignore [import-untyped]
@@ -25,6 +25,9 @@
 
 from core.uploader.base import Uploader
 
+if TYPE_CHECKING:
+    from core.uploader._orthanc import StudyTags
+
 
 class DicomWebUploader(Uploader):
     """Upload strategy for a DicomWeb server."""
@@ -51,10 +54,11 @@ def _set_config(self) -> None:
         self.http_timeout = int(config("HTTP_TIMEOUT", default=30))
 
     def _upload_dicom_image(
-        self, study_id: str, pseudo_anon_image_id: str, project_slug: str
+        self,
+        study_id: str,
+        study_tags: StudyTags,  # noqa: ARG002
     ) -> None:
         """Upload a Dicom resource to the DicomWeb server from within Orthanc."""
-        logger.info("Starting DICOMweb upload of '{}' for {}", pseudo_anon_image_id, project_slug)
         if not self._check_dicomweb_server_exists():
             logger.info("Creating new DICOMWeb credentials")
             self._setup_dicomweb_credentials()
@@ -62,7 +66,7 @@ def _upload_dicom_image(
         self._validate_dicomweb_server()
 
         headers = {"content-type": "application/json", "accept": "application/dicom+json"}
-        payload = {"Resources": [study_id], "Synchronous": False}
+        payload = {"Resources": [study_id], "Synchronous": True}
 
         try:
             response = requests.post(
@@ -76,7 +80,6 @@ def _upload_dicom_image(
         except requests.exceptions.RequestException:
             logger.error("Failed to send via stow")
             raise
-        logger.info("Finished DICOMweb upload of '{}'", pseudo_anon_image_id)
 
     def _check_dicomweb_server_exists(self) -> bool:
         """Checks if the dicomweb server exists."""
@@ -86,9 +89,7 @@ def _check_dicomweb_server_exists(self) -> bool:
             timeout=self.http_timeout,
         )
         success_code = 200
-        if response.status_code != success_code:
-            return False
-        return True
+        return response.status_code == success_code
 
     def _validate_dicomweb_server(self) -> None:
         """Check if the DICOMweb server is reachable from within the Orthanc instance."""
@@ -122,7 +123,6 @@ def _setup_dicomweb_credentials(self) -> None:
             "Username": self.endpoint_user,
             "Password": self.endpoint_password,
             "HasDelete": True,
-            "Timeout": self.http_timeout,
         }
 
         headers = {"content-type": "application/json"}
diff --git a/pixl_core/src/core/uploader/_ftps.py b/pixl_core/src/core/uploader/_ftps.py
index 00fc20517..2cac14d4d 100644
--- a/pixl_core/src/core/uploader/_ftps.py
+++ b/pixl_core/src/core/uploader/_ftps.py
@@ -30,6 +30,7 @@
     from socket import socket
 
     from core.exports import ParquetExport
+    from core.uploader._orthanc import StudyTags
 
 from loguru import logger
 
@@ -77,13 +78,17 @@ def _set_config(self) -> None:
         self.port = int(self.keyvault.fetch_secret(f"{az_prefix}--ftp--port"))
 
     def _upload_dicom_image(
-        self, study_id: str, pseudo_anon_image_id: str, project_slug: str
+        self,
+        study_id: str,
+        study_tags: StudyTags,
     ) -> None:
         """Upload a DICOM image to the FTPS server."""
-        logger.info("Starting FTPS upload of '{}'", pseudo_anon_image_id)
         zip_content = get_study_zip_archive(study_id)
-        self.send_via_ftps(zip_content, pseudo_anon_image_id, remote_directory=project_slug)
-        logger.info("Finished FTPS upload of '{}'", pseudo_anon_image_id)
+        self.send_via_ftps(
+            zip_content,
+            study_tags.pseudo_anon_image_id,
+            remote_directory=self.project_slug,
+        )
 
     def send_via_ftps(
         self, zip_content: BinaryIO, pseudo_anon_image_id: str, remote_directory: str
diff --git a/pixl_core/src/core/uploader/_orthanc.py b/pixl_core/src/core/uploader/_orthanc.py
index 05dfd5a3c..e00606e3e 100644
--- a/pixl_core/src/core/uploader/_orthanc.py
+++ b/pixl_core/src/core/uploader/_orthanc.py
@@ -16,6 +16,7 @@
 from __future__ import annotations
 
 import json
+from dataclasses import dataclass
 from io import BytesIO
 
 import requests
@@ -34,20 +35,30 @@ def get_study_zip_archive(resourceId: str) -> BytesIO:
     return BytesIO(response_study.content)
 
 
-def get_tags_by_study(study_id: str) -> tuple[str, str]:
+@dataclass
+class StudyTags:
+    """Tags for a study."""
+
+    pseudo_anon_image_id: str
+    patient_id: str
+
+
+def get_tags_by_study(study_id: str) -> StudyTags:
     """
     Queries the Orthanc server at the study level, returning the
-    PatientID and UCLHPIXLProjectName DICOM tags.
-    BEWARE: post-anonymisation, the PatientID is NOT
-    the patient ID, it's the pseudo-anonymised ID generated
-    from the hash of the concatenated Patient ID (MRN) and Accession Number fields.
+    Study Instance UID and PatientID DICOM tags.
+    BEWARE: post-anonymisation, the Study Instance UID is NOT
+    the Study Instance UID, it's the pseudo-anonymised ID generated randomly.
     """
     query = f"{ORTHANC_ANON_URL}/studies/{study_id}/shared-tags?simplify=true"
     fail_msg = "Could not query study for resource '%s'"
 
     response_study = _query_orthanc_anon(study_id, query, fail_msg)
     json_response = json.loads(response_study.content.decode())
-    return json_response["PatientID"], json_response["UCLHPIXLProjectName"]
+    return StudyTags(
+        pseudo_anon_image_id=json_response["StudyInstanceUID"],
+        patient_id=json_response["PatientID"],
+    )
 
 
 def _query_orthanc_anon(resourceId: str, query: str, fail_msg: str) -> requests.Response:
diff --git a/pixl_core/src/core/uploader/_xnat.py b/pixl_core/src/core/uploader/_xnat.py
new file mode 100644
index 000000000..a8c345605
--- /dev/null
+++ b/pixl_core/src/core/uploader/_xnat.py
@@ -0,0 +1,103 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+"""Uploader subclass for XNAT."""
+
+from __future__ import annotations
+
+import os
+from typing import TYPE_CHECKING, BinaryIO, Optional
+
+import xnat
+
+from core.uploader.base import Uploader
+
+from ._orthanc import get_study_zip_archive
+
+if TYPE_CHECKING:
+    from xnat.core import XNATBaseObject
+
+    from core.exports import ParquetExport
+    from core.uploader._orthanc import StudyTags
+
+
+class XNATUploader(Uploader):
+    """Upload strategy for an XNAT server."""
+
+    def __init__(self, project_slug: str, keyvault_alias: Optional[str]) -> None:
+        """Create instance of parent class"""
+        super().__init__(project_slug, keyvault_alias)
+
+    def _set_config(self) -> None:
+        """
+        Configure XNATUploader.
+
+        "XNAT_DESTINATION":
+        - if "/archive", will send data straight to the archive
+        - if "/prearchive", will send data to the prearchive for manual review before archiving
+
+        "XNAT_OVERWRITE":
+          - if 'none', will error if the session already exists.
+          - if 'append', will append the data to an existing session or create a new one if it
+            doesn't exist.
+            If there is a conflict with existing series, an error will be raised.
+          - if 'delete', will append the data to an existing session or create a new one if it
+            doesn't exist.
+            If there is a conflict with existing series, the existing series will be overwritten.
+        """
+        # Use the Azure KV alias as prefix if it exists, otherwise use the project name
+        az_prefix = self.keyvault_alias
+        az_prefix = az_prefix if az_prefix else self.project_slug
+
+        self.host = self.keyvault.fetch_secret(f"{az_prefix}--xnat--host")
+        self.user = self.keyvault.fetch_secret(f"{az_prefix}--xnat--username")
+        self.password = self.keyvault.fetch_secret(f"{az_prefix}--xnat--password")
+        self.port = int(self.keyvault.fetch_secret(f"{az_prefix}--xnat--port"))
+        self.url = f"https://{self.host}:{self.port}"
+        self.destination = os.environ["XNAT_DESTINATION"]
+        self.overwrite = os.environ["XNAT_OVERWRITE"]
+
+    def _upload_dicom_image(
+        self,
+        study_id: str,
+        study_tags: StudyTags,
+    ) -> None:
+        """Upload a DICOM image to the XNAT instance."""
+        zip_content = get_study_zip_archive(study_id)
+        self.upload_to_xnat(zip_content, study_tags)
+
+    def upload_to_xnat(
+        self,
+        zip_content: BinaryIO,
+        study_tags: StudyTags,
+    ) -> XNATBaseObject:
+        with xnat.connect(
+            server=self.url,
+            user=self.user,
+            password=self.password,
+        ) as session:
+            session.services.import_(
+                data=zip_content,
+                overwrite=self.overwrite,
+                destination=self.destination,
+                project=self.project_slug,
+                subject=study_tags.patient_id,
+                experiment=study_tags.pseudo_anon_image_id,
+                content_type="application/zip",
+                import_handler="DICOM-zip",
+            )
+
+    def upload_parquet_files(self, parquet_export: ParquetExport) -> None:  # noqa: ARG002
+        msg = "XNATUploader does not support parquet files"
+        raise NotImplementedError(msg)
diff --git a/pixl_core/src/core/uploader/base.py b/pixl_core/src/core/uploader/base.py
index ab44576ef..887776513 100644
--- a/pixl_core/src/core/uploader/base.py
+++ b/pixl_core/src/core/uploader/base.py
@@ -17,12 +17,17 @@
 
 from abc import ABC, abstractmethod
 from datetime import datetime, timezone
-from typing import Any, Optional
+from typing import TYPE_CHECKING, Any, Optional
+
+from loguru import logger
 
 from core.db.queries import have_already_exported_image, update_exported_at
 from core.project_config.secrets import AzureKeyVault
 from core.uploader._orthanc import get_tags_by_study
 
+if TYPE_CHECKING:
+    from core.uploader._orthanc import StudyTags
+
 
 class Uploader(ABC):
     """Upload strategy interface."""
@@ -56,14 +61,29 @@ def upload_dicom_and_update_database(self, study_id: str) -> None:
         :param study_id: Orthanc Study ID
         :raise: if the image has already been exported
         """
-        pseudo_anon_image_id, project_slug = self._get_tags_by_study(study_id)
-        self.check_already_exported(pseudo_anon_image_id)
-        self._upload_dicom_image(study_id, pseudo_anon_image_id, project_slug)
-        update_exported_at(pseudo_anon_image_id, datetime.now(tz=timezone.utc))
+        study_tags = self._get_tags_by_study(study_id)
+        self.check_already_exported(study_tags.pseudo_anon_image_id)
+
+        logger.info(
+            "Starting {} upload of '{}' for {}",
+            self.__class__.__name__.removesuffix("Uploader"),
+            study_tags.pseudo_anon_image_id,
+            self.project_slug,
+        )
+        self._upload_dicom_image(study_id, study_tags)
+        logger.success(
+            "Finished {} upload of '{}'",
+            self.__class__.__name__.removesuffix("Uploader"),
+            study_tags.pseudo_anon_image_id,
+        )
+
+        update_exported_at(study_tags.pseudo_anon_image_id, datetime.now(tz=timezone.utc))
 
     @abstractmethod
     def _upload_dicom_image(
-        self, study_id: str, pseudo_anon_image_id: str, project_slug: str
+        self,
+        study_id: str,
+        study_tags: StudyTags,
     ) -> None:
         """
         Abstract method to upload DICOM images, should not be called directly.
@@ -88,6 +108,6 @@ def check_already_exported(pseudo_anon_image_id: str) -> None:
             raise RuntimeError(msg)
 
     @staticmethod
-    def _get_tags_by_study(study_id: str) -> tuple[str, str]:
+    def _get_tags_by_study(study_id: str) -> StudyTags:
         """Helper method for getting tags by study ID, can be overriden for testing."""
         return get_tags_by_study(study_id)
diff --git a/pixl_core/tests/conftest.py b/pixl_core/tests/conftest.py
index c6fb50bfd..77325b985 100644
--- a/pixl_core/tests/conftest.py
+++ b/pixl_core/tests/conftest.py
@@ -23,6 +23,8 @@
 import pytest
 import requests
 from core.db.models import Base, Extract, Image
+from core.patient_queue.message import Message
+from pydicom.uid import generate_uid
 from pytest_pixl.helpers import run_subprocess
 from sqlalchemy import Engine, create_engine
 from sqlalchemy.orm import Session, sessionmaker
@@ -38,19 +40,26 @@
 
 os.environ["PIXL_MAX_MESSAGES_IN_FLIGHT"] = "10"
 os.environ["RABBITMQ_USERNAME"] = "guest"
-os.environ["RABBITMQ_PASSWORD"] = "guest"  # noqa: S105 Hardcoding password
+os.environ["RABBITMQ_PASSWORD"] = "guest"
 os.environ["RABBITMQ_HOST"] = "localhost"
 os.environ["RABBITMQ_PORT"] = "25672"
 os.environ["PROJECT_CONFIGS_DIR"] = str(TEST_DIR.parents[1] / "projects/configs")
 
 os.environ["FTP_HOST"] = "localhost"
 os.environ["FTP_USER_NAME"] = "pixl"
-os.environ["FTP_PASSWORD"] = "longpassword"  # noqa: S105 Hardcoding password
+os.environ["FTP_PASSWORD"] = "longpassword"
 os.environ["FTP_PORT"] = "20021"
 
 os.environ["ORTHANC_ANON_URL"] = "http://localhost:8043"
 os.environ["ORTHANC_ANON_USERNAME"] = "orthanc"
-os.environ["ORTHANC_ANON_PASSWORD"] = "orthanc"  # noqa: S105, hardcoded password
+os.environ["ORTHANC_ANON_PASSWORD"] = "orthanc"
+
+os.environ["XNAT_HOST"] = "localhost"
+os.environ["XNAT_USER_NAME"] = "pixl"
+os.environ["XNAT_PASSWORD"] = "longpassword"
+os.environ["XNAT_PORT"] = "8080"
+os.environ["XNAT_DESTINATION"] = "/archive"
+os.environ["XNAT_OVERWRITE"] = "none"
 
 
 @pytest.fixture(scope="package")
@@ -152,16 +161,18 @@ def rows_in_session(db_session) -> Session:
         accession_number="123",
         study_date=STUDY_DATE,
         mrn="mrn",
+        study_uid="1.2.3",
         extract=extract,
         exported_at=datetime.datetime.now(tz=datetime.timezone.utc),
-        hashed_identifier="already_exported",
+        pseudo_study_uid=generate_uid(entropy_srcs=["already_exported"]),
     )
     image_not_exported = Image(
         accession_number="234",
         study_date=STUDY_DATE,
         mrn="mrn",
+        study_uid="2.3.4",
         extract=extract,
-        hashed_identifier="not_yet_exported",
+        pseudo_study_uid=generate_uid(entropy_srcs=["not_yet_exported"]),
     )
     with db_session:
         db_session.add_all([extract, image_exported, image_not_exported])
@@ -173,13 +184,21 @@ def rows_in_session(db_session) -> Session:
 @pytest.fixture()
 def not_yet_exported_dicom_image(rows_in_session) -> Image:
     """Return a DICOM image from the database."""
-    return rows_in_session.query(Image).filter(Image.hashed_identifier == "not_yet_exported").one()
+    return (
+        rows_in_session.query(Image)
+        .filter(Image.pseudo_study_uid == generate_uid(entropy_srcs=["not_yet_exported"]))
+        .one()
+    )
 
 
 @pytest.fixture()
 def already_exported_dicom_image(rows_in_session) -> Image:
     """Return a DICOM image from the database."""
-    return rows_in_session.query(Image).filter(Image.hashed_identifier == "already_exported").one()
+    return (
+        rows_in_session.query(Image)
+        .filter(Image.pseudo_study_uid == generate_uid(entropy_srcs=["already_exported"]))
+        .one()
+    )
 
 
 @pytest.fixture(autouse=True)
@@ -188,3 +207,19 @@ def export_dir(tmp_path_factory: pytest.TempPathFactory) -> pathlib.Path:
     export_dir = tmp_path_factory.mktemp("export_base") / "exports"
     export_dir.mkdir()
     return export_dir
+
+
+@pytest.fixture()
+def mock_message() -> Message:
+    """An example Message used for testing"""
+    return Message(
+        mrn="111",
+        accession_number="123",
+        study_uid="1.2.3",
+        study_date=datetime.date.fromisoformat("2022-11-22"),
+        procedure_occurrence_id="234",
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.strptime(
+            "Dec 7 2023 2:08PM", "%b %d %Y %I:%M%p"
+        ).replace(tzinfo=datetime.timezone.utc),
+    )
diff --git a/pixl_core/tests/data/dicom_series.zip b/pixl_core/tests/data/dicom_series.zip
new file mode 100644
index 000000000..dee661c7e
Binary files /dev/null and b/pixl_core/tests/data/dicom_series.zip differ
diff --git a/pixl_core/tests/data/xnat_project.xml b/pixl_core/tests/data/xnat_project.xml
new file mode 100644
index 000000000..26f07edac
--- /dev/null
+++ b/pixl_core/tests/data/xnat_project.xml
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="utf-8"?>
+<ProjectData 
+    ID="some-project-slug"
+    secondary_ID="Some Project Slug"
+    name="Some Project Slug: This is not a real project."
+>
+</ProjectData>
\ No newline at end of file
diff --git a/pixl_core/tests/docker-compose.yml b/pixl_core/tests/docker-compose.yml
index e6d81fa97..204039d4a 100644
--- a/pixl_core/tests/docker-compose.yml
+++ b/pixl_core/tests/docker-compose.yml
@@ -42,6 +42,7 @@ services:
             RAW_DICOM_PORT: "4242"
             RAW_IP_ADDR: "orthanc-raw" # aka. hostname
             DICOM_WEB_PLUGIN_ENABLED: true
+            TZ: "Europe/London"
         ports:
             - "127.0.0.1:4243:4242"
             - "127.0.0.1:8043:8042"
@@ -66,6 +67,7 @@ services:
             RAW_DICOM_PORT: "4242"
             RAW_IP_ADDR: "dicom-web" # aka. hostname
             DICOM_WEB_PLUGIN_ENABLED: true
+            TZ: "Europe/London"
         ports:
             - "127.0.0.1:4244:4242"
             - "127.0.0.1:8044:8042"
diff --git a/pixl_core/tests/patient_queue/test_message.py b/pixl_core/tests/patient_queue/test_message.py
index f70ca2491..a4785c63f 100644
--- a/pixl_core/tests/patient_queue/test_message.py
+++ b/pixl_core/tests/patient_queue/test_message.py
@@ -13,27 +13,14 @@
 #  limitations under the License.
 from __future__ import annotations
 
-import datetime
+from core.patient_queue.message import deserialise
 
-from core.patient_queue.message import Message, deserialise
 
-msg = Message(
-    mrn="111",
-    accession_number="123",
-    study_date=datetime.date.fromisoformat("2022-11-22"),
-    procedure_occurrence_id="234",
-    project_name="test project",
-    extract_generated_timestamp=datetime.datetime.strptime(
-        "Dec 7 2023 2:08PM", "%b %d %Y %I:%M%p"
-    ).replace(tzinfo=datetime.timezone.utc),
-)
-
-
-def test_serialise() -> None:
+def test_serialise(mock_message) -> None:
     """Checks that messages can be correctly serialised"""
-    msg_body = msg.serialise(deserialisable=False)
+    msg_body = mock_message.serialise(deserialisable=False)
     assert (
-        msg_body == b'{"mrn": "111", "accession_number": "123", '
+        msg_body == b'{"mrn": "111", "accession_number": "123", "study_uid": "1.2.3", '
         b'"study_date": "2022-11-22", '
         b'"procedure_occurrence_id": "234", '
         b'"project_name": "test project", '
@@ -41,7 +28,7 @@ def test_serialise() -> None:
     )
 
 
-def test_deserialise() -> None:
+def test_deserialise(mock_message) -> None:
     """Checks if deserialised messages are the same as the original"""
-    serialised_msg = msg.serialise()
-    assert deserialise(serialised_msg) == msg
+    serialised_msg = mock_message.serialise()
+    assert deserialise(serialised_msg) == mock_message
diff --git a/pixl_core/tests/patient_queue/test_producer.py b/pixl_core/tests/patient_queue/test_producer.py
index 3a684ffe3..2df0ca3b6 100644
--- a/pixl_core/tests/patient_queue/test_producer.py
+++ b/pixl_core/tests/patient_queue/test_producer.py
@@ -14,18 +14,9 @@
 from __future__ import annotations
 
 import pytest
-from core.patient_queue.message import Message
 from core.patient_queue.producer import PixlProducer
 
 TEST_QUEUE = "test_publish"
-TEST_MESSAGE = Message(
-    mrn="111",
-    accession_number="123",
-    study_date="2022-11-22T13:33:00+00:00",
-    procedure_occurrence_id="234",
-    project_name="test project",
-    extract_generated_timestamp="2023-12-07T14:08:00+00:00",
-)
 
 
 @pytest.mark.usefixtures("run_containers")
@@ -36,14 +27,14 @@ def test_create_pixl_producer() -> None:
 
 
 @pytest.mark.usefixtures("run_containers")
-def test_publish() -> None:
+def test_publish(mock_message) -> None:
     """
     Checks that after publishing, there is one message in the queue.
     Will only work if nothing has been added to queue before.
     """
     with PixlProducer(queue_name=TEST_QUEUE) as pp:
         pp.clear_queue()
-        pp.publish(messages=[TEST_MESSAGE])
+        pp.publish(messages=[mock_message], priority=1)
 
     with PixlProducer(queue_name=TEST_QUEUE) as pp:
         assert pp.message_count == 1
diff --git a/pixl_core/tests/patient_queue/test_subscriber.py b/pixl_core/tests/patient_queue/test_subscriber.py
index 57711b886..82c484fc9 100644
--- a/pixl_core/tests/patient_queue/test_subscriber.py
+++ b/pixl_core/tests/patient_queue/test_subscriber.py
@@ -17,20 +17,11 @@
 from unittest.mock import AsyncMock
 
 import pytest
-from core.patient_queue.message import Message
 from core.patient_queue.producer import PixlProducer
 from core.patient_queue.subscriber import PixlConsumer
 from core.token_buffer.tokens import TokenBucket
 
 TEST_QUEUE = "test_consume"
-TEST_MESSAGE = Message(
-    mrn="111",
-    accession_number="123",
-    study_date="2022-11-22T13:33:00+00:00",
-    procedure_occurrence_id="234",
-    project_name="test project",
-    extract_generated_timestamp="2023-12-07T14:08:00+00:00",
-)
 
 
 class ExpectedTestError(Exception):
@@ -42,14 +33,17 @@ class ExpectedTestError(Exception):
 @pytest.mark.xfail(
     reason="Sanity check that async test gets run", strict=True, raises=ExpectedTestError
 )
-async def test_create() -> None:
+async def test_create(mock_message) -> None:
     """Checks consume is working."""
     with PixlProducer(queue_name=TEST_QUEUE) as producer:
-        producer.publish(messages=[TEST_MESSAGE])
+        producer.publish(messages=[mock_message], priority=1)
 
     consume = AsyncMock()
     async with PixlConsumer(
-        queue_name=TEST_QUEUE, token_bucket=TokenBucket(), callback=consume
+        queue_name=TEST_QUEUE,
+        token_bucket=TokenBucket(),
+        token_bucket_key="primary",  # noqa: S106
+        callback=consume,
     ) as consumer:
         # Create a Task to run pc.run in the background
         task = asyncio.create_task(consumer.run())
diff --git a/pixl_core/tests/project_config/test_project_config.py b/pixl_core/tests/project_config/test_project_config.py
index d15f79cf2..3a09ae6d5 100644
--- a/pixl_core/tests/project_config/test_project_config.py
+++ b/pixl_core/tests/project_config/test_project_config.py
@@ -42,7 +42,7 @@ def base_yaml_data():
         "project": {"name": "myproject", "modalities": ["DX", "CR"]},
         "tag_operation_files": {
             "base": ["test-extract-uclh-omop-cdm.yaml"],
-            "manufacturer_overrides": "manufacturer-overrides/mri-diffusion.yaml",
+            "manufacturer_overrides": ["mri-diffusion.yaml"],
         },
         "destination": {"dicom": "ftps", "parquet": "ftps"},
     }
@@ -93,7 +93,8 @@ def ids_for_parameterised_test(val):
 )
 def test_all_real_configs(yaml_file):
     """Test that all production configs are valid"""
-    load_project_config(yaml_file.stem)
+    config = load_project_config(yaml_file.stem)
+    assert config.project.name == yaml_file.stem
 
 
 def test_load_tag_operations():
@@ -121,7 +122,7 @@ def test_load_tag_operations_no_manufacturer_overrides(base_yaml_data):
     tag_operations = load_tag_operations(project_config)
 
     # Assert
-    assert tag_operations.manufacturer_overrides is None
+    assert tag_operations.manufacturer_overrides == []
 
 
 @pytest.fixture()
diff --git a/pixl_core/tests/token_buffer/test_tokens.py b/pixl_core/tests/token_buffer/test_tokens.py
index 8e464ad40..c55e2ac66 100644
--- a/pixl_core/tests/token_buffer/test_tokens.py
+++ b/pixl_core/tests/token_buffer/test_tokens.py
@@ -13,28 +13,39 @@
 #  limitations under the License.
 from __future__ import annotations
 
+import re
 import time
 
+import pytest
 from core.token_buffer import TokenBucket
 
 
 def test_retrieve_token() -> None:
     """Checks whether token can be retrieved from created token bucket."""
     bucket = TokenBucket()
-    assert bucket.has_token
+    assert bucket.has_token(key="primary")
+    assert bucket.has_token(key="secondary")
+
+
+def test_invalid_token_key() -> None:
+    """Checks whether invalid key raises an exception."""
+    bucket = TokenBucket()
+    match = re.escape("Key must be one of ['primary', 'secondary'], not 'invalid'")
+    with pytest.raises(ValueError, match=match):
+        bucket.has_token(key="invalid")
 
 
 def test_refill_tokens() -> None:
     """Checks whether the refill happens after one second for a bucket size of 1."""
     bucket = TokenBucket(rate=1, capacity=1)
 
-    assert bucket.has_token
+    assert bucket.has_token(key="primary")
     # Interrogating the bucket within 1 second we find that it's empty
-    assert bucket.has_token is False
+    assert bucket.has_token(key="primary") is False
 
     # but will be refilled after 1 second
     time.sleep(1)
-    assert bucket.has_token
+    assert bucket.has_token(key="primary")
 
 
 def test_zero_rate() -> None:
diff --git a/pixl_core/tests/uploader/test_base.py b/pixl_core/tests/uploader/test_base.py
index 4595a8df1..e1806fe3a 100644
--- a/pixl_core/tests/uploader/test_base.py
+++ b/pixl_core/tests/uploader/test_base.py
@@ -16,6 +16,8 @@
 import pytest
 import sqlalchemy
 from core.db.models import Image
+from core.uploader import DicomWebUploader, FTPSUploader, XNATUploader, get_uploader
+from core.uploader._orthanc import StudyTags
 from core.uploader.base import Uploader
 from loguru import logger
 from sqlalchemy.orm import sessionmaker
@@ -28,22 +30,26 @@ class DumbUploader(Uploader):
     Allows testing of the database interaction at the top level call to uploader.
     """
 
-    def __init__(self, hashed_identifier) -> None:
+    def __init__(self, pseudo_study_uid) -> None:
         """Initialise the mock uploader with hardcoded values for FTPS config."""
-        self.hashed_identifier = hashed_identifier
+        self.project_slug = "project_slug"
+        self.pseudo_study_uid = pseudo_study_uid
 
-    def _get_tags_by_study(self, study_id: str) -> tuple[str, str]:
-        logger.info("Mocked getting tags for: {} to return {}", study_id, self.hashed_identifier)
-        return self.hashed_identifier, "project_slug"
+    def _get_tags_by_study(self, study_id: str) -> StudyTags:
+        logger.info("Mocked getting tags for: {} to return {}", study_id, self.pseudo_study_uid)
+        return StudyTags(self.pseudo_study_uid, "patient-id")
 
     def _upload_dicom_image(
-        self, study_id: str, pseudo_anon_image_id: str, project_slug: str
+        self,
+        study_id: str,
+        study_tags: StudyTags,
     ) -> None:
         logger.info(
             "Mocked uploader with no upload functionality for {}, {}, {}",
             study_id,
-            pseudo_anon_image_id,
-            project_slug,
+            study_tags.pseudo_anon_image_id,
+            self.project_slug,
+            study_tags.patient_id,
         )
 
     def _set_config(self) -> None:
@@ -65,7 +71,7 @@ def test_export_date_updated(db_engine, not_yet_exported_dicom_image) -> None:
     """
     # ARRANGE
     study_id = "test-study-id"
-    uploader = DumbUploader(not_yet_exported_dicom_image.hashed_identifier)
+    uploader = DumbUploader(not_yet_exported_dicom_image.pseudo_study_uid)
 
     # ACT
     uploader.upload_dicom_and_update_database(study_id)
@@ -74,7 +80,7 @@ def test_export_date_updated(db_engine, not_yet_exported_dicom_image) -> None:
     InMemorySession = sessionmaker(db_engine)
     with InMemorySession() as session:
         output = (
-            session.query(Image).filter(Image.hashed_identifier == uploader.hashed_identifier).one()
+            session.query(Image).filter(Image.pseudo_study_uid == uploader.pseudo_study_uid).one()
         )
     assert output.exported_at is not None
 
@@ -99,7 +105,30 @@ def test_study_already_exported_raises(already_exported_dicom_image) -> None:
     THEN an exception is raised
     """
     study_id = "test-study-id"
-    uploader = DumbUploader(already_exported_dicom_image.hashed_identifier)
+    uploader = DumbUploader(already_exported_dicom_image.pseudo_study_uid)
 
     with pytest.raises(RuntimeError, match="Image already exported"):
         uploader.upload_dicom_and_update_database(study_id)
+
+
+@pytest.mark.parametrize(
+    ("project_slug", "expected_uploader_class"),
+    [
+        ("test-extract-uclh-omop-cdm", FTPSUploader),
+        ("test-extract-uclh-omop-cdm-dicomweb", DicomWebUploader),
+        ("test-extract-uclh-omop-cdm-xnat", XNATUploader),
+    ],
+)
+def test_get_uploader(project_slug, expected_uploader_class, monkeypatch) -> None:
+    """Test the correct uploader class is returned."""
+    with monkeypatch.context() as m:
+        # Mock the __init__ method so that we don't attempt to connect to AzureKeyVault.
+        # Otherwise AzureKeyVault._check_envvars will raise an exception for undefined
+        # environment variables.
+        m.setattr(
+            "core.uploader.base.Uploader.__init__",
+            lambda self, project_slug, keyvault_alias: None,  # noqa: ARG005
+        )
+
+        uploader = get_uploader(project_slug)
+        assert isinstance(uploader, expected_uploader_class)
diff --git a/pixl_core/tests/uploader/test_dicomweb.py b/pixl_core/tests/uploader/test_dicomweb.py
index 103afc9c5..63342a2b5 100644
--- a/pixl_core/tests/uploader/test_dicomweb.py
+++ b/pixl_core/tests/uploader/test_dicomweb.py
@@ -20,6 +20,7 @@
 import pytest
 import requests
 from core.uploader._dicomweb import DicomWebUploader
+from core.uploader._orthanc import StudyTags
 from decouple import config  # type ignore [import-untyped]
 
 ORTHANC_ANON_URL = config("ORTHANC_ANON_URL")
@@ -27,7 +28,7 @@
 ORTHANC_PASSWORD = config("ORTHANC_ANON_PASSWORD")
 
 DICOMWEB_USERNAME = "orthanc_dicomweb"
-DICOMWEB_PASSWORD = "orthanc_dicomweb"  # noqa: S105, hardcoded password
+DICOMWEB_PASSWORD = "orthanc_dicomweb"
 
 LOCAL_DICOMWEB_URL = "http://localhost:8044"
 
@@ -93,8 +94,13 @@ def test_upload_dicom_image(
     study_id, run_containers, dicomweb_uploader, not_yet_exported_dicom_image
 ) -> None:
     """Tests that DICOM image can be uploaded to a DICOMWeb server"""
+    study_tags = StudyTags(
+        pseudo_anon_image_id=not_yet_exported_dicom_image.pseudo_study_uid,
+        patient_id="patient",
+    )
     dicomweb_uploader._upload_dicom_image(  # noqa: SLF001
-        study_id, not_yet_exported_dicom_image.hashed_identifier, "project"
+        study_id,
+        study_tags,
     )
 
     # Check that the instance has arrived in the DICOMweb server
@@ -109,7 +115,7 @@ def test_dicomweb_upload_fails_with_wrong_credentials(
 ) -> None:
     """Tests that the DICOMWeb uploader fails when given wrong credentials."""
     dicomweb_uploader.endpoint_user = "wrong"
-    dicomweb_uploader.endpoint_password = "wrong"  # noqa: S105, hardcoded password
+    dicomweb_uploader.endpoint_password = "wrong"
 
     with pytest.raises(requests.exceptions.ConnectionError):
         dicomweb_uploader._setup_dicomweb_credentials()  # noqa: SLF001, private method
diff --git a/pixl_core/tests/uploader/test_ftps.py b/pixl_core/tests/uploader/test_ftps.py
index 6a8bc19b1..6a18f54c2 100644
--- a/pixl_core/tests/uploader/test_ftps.py
+++ b/pixl_core/tests/uploader/test_ftps.py
@@ -25,6 +25,7 @@
 from core.db.queries import update_exported_at
 from core.exports import ParquetExport
 from core.uploader._ftps import FTPSUploader
+from pydicom.uid import generate_uid
 from pytest_pixl.plugin import FtpHostAddress
 
 TEST_DIR = Path(__file__).parents[1]
@@ -77,7 +78,7 @@ def test_send_via_ftps(
     """Tests that DICOM image can be uploaded to the correct location"""
     # ARRANGE
     # Get the pseudo identifier from the test image
-    pseudo_anon_id = not_yet_exported_dicom_image.hashed_identifier
+    pseudo_anon_id = not_yet_exported_dicom_image.pseudo_study_uid
     project_slug = "some-project-slug"
     expected_output_file = ftps_home_dir / project_slug / (pseudo_anon_id + ".zip")
 
@@ -94,9 +95,11 @@ def test_update_exported_and_save(rows_in_session) -> None:
     expected_export_time = datetime.now(tz=timezone.utc)
 
     # ACT
-    update_exported_at("not_yet_exported", expected_export_time)
+    update_exported_at(generate_uid(entropy_srcs=["not_yet_exported"]), expected_export_time)
     new_row = (
-        rows_in_session.query(Image).filter(Image.hashed_identifier == "not_yet_exported").one()
+        rows_in_session.query(Image)
+        .filter(Image.pseudo_study_uid == generate_uid(entropy_srcs=["not_yet_exported"]))
+        .one()
     )
     actual_export_time = new_row.exported_at.replace(tzinfo=timezone.utc)
 
diff --git a/pixl_core/tests/uploader/test_xnat.py b/pixl_core/tests/uploader/test_xnat.py
new file mode 100644
index 000000000..2205a0c11
--- /dev/null
+++ b/pixl_core/tests/uploader/test_xnat.py
@@ -0,0 +1,199 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Test functionality to upload files to an XNAT instance."""
+
+import io
+import os
+from collections.abc import Generator
+from pathlib import Path
+
+import pytest
+import xnat
+import xnat4tests
+from core.uploader._orthanc import StudyTags
+from core.uploader._xnat import XNATUploader
+
+TEST_DIR = Path(__file__).parents[1]
+
+
+class MockXNATUploader(XNATUploader):
+    """Mock XNATUploader for testing."""
+
+    def __init__(self, project_slug: str) -> None:
+        """Initialise the mock uploader with hardcoded values for FTPS config."""
+        self.host = os.environ["XNAT_HOST"]
+        self.user = os.environ["XNAT_USER_NAME"]
+        self.password = os.environ["XNAT_PASSWORD"]
+        self.port = os.environ["XNAT_PORT"]
+        self.url = f"http://{self.host}:{self.port}"
+        self.destination = os.environ["XNAT_DESTINATION"]
+        self.overwrite = os.environ["XNAT_OVERWRITE"]
+        self.project_slug = project_slug
+
+
+@pytest.fixture(scope="session")
+def xnat_project_slug() -> str:
+    """Name of the XNAT project"""
+    return "some-project-slug"
+
+
+@pytest.fixture()
+def xnat_uploader(xnat_project_slug) -> MockXNATUploader:
+    """Return a MockXNATUploader object."""
+    return MockXNATUploader(project_slug=xnat_project_slug)
+
+
+@pytest.fixture()
+def zip_parquet() -> Generator:
+    """Directory containing parquet test data."""
+    test_zip_file = TEST_DIR / "data" / "public.zip"
+    with test_zip_file.open("rb") as file_content:
+        yield file_content
+
+
+@pytest.fixture()
+def zip_dicoms() -> Generator:
+    """
+    Zip file containing the test DICOMs for uploading to the XNAT instance.
+
+    The zip file contains a single study with two DICOMs:
+    - 987654321_AA12345601_AP.dcm
+    - 987654321_AA12345601_include123.dcm
+    """
+    test_zip_file = TEST_DIR / "data" / "dicom_series.zip"
+    with test_zip_file.open("rb") as file_content:
+        yield io.BytesIO(file_content.read())
+
+
+@pytest.fixture(scope="session")
+def xnat_study_tags() -> StudyTags:
+    """Return a StudyTags object for the study to be uploaded to XNAT."""
+    return StudyTags(
+        pseudo_anon_image_id="1.3.6.1.4.1.14519.5.2.1.99.1071.12985477682660597455732044031486",
+        patient_id="987654321",
+    )
+
+
+@pytest.fixture(scope="session")
+def xnat_server(xnat_project_slug) -> Generator:
+    """
+    Start the XNAT server.
+
+    Note, it can take several minutes for the server to start up.
+
+    Once the server has started, you can log in by visiting http://localhost:8080
+    with the username and password set in the `XNAT_USER_NAME` and `XNAT_PASSWORD`
+    environment variables.
+    """
+    config = xnat4tests.Config(
+        xnat_port=os.environ["XNAT_PORT"],
+        docker_host=os.environ["XNAT_HOST"],
+        build_args={
+            "xnat_version": "1.8.10.1",
+        },
+    )
+    xnat4tests.start_xnat(config)
+
+    # Create the project as well as a non-admin user to perform the upload
+    with xnat.connect(
+        server=config.xnat_uri,
+        user="admin",
+        password="admin",  # noqa: S106
+    ) as session:
+        session.post(
+            path="/xapi/users/",
+            json=dict(  # noqa: C408
+                admin=False,
+                username=os.environ["XNAT_USER_NAME"],
+                password=os.environ["XNAT_PASSWORD"],
+                firstName="pixl",
+                lastName="uploader",
+                email="pixl-uploader@pixl",
+                verified=True,
+                enabled=True,
+            ),
+            headers={"Content-Type": "application/json"},
+            accepted_status=[201, 409],
+        )
+
+        # XNAT requires project metadata to be uploaded as XML
+        with (TEST_DIR / "data" / "xnat_project.xml").open() as file:
+            project_xml = file.read()
+        session.skip_response_content_check = (
+            True  # so XNATPy doesn't raise an error if the project exists
+        )
+        session.post(
+            path="/data/projects",
+            data=project_xml,
+            headers={"Content-Type": "application/xml"},
+            accepted_status=[200, 409],
+        )
+        session.put(
+            path=f"/data/projects/{xnat_project_slug}/users/Owners/pixl",
+            accepted_status=[200],
+        )
+
+    yield config.xnat_uri
+
+    # If a test instance already exists, xnat4tests will reuse it for subsequent tests.
+    # This can save a lot of time when testing locally as it takes several minutes to start
+    # the XNAT server.
+    if os.environ.get("XNAT_DESTROY_INSTANCE", "False").lower() == "true":
+        xnat4tests.stop_xnat(config)
+        return
+
+    # If we're keeping the instance, we need to remove the data before next test run.
+    # We do not delete the project itself as Project IDs cannot be reused.
+    with xnat.connect(
+        server=config.xnat_uri,
+        user="admin",
+        password="admin",  # noqa: S106
+    ) as session:
+        project = session.projects[xnat_project_slug]
+        for subject in project.subjects.values():
+            session.delete(
+                path=f"/data/projects/{project.id}/subjects/{subject.label}",
+                query={"removeFiles": "True"},
+            )
+
+
+@pytest.mark.usefixtures("xnat_server")
+def test_upload_to_xnat(zip_dicoms, xnat_uploader, xnat_study_tags) -> None:
+    """Tests that DICOM image can be uploaded to the correct location"""
+    xnat_uploader.upload_to_xnat(
+        zip_content=zip_dicoms,
+        study_tags=xnat_study_tags,
+    )
+
+    with xnat.connect(
+        server=xnat_uploader.url,
+        user=xnat_uploader.user,
+        password=xnat_uploader.password,
+    ) as session:
+        assert xnat_uploader.project_slug in session.projects
+        project = session.projects[xnat_uploader.project_slug]
+
+        assert xnat_study_tags.patient_id in project.subjects
+        subject = project.subjects[xnat_study_tags.patient_id]
+
+        assert len(subject.experiments) == 1
+        experiment = subject.experiments[0]
+        assert experiment.label == xnat_study_tags.pseudo_anon_image_id.replace(".", "_")
+        assert len(experiment.scans) == 2
+
+
+def test_parquet_export_not_implemented(xnat_uploader, zip_parquet) -> None:
+    """Tests that calling XNATUploader.upload_parquet_files raises an error."""
+    with pytest.raises(NotImplementedError, match="XNATUploader does not support parquet files"):
+        xnat_uploader.upload_parquet_files(zip_parquet)
diff --git a/pixl_dcmd/README.md b/pixl_dcmd/README.md
index fc118e774..2c8b57682 100644
--- a/pixl_dcmd/README.md
+++ b/pixl_dcmd/README.md
@@ -3,20 +3,48 @@
 The `pixl_dcmd` package provides helper functions for de-identifying DICOM data. It is currently
 only used by the [`orthanc-anon` plugin](../orthanc/orthanc-anon/plugin/pixl.py).
 
-The reason for having this as a separate package instead of having the functionality in `pixl_core`
-is because `orthanc` requires Python 3.9, whereas the rest of PIXL is on 3.10 or higher.
+For external users, the `pixl_dcmd` package provides the following functionality:
 
-Specifically, the `pixl_dcmd` package provides the following functionality:
+- `anonymise_dicom()`: Applies the [anonymisation operations](#tag-scheme-anonymisation) 
+   for the appropriate tag scheme using [Kitware Dicom Anonymizer](https://github.com/KitwareMedical/dicom-anonymizer)
+   and deletes any tags not mentioned in the tag scheme. The dataset is updated in place.
+     - Will throw a `PixlSkipInstanceError` for any series based on the project config file. Specifically, an error
+       will be thrown if:
+       - the series description matches any series in `series_filters` (usually to remove localiser series)
+       - the modality of the DICOM is not in `modalities`
+- `anonymise_and_validate_dicom()`: Compares DICOM validation issues before and after calling `anonymise_dicom`
+  and returns a dictionary of the new issues
 
-- `anonymise_dicom()`: Applies the [anonymisation operations](#tag-scheme-anonymisation) for the appropriate tag scheme using [Kitware Dicom Anonymizer](https://github.com/KitwareMedical/dicom-anonymizer)) and deletes any tags not mentioned in the tag scheme.
-- `write_dataset_to_bytes()`: writes a DICOM dataset to a bytes object
+```python
+import os
+import pathlib
+import pydicom
+
+from core.project_config.pixl_config_model import load_config_and_validate
+from pixl_dcmd import anonymise_and_validate_dicom
+
+config_dir = pathlib.Path().cwd().parents[2] / "projects" / "configs"
+config_path = config_dir / "test-external-user.yaml"
+os.environ["PROJECT_CONFIGS_DIR"] = config_dir.as_posix()  # needed to validate config
+config = load_config_and_validate(config_path)
+
+dataset_path = pydicom.data.get_testdata_file(
+    "MR-SIEMENS-DICOM-WithOverlays.dcm", download=True,
+)
+dataset = pydicom.dcmread(dataset_path)
+
+# the dataset is updated inplace
+validation_issues = anonymise_and_validate_dicom(dataset, config=config)
+assert validation_issues == {}
+assert dataset != pydicom.dcmread(dataset_path)
+```
 
 ## Installation
 
-Install the Python dependencies with
+Install the Python dependencies from the `pixl_dcmd` directory:
 
 ```bash
-pip install -e ../pixl_core/ -e .[test,dev]
+python -m pip install -e ../pixl_core/ -e ".[test,dev]"
 ```
 
 ## Test
diff --git a/pixl_dcmd/pyproject.toml b/pixl_dcmd/pyproject.toml
index 213f2f934..fa0168384 100644
--- a/pixl_dcmd/pyproject.toml
+++ b/pixl_dcmd/pyproject.toml
@@ -1,32 +1,54 @@
 [project]
 name = "pixl_dcmd"
-version = "0.0.2"
+version = "0.2.0rc0"
 authors = [{ name = "PIXL authors" }]
 description = "DICOM header anonymisation functions"
 readme = "README.md"
 requires-python = ">=3.11"
 classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "arrow==1.2.3",
+    "core==0.2.0rc0",
+    "arrow==1.3.0",
+    "dicom-anonymizer==1.0.13.post1",
+    "dicom-validator==0.6.3",
+    "logger==1.4",
     "pydicom==2.4.4",
     "pydicom-data",
-    "logger==1.4",
-    "requests==2.31.0",
-    "python-decouple==3.6",
+    "python-decouple==3.8",
+    "requests==2.32.3",
     "types-requests~=2.28",
-    "dicom-anonymizer==1.0.12",
 ]
 
 [project.optional-dependencies]
-test = ["dcm2niix==1.0.20220715", "nibabel==5.2.0", "pytest==7.4.2"]
-dev = ["mypy", "pre-commit", "ruff"]
+test = [
+    "core[test]==0.2.0rc0",
+    "dcm2niix==1.0.20220715",
+    "nibabel==5.3.2",
+]
+dev = [
+    "core[dev]==0.2.0rc0",
+]
 
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
-[tool.ruff]
-extend = "./ruff.toml"
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
+
 
 [tool.ruff.lint.extend-per-file-ignores]
 "./tests/**" = ["D100"]
diff --git a/pixl_dcmd/ruff.toml b/pixl_dcmd/ruff.toml
deleted file mode 100644
index 45c40ded8..000000000
--- a/pixl_dcmd/ruff.toml
+++ /dev/null
@@ -1,2 +0,0 @@
-[lint.extend-per-file-ignores]
-"src/pixl_dcmd/main.py" = ["PLR2004", "PLR0912", "PLR0915"] #  Magic value used in comparison, Too many branches, Too many statements
diff --git a/pixl_dcmd/src/pixl_dcmd/__init__.py b/pixl_dcmd/src/pixl_dcmd/__init__.py
index 111140c05..368a2d821 100644
--- a/pixl_dcmd/src/pixl_dcmd/__init__.py
+++ b/pixl_dcmd/src/pixl_dcmd/__init__.py
@@ -16,7 +16,11 @@
 from pixl_dcmd.main import (
     anonymise_dicom,
     write_dataset_to_bytes,
-    should_exclude_series,
+    anonymise_and_validate_dicom,
 )
 
-__all__ = ["anonymise_dicom", "write_dataset_to_bytes", "should_exclude_series"]
+__all__ = [
+    "anonymise_dicom",
+    "write_dataset_to_bytes",
+    "anonymise_and_validate_dicom",
+]
diff --git a/pixl_dcmd/src/pixl_dcmd/_database.py b/pixl_dcmd/src/pixl_dcmd/_database.py
index c4b0a3737..154816341 100644
--- a/pixl_dcmd/src/pixl_dcmd/_database.py
+++ b/pixl_dcmd/src/pixl_dcmd/_database.py
@@ -14,12 +14,17 @@
 
 """Interaction with the PIXL database."""
 
-from typing import Optional
 from decouple import config  # type: ignore [import-untyped]
+import pydicom
+from loguru import logger
+from pydicom.uid import generate_uid, UID
+from sqlalchemy.orm.session import Session
 
 from core.db.models import Image, Extract
-from sqlalchemy import URL, create_engine
-from sqlalchemy.orm import sessionmaker
+from sqlalchemy import URL, create_engine, exists
+from sqlalchemy.orm import sessionmaker, exc
+
+from pixl_dcmd._dicom_helpers import StudyInfo
 
 url = URL.create(
     drivername="postgresql+psycopg2",
@@ -33,40 +38,117 @@
 engine = create_engine(url)
 
 
-def add_hashed_identifier_and_save_to_db(
-    existing_image: Image, hashed_value: str
-) -> Optional[Image]:
+def get_uniq_pseudo_study_uid_and_update_db(
+    project_slug: str, original_study_info: StudyInfo
+) -> UID:
+    """
+    Checks if record (by slug and study info) exists in the database,
+    gets the pseudo_study_uid if it is not None or records a new, unique one.
+    Returns the pseudo_study_uid.
+    """
     PixlSession = sessionmaker(engine)
     with PixlSession() as pixl_session, pixl_session.begin():
-        existing_image.hashed_identifier = hashed_value
-        pixl_session.add(existing_image)
-
-        updated_image: Optional[Image] = (
-            pixl_session.query(Image)
-            .filter(
-                Image.accession_number == existing_image.accession_number,
-                Image.mrn == existing_image.mrn,
-                Image.hashed_identifier == hashed_value,
-            )
-            .one_or_none()
+        existing_image = get_unexported_image(
+            project_slug,
+            original_study_info,
+            pixl_session,
         )
-
-        return updated_image
+        if existing_image.pseudo_study_uid is None:
+            pseudo_study_uid = generate_uid()
+            while not is_unique_pseudo_study_uid(pseudo_study_uid, pixl_session):
+                pseudo_study_uid = generate_uid()
+            add_pseudo_study_uid_to_db(existing_image, pseudo_study_uid, pixl_session)
+        else:
+            pseudo_study_uid = existing_image.pseudo_study_uid
+        return UID(pseudo_study_uid, validation_mode=pydicom.config.RAISE)
 
 
-def query_db(project_slug: str, mrn: str, accession_number: str) -> Image:
+def get_pseudo_patient_id_and_update_db(
+    project_slug: str, original_study_info: StudyInfo, pseudo_patient_id: str
+) -> str:
+    """
+    Checks if record (by slug and study info) exists in the database,
+    gets the pseudo_paitent_id if it is not None otherwise use the
+    patient ID from the DICOM dataset.
+    Returns the pseudo_paitent_id.
+    """
     PixlSession = sessionmaker(engine)
     with PixlSession() as pixl_session, pixl_session.begin():
+        existing_image = get_unexported_image(
+            project_slug,
+            original_study_info,
+            pixl_session,
+        )
+        if existing_image.pseudo_patient_id is None:
+            logger.debug("Adding pseudo patient ID to image")
+            add_pseudo_patient_id_to_db(existing_image, pseudo_patient_id, pixl_session)
+            return pseudo_patient_id  # type: ignore
+        return existing_image.pseudo_patient_id  # type: ignore
+
+
+def add_pseudo_study_uid_to_db(
+    existing_image: Image, pseudo_study_uid: str, pixl_session: Session
+) -> None:
+    """
+    Add a pseudo study UID generated during anonymisation to the database
+    for an existing image generated by populate command.
+    """
+    existing_image.pseudo_study_uid = pseudo_study_uid
+    pixl_session.add(existing_image)
+
+
+def add_pseudo_patient_id_to_db(
+    existing_image: Image, pseudo_patient_id: str, pixl_session: Session
+) -> None:
+    """
+    Add a pseudo patient ID from DICOM tags to the database
+    for an existing image generated by populate command.
+    """
+    existing_image.pseudo_patient_id = pseudo_patient_id
+    pixl_session.add(existing_image)
+
+
+def is_unique_pseudo_study_uid(pseudo_study_uid: str, pixl_session: Session) -> bool:
+    """
+    Check that random uid generated is not already in the database.
+    """
+    return not pixl_session.query(
+        exists().where(Image.pseudo_study_uid == pseudo_study_uid)
+    ).scalar()
+
+
+def get_unexported_image(
+    project_slug: str,
+    study_info: StudyInfo,
+    pixl_session: Session,
+) -> Image:
+    """
+    Get an existing, non-exported (for this project) image record from the database
+    identified by the study UID. If no result is found, retry with querying on
+    MRN + accession number. If this fails as well, raise a NoResultFound.
+    """
+    try:
         existing_image: Image = (
             pixl_session.query(Image)
             .join(Extract)
             .filter(
                 Extract.slug == project_slug,
-                Image.accession_number == accession_number,
-                Image.mrn == mrn,
+                Image.study_uid == study_info.study_uid,
                 Image.exported_at == None,  # noqa: E711
             )
             .one()
         )
-
-        return existing_image
+    # If no image is found by study UID, try MRN + accession number
+    except exc.NoResultFound:
+        existing_image = (
+            pixl_session.query(Image)
+            .join(Extract)
+            .filter(
+                Extract.slug == project_slug,
+                Image.mrn == study_info.mrn,
+                Image.accession_number == study_info.accession_number,
+                Image.exported_at == None,  # noqa: E711
+            )
+            .one()
+        )
+    return existing_image
diff --git a/pixl_dcmd/src/pixl_dcmd/_dicom_helpers.py b/pixl_dcmd/src/pixl_dcmd/_dicom_helpers.py
index 75e73799f..96cbe5de8 100644
--- a/pixl_dcmd/src/pixl_dcmd/_dicom_helpers.py
+++ b/pixl_dcmd/src/pixl_dcmd/_dicom_helpers.py
@@ -15,23 +15,73 @@
 
 from __future__ import annotations
 
+from dataclasses import dataclass
+import logging
+from pathlib import Path
+
+from dicom_validator.spec_reader.edition_reader import EditionReader
+from dicom_validator.validator.iod_validator import IODValidator
 from pydicom import Dataset
-from loguru import logger
-
-from core.dicom_tags import DICOM_TAG_PROJECT_NAME
-
-
-def get_project_name_as_string(dataset: Dataset) -> str:
-    raw_slug = dataset.get_private_item(
-        DICOM_TAG_PROJECT_NAME.group_id,
-        DICOM_TAG_PROJECT_NAME.offset_id,
-        DICOM_TAG_PROJECT_NAME.creator_string,
-    ).value
-    # Get both strings and bytes, which is fun
-    if isinstance(raw_slug, bytes):
-        logger.debug(f"Bytes slug {raw_slug!r}")
-        slug = raw_slug.decode("utf-8").strip()
-    else:
-        logger.debug(f"String slug '{raw_slug}'")
-        slug = raw_slug
-    return slug
+
+
+class DicomValidator:
+    def __init__(self, edition: str = "current"):
+        self.edition = edition
+
+        # Default from dicom_validator but defining here to be explicit
+        standard_path = str(Path.home() / "dicom-validator")
+        edition_reader = EditionReader(standard_path)
+        destination = edition_reader.get_revision(self.edition, False)
+        json_path = Path(destination, "json")
+        self.dicom_info = EditionReader.load_dicom_info(json_path)
+
+    def validate_original(self, dataset: Dataset) -> None:
+        self.original_errors = IODValidator(
+            dataset,
+            self.dicom_info,
+            log_level=logging.ERROR,
+        ).validate()
+
+    def validate_anonymised(self, dataset: Dataset) -> dict:
+        # Check that the original dataset has been validated
+        try:
+            orig_errors = self.original_errors
+        except AttributeError:
+            raise ValueError("Original dataset not yet validated")
+
+        self.anon_errors = IODValidator(
+            dataset,
+            self.dicom_info,
+            log_level=logging.ERROR,
+        ).validate()
+        self.diff_errors: dict = {}
+
+        for key in self.anon_errors.keys():
+            if key in self.original_errors.keys():
+                # Keep only errors introduced after the anonymisation
+                # The keys of the dictionary containt the actual errors
+                diff = set(self.anon_errors[key].keys()) - set(orig_errors[key].keys())
+                if diff:
+                    self.diff_errors[key] = diff
+            else:
+                self.diff_errors[key] = self.anon_errors[key]
+
+        return self.diff_errors
+
+
+@dataclass
+class StudyInfo:
+    """Identifiers used for an imaging study"""
+
+    mrn: str
+    accession_number: str
+    study_uid: str
+
+
+def get_study_info(dataset: Dataset) -> StudyInfo:
+    """Read study identifiers from dicom dataset."""
+    return StudyInfo(
+        mrn=dataset[0x0010, 0x0020].value,
+        accession_number=dataset[0x0008, 0x0050].value,
+        study_uid=dataset[0x0020, 0x000D].value,
+    )
diff --git a/pixl_dcmd/src/pixl_dcmd/_tag_schemes.py b/pixl_dcmd/src/pixl_dcmd/_tag_schemes.py
index d9aab56bb..c06f2a6c4 100644
--- a/pixl_dcmd/src/pixl_dcmd/_tag_schemes.py
+++ b/pixl_dcmd/src/pixl_dcmd/_tag_schemes.py
@@ -33,13 +33,14 @@ def merge_tag_schemes(
         all_tags.update(_scheme_list_to_dict(base_tags))
 
     if tag_operations.manufacturer_overrides and manufacturer:
-        manufacturer_tags = [
-            tag
-            for override in tag_operations.manufacturer_overrides
-            if re.search(override["manufacturer"], manufacturer, re.IGNORECASE)
-            for tag in override["tags"]
-        ]
-        all_tags.update(_scheme_list_to_dict(manufacturer_tags))
+        for override_file in tag_operations.manufacturer_overrides:
+            manufacturer_tags = [
+                tag
+                for override in override_file
+                if re.search(override["manufacturer"], manufacturer, re.IGNORECASE)
+                for tag in override["tags"]
+            ]
+            all_tags.update(_scheme_list_to_dict(manufacturer_tags))
 
     return list(all_tags.values())
 
diff --git a/pixl_dcmd/src/pixl_dcmd/main.py b/pixl_dcmd/src/pixl_dcmd/main.py
index 0845c620e..c69f73dee 100644
--- a/pixl_dcmd/src/pixl_dcmd/main.py
+++ b/pixl_dcmd/src/pixl_dcmd/main.py
@@ -13,28 +13,34 @@
 #  limitations under the License.
 from __future__ import annotations
 
+import typing
 from io import BytesIO
-from loguru import logger
-from os import PathLike
-from typing import Any, BinaryIO, Callable, Union
-
-from core.exceptions import PixlDiscardError
-from core.project_config import load_project_config
 
 import requests
+from core.exceptions import PixlSkipInstanceError
 from core.project_config import load_tag_operations
 from decouple import config
-from pydicom import DataElement, Dataset, dcmwrite
 from dicomanonymizer.simpledicomanonymizer import (
-    actions_map_name_functions,
+    ActionsMapNameFunctions,
     anonymize_dataset,
 )
+from loguru import logger
+from pydicom import DataElement, Dataset, dcmwrite
+
+from core.project_config.pixl_config_model import PixlConfig
+from pixl_dcmd._database import (
+    get_uniq_pseudo_study_uid_and_update_db,
+    get_pseudo_patient_id_and_update_db,
+)
+from pixl_dcmd._dicom_helpers import (
+    DicomValidator,
+    get_study_info,
+)
+from pixl_dcmd._tag_schemes import _scheme_list_to_dict, merge_tag_schemes
 
-from pixl_dcmd._dicom_helpers import get_project_name_as_string
-from pixl_dcmd._tag_schemes import merge_tag_schemes, _scheme_list_to_dict
-from pixl_dcmd._database import add_hashed_identifier_and_save_to_db, query_db
 
-DicomDataSetType = Union[Union[str, bytes, PathLike[Any]], BinaryIO]
+if typing.TYPE_CHECKING:
+    from pixl_dcmd._dicom_helpers import StudyInfo
 
 
 def write_dataset_to_bytes(dataset: Dataset) -> bytes:
@@ -50,69 +56,118 @@ def write_dataset_to_bytes(dataset: Dataset) -> bytes:
         return buffer.read()
 
 
-def should_exclude_series(dataset: Dataset) -> bool:
-    slug = get_project_name_as_string(dataset)
-
+def _should_exclude_series(dataset: Dataset, cfg: PixlConfig) -> bool:
     series_description = dataset.get("SeriesDescription")
-    cfg = load_project_config(slug)
     if cfg.is_series_excluded(series_description):
         logger.info("FILTERING OUT series description: {}", series_description)
         return True
     return False
 
 
-def anonymise_dicom(dataset: Dataset) -> None:
+def anonymise_dicom_and_update_db(
+    dataset: Dataset,
+    *,
+    config: PixlConfig,
+) -> dict:
+    """Anonymise and validate a DICOM dataset and update the PIXL database."""
+    identifiable_study_info = get_study_info(dataset)
+    validation_errors = anonymise_and_validate_dicom(dataset, config=config)
+    _generate_pseudo_uids_and_synchronise_pixl_db(
+        dataset=dataset,
+        project_name=config.project.name,
+        identifiable_study_info=identifiable_study_info,
+    )
+    return validation_errors
+
+
+def anonymise_and_validate_dicom(
+    dataset: Dataset,
+    *,
+    config: PixlConfig,
+) -> dict:
+    """
+    Anonymise dataset using allow list and compare DICOM validation errors before
+    and after anonymising.
+
+    :param dataset: DICOM dataset to be anonymised, updated in place
+    :param config: Project config to use for anonymisation
+    :return: dictionary of validation errors
+    """
+    # Set up Dicom validator and validate the original dataset
+    dicom_validator = DicomValidator(edition="2024e")
+    dicom_validator.validate_original(dataset)
+
+    anonymise_dicom(dataset, config=config)
+
+    # Validate the anonymised dataset
+    validation_errors = dicom_validator.validate_anonymised(dataset)
+    if validation_errors:
+        logger.warning(
+            "The anonymisation introduced the following validation errors:\n{}",
+            _parse_validation_results(validation_errors),
+        )
+    return validation_errors
+
+
+def anonymise_dicom(
+    dataset: Dataset,
+    config: PixlConfig,
+) -> None:
     """
     Anonymises a DICOM dataset as Received by Orthanc in place.
     Finds appropriate configuration based on project name and anonymises by
     - dropping datasets of the wrong modality
     - recursively applying tag operations based on the config file
     - deleting any tags not in the tag scheme recursively
+
+    :param dataset: DICOM dataset to be anonymised, updated in place
+    :param config: Project config to use for anonymisation
     """
-    project_slug = get_project_name_as_string(dataset)
 
-    project_config = load_project_config(project_slug)
-    logger.debug(f"Received instance for project {project_slug}")
-    if dataset.Modality not in project_config.project.modalities:
+    study_info = get_study_info(dataset)
+    logger.debug(
+        f"Processing instance for project {config.project.name}:  {study_info}"
+    )
+
+    # Do before anonymisation in case someone decides to delete the
+    # Series Description tag as part of anonymisation.
+    if _should_exclude_series(dataset, config):
+        msg = "DICOM instance discarded due to its series description"
+        raise PixlSkipInstanceError(msg)
+    if dataset.Modality not in config.project.modalities:
         msg = f"Dropping DICOM Modality: {dataset.Modality}"
-        raise PixlDiscardError(msg)
+        raise PixlSkipInstanceError(msg)
 
-    logger.info("Anonymising received instance")
+    logger.debug("Anonymising instance for: {}", study_info)
 
     # Merge tag schemes
-    tag_operations = load_tag_operations(project_config)
+    tag_operations = load_tag_operations(config)
     tag_scheme = merge_tag_schemes(tag_operations, manufacturer=dataset.Manufacturer)
 
-    modalities = project_config.project.modalities
-
-    logger.info(
-        f"Applying DICOM tag anonymisation according to {project_config.tag_operation_files}"
+    logger.debug(
+        f"Applying DICOM tag anonymisation according to {config.tag_operation_files}"
     )
     logger.trace(f"Tag scheme: {tag_scheme}")
 
-    if (0x0008, 0x0060) in dataset and dataset.Modality not in modalities:
-        msg = f"Dropping DICOM Modality: {dataset.Modality}"
-        raise PixlDiscardError(msg)
-
-    logger.info("Anonymising received instance")
-
-    _anonymise_dicom_from_scheme(dataset, project_slug, tag_scheme)
-
-    enforce_whitelist(dataset, tag_scheme, recursive=True)
+    _enforce_allowlist(dataset, tag_scheme, recursive=True)
+    _anonymise_dicom_from_scheme(dataset, config.project.name, tag_scheme)
 
 
 def _anonymise_dicom_from_scheme(
-    dataset: Dataset, project_slug: str, tag_scheme: list[dict]
+    dataset: Dataset,
+    project_slug: str,
+    tag_scheme: list[dict],
 ) -> None:
     """
     Converts tag scheme to tag actions and calls _anonymise_recursively.
     """
     tag_actions = _convert_schema_to_actions(dataset, project_slug, tag_scheme)
+
     _anonymise_recursively(dataset, tag_actions)
 
 
 def _anonymise_recursively(
-    dataset: Dataset, tag_actions: dict[tuple, Callable]
+    dataset: Dataset, tag_actions: dict[tuple, typing.Callable]
 ) -> None:
     """
     Anonymises a DICOM dataset recursively (for items in sequences) in place.
@@ -126,33 +181,31 @@ def _anonymise_recursively(
 
 def _convert_schema_to_actions(
     dataset: Dataset, project_slug: str, tags_list: list[dict]
-) -> dict[tuple, Callable]:
+) -> dict[tuple, typing.Callable]:
     """
-    Convert the tag schema to actions (funcitons) for the anonymiser.
+    Convert the tag schema to actions (functions) for the anonymiser.
     See https://github.com/KitwareMedical/dicom-anonymizer for more details.
     Added custom function secure-hash for linking purposes. This function needs the MRN and
     Accession Number, hence why the dataset is passed in as well.
     """
 
-    # Get the MRN, Accession Number before we've anonymised them
-    mrn = dataset[0x0010, 0x0020].value  # Patient ID
-    accession_number = dataset[0x0008, 0x0050].value  # Accession Number
-
     tag_actions = {}
     for tag in tags_list:
         group_el = (tag["group"], tag["element"])
         if tag["op"] == "secure-hash":
             tag_actions[group_el] = lambda _dataset, _tag: _secure_hash(
-                _dataset, project_slug, _tag, mrn, accession_number
+                _dataset, project_slug, _tag
             )
             continue
-        tag_actions[group_el] = actions_map_name_functions[tag["op"]]
+        tag_actions[group_el] = ActionsMapNameFunctions[tag["op"]].value.function
 
     return tag_actions
 
 
 def _secure_hash(
-    dataset: Dataset, project_slug: str, tag: tuple, mrn: str, accession_number: str
+    dataset: Dataset,
+    project_slug: str,
+    tag: tuple,
 ) -> None:
     """
     Use the hasher API to consistently but securely hash ids later used for linking.
@@ -163,24 +216,16 @@ def _secure_hash(
     if tag in dataset:
         message = f"Securely hashing: (0x{grp:04x},0x{el:04x})"
         logger.debug(f"\t{message}")
-        if grp == 0x0010 and el == 0x0020:  # Patient ID
-            pat_value = mrn + accession_number
-
-            hashed_value = _hash_values(pat_value, project_slug)
-            # Query PIXL database
-            existing_image = query_db(project_slug, mrn, accession_number)
-            # Insert the hashed_value into the PIXL database
-            add_hashed_identifier_and_save_to_db(existing_image, hashed_value)
-        elif dataset[grp, el].VR == "SH":
+        if dataset[grp, el].VR == "LO":
             pat_value = str(dataset[grp, el].value)
-            hashed_value = _hash_values(pat_value, project_slug, hash_len=16)
+            hashed_value = _hash_values(pat_value, project_slug, hash_len=64)
+        else:
+            # This is because we currently only hash patient id specifically.
+            # Other types can be added easily if needed.
+            raise PixlSkipInstanceError(f"Tag {tag} is not an LO VR type, cannot hash.")
 
         dataset[grp, el].value = hashed_value
 
-    else:
-        message = f"Missing linking variable (0x{grp:04x},0x{el:04x})"
-        logger.warning(f"\t{message}")
-
 
 def _hash_values(pat_value: str, project_slug: str, hash_len: int = 0) -> str:
     """
@@ -201,16 +246,16 @@ def _hash_values(pat_value: str, project_slug: str, hash_len: int = 0) -> str:
     return response.text
 
 
-def enforce_whitelist(
+def _enforce_allowlist(
     dataset: Dataset, tag_scheme: list[dict], recursive: bool
 ) -> None:
     """
-    Enforce the whitelist on the dataset.
+    Enforce the allowlist on the dataset.
     """
-    dataset.walk(lambda ds, de: _whitelist_tag(ds, de, tag_scheme), recursive)
+    dataset.walk(lambda ds, de: _allowlist_tag(ds, de, tag_scheme), recursive)
 
 
-def _whitelist_tag(dataset: Dataset, de: DataElement, tag_scheme: list[dict]) -> None:
+def _allowlist_tag(dataset: Dataset, de: DataElement, tag_scheme: list[dict]) -> None:
     """Delete element if it is not in the tagging schemе."""
     tag_dict = _scheme_list_to_dict(tag_scheme)
     if (de.tag.group, de.tag.element) in tag_dict and tag_dict[
@@ -218,3 +263,39 @@ def _whitelist_tag(dataset: Dataset, de: DataElement, tag_scheme: list[dict]) ->
     ]["op"] != "delete":
         return
     del dataset[de.tag]
+
+
+def _parse_validation_results(results: dict) -> str:
+    """Parse the validation results into a human-readable string."""
+    res_str = ""
+    for key, value in results.items():
+        res_str += f"{key}: {value}\n"
+    return res_str
+
+
+def _generate_pseudo_uids_and_synchronise_pixl_db(
+    dataset: Dataset,
+    project_name: str,
+    identifiable_study_info: StudyInfo,
+) -> None:
+    """
+    Synchronise the anonymisation with the pixl database.
+
+    If the pixl database has a value for set for the pseudo identifier, then update the
+    DICOM data with the value, otherwise save the anonymised data from the DICOM dataset
+    to the pixl database.
+
+    - pseudo_study_uid -> DICOM study uid tag
+    - pseudo_patient_id -> DICOM patient identifier tag
+    """
+    dataset[0x0020, 0x000D].value = get_uniq_pseudo_study_uid_and_update_db(
+        project_name,
+        identifiable_study_info,
+    )
+
+    anonymised_study_info = get_study_info(dataset)
+    dataset[0x0010, 0x0020].value = get_pseudo_patient_id_and_update_db(
+        project_name,
+        identifiable_study_info,
+        anonymised_study_info.mrn,
+    )
diff --git a/pixl_dcmd/src/pixl_dcmd/tagrecording.py b/pixl_dcmd/src/pixl_dcmd/tagrecording.py
index ca1287874..b3d9f7ab9 100644
--- a/pixl_dcmd/src/pixl_dcmd/tagrecording.py
+++ b/pixl_dcmd/src/pixl_dcmd/tagrecording.py
@@ -24,9 +24,11 @@
 
 
 def record_dicom_headers(receivedDicom: bytes) -> None:
-    with importlib.resources.files("pixl_dcmd").joinpath(
-        "resources/recorded-headers.yml"
-    ).open() as f:
+    with (
+        importlib.resources.files("pixl_dcmd")
+        .joinpath("resources/recorded-headers.yml")
+        .open() as f
+    ):
         recording_config = yaml.safe_load(f)
     dataset = dcmread(BytesIO(receivedDicom))
     with _header_log_path().open("a") as f:
diff --git a/pixl_dcmd/tests/conftest.py b/pixl_dcmd/tests/conftest.py
index 198bdd913..15011f94a 100644
--- a/pixl_dcmd/tests/conftest.py
+++ b/pixl_dcmd/tests/conftest.py
@@ -11,21 +11,26 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-"""CLI testing fixtures."""
+"""DCMD testing fixtures."""
 
 from __future__ import annotations
 
-from collections.abc import Generator
 import datetime
 import os
 import pathlib
 import tempfile
+import typing
+from collections.abc import Generator
 from typing import Optional
 
+from pixl_dcmd._dicom_helpers import get_study_info
+from core.project_config import load_project_config
 import pytest
 import pytest_pixl.dicom
 import requests
 from core.db.models import Base, Extract, Image
+from pydicom import Dataset, dcmread
+from pytest_pixl.dicom import generate_dicom_dataset
 from sqlalchemy import Engine, create_engine
 from sqlalchemy.orm import Session, sessionmaker
 
@@ -36,30 +41,59 @@
 os.environ["PROJECT_CONFIGS_DIR"] = str(
     pathlib.Path(__file__).parents[2] / "projects/configs"
 )
+from pathlib import Path
+from decouple import config
+
+
+if typing.TYPE_CHECKING:
+    from core.project_config.pixl_config_model import PixlConfig
+
+
+PROJECT_CONFIGS_DIR = Path(config("PROJECT_CONFIGS_DIR"))
 
 STUDY_DATE = datetime.date.fromisoformat("2023-01-01")
 TEST_PROJECT_SLUG = "test-extract-uclh-omop-cdm"
 
-EXPORTED_MRN = "987654321"
-EXPORTED_ACCESSION_NUMBER = "AA12345601"
+
+@pytest.fixture()
+def exported_dicom_dataset() -> Dataset:
+    exported_dicom_file = (
+        pathlib.Path(__file__).parents[2] / "test/resources/Dicom1.dcm"
+    )
+    return dcmread(exported_dicom_file)
 
 
 @pytest.fixture()
-def rows_in_session(db_session) -> Session:
+def not_exported_dicom_dataset() -> Dataset:
+    exported_dicom_file = (
+        pathlib.Path(__file__).parents[2] / "test/resources/Dicom2.dcm"
+    )
+    return dcmread(exported_dicom_file)
+
+
+@pytest.fixture()
+def rows_in_session(
+    db_session, exported_dicom_dataset, not_exported_dicom_dataset
+) -> Session:
     """Insert a test row for each table, returning the session for use in tests."""
     extract = Extract(slug=TEST_PROJECT_SLUG)
 
+    exported_study_info = get_study_info(exported_dicom_dataset)
+    not_exported_study_info = get_study_info(not_exported_dicom_dataset)
+
     image_exported = Image(
-        accession_number=EXPORTED_ACCESSION_NUMBER,
+        mrn=exported_study_info.mrn,
+        accession_number=exported_study_info.accession_number,
+        study_uid=exported_study_info.study_uid,
         study_date=STUDY_DATE,
-        mrn=EXPORTED_MRN,
         extract=extract,
         exported_at=datetime.datetime.now(tz=datetime.timezone.utc),
     )
     image_not_exported = Image(
-        accession_number="AA12345605",
+        mrn=not_exported_study_info.mrn,
+        accession_number=not_exported_study_info.accession_number,
+        study_uid=not_exported_study_info.study_uid,
         study_date=STUDY_DATE,
-        mrn="987654321",
         extract=extract,
     )
     with db_session:
@@ -70,14 +104,80 @@ def rows_in_session(db_session) -> Session:
 
 
 @pytest.fixture()
-def row_for_dicom_testing(db_session) -> Session:
-    """Insert a test row for each table, returning the session for use in tests."""
+def row_for_testing_image_with_pseudo_patient_id(
+    db_session, not_exported_dicom_dataset
+) -> Session:
+    """Insert a test row for the image with a pseudo patient ID."""
+    extract = Extract(slug=TEST_PROJECT_SLUG)
+
+    study_info = get_study_info(not_exported_dicom_dataset)
+    image = Image(
+        mrn=study_info.mrn,
+        accession_number=study_info.accession_number,
+        study_uid=study_info.study_uid,
+        study_date=STUDY_DATE,
+        extract=extract,
+        pseudo_patient_id="AAA00",
+    )
+    with db_session:
+        db_session.add_all([extract, image])
+        db_session.commit()
+
+    return db_session
+
+
+def ids_for_parameterised_test(val: pathlib.Path) -> str:
+    """Generate test ID for parameterised tests"""
+    return str(val.stem)
+
+
+@pytest.fixture()
+@pytest.mark.parametrize(
+    ("yaml_file"), PROJECT_CONFIGS_DIR.glob("*.yaml"), ids=ids_for_parameterised_test
+)
+def row_for_dicom_testing(db_session, yaml_file) -> Session:
+    """
+    Insert a test row for the fake DICOM dataset generated by
+    pytest_pixl.dicom.generate_dicom_dataset.
+    """
+
+    config = load_project_config(yaml_file.stem)
+    modality = config.project.modalities[0]
+
+    extract = Extract(slug=config.project.name)
+    ds = pytest_pixl.dicom.generate_dicom_dataset(Modality=modality)
+    study_info = get_study_info(ds)
+
+    image_not_exported = Image(
+        mrn=study_info.mrn,
+        accession_number=study_info.accession_number,
+        study_uid=study_info.study_uid,
+        study_date=STUDY_DATE,
+        extract=extract,
+    )
+    with db_session:
+        db_session.add_all([extract, image_not_exported])
+        db_session.commit()
+
+    return db_session
+
+
+@pytest.fixture()
+def row_for_single_dicom_testing(db_session) -> Session:
+    """
+    Insert a test row for the fake DICOM dataset generated by
+    pytest_pixl.dicom.generate_dicom_dataset.
+    """
+
     extract = Extract(slug=TEST_PROJECT_SLUG)
+    ds = pytest_pixl.dicom.generate_dicom_dataset()
+    study_info = get_study_info(ds)
 
     image_not_exported = Image(
-        accession_number="BB01234567",
+        mrn=study_info.mrn,
+        accession_number=study_info.accession_number,
+        study_uid=study_info.study_uid,
         study_date=STUDY_DATE,
-        mrn="ID123456",
         extract=extract,
     )
     with db_session:
@@ -176,3 +276,44 @@ def mock_get(key, default) -> Optional[str]:
         return os.environ.get(key, default)
 
     monkeypatch.setattr(os.environ, "get", mock_get)
+
+
+@pytest.fixture()
+def vanilla_dicom_image_DX(row_for_dicom_testing) -> Dataset:
+    """
+    A DICOM image with diffusion data to test the anonymisation process.
+    Private tags were added to match the tag operations defined in the project config, so we can
+    test whether the anonymisation process works as expected when defining overrides.
+    The row_for_mri_dicom_testing dependency is to make sure the database is populated with the
+    project slug, which is used to anonymise the DICOM image.
+    """
+    return generate_dicom_dataset(Modality="DX")
+
+
+@pytest.fixture()
+def vanilla_single_dicom_image_DX(row_for_single_dicom_testing) -> Dataset:
+    """
+    A DICOM image with diffusion data to test the anonymisation process.
+    Private tags were added to match the tag operations defined in the project config, so we can
+    test whether the anonymisation process works as expected when defining overrides.
+    The row_for_single_dicom_testing dependency is to make sure the database is populated with the
+    project slug, which is used to anonymise the DICOM image.
+    """
+    return generate_dicom_dataset(Modality="DX")
+
+
+@pytest.fixture()
+def vanilla_dicom_image_MR(row_for_dicom_testing) -> Dataset:
+    """
+    A DICOM image with MX data to test the anonymisation process.
+    Private tags were added to match the tag operations defined in the project config, so we can
+    test whether the anonymisation process works as expected when defining overrides.
+    The row_for_mri_dicom_testing dependency is to make sure the database is populated with the
+    project slug, which is used to anonymise the DICOM image.
+    """
+    return generate_dicom_dataset(Modality="MR")
+
+
+@pytest.fixture(scope="module")
+def test_project_config() -> PixlConfig:
+    return load_project_config(TEST_PROJECT_SLUG)
diff --git a/pixl_dcmd/tests/test_database.py b/pixl_dcmd/tests/test_database.py
new file mode 100644
index 000000000..5c5a1b455
--- /dev/null
+++ b/pixl_dcmd/tests/test_database.py
@@ -0,0 +1,116 @@
+#  Copyright (c) 2022 University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+from __future__ import annotations
+
+import datetime
+
+import pytest
+from core.db.models import Extract, Image
+from pixl_dcmd._database import (
+    get_unexported_image,
+    get_uniq_pseudo_study_uid_and_update_db,
+    get_pseudo_patient_id_and_update_db,
+)
+from pixl_dcmd._dicom_helpers import StudyInfo
+from sqlalchemy.orm import Session
+
+STUDY_DATE = datetime.date.fromisoformat("2023-01-01")
+TEST_PROJECT_SLUG = "test-extract-uclh-omop-cdm"
+TEST_STUDY_INFO = StudyInfo(
+    mrn="123456", accession_number="abcde", study_uid="1.2.3.4.5"
+)
+TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID = StudyInfo(
+    mrn="234567", accession_number="bcdef", study_uid="2.3.4.5.6"
+)
+
+
+@pytest.fixture()
+def rows_for_database_testing(db_session) -> Session:
+    """
+    Insert a test row for the fake DICOM dataset generated by
+    pytest_pixl.dicom.generate_dicom_dataset.
+    """
+    extract = Extract(slug=TEST_PROJECT_SLUG)
+
+    existing_image = Image(
+        mrn=TEST_STUDY_INFO.mrn,
+        accession_number=TEST_STUDY_INFO.accession_number,
+        study_uid=TEST_STUDY_INFO.study_uid,
+        study_date=STUDY_DATE,
+        extract=extract,
+    )
+
+    existing_image_with_pseudo_study_uid = Image(
+        mrn=TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.mrn,
+        accession_number=TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.accession_number,
+        study_uid=TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.study_uid,
+        study_date=STUDY_DATE,
+        extract=extract,
+        # This should be a valid VR UI value!
+        # https://dicom.nema.org/medical/dicom/current/output/html/part05.html#table_6.2-1
+        pseudo_study_uid="0.0.0.0.0.0",
+        pseudo_patient_id=TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.mrn,
+    )
+
+    with db_session:
+        db_session.add_all(
+            [extract, existing_image, existing_image_with_pseudo_study_uid]
+        )
+        db_session.commit()
+
+    return db_session
+
+
+def test_get_uniq_pseudo_study_uid_and_update_db(rows_for_database_testing, db_session):
+    """
+    GIVEN an existing image that already has a pseudo_study_uid
+    WHEN we query the database for that image
+    THEN the function should return the existing pseudo_study_uid.
+    """
+    pseudo_study_uid = get_uniq_pseudo_study_uid_and_update_db(
+        TEST_PROJECT_SLUG, TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID
+    )
+    assert pseudo_study_uid == "0.0.0.0.0.0"
+
+
+def test_get_pseudo_patient_id_and_update_db(rows_for_database_testing, db_session):
+    """
+    GIVEN an existing image that already has pseudo_patient_id in the database
+    WHEN we query the dataset for that image
+    THEN the function should return the existing pseudo_patient_id
+    """
+    get_pseudo_patient_id_and_update_db(
+        TEST_PROJECT_SLUG,
+        TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID,
+        TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.mrn,
+    )
+    result = get_unexported_image(
+        TEST_PROJECT_SLUG, TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID, db_session
+    )
+    assert result.pseudo_patient_id == TEST_STUDY_INFO_WITH_PSEUDO_PATIENT_ID.mrn
+
+
+def test_get_unexported_image_fallback(rows_for_database_testing, db_session):
+    """
+    GIVEN a database entry with a non-exported image
+    WHEN we query that image with a non-matching study UID
+    THEN the querying should fall back to querying on MRN and accession number and return the image.
+    """
+    wrong_uid_info = StudyInfo(
+        mrn="123456",
+        accession_number="abcde",
+        study_uid="nope",
+    )
+    result = get_unexported_image(TEST_PROJECT_SLUG, wrong_uid_info, db_session)
+    assert result.study_uid == TEST_STUDY_INFO.study_uid
diff --git a/pixl_dcmd/tests/test_dicom_validator.py b/pixl_dcmd/tests/test_dicom_validator.py
new file mode 100644
index 000000000..fe58adf54
--- /dev/null
+++ b/pixl_dcmd/tests/test_dicom_validator.py
@@ -0,0 +1,87 @@
+#  Copyright (c) 2022 University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+from __future__ import annotations
+
+import pytest
+from pixl_dcmd._dicom_helpers import DicomValidator
+from pixl_dcmd.main import anonymise_dicom
+from pydicom import Dataset
+
+
+def test_validation_check_works(vanilla_single_dicom_image_DX: Dataset) -> None:
+    """
+    GIVEN a DICOM dataset
+    WHEN the dataset is validated against itself (withouth anonymisation)
+    THEN no errors should be raised
+    """
+    validator = DicomValidator()
+    validator.validate_original(vanilla_single_dicom_image_DX)
+    assert not validator.validate_anonymised(vanilla_single_dicom_image_DX)
+
+
+def test_validation_after_anonymisation_works(
+    vanilla_single_dicom_image_DX: Dataset,
+    test_project_config,
+) -> None:
+    """
+    GIVEN a DICOM dataset
+    WHEN the dataset is validated after anonymisation
+    THEN no errors should be raised
+    """
+    validator = DicomValidator()
+    validator.validate_original(vanilla_single_dicom_image_DX)
+    anonymise_dicom(vanilla_single_dicom_image_DX, config=test_project_config)
+
+    assert not validator.validate_anonymised(vanilla_single_dicom_image_DX)
+
+
+@pytest.fixture()
+def non_compliant_dicom_image(vanilla_single_dicom_image_DX: Dataset) -> Dataset:
+    """A DICOM dataset that is not compliant with the DICOM standard."""
+    del vanilla_single_dicom_image_DX.PatientName
+    return vanilla_single_dicom_image_DX
+
+
+def test_validation_passes_for_non_compliant_dicom(non_compliant_dicom_image) -> None:
+    """
+    GIVEN a DICOM dataset that is not compliant with the DICOM standard
+    WHEN the dataset is validated after anonymisation
+    THEN no errors should be raised
+    """
+    validator = DicomValidator()
+    validator.validate_original(non_compliant_dicom_image)
+    assert not validator.validate_anonymised(non_compliant_dicom_image)
+
+
+def test_validation_fails_after_invalid_tag_modification(
+    vanilla_single_dicom_image_DX,
+) -> None:
+    """
+    GIVEN a DICOM dataset
+    WHEN an invalid tag operation is performed (e.g. deleting a required tag)
+    THEN validation should return a non-empty list of errors
+    """
+    validator = DicomValidator()
+    validator.validate_original(vanilla_single_dicom_image_DX)
+    del vanilla_single_dicom_image_DX.PatientName
+    validation_result = validator.validate_anonymised(vanilla_single_dicom_image_DX)
+
+    assert len(validation_result) == 1
+    assert "Patient" in validation_result.keys()
+    assert len(validation_result["Patient"]) == 1
+    assert (
+        "Tag (0010,0010) (Patient's Name) is missing"
+        in validation_result["Patient"].keys()
+    )
diff --git a/pixl_dcmd/tests/test_main.py b/pixl_dcmd/tests/test_main.py
index 880dd074e..951c5870d 100644
--- a/pixl_dcmd/tests/test_main.py
+++ b/pixl_dcmd/tests/test_main.py
@@ -16,6 +16,8 @@
 import pathlib
 import re
 from pathlib import Path
+import logging
+import typing
 
 import nibabel
 import numpy as np
@@ -24,49 +26,56 @@
 import sqlalchemy
 from core.db.models import Image
 from core.dicom_tags import (
-    DICOM_TAG_PROJECT_NAME,
     PrivateDicomTag,
     add_private_tag,
     create_private_tag,
 )
 from core.project_config import load_project_config, load_tag_operations
+from core.project_config.pixl_config_model import load_config_and_validate
 from decouple import config
-from pydicom.data import get_testdata_file
-
-from pydicom.dataset import Dataset
-
-from pytest_pixl.dicom import generate_dicom_dataset
-from pytest_pixl.helpers import run_subprocess
 
+from pixl_dcmd._dicom_helpers import get_study_info
 from pixl_dcmd.main import (
+    anonymise_dicom_and_update_db,
     _anonymise_dicom_from_scheme,
-    enforce_whitelist,
+    anonymise_and_validate_dicom,
     anonymise_dicom,
-    should_exclude_series,
+    _enforce_allowlist,
+    _should_exclude_series,
 )
+from pytest_pixl.dicom import generate_dicom_dataset
+from pytest_pixl.helpers import run_subprocess
+from conftest import ids_for_parameterised_test
+
+if typing.TYPE_CHECKING:
+    from core.project_config.pixl_config_model import PixlConfig
 
 PROJECT_CONFIGS_DIR = Path(config("PROJECT_CONFIGS_DIR"))
 TEST_PROJECT_SLUG = "test-extract-uclh-omop-cdm"
 
 
 @pytest.fixture(scope="module")
-def tag_scheme() -> list[dict]:
+def tag_scheme(test_project_config: PixlConfig) -> list[dict]:
     """Base tag scheme for testing."""
-    tag_ops = load_tag_operations(load_project_config(TEST_PROJECT_SLUG))
+    tag_ops = load_tag_operations(test_project_config)
     return tag_ops.base[0]
 
 
-def _mri_diffusion_tags(manufacturer: str = "Philips") -> list[PrivateDicomTag]:
+def _get_mri_diffusion_tags(
+    config: PixlConfig,
+    manufacturer: str,
+) -> list[PrivateDicomTag]:
     """
     Private DICOM tags for testing the anonymisation process.
     These tags from `/projects/configs/tag-operations/manufacturer-overrides/mri-diffusion.yaml`
     so we can test whether the manufacturer overrides work during anonymisation
     """
-    project_config = load_project_config(TEST_PROJECT_SLUG)
-    tag_ops = load_tag_operations(project_config)
+    tag_ops = load_tag_operations(config)
+    mri_diffusion_overrides = tag_ops.manufacturer_overrides[0]
+
     manufacturer_overrides = [
         override
-        for override in tag_ops.manufacturer_overrides
+        for override in mri_diffusion_overrides
         if re.search(override["manufacturer"], manufacturer, re.IGNORECASE)
     ][0]
 
@@ -77,27 +86,7 @@ def _mri_diffusion_tags(manufacturer: str = "Philips") -> list[PrivateDicomTag]:
 
 
 @pytest.fixture()
-def vanilla_dicom_image() -> Dataset:
-    """
-    A DICOM image with diffusion data to test the anonymisation process.
-    Private tags were added to match the tag operations defined in the project config, so we can
-    test whether the anonymisation process works as expected when defining overrides.
-    """
-    ds = generate_dicom_dataset(Modality="DX")
-
-    # Make sure the project name tag is added for anonymisation to work
-    add_private_tag(ds, DICOM_TAG_PROJECT_NAME)
-    # Update the project name tag to a known value
-    block = ds.private_block(
-        DICOM_TAG_PROJECT_NAME.group_id, DICOM_TAG_PROJECT_NAME.creator_string
-    )
-    ds[block.get_tag(DICOM_TAG_PROJECT_NAME.offset_id)].value = TEST_PROJECT_SLUG
-
-    return ds
-
-
-@pytest.fixture()
-def mri_diffusion_dicom_image() -> Dataset:
+def mri_diffusion_dicom_image(test_project_config: PixlConfig) -> pydicom.Dataset:
     """
     A DICOM image with diffusion data to test the anonymisation process.
     Private tags were added to match the tag operations defined in the project config, so we can
@@ -105,52 +94,131 @@ def mri_diffusion_dicom_image() -> Dataset:
     """
     manufacturer = "Philips"
     ds = generate_dicom_dataset(Manufacturer=manufacturer, Modality="DX")
-    tags = _mri_diffusion_tags(manufacturer)
+    tags = _get_mri_diffusion_tags(
+        config=test_project_config, manufacturer=manufacturer
+    )
     for tag in tags:
         add_private_tag(ds, tag)
 
-    # Make sure the project name tag is added for anonymisation to work
-    add_private_tag(ds, DICOM_TAG_PROJECT_NAME)
-    # Update the project name tag to a known value
-    block = ds.private_block(
-        DICOM_TAG_PROJECT_NAME.group_id, DICOM_TAG_PROJECT_NAME.creator_string
-    )
-    ds[block.get_tag(DICOM_TAG_PROJECT_NAME.offset_id)].value = TEST_PROJECT_SLUG
-
     return ds
 
 
-def test_enforce_whitelist_removes_overlay_plane() -> None:
+def test_enforce_allowlist_removes_overlay_plane() -> None:
     """Checks that overlay planes are removed."""
-    ds = get_testdata_file(
+    ds = pydicom.data.get_testdata_file(
         "MR-SIEMENS-DICOM-WithOverlays.dcm", read=True, download=True
     )
     assert (0x6000, 0x3000) in ds
 
-    enforce_whitelist(ds, {}, recursive=True)
+    _enforce_allowlist(ds, {}, recursive=True)
     assert (0x6000, 0x3000) not in ds
 
 
-def test_anonymisation(row_for_dicom_testing, vanilla_dicom_image: Dataset) -> None:
+def test_anonymisation(
+    vanilla_single_dicom_image_DX: pydicom.Dataset,
+    test_project_config: PixlConfig,
+) -> None:
     """
     Test whether anonymisation works as expected on a vanilla DICOM dataset
     """
 
-    orig_patient_id = vanilla_dicom_image.PatientID
-    orig_patient_name = vanilla_dicom_image.PatientName
+    orig_patient_id = vanilla_single_dicom_image_DX.PatientID
+    orig_patient_name = vanilla_single_dicom_image_DX.PatientName
+    orig_study_date = vanilla_single_dicom_image_DX.StudyDate
+
+    anonymise_dicom(vanilla_single_dicom_image_DX, config=test_project_config)
+
+    assert vanilla_single_dicom_image_DX.PatientID != orig_patient_id
+    assert vanilla_single_dicom_image_DX.PatientName != orig_patient_name
+    assert vanilla_single_dicom_image_DX.StudyDate != orig_study_date
+
+
+def test_anonymise_unimplemented_tag(
+    vanilla_single_dicom_image_DX: pydicom.Dataset,
+    test_project_config: PixlConfig,
+) -> None:
+    """
+    GIVEN DICOM data with an OB data type tag within a sequence
+    WHEN anonymise_dicom is run that has "replace" tag operation on the sequence, but not the OB element
+    THEN the sequence should exist, but not the OB element
+
+    VR OB is not implemented by the dicom anonymisation library, so this
+    is testing that we can still successfully de-identify data with this data type
+    """
+    nested_ds = pydicom.Dataset()
+    nested_block = nested_ds.private_block(0x0013, "VR OB CREATOR", create=True)
+    nested_block.add_new(0x0011, "OB", b"")
+
+    # create private sequence tag with the nested dataset
+    block = vanilla_single_dicom_image_DX.private_block(
+        0x0013, "VR OB CREATOR", create=True
+    )
+    block.add_new(0x0010, "SQ", [nested_ds])
+
+    anonymise_dicom(vanilla_single_dicom_image_DX, config=test_project_config)
+
+    assert (0x0013, 0x0010) in vanilla_single_dicom_image_DX
+    assert (0x0013, 0x1010) in vanilla_single_dicom_image_DX
+    sequence = vanilla_single_dicom_image_DX[(0x0013, 0x1010)]
+    assert (0x0013, 0x1011) not in sequence[0]
+
+
+def test_anonymise_and_validate_as_external_user(
+    test_project_config: PixlConfig,
+) -> None:
+    """
+    GIVEN an example MR dataset and configuration to anonymise this
+    WHEN the anonymisation and validation is called not using PIXL infrastructure
+    THEN the dataset is anonymised inplace
+
+    Note: If we update this test, make sure to update the documentation stub.
+    Or if we end up building docs, then convert this test to a doctest
+    """
+    dataset_path = pydicom.data.get_testdata_file(
+        "MR-SIEMENS-DICOM-WithOverlays.dcm", download=True
+    )
+    dataset = pydicom.dcmread(dataset_path)
 
-    # Sanity check: study date should be present before anonymisation
-    assert "StudyDate" in vanilla_dicom_image
+    config_path = (
+        pathlib.Path(__file__).parents[2] / "projects/configs/test-external-user.yaml"
+    )
+    config = load_config_and_validate(config_path)
 
-    anonymise_dicom(vanilla_dicom_image)
+    validation_issues = anonymise_and_validate_dicom(dataset, config=config)
+
+    assert validation_issues == {}
+    assert dataset != pydicom.dcmread(dataset_path)
+
+
+@pytest.mark.parametrize(
+    ("yaml_file"), PROJECT_CONFIGS_DIR.glob("*.yaml"), ids=ids_for_parameterised_test
+)
+def test_anonymise_and_validate_dicom(caplog, request, yaml_file) -> None:
+    """
+    Test whether anonymisation and validation works as expected on a vanilla DICOM dataset
+    GIVEN a project configuration with tag operations that creates a DICOM dataset
+    WHEN the anonymisation and validation process is run
+    THEN the dataset should be anonymised and validated without any warnings or errors
+    """
+    caplog.clear()
+    caplog.set_level(logging.WARNING)
+    config = load_project_config(yaml_file.stem)
+    modality = config.project.modalities[0]
+    dicom_image = request.getfixturevalue(f"vanilla_dicom_image_{modality}")
+
+    validation_errors = anonymise_and_validate_dicom(
+        dicom_image,
+        config=config,
+    )
 
-    assert vanilla_dicom_image.PatientID != orig_patient_id
-    assert vanilla_dicom_image.PatientName != orig_patient_name
-    assert "StudyDate" not in vanilla_dicom_image
+    assert "WARNING" not in [record.levelname for record in caplog.records]
+    assert not validation_errors
 
 
+@pytest.mark.usefixtures("row_for_single_dicom_testing")
 def test_anonymisation_with_overrides(
-    row_for_dicom_testing, mri_diffusion_dicom_image: Dataset
+    mri_diffusion_dicom_image: pydicom.Dataset,
+    test_project_config: PixlConfig,
 ) -> None:
     """
     Test that the anonymisation process works with manufacturer overrides.
@@ -160,12 +228,12 @@ def test_anonymisation_with_overrides(
     """
 
     # Sanity check
-    # (0x2001, 0x1003) is one of the tags whitelisted by the overrides for Philips manufacturer
+    # (0x2001, 0x1003) is one of the tags allow-listed by the overrides for Philips manufacturer
     assert (0x2001, 0x1003) in mri_diffusion_dicom_image
     original_patient_id = mri_diffusion_dicom_image.PatientID
     original_private_tag = mri_diffusion_dicom_image[(0x2001, 0x1003)]
 
-    anonymise_dicom(mri_diffusion_dicom_image)
+    anonymise_dicom(mri_diffusion_dicom_image, config=test_project_config)
 
     # Whitelisted tags should still be present
     assert (0x0010, 0x0020) in mri_diffusion_dicom_image
@@ -174,55 +242,146 @@ def test_anonymisation_with_overrides(
     assert mri_diffusion_dicom_image[(0x2001, 0x1003)] == original_private_tag
 
 
-def test_image_already_exported_throws(rows_in_session):
+@pytest.mark.usefixtures("rows_in_session")
+def test_image_already_exported_throws(test_project_config, exported_dicom_dataset):
     """
     GIVEN a dicom image which has no un-exported rows in the pipeline database
     WHEN the dicom tag scheme is applied
     THEN an exception will be thrown as
     """
-    exported_dicom = pathlib.Path(__file__).parents[2] / "test/resources/Dicom1.dcm"
-    input_dataset = pydicom.dcmread(exported_dicom)
-
-    # Make sure the project name tag is added for anonymisation to work
-    add_private_tag(input_dataset, DICOM_TAG_PROJECT_NAME)
-    # Update the project name tag to a known value
-    block = input_dataset.private_block(
-        DICOM_TAG_PROJECT_NAME.group_id, DICOM_TAG_PROJECT_NAME.creator_string
-    )
-    input_dataset[
-        block.get_tag(DICOM_TAG_PROJECT_NAME.offset_id)
-    ].value = TEST_PROJECT_SLUG
     with pytest.raises(sqlalchemy.exc.NoResultFound):
-        anonymise_dicom(input_dataset)
+        anonymise_dicom_and_update_db(
+            exported_dicom_dataset,
+            config=test_project_config,
+        )
 
 
-def test_pseudo_identifier_processing(rows_in_session):
+def test_pseudo_identifier_processing(
+    rows_in_session,
+    monkeypatch,
+    exported_dicom_dataset,
+    not_exported_dicom_dataset,
+    test_project_config,
+):
     """
     GIVEN a dicom image that hasn't been exported in the pipeline db
     WHEN the dicom tag scheme is applied
-    THEN the patient identifier tag should be the mrn and accession hashed
-      and the pipeline db row should now have the fake hash
+    THEN the patient identifier tag should be the mrn hashed
+        the study instance uid should be replaced with a new uid
+        and the db should have the pseudo study id
     """
-    exported_dicom = pathlib.Path(__file__).parents[2] / "test/resources/Dicom2.dcm"
-    dataset = pydicom.dcmread(exported_dicom)
+    exported_study_info = get_study_info(exported_dicom_dataset)
+    not_exported_study_info = get_study_info(not_exported_dicom_dataset)
+
+    class FakeUID:
+        i = 1
+
+        @classmethod
+        def fake_uid(cls):
+            uid = f"2.25.{cls.i}"
+            cls.i += 1
+            return pydicom.uid.UID(uid)
+
+    monkeypatch.setattr("pixl_dcmd._database.generate_uid", FakeUID.fake_uid)
+    other_image = (
+        rows_in_session.query(Image)
+        .filter(Image.accession_number == exported_study_info.accession_number)
+        .one()
+    )
+    other_image.pseudo_study_uid = "2.25.1"
+    rows_in_session.add(other_image)
+    rows_in_session.commit()
 
-    accession_number = "AA12345605"
-    mrn = "987654321"
-    fake_hash = "-".join(list(f"{mrn}{accession_number}"))
+    mrn = exported_study_info.mrn
+    fake_hash = "-".join(list(mrn))
     print("fake_hash = ", fake_hash)
-    anonymise_dicom(dataset)
+
+    anonymise_dicom_and_update_db(
+        not_exported_dicom_dataset, config=test_project_config
+    )
+
     image = (
         rows_in_session.query(Image)
-        .filter(Image.accession_number == "AA12345605")
+        .filter(Image.accession_number == not_exported_study_info.accession_number)
         .one()
     )
     print("after tags applied")
-    assert dataset[0x0010, 0x0020].value == fake_hash
-    assert image.hashed_identifier == fake_hash
+    assert not_exported_dicom_dataset[0x0010, 0x0020].value == fake_hash
+    assert image.pseudo_study_uid == not_exported_dicom_dataset[0x0020, 0x000D].value
+    assert image.pseudo_study_uid == "2.25.2"  # 2nd image in the db
+
+
+def test_pseudo_patient_id_processing(
+    row_for_testing_image_with_pseudo_patient_id,
+    not_exported_dicom_dataset,
+    test_project_config,
+):
+    """
+    GIVEN an `Image` entity in the database which has a `pseudo_patient_id` set
+    WHEN the matching DICOM data is anonymised
+    THEN the DICOM's patient ID tag should be the original `pseudo_study_id`
+    value from the database, the database's `pseudo_patient_id` shouldn't have changed
+    """
+    study_info = get_study_info(not_exported_dicom_dataset)
+    original_image: Image = (
+        row_for_testing_image_with_pseudo_patient_id.query(Image)
+        .filter(Image.accession_number == study_info.accession_number)
+        .one()
+    )
+    assert (
+        not_exported_dicom_dataset[0x0010, 0x0020].value
+        != original_image.pseudo_patient_id
+    )
+
+    anonymise_dicom_and_update_db(
+        not_exported_dicom_dataset, config=test_project_config
+    )
+
+    anonymised_image: Image = (
+        row_for_testing_image_with_pseudo_patient_id.query(Image)
+        .filter(Image.accession_number == study_info.accession_number)
+        .one()
+    )
+
+    assert original_image.pseudo_patient_id == anonymised_image.pseudo_patient_id
+    assert (
+        not_exported_dicom_dataset[0x0010, 0x0020].value
+        == original_image.pseudo_patient_id
+    )
+
+
+def test_no_pseudo_patient_id_processing(
+    rows_in_session,
+    not_exported_dicom_dataset,
+    test_project_config,
+):
+    """
+    GIVEN an `Image` entity in the database which doesn't have a `pseudo_patient_id` set
+    WHEN the matching DICOM data is anonymised
+    THEN database's `pseudo_patient_id` field should be set, and match the value from the
+    DICOM's patient identifier tag at the end of anonymisation
+    """
+    study_info = get_study_info(not_exported_dicom_dataset)
+
+    anonymise_dicom_and_update_db(
+        not_exported_dicom_dataset, config=test_project_config
+    )
+
+    anonymised_image: Image = (
+        rows_in_session.query(Image)
+        .filter(Image.accession_number == study_info.accession_number)
+        .one()
+    )
+
+    assert anonymised_image.pseudo_patient_id is not None
+    assert (
+        anonymised_image.pseudo_patient_id
+        == not_exported_dicom_dataset[0x0010, 0x0020].value
+    )
 
 
 @pytest.fixture()
-def dicom_series_to_keep() -> list[Dataset]:
+def dicom_series_to_keep() -> list[pydicom.Dataset]:
     series = [
         "",
         "whatever",
@@ -231,7 +390,7 @@ def dicom_series_to_keep() -> list[Dataset]:
 
 
 @pytest.fixture()
-def dicom_series_to_exclude() -> list[Dataset]:
+def dicom_series_to_exclude() -> list[pydicom.Dataset]:
     series = [
         "positioning",
         "foo_barpositioning",
@@ -245,21 +404,20 @@ def dicom_series_to_exclude() -> list[Dataset]:
     return [_make_dicom(s) for s in series]
 
 
-def _make_dicom(series_description) -> Dataset:
-    ds = generate_dicom_dataset(SeriesDescription=series_description)
-    add_private_tag(ds, DICOM_TAG_PROJECT_NAME, "test-extract-uclh-omop-cdm")
-    return ds
+def _make_dicom(series_description) -> pydicom.Dataset:
+    return generate_dicom_dataset(SeriesDescription=series_description)
 
 
 def test_should_exclude_series(dicom_series_to_exclude, dicom_series_to_keep):
+    config = load_project_config(TEST_PROJECT_SLUG)
     for s in dicom_series_to_keep:
-        assert not should_exclude_series(s)
+        assert not _should_exclude_series(s, config)
     for s in dicom_series_to_exclude:
-        assert should_exclude_series(s)
+        assert _should_exclude_series(s, config)
 
 
 def test_can_nifti_convert_post_anonymisation(
-    row_for_dicom_testing, tmp_path, directory_of_mri_dicoms, tag_scheme
+    row_for_single_dicom_testing, tmp_path, directory_of_mri_dicoms, tag_scheme
 ):
     """Can a DICOM image that has passed through our tag processing be converted to NIFTI"""
     # Create a directory to store anonymised DICOM files
@@ -285,7 +443,6 @@ def test_can_nifti_convert_post_anonymisation(
             "op": "keep",
         },
     ]
-
     # Get test DICOMs from the fixture, anonymise and save
     for dcm_path in directory_of_mri_dicoms.glob("*.dcm"):
         dcm = pydicom.dcmread(dcm_path)
@@ -323,7 +480,7 @@ def test_can_nifti_convert_post_anonymisation(
 
 
 @pytest.fixture
-def sequenced_dicom():
+def sequenced_dicom_mock_db(monkeypatch):
     """
     Create a DICOM dataset with
     a private sequence tag
@@ -332,12 +489,14 @@ def sequenced_dicom():
             (group=0x0011, offset=0x0011, creator="UCLH PIXL", VR="SH", value="nested_priv_tag) and
         a public child tag
             (group=0x0010, element=0x0020), VR="LO", value="987654321").
+
+    Also mock db functions
     """
     # Create a test DICOM with a sequence tag
     exported_dicom = pathlib.Path(__file__).parents[2] / "test/resources/Dicom1.dcm"
     dataset = pydicom.dcmread(exported_dicom)
     # create nested dataset to put into sequence
-    nested_ds = Dataset()
+    nested_ds = pydicom.Dataset()
     # nested public tag
     nested_ds.add_new((0x0010, 0x0020), "LO", "987654321")
     # nested private tag
@@ -348,10 +507,14 @@ def sequenced_dicom():
     block = dataset.private_block(0x0011, "UCLH PIXL", create=True)
     block.add_new(0x0010, "SQ", [nested_ds])
 
+    # Mock the database functions
+    monkeypatch.setattr(
+        "pixl_dcmd.main.get_uniq_pseudo_study_uid_and_update_db", lambda *args: None
+    )
     return dataset
 
 
-def test_del_tag_keep_sq(sequenced_dicom):
+def test_del_tag_keep_sq(sequenced_dicom_mock_db):
     """
     GIVEN a dicom image that has a private sequence tag marked to be kept with
     - a private child tag that is marked to be deleted
@@ -362,22 +525,22 @@ def test_del_tag_keep_sq(sequenced_dicom):
     - the child tags should be deleted/replaced
     """
     ## ARRANGE (or rather check arrangement is as expected)
-    assert (0x0011, 0x0010) in sequenced_dicom
-    assert (0x0011, 0x1010) in sequenced_dicom
-    assert (0x0011, 0x1011) in sequenced_dicom.get_private_item(
+    assert (0x0011, 0x0010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1011) in sequenced_dicom_mock_db.get_private_item(
         0x0011, 0x0010, "UCLH PIXL"
     )[0]
     assert (
-        sequenced_dicom.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
+        sequenced_dicom_mock_db.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
         .get_private_item(0x0011, 0x0011, "UCLH PIXL")
         .value
         == "nested_priv_tag"
     )
-    assert (0x0010, 0x0020) in sequenced_dicom.get_private_item(
+    assert (0x0010, 0x0020) in sequenced_dicom_mock_db.get_private_item(
         0x0011, 0x0010, "UCLH PIXL"
     )[0]
     assert (
-        sequenced_dicom.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
+        sequenced_dicom_mock_db.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
         .get_item((0x0010, 0x0020))
         .value
         == "987654321"
@@ -408,26 +571,26 @@ def test_del_tag_keep_sq(sequenced_dicom):
     ]
 
     ## ACT
-    _anonymise_dicom_from_scheme(sequenced_dicom, TEST_PROJECT_SLUG, tag_scheme)
+    _anonymise_dicom_from_scheme(sequenced_dicom_mock_db, TEST_PROJECT_SLUG, tag_scheme)
 
     ## ASSERT
     # Check that the sequence tag has been kept
-    assert (0x0011, 0x0010) in sequenced_dicom
-    assert (0x0011, 0x1010) in sequenced_dicom
+    assert (0x0011, 0x0010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1010) in sequenced_dicom_mock_db
     # check private tag is deleted
-    assert (0x0011, 0x1011) not in sequenced_dicom.get_private_item(
+    assert (0x0011, 0x1011) not in sequenced_dicom_mock_db.get_private_item(
         0x0011, 0x0010, "UCLH PIXL"
     )[0]
     # check public tag is replaced
     assert (
-        sequenced_dicom.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
+        sequenced_dicom_mock_db.get_private_item(0x0011, 0x0010, "UCLH PIXL")[0]
         .get_item((0x0010, 0x0020))
         .value
         != "987654321"
     )
 
 
-def test_keep_tag_del_sq(sequenced_dicom):
+def test_keep_tag_del_sq(sequenced_dicom_mock_db):
     """
     GIVEN a dicom image that has a private sequence tag marked to be deleted with
         a private child tag that is marked to be kept
@@ -435,8 +598,8 @@ def test_keep_tag_del_sq(sequenced_dicom):
     THEN the sequence tag should be deleted
     """
     ## ARRANGE (or rather check arrangement is as expected)
-    assert (0x0011, 0x0010) in sequenced_dicom
-    assert (0x0011, 0x1010) in sequenced_dicom
+    assert (0x0011, 0x0010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1010) in sequenced_dicom_mock_db
 
     # Create a tag scheme that deletes the sequence tag, but keeps the nested tags
     tag_scheme = [
@@ -456,18 +619,17 @@ def test_keep_tag_del_sq(sequenced_dicom):
             "op": "replace",
         },
     ]
-
     ## ACT
-    _anonymise_dicom_from_scheme(sequenced_dicom, TEST_PROJECT_SLUG, tag_scheme)
+    _anonymise_dicom_from_scheme(sequenced_dicom_mock_db, TEST_PROJECT_SLUG, tag_scheme)
 
     ## ASSERT
     # Check that the sequence tag has been deleted
-    assert (0x0011, 0x1010) not in sequenced_dicom
+    assert (0x0011, 0x1010) not in sequenced_dicom_mock_db
     with pytest.raises(KeyError):
-        sequenced_dicom.get_private_item(0x0011, 0x0010, "UCLH PIXL")
+        sequenced_dicom_mock_db.get_private_item(0x0011, 0x0010, "UCLH PIXL")
 
 
-def test_whitelist_child_elements_deleted(sequenced_dicom):
+def test_allowlist_child_elements_deleted(sequenced_dicom_mock_db):
     """
     GIVEN a dicom image that has a public and private sequence tags
     WHEN the dicom tag scheme is applied
@@ -475,13 +637,15 @@ def test_whitelist_child_elements_deleted(sequenced_dicom):
     """
     ## ARRANGE (or rather check arrangement is as expected)
     # check that the sequence tag is present
-    assert (0x0011, 0x0010) in sequenced_dicom
-    assert (0x0011, 0x1010) in sequenced_dicom
+    assert (0x0011, 0x0010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1010) in sequenced_dicom_mock_db
     # check that the children are present
-    assert (0x0011, 0x1011) in sequenced_dicom[(0x0011, 0x1010)][0]
-    sequenced_dicom[(0x0011, 0x1010)][0][(0x0011, 0x1011)].value == "nested_priv_tag"
-    assert (0x0010, 0x0020) in sequenced_dicom[(0x0011, 0x1010)][0]
-    sequenced_dicom[(0x0011, 0x1010)][0][(0x0010, 0x0020)].value == "987654321"
+    assert (0x0011, 0x1011) in sequenced_dicom_mock_db[(0x0011, 0x1010)][0]
+    sequenced_dicom_mock_db[(0x0011, 0x1010)][0][
+        (0x0011, 0x1011)
+    ].value == "nested_priv_tag"
+    assert (0x0010, 0x0020) in sequenced_dicom_mock_db[(0x0011, 0x1010)][0]
+    sequenced_dicom_mock_db[(0x0011, 0x1010)][0][(0x0010, 0x0020)].value == "987654321"
 
     # set tag scheme to keep sequence
     tag_scheme = [
@@ -497,17 +661,17 @@ def test_whitelist_child_elements_deleted(sequenced_dicom):
         },
     ]
     # Whitelist
-    enforce_whitelist(sequenced_dicom, tag_scheme, recursive=True)
+    _enforce_allowlist(sequenced_dicom_mock_db, tag_scheme, recursive=True)
 
     # Check that the sequence tag is kept
-    assert (0x0011, 0x0010) in sequenced_dicom
-    assert (0x0011, 0x1010) in sequenced_dicom
+    assert (0x0011, 0x0010) in sequenced_dicom_mock_db
+    assert (0x0011, 0x1010) in sequenced_dicom_mock_db
     # Check that children are deleted
-    assert (0x0011, 0x1011) not in sequenced_dicom[(0x0011, 0x1010)][0]
-    assert (0x0010, 0x0020) not in sequenced_dicom[(0x0011, 0x1010)][0]
+    assert (0x0011, 0x1011) not in sequenced_dicom_mock_db[(0x0011, 0x1010)][0]
+    assert (0x0010, 0x0020) not in sequenced_dicom_mock_db[(0x0011, 0x1010)][0]
     with pytest.raises(KeyError):
-        sequenced_dicom[(0x0011, 0x1010)][0].get_private_item(
+        sequenced_dicom_mock_db[(0x0011, 0x1010)][0].get_private_item(
             0x0011, 0x0011, "UCLH PIXL"
         )
     with pytest.raises(KeyError):
-        sequenced_dicom[(0x0011, 0x1010)][0][0x0010, 0x0020]
+        sequenced_dicom_mock_db[(0x0011, 0x1010)][0][0x0010, 0x0020]
diff --git a/pixl_dcmd/tests/test_tag_schemes.py b/pixl_dcmd/tests/test_tag_schemes.py
index 87fdcac46..108bb1e39 100644
--- a/pixl_dcmd/tests/test_tag_schemes.py
+++ b/pixl_dcmd/tests/test_tag_schemes.py
@@ -39,7 +39,20 @@ def test_merge_base_only_tags(base_only_tag_scheme):
     THEN the result should be the same as the base file
     """
     tags = merge_tag_schemes(base_only_tag_scheme)
-    expected = base_only_tag_scheme.base[0]
+    expected = [*base_only_tag_scheme.base[0], *base_only_tag_scheme.base[1]]
+    count_tags = dict()
+    for tag in expected:
+        key = f"{tag['group']:04x},{tag['element']:04x}"
+        if key in count_tags:
+            count_tags[key] += 1
+        else:
+            count_tags[key] = 1
+
+    for key, values in count_tags.items():
+        assert (
+            values == 1
+        ), f"{key} is replicated please check config files to remove it"
+
     assert tags == expected
 
 
@@ -68,24 +81,34 @@ def tag_ops_with_manufacturer_overrides(tmp_path_factory):
         {"name": "tag3", "group": 0x003, "element": 0x1002, "op": "delete"},
     ]
     manufacturer_overrides_tags = [
-        {
-            "manufacturer": "manufacturer_1",
-            "tags": [
-                # Override tag1 for manufacturer 1
-                {"name": "tag1", "group": 0x001, "element": 0x1000, "op": "keep"},
-                {"name": "tag4", "group": 0x004, "element": 0x1011, "op": "delete"},
-                {"name": "tag5", "group": 0x005, "element": 0x1012, "op": "delete"},
-            ],
-        },
-        {
-            "manufacturer": "manufacturer_2",
-            "tags": [
-                {"name": "tag6", "group": 0x006, "element": 0x1100, "op": "keep"},
-                {"name": "tag7", "group": 0x007, "element": 0x1111, "op": "delete"},
-                # Override tag3 for manufacturer 2
-                {"name": "tag3", "group": 0x003, "element": 0x1002, "op": "keep"},
-            ],
-        },
+        [
+            {
+                "manufacturer": "manufacturer_1",
+                "tags": [
+                    # Override tag1 for manufacturer 1
+                    {"name": "tag1", "group": 0x001, "element": 0x1000, "op": "keep"},
+                    {"name": "tag4", "group": 0x004, "element": 0x1011, "op": "delete"},
+                ],
+            },
+            {
+                "manufacturer": "manufacturer_2",
+                "tags": [
+                    {"name": "tag6", "group": 0x006, "element": 0x1100, "op": "keep"},
+                    {"name": "tag7", "group": 0x007, "element": 0x1111, "op": "delete"},
+                    # Override tag3 for manufacturer 2
+                    {"name": "tag3", "group": 0x003, "element": 0x1002, "op": "keep"},
+                ],
+            },
+        ],
+        [
+            {
+                "manufacturer": "manufacturer_1",
+                "tags": [
+                    # Override tag1 for manufacturer 1
+                    {"name": "tag5", "group": 0x005, "element": 0x1012, "op": "delete"},
+                ],
+            },
+        ],
     ]
 
     return TagOperations(
diff --git a/pixl_export/README.md b/pixl_export/README.md
index 10141c7aa..9e34f283e 100644
--- a/pixl_export/README.md
+++ b/pixl_export/README.md
@@ -26,13 +26,13 @@ On Windows, follow [these instructions](https://www.postgresqltutorial.com/postg
 Then install the Python dependencies with
 
 ```bash
-pip install -e ../pixl_core/ -e .
+python -m pip install -e ../pixl_core/ -e .
 ```
 
 ## Test
 
 ```bash
-pip install -e ../pixl_core/ -e .[test]
+python -m pip install -e ../pixl_core/ -e ".[test]"
 pytest
 ```
 
diff --git a/pixl_export/pyproject.toml b/pixl_export/pyproject.toml
index 2d3e8d998..16a5b74a9 100644
--- a/pixl_export/pyproject.toml
+++ b/pixl_export/pyproject.toml
@@ -1,38 +1,45 @@
 [project]
 name = "pixl_export"
-version = "0.0.2"
+version = "0.2.0rc0"
 authors = [{ name = "PIXL authors" }]
 description = "PIXL electronic health record extractor"
 readme = "README.md"
 requires-python = ">=3.10"
 classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "core",
-    "uvicorn==0.23.2",
-    "python-decouple==3.6",
-    "psycopg2-binary==2.9.9",
-    "azure-identity==1.12.0",
-    "azure-storage-blob==12.14.1",
-    "pyarrow==14.0.1",
+    "core==0.2.0rc0",
+    "uvicorn==0.32.1",
+    "azure-storage-blob==12.24.0",
 ]
 
 [project.optional-dependencies]
 test = [
-    "pytest==7.4.2",
-    "pytest-asyncio==0.21.1",
-    "pytest-pixl",
-    "httpx==0.24.*",
+    "core[test]==0.2.0rc0",
 ]
 dev = [
-    "mypy",
-    "pre-commit",
-    "ruff",
+    "core[dev]==0.2.0rc0",
 ]
 
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
+
 [tool.pytest.ini_options]
 markers = ["processing"]
 
@@ -44,3 +51,4 @@ extend = "../ruff.toml"
 
 [tool.setuptools.package-data]
 pixl_export = ["sql/*.sql", "report_deid/*.txt"]
+
diff --git a/pixl_export/src/pixl_export/_databases.py b/pixl_export/src/pixl_export/_databases.py
index c446e3d7d..a32998065 100644
--- a/pixl_export/src/pixl_export/_databases.py
+++ b/pixl_export/src/pixl_export/_databases.py
@@ -26,7 +26,7 @@
 class Database:
     """Fake database wrapper"""
 
-    def __init__(  # noqa: PLR0913 Too many arguments in function definition
+    def __init__(
         self,
         db_name: Optional[str] = None,
         username: Optional[str] = None,
diff --git a/pixl_export/src/pixl_export/main.py b/pixl_export/src/pixl_export/main.py
index 8a5e5d653..1333df0ac 100644
--- a/pixl_export/src/pixl_export/main.py
+++ b/pixl_export/src/pixl_export/main.py
@@ -21,13 +21,13 @@
     datetime,  # noqa: TCH003, always import datetime otherwise pydantic throws error
 )
 from pathlib import Path
+from typing import Annotated
 
 from core.exports import ParquetExport
 from core.rest_api.router import router
 from core.uploader import get_uploader
-from core.uploader._orthanc import get_tags_by_study
 from decouple import config  # type: ignore [import-untyped]
-from fastapi import FastAPI, HTTPException
+from fastapi import Body, FastAPI, HTTPException
 from fastapi.responses import JSONResponse
 from loguru import logger
 from pydantic import BaseModel
@@ -61,12 +61,6 @@ class ExportPatientData(BaseModel):
     output_dir: Path = EXPORT_API_EXPORT_ROOT_DIR
 
 
-class StudyData(BaseModel):
-    """Uniquely identify a study when talking to the API"""
-
-    study_id: str
-
-
 @app.post(
     "/export-patient-data",
     summary="Copy all matching radiology reports in the PIXL DB to a parquet file \
@@ -97,16 +91,16 @@ def export_patient_data(export_params: ExportPatientData) -> None:
     "/export-dicom-from-orthanc",
     summary="Download a zipped up study from orthanc anon and upload it via the appropriate route",
 )
-def export_dicom_from_orthanc(study_data: StudyData) -> None:
+def export_dicom_from_orthanc(
+    study_id: Annotated[str, Body()],
+    project_name: Annotated[str, Body()],
+) -> None:
     """
     Download zipped up study data from orthanc anon and route it appropriately.
     Intended only for orthanc-anon to call, as only it knows when its data is ready for download.
-    Because we're post-anonymisation, the "PatientID" tag returned is actually
-    the hashed image ID (MRN + Accession number).
+    Because we're post-anonymisation, the "StudyInstanceUID" tag returned is actually
+    the Pseudo Study UID (a randomly selected, but consistent UID).
     """
-    study_id = study_data.study_id
-    _, project_slug = get_tags_by_study(study_id)
-
-    uploader = get_uploader(project_slug)
+    uploader = get_uploader(project_name)
     logger.debug("Sending {} via '{}'", study_id, type(uploader).__name__)
     uploader.upload_dicom_and_update_database(study_id)
diff --git a/pixl_export/tests/conftest.py b/pixl_export/tests/conftest.py
index b35cb06e6..fe0c9efe6 100644
--- a/pixl_export/tests/conftest.py
+++ b/pixl_export/tests/conftest.py
@@ -30,17 +30,11 @@
 os.environ["PIXL_DB_PORT"] = "35432"
 os.environ["PIXL_DB_NAME"] = "pixl"
 os.environ["PIXL_DB_USER"] = "postgres"
-os.environ["PIXL_DB_PASSWORD"] = "postgres"  # noqa: S105
-os.environ["EMAP_UDS_HOST"] = "localhost"
-os.environ["EMAP_UDS_PORT"] = "35433"
-os.environ["EMAP_UDS_NAME"] = "emap"
-os.environ["EMAP_UDS_USER"] = "postgres"
-os.environ["EMAP_UDS_PASSWORD"] = "postgres"  # noqa: S105
-os.environ["EMAP_UDS_SCHEMA_NAME"] = "star"
+os.environ["PIXL_DB_PASSWORD"] = "postgres"
 os.environ["PROJECT_CONFIGS_DIR"] = str(Path(__file__).parents[2] / "projects/configs")
 
 os.environ["ORTHANC_ANON_USERNAME"] = "orthanc_anon_username"
-os.environ["ORTHANC_ANON_PASSWORD"] = "orthanc_anon_password"  # noqa: S105 password used in test only
+os.environ["ORTHANC_ANON_PASSWORD"] = "orthanc_anon_password"
 os.environ["ORTHANC_ANON_URL"] = "http://orthanc-anon:8042"
 
 TEST_DIR = Path(__file__).parent
diff --git a/pixl_export/tests/test_app.py b/pixl_export/tests/test_app.py
index 1946dfb59..ff46b5894 100644
--- a/pixl_export/tests/test_app.py
+++ b/pixl_export/tests/test_app.py
@@ -29,4 +29,5 @@ def test_heartbeat_response_is_200() -> None:
 
 
 def test_initial_state_has_no_token() -> None:
-    assert not AppState().token_bucket.has_token
+    assert not AppState().token_bucket.has_token(key="primary")
+    assert not AppState().token_bucket.has_token(key="secondary")
diff --git a/pixl_imaging/README.md b/pixl_imaging/README.md
index d23fa0c66..9f3419db8 100644
--- a/pixl_imaging/README.md
+++ b/pixl_imaging/README.md
@@ -1,20 +1,41 @@
 # PIXL Imaging API
 
-The PIXL imaging API processes messages from the imaging queue created by the [CLI](../cli/README.md) 
-to query images from the [VNA](https://en.wikipedia.org/wiki/Vendor_Neutral_Archive) and transfers them to the [`orthanc-raw` instance](../orthanc/orthanc-raw/README.md).
+The PIXL imaging API processes messages created by the [CLI](../cli/README.md) and sent to imaging queues
+to query images from a dicom server and transfer them to the [`orthanc-raw` instance](../orthanc/orthanc-raw/README.md).
 
-It exposes a single HTTP endpoint that expects a JSON-formatted message structured as defined by the
-[`Message`](../pixl_core/src/core/patient_queue/message.py) class in `pixl_core/patient_queue`.
-On arrival of the input message it will issue a DICOMWeb request to `orthanc-raw`, which then queries the VNA
-for the requested imaging study, if it didn't already exist.
+The imaging API has two queues:
+
+- `imaging-primary`, for querying the VNA
+- `imaging-secondary`, for querying PACS
+
+The imaging API uses RabbitMQ to expose a single HTTP endpoint that expects a JSON-formatted message structured as
+defined by the [`Message`](../pixl_core/src/core/patient_queue/message.py) class in `pixl_core/patient_queue`.
+
+Users should send messages to the `imaging-primary` queue only. On arrival of the input message, the imaging API
+will query the VNA for the requested study. If the study does not exist in the VNA, the input message will be sent
+to the `imaging-secondary` queue for processing. When the `imaging-secondary` queue processes a message, if the
+study does not exist in PACS an error is raised.
+
+If the study has be identified in VNA or PACS, a query to `orthanc-raw` is made to check if the study already
+exists locally. If it does exist locally, a check is made to ensure all instances exist locally and any missing
+instances are retrieved. If the study does not exist locally, the entire study is retrieved from the archive.
+
+Once the study and all its instances are in `orthanc-raw`, the study is sent to `orthanc-anon` via a C-STORE
+operation.
+
+>[!NOTE]  
+> When querying the archives, if we do not know the `StudyInstanceUID` we will query by MRN and Accession Number.
+> This may result in multiple studies being found in the archives. In this instance, all studies returned by the
+> query will be retrieved and sent to Orthanc Anon for anonymisation. In Orthanc Anon, the studies will be combined
+> into a single study as they share the same MRN and Accession Number.
 
 ## Installation
 
 ```bash
 python -m pip install --upgrade pip
-pip install -e pytest-pixl/
-pip install -e pixl_core/[test]
-pip install -e pixl_imaging/[test]
+python -m pip install -e pytest-pixl/
+python -m pip install -e "pixl_core/[test]"
+python -m pip install -e "pixl_imaging/[test]"
 ```
 
 ## Test
@@ -34,8 +55,8 @@ Usage should be from the CLI driver, which interacts with the endpoint.
 
 The database tables are updated using alembic, see the [alembic](alembic) dir for more details.
 
-The `SKIP_ALEMBIC` environmental variable is used to control whether migrations are applied to the database.
+The `SKIP_ALEMBIC` environmental variable is used to control whether migrations are applied to the database (see variable at '.env.sample' and 'test/.env').
 
-- Tests that don't use the database use `SKIP_ALEMBIC=true`, but otherwise you probably want to run this.
+- `SKIP_ALEMBIC` is set to true for tests that do not use the database (e.g. `SKIP_ALEMBIC=true`). Otherwise you probably want to run this.
 - If you wanted to test out new migrations from a test/dev deployment on the GAE with data in,
   then you can redeploy just the `imaging-api` container while keeping the `postgres` container up. 
diff --git a/pixl_imaging/alembic/versions/83dcb3812628_add_study_uid_column_to_image_table.py b/pixl_imaging/alembic/versions/83dcb3812628_add_study_uid_column_to_image_table.py
new file mode 100644
index 000000000..5876f45a1
--- /dev/null
+++ b/pixl_imaging/alembic/versions/83dcb3812628_add_study_uid_column_to_image_table.py
@@ -0,0 +1,46 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""
+Add study UID column to Image table
+
+Revision ID: 83dcb3812628
+Revises: cb5ee12a6e20
+Create Date: 2024-08-01 16:14:47.995586
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "83dcb3812628"
+down_revision: Union[str, None] = "cb5ee12a6e20"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column("image", sa.Column("study_uid", sa.String(), nullable=True), schema="pipeline")
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("image", "study_uid", schema="pipeline")
+    # ### end Alembic commands ###
diff --git a/pixl_imaging/alembic/versions/cb5ee12a6e20_replace_hashed_id_with_pseudo_study_uid.py b/pixl_imaging/alembic/versions/cb5ee12a6e20_replace_hashed_id_with_pseudo_study_uid.py
new file mode 100644
index 000000000..eba9fc341
--- /dev/null
+++ b/pixl_imaging/alembic/versions/cb5ee12a6e20_replace_hashed_id_with_pseudo_study_uid.py
@@ -0,0 +1,43 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""
+replace_hashed_id_with_pseudo_study_uid
+Revision ID: cb5ee12a6e20
+Revises: bcaef54e2bfe
+Create Date: 2024-05-01 20:31:31.670512
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "cb5ee12a6e20"
+down_revision: Union[str, None] = "bcaef54e2bfe"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.alter_column(
+        "image", "hashed_identifier", new_column_name="pseudo_study_uid", schema="pipeline"
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "image", "pseudo_study_uid", new_column_name="hashed_identifier", schema="pipeline"
+    )
diff --git a/pixl_imaging/alembic/versions/d947cc715eb1_add_pseudo_patient_id_column_to_image_table.py b/pixl_imaging/alembic/versions/d947cc715eb1_add_pseudo_patient_id_column_to_image_table.py
new file mode 100644
index 000000000..c75d2b1ac
--- /dev/null
+++ b/pixl_imaging/alembic/versions/d947cc715eb1_add_pseudo_patient_id_column_to_image_table.py
@@ -0,0 +1,50 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""
+Add pseudo patient ID to image table
+
+Revision ID: d947cc715eb1
+Revises: 83dcb3812628
+Create Date: 2024-08-21 11:42:57.946914
+
+"""
+
+from collections.abc import Sequence
+from typing import Union
+
+import sqlalchemy as sa
+
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "d947cc715eb1"
+down_revision: Union[str, None] = "83dcb3812628"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        "image",
+        sa.Column("pseudo_patient_id", sa.String(length=255), nullable=True),
+        schema="pipeline",
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("image", "pseudo_patient_id", schema="pipeline")
+    # ### end Alembic commands ###
diff --git a/pixl_imaging/pyproject.toml b/pixl_imaging/pyproject.toml
index 82994dbf7..55d6e3992 100644
--- a/pixl_imaging/pyproject.toml
+++ b/pixl_imaging/pyproject.toml
@@ -1,38 +1,47 @@
 [project]
 name = "pixl_imaging"
-version = "0.0.2"
-authors = [
-  { name="PIXL authors" },
-]
+version = "0.2.0rc0"
+authors = [{ name = "PIXL authors" }]
 description = "PIXL image extractor"
 readme = "README.md"
 requires-python = ">=3.10"
-classifiers = [
-    "Programming Language :: Python :: 3"
-]
+classifiers = ["Programming Language :: Python :: 3"]
 dependencies = [
-    "aiohttp==3.9.3",
-    "alembic==1.13.1",
+    "core==0.2.0rc0",
+    "aiohttp==3.10.11",
+    "alembic==1.14.0",
     "pydicom==2.4.4",
-    "python-decouple==3.6",
-    "uvicorn==0.23.2",
+    "uvicorn==0.32.1",
 ]
 
 [project.optional-dependencies]
 test = [
-    "pytest==7.4.2",
-    "pytest-asyncio==0.21.1"
+    "core[test]==0.2.0rc0",
 ]
 dev = [
-    "mypy",
-    "pre-commit",
-    "ruff",
+    "core[dev]==0.2.0rc0",
 ]
 
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 
+[tool.coverage.report]
+exclude_also = [
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod",
+]
+
 [tool.pytest.ini_options]
 markers = ["processing"]
 
@@ -41,11 +50,11 @@ extend = "../ruff.toml"
 
 [tool.ruff.lint.extend-per-file-ignores]
 "./tests/**" = [
-    "D1",  # Documentation of methods
-    "S105",  # Hardcoded passwords
-    "SLF001"  # Access private members of a class
+    "D1",     # Documentation of methods
+    "S105",   # Hardcoded passwords
+    "SLF001", # Access private members of a class
 ]
 "./alembic/**" = [
-    "INP001",  # is part of an implicit namespace package. Add an `__init__.py`
-    "D103",  # Missing docstring in public function
+    "INP001", # is part of an implicit namespace package. Add an `__init__.py`
+    "D103",   # Missing docstring in public function
 ]
diff --git a/pixl_imaging/src/pixl_imaging/_orthanc.py b/pixl_imaging/src/pixl_imaging/_orthanc.py
index c838f177b..08132036d 100644
--- a/pixl_imaging/src/pixl_imaging/_orthanc.py
+++ b/pixl_imaging/src/pixl_imaging/_orthanc.py
@@ -13,7 +13,6 @@
 #  limitations under the License.
 from __future__ import annotations
 
-from abc import ABC, abstractmethod
 from asyncio import sleep
 from time import time
 from typing import Any, Optional
@@ -24,35 +23,58 @@
 from loguru import logger
 
 
-class Orthanc(ABC):
-    def __init__(self, url: str, username: str, password: str) -> None:
+class Orthanc:
+    def __init__(  # noqa: PLR0913
+        self,
+        url: str,
+        username: str,
+        password: str,
+        http_timeout: int,
+        dicom_timeout: int,
+        aet: str,
+    ) -> None:
         if not url:
             msg = "URL for orthanc is required"
             raise ValueError(msg)
         self._url = url.rstrip("/")
+        self._aet = aet
         self._username = username
         self._password = password
 
         self._auth = aiohttp.BasicAuth(login=username, password=password)
+        self.http_timeout = http_timeout
+        self.dicom_timeout = dicom_timeout
 
     @property
-    @abstractmethod
     def aet(self) -> str:
         """Application entity title (AET) of this Orthanc instance"""
+        return self._aet
 
     @property
     async def modalities(self) -> Any:
         """Accessible modalities from this Orthanc instance"""
         return await self._get("/modalities")
 
-    async def get_jobs(self) -> Any:
-        """Get expanded details for all jobs."""
-        return await self._get("/jobs?expand")
-
     async def query_local(self, data: dict) -> Any:
         """Query local Orthanc instance for resourceId."""
+        logger.debug("Running query on local Orthanc with {}", data)
         return await self._post("/tools/find", data=data)
 
+    async def get_local_study(self, study_id: str) -> Any:
+        """Query local Orthanc instance for study."""
+        return await self._get(f"/studies/{study_id}")
+
+    async def get_local_study_statistics(self, study_id: str) -> Any:
+        """Query local Orthanc instance for study statistics."""
+        return await self._get(f"/studies/{study_id}/statistics")
+
+    async def get_local_study_instances(self, study_id: str) -> Any:
+        """Get the instances of a study."""
+        return await self._get(
+            f"/studies/{study_id}/instances?short=true",
+            timeout=self.dicom_timeout,  # this API call can sometimes take several minutes
+        )
+
     async def query_remote(self, data: dict, modality: str) -> Optional[str]:
         """Query a particular modality, available from this node"""
         logger.debug("Running query on modality: {} with {}", modality, data)
@@ -60,46 +82,59 @@ async def query_remote(self, data: dict, modality: str) -> Optional[str]:
         response = await self._post(
             f"/modalities/{modality}/query",
             data=data,
-            timeout=config("PIXL_QUERY_TIMEOUT", default=10, cast=float),
         )
         logger.debug("Query response: {}", response)
-        query_answers = await self._get(f"/queries/{response['ID']}/answers")
+        query_answers = await self.get_remote_query_answers(response["ID"])
         if len(query_answers) > 0:
             return str(response["ID"])
 
         return None
 
-    async def modify_private_tags_by_study(
-        self,
-        *,
-        study_id: str,
-        private_creator: str,
-        tag_replacement: dict,
-    ) -> Any:
-        # According to the docs, you can't modify tags for an instance using the instance API
-        # (the best you can do is download a modified version), so do it via the studies API.
-        # KeepSource=false needed to stop it making a copy
-        # https://orthanc.uclouvain.be/api/index.html#tag/Studies/paths/~1studies~1{id}~1modify/post
-        return await self._post(
-            f"/studies/{study_id}/modify",
-            {
-                "PrivateCreator": private_creator,
-                "Permissive": False,
-                "KeepSource": False,
-                "Replace": tag_replacement,
-            },
+    async def get_remote_query_answers(self, query_id: str) -> Any:
+        """Get the answers to a query"""
+        return await self._get(f"/queries/{query_id}/answers")
+
+    async def get_remote_query_answer_content(self, query_id: str, answer_id: str) -> Any:
+        """Get the content of a query answer"""
+        return await self._get(f"/queries/{query_id}/answers/{answer_id}/content")
+
+    async def get_remote_query_answer_instances(self, query_id: str, answer_id: str) -> Any:
+        """Get the instances of a query answer, using DICOM timeout as can take a while"""
+        response = await self._post(
+            f"/queries/{query_id}/answers/{answer_id}/query-instances",
+            data={"Query": {}},
+            timeout=self.dicom_timeout,
         )
+        return response["ID"]
 
-    async def retrieve_from_remote(self, query_id: str) -> str:
+    async def retrieve_study_from_remote(self, query_id: str) -> str:
         response = await self._post(
             f"/queries/{query_id}/retrieve",
             data={"TargetAet": self.aet, "Synchronous": False},
         )
         return str(response["ID"])
 
-    async def wait_for_job_success_or_raise(self, query_id: str, timeout: float) -> None:
+    async def retrieve_instances_from_remote(
+        self, modality: str, missing_instances: list[dict[str, str]]
+    ) -> str:
+        """Retieve missing instances from remote modality in a single c-move query."""
+        response = await self._post(
+            f"/modalities/{modality}/move",
+            data={
+                "Level": "Instance",
+                "TargetAet": self.aet,
+                "Synchronous": False,
+                "Resources": missing_instances,
+            },
+        )
+        return str(response["ID"])
+
+    async def get_jobs(self) -> Any:
+        """Get expanded details for all jobs."""
+        return await self._get("/jobs?expand")
+
+    async def wait_for_job_success_or_raise(self, job_id: str, job_type: str, timeout: int) -> None:
         """Wait for job to complete successfully, or raise exception if fails or exceeds timeout."""
-        job_id = await self.retrieve_from_remote(query_id=query_id)  # C-Move
         job_info = {"State": "Pending"}
         start_time = time()
 
@@ -110,12 +145,15 @@ async def wait_for_job_success_or_raise(self, query_id: str, timeout: float) ->
                     f"Error code={job_info['ErrorCode']} Cause={job_info['ErrorDescription']}"
                 )
                 raise PixlDiscardError(msg)
-
+            if job_type == "modify":
+                logger.debug("Modify job: {}", job_info)
             if (time() - start_time) > timeout:
-                msg = f"Failed to transfer {job_id} in {timeout} seconds"
+                msg = f"Failed to finish {job_type} job {job_id} in {timeout} seconds"
+                await sleep(10)
                 raise PixlDiscardError(msg)
-
-            await sleep(1)
+            await sleep(10)
+            if job_info["State"] == "Pending":
+                start_time = time()
             job_info = await self.job_state(job_id=job_id)
 
     async def job_state(self, job_id: str) -> Any:
@@ -123,26 +161,36 @@ async def job_state(self, job_id: str) -> Any:
         # See: https://book.orthanc-server.com/users/advanced-rest.html#jobs-monitoring
         return await self._get(f"/jobs/{job_id}")
 
-    async def _get(self, path: str) -> Any:
+    async def _get(self, path: str, timeout: int | None = None) -> Any:
+        # Optionally override default http timeout
+        http_timeout = timeout or self.http_timeout
         async with (
             aiohttp.ClientSession() as session,
-            session.get(f"{self._url}{path}", auth=self._auth, timeout=10) as response,
+            session.get(
+                f"{self._url}{path}",
+                auth=self._auth,
+                timeout=http_timeout,
+            ) as response,
         ):
             return await _deserialise(response)
 
-    async def _post(self, path: str, data: dict, timeout: Optional[float] = None) -> Any:
+    async def _post(self, path: str, data: dict, timeout: int | None = None) -> Any:
+        # Optionally override default http timeout
+        http_timeout = timeout or self.http_timeout
         async with (
             aiohttp.ClientSession() as session,
             session.post(
-                f"{self._url}{path}", json=data, auth=self._auth, timeout=timeout
+                f"{self._url}{path}", json=data, auth=self._auth, timeout=http_timeout
             ) as response,
         ):
             return await _deserialise(response)
 
-    async def delete(self, path: str, timeout: Optional[float] = 10) -> None:
+    async def delete(self, path: str) -> None:
         async with (
             aiohttp.ClientSession() as session,
-            session.delete(f"{self._url}{path}", auth=self._auth, timeout=timeout) as response,
+            session.delete(
+                f"{self._url}{path}", auth=self._auth, timeout=self.http_timeout
+            ) as response,
         ):
             await _deserialise(response)
 
@@ -161,8 +209,13 @@ def __init__(self) -> None:
             url=config("ORTHANC_RAW_URL"),
             username=config("ORTHANC_RAW_USERNAME"),
             password=config("ORTHANC_RAW_PASSWORD"),
+            http_timeout=config("PIXL_QUERY_TIMEOUT", default=10, cast=int),
+            dicom_timeout=config("PIXL_DICOM_TRANSFER_TIMEOUT", default=240, cast=int),
+            aet=config("ORTHANC_RAW_AE_TITLE"),
         )
 
+        self.autoroute_to_anon = config("ORTHANC_AUTOROUTE_RAW_TO_ANON", default=False, cast=bool)
+
     async def raise_if_pending_jobs(self) -> None:
         """
         Raise PixlRequeueMessageError if there are pending jobs on the server.
@@ -171,15 +224,72 @@ async def raise_if_pending_jobs(self) -> None:
         PixlRequeueMessageError will cause the rabbitmq message to be requeued
         """
         jobs = await self.get_jobs()
+        unfinished_jobs = [x for x in jobs if x["State"] not in ("Success", "Failure")]
+        for job in unfinished_jobs:
+            logger.trace(
+                "{}, {}, {}, {}, {}",
+                job["State"],
+                job.get("CreationTime"),
+                job.get("ID"),
+                job.get("Type"),
+                job.get("EffectiveRuntime"),
+            )
         for job in jobs:
             if job["State"] == "Pending":
                 msg = "Pending messages in orthanc raw"
                 raise PixlRequeueMessageError(msg)
 
-    @property
-    def aet(self) -> str:
-        return str(config("ORTHANC_RAW_AE_TITLE"))
-
-    async def send_existing_study_to_anon(self, resource_id: str) -> Any:
+    async def send_study_to_anon(self, resource_id: str) -> Any:
         """Send study to orthanc anon."""
-        return await self._post("/send-to-anon", data={"ResourceId": resource_id})
+        response = await self._post(
+            "/modalities/PIXL-Anon/store",
+            data={
+                "Resources": [resource_id],
+                "Asynchronous": True,
+            },
+        )
+
+        logger.debug("Successfully triggered c-store of study to anon modality: {}", resource_id)
+        return str(response["ID"])
+
+
+class PIXLAnonOrthanc(Orthanc):
+    """Orthanc Anon connection."""
+
+    def __init__(self) -> None:
+        super().__init__(
+            url=config("ORTHANC_ANON_URL"),
+            username=config("ORTHANC_ANON_USERNAME"),
+            password=config("ORTHANC_ANON_PASSWORD"),
+            http_timeout=config("PIXL_QUERY_TIMEOUT", default=10, cast=int),
+            dicom_timeout=config("PIXL_DICOM_TRANSFER_TIMEOUT", default=240, cast=int),
+            aet=config("ORTHANC_ANON_AE_TITLE"),
+        )
+
+        self.autoroute_to_endpoint = config(
+            "ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT", default=False, cast=bool
+        )
+
+    async def notify_anon_to_retrieve_study_resources(
+        self,
+        orthanc_raw: PIXLRawOrthanc,
+        resource_ids: list[str],
+        project_name: str,
+    ) -> Any:
+        """Notify Orthanc Anon of study resources to retrieve from Orthanc Raw."""
+        resources_info = [
+            await orthanc_raw.get_local_study(study_id=resource_id) for resource_id in resource_ids
+        ]
+        study_uids = [
+            resource_info["MainDicomTags"]["StudyInstanceUID"] for resource_info in resources_info
+        ]
+        logger.debug("Notify Orthanc Anon to import resources {} from Orthanc Raw", resource_ids)
+
+        await self._post(
+            path="/import-from-raw",
+            data={
+                "ResourceIDs": resource_ids,
+                "StudyInstanceUIDs": study_uids,
+                "ProjectName": project_name,
+            },
+        )
diff --git a/pixl_imaging/src/pixl_imaging/_processing.py b/pixl_imaging/src/pixl_imaging/_processing.py
index 4d845f54b..a1a92274d 100644
--- a/pixl_imaging/src/pixl_imaging/_processing.py
+++ b/pixl_imaging/src/pixl_imaging/_processing.py
@@ -13,14 +13,16 @@
 #  limitations under the License.
 from __future__ import annotations
 
+import datetime
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any
+from enum import StrEnum
+from typing import TYPE_CHECKING, Any, Optional
+from zoneinfo import ZoneInfo
 
-from core.dicom_tags import DICOM_TAG_PROJECT_NAME
-from core.exceptions import PixlDiscardError
+from core.exceptions import PixlDiscardError, PixlOutOfHoursError, PixlStudyNotInPrimaryArchiveError
 from decouple import config
 
-from pixl_imaging._orthanc import Orthanc, PIXLRawOrthanc
+from pixl_imaging._orthanc import Orthanc, PIXLAnonOrthanc, PIXLRawOrthanc
 
 if TYPE_CHECKING:
     from core.patient_queue.message import Message
@@ -28,125 +30,315 @@
 from loguru import logger
 
 
-async def process_message(message: Message) -> None:
+class DicomModality(StrEnum):
+    primary = config("PRIMARY_DICOM_SOURCE_MODALITY")
+    secondary = config("SECONDARY_DICOM_SOURCE_MODALITY")
+
+
+async def process_message(message: Message, archive: DicomModality) -> None:
     """
     Process message from queue by retrieving a study with the given Patient and Accession Number.
     We may receive multiple messages with same Patient + Acc Num, either as retries or because
     they are needed for multiple projects.
     """
-    logger.debug("Processing: {}", message.identifier)
+    logger.trace("Processing: {}. Querying {} archive.", message.identifier, archive.name)
 
     study = ImagingStudy.from_message(message)
     orthanc_raw = PIXLRawOrthanc()
-    try:
-        await _process_message(study, orthanc_raw)
-    except PixlDiscardError:
-        # if a message has failed mid-transfer, can have partial study in orthanc-raw
-        # delete this so that it doesn't become stable and is exported
-        studies_to_delete = await orthanc_raw.query_local(study.orthanc_query_dict)
-        for study_to_delete in studies_to_delete:
-            logger.info(
-                "Deleting study '{}' from message {}", study_to_delete, study.message.identifier
-            )
-            await orthanc_raw.delete(f"/studies/{study_to_delete}")
-        raise
+    orthanc_anon = PIXLAnonOrthanc()
+    await _process_message(
+        study=study,
+        orthanc_raw=orthanc_raw,
+        archive=archive,
+        orthanc_anon=orthanc_anon,
+    )
 
 
-async def _process_message(study: ImagingStudy, orthanc_raw: PIXLRawOrthanc) -> None:
+async def _process_message(
+    study: ImagingStudy,
+    orthanc_raw: PIXLRawOrthanc,
+    archive: DicomModality,
+    orthanc_anon: PIXLAnonOrthanc,
+) -> None:
+    """
+    Retrieve a study from the archives and send it to Orthanc Anon.
+
+    Querying the archives:
+    If 'archive' is 'secondary' and it's during working hours:
+        - raise a PixlOutOfHoursError to have the message requeued
+    If the study doesn't exist and 'archive' is primary:
+        - publish the message to the secondary imaging queue
+        - raise a PixlDiscardError
+    If the study doesn't exist and 'archive' is secondary:
+        - raise a PixlDiscardError
+
+    Querying Orthanc Raw:
+    If the study already exists in Orthanc Raw:
+        - query the archive to determine whether any instances are missing
+        - retrieve any missing instances
+    If it doesn't already exist in Orthanc Raw:
+        - query the archive for the study
+        - retrieve the study from the VNA / PACS
+
+    Then:
+        - send the study to Orthanc Anon if ORTHANC_AUTOROUTE_RAW_TO_ANON is True
+        - if the C-STORE operation to Orthanc Anon is successful, and
+          ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT is True, send the study to the appropriate destination
+    """
     await orthanc_raw.raise_if_pending_jobs()
 
-    study_exists = await _update_or_resend_existing_study_(
-        study.message.project_name, orthanc_raw, study
+    if archive.name == "secondary" and (_is_daytime() or _is_weekend()):
+        msg = "Not querying secondary archive during the daytime or on the weekend."
+        raise PixlOutOfHoursError(msg)
+
+    logger.info("Processing: {}. Querying {} archive.", study.message.identifier, archive.name)
+
+    study_query_id = await _find_study_in_archive_or_raise(
+        orthanc_raw=orthanc_raw,
+        study=study,
+        archive=archive,
     )
-    if study_exists:
+
+    existing_local_resources = await _get_study_resources(
+        orthanc_raw=orthanc_raw,
+        study=study,
+    )
+
+    if not existing_local_resources:
+        await _retrieve_study(
+            orthanc_raw=orthanc_raw,
+            study_query_id=study_query_id,
+        )
+    else:
+        await _retrieve_missing_instances(
+            resources=existing_local_resources,
+            orthanc_raw=orthanc_raw,
+            study=study,
+            study_query_id=study_query_id,
+            modality=archive.value,
+        )
+
+    resources = await _get_study_resources(
+        orthanc_raw=orthanc_raw,
+        study=study,
+    )
+
+    if not orthanc_raw.autoroute_to_anon:
+        logger.debug("Auto-routing to Orthanc Anon is not enabled. Not sending study {}", resources)
         return
 
-    query_id = await _find_study_in_vna_or_raise(orthanc_raw, study)
-    timeout: float = config("PIXL_DICOM_TRANSFER_TIMEOUT", cast=float)
-    await orthanc_raw.wait_for_job_success_or_raise(query_id, timeout)
+    await orthanc_anon.notify_anon_to_retrieve_study_resources(
+        orthanc_raw=orthanc_raw,
+        resource_ids=resources,
+        project_name=study.message.project_name,
+    )
 
-    # Now that instance has arrived in orthanc raw, we can set its project name tag via the API
-    studies = await orthanc_raw.query_local(study.orthanc_query_dict)
-    logger.debug("Local instances for study: {}", studies)
-    await _add_project_to_study(study.message.project_name, orthanc_raw, studies)
 
-    return
+async def _get_study_resources(
+    orthanc_raw: PIXLRawOrthanc,
+    study: ImagingStudy,
+) -> list[str]:
+    """Get a list of existing resources for a study in Orthanc Raw."""
+    existing_resources: list[str] = await study.query_local(orthanc_raw)
 
+    logger.debug(
+        'Found {} existing resources for study "{}"',
+        existing_resources,
+        study,
+    )
 
-async def _update_or_resend_existing_study_(
-    project_name: str, orthanc_raw: PIXLRawOrthanc, study: ImagingStudy
-) -> bool:
+    return existing_resources
+
+
+async def _find_study_in_archive_or_raise(
+    orthanc_raw: Orthanc,
+    study: ImagingStudy,
+    archive: DicomModality,
+) -> str:
     """
-    If study does not yet exist in orthanc raw, do nothing.
-    If study exists in orthanc raw and has the wrong project name, update it.
-    If study exists in orthanc raw and has the correct project name, send to orthanc anon.
+    Query an archive for a study.
+
+    If 'archive' is 'secondary' and it's during working hours:
+        - raise a PixlOutOfHoursError to have the message requeued
+    If the study doesn't exist, and 'archive' is primary:
+        - raise a PixlStudyNotInPrimaryArchiveError if a secondary archive is defined
+        - raise a PixlDiscardError if a secondary archive is not defined
+    If the study doesn't exist and 'archive' is secondary:
+        - raise a PixlDiscardError
+
+    When querying an archive, the study is first queried using its UID it it's available.
+    If the UID is an empty string, or if the study is not found, the study is queried using
+    the MRN and accession number.
 
-    Return True if study exists in orthanc raw, otherwise False.
     """
-    existing_resources = await study.query_local(orthanc_raw, project_tag=True)
-    if len(existing_resources) == 0:
-        return False
-
-    # Check whether study already has the correct project name
-    different_project: list[str] = []
-
-    if len(existing_resources) > 1:
-        # Only keep one study, the one which has the largest number of series
-        sorted_resources = sorted(existing_resources, key=lambda x: len(x["LastUpdate"]))
-        logger.debug(
-            "Found more than one resource for study, only keeping the last updated resource: {}",
-            sorted_resources,
+    query_id = await _find_study_in_archive(
+        orthanc_raw=orthanc_raw,
+        study=study,
+        modality=archive.value,
+    )
+
+    if query_id is not None:
+        return query_id
+
+    if archive.name == "secondary":
+        msg = f"Failed to find study {study.message.identifier} in primary or secondary archive."
+        raise PixlDiscardError(msg)
+
+    if config("SECONDARY_DICOM_SOURCE_AE_TITLE") == config("PRIMARY_DICOM_SOURCE_AE_TITLE"):
+        msg = (
+            f"Failed to find study {study.message.identifier} in primary archive "
+            "and SECONDARY_DICOM_SOURCE_AE_TITLE is the same as PRIMARY_DICOM_SOURCE_AE_TITLE."
         )
-        existing_resources = [sorted_resources.pop(-1)]
-        for delete_resource in sorted_resources:
-            await orthanc_raw.delete(f"/studies/{delete_resource['ID']}")
-
-    for resource in existing_resources:
-        project_tags = (
-            resource["RequestedTags"].get(DICOM_TAG_PROJECT_NAME.tag_nickname),
-            resource["RequestedTags"].get(
-                "Unknown Tag & Data"
-            ),  # Fallback for testing where we're not using the entire plugin, remains undefined
+        raise PixlDiscardError(msg)
+
+    msg = (
+        f"Failed to find study {study.message.identifier} in primary archive, "
+        "sending message to secondary imaging queue."
+    )
+    raise PixlStudyNotInPrimaryArchiveError(msg)
+
+
+async def _find_study_in_archive(
+    orthanc_raw: Orthanc,
+    study: ImagingStudy,
+    modality: str,
+) -> Optional[str]:
+    """
+    Query the primary archive for the study using its UID.
+    If UID is not available, query on MRN and accession number.
+    """
+    query_response = None
+    if study.message.study_uid:
+        query_response = await orthanc_raw.query_remote(
+            data=study.orthanc_uid_query_dict,
+            modality=modality,
         )
-        if project_name not in project_tags:
-            different_project.append(resource["ID"])
+    if query_response is not None:
+        return query_response
+
+    logger.debug(
+        "No study found in modality {} with UID '{}', trying MRN and accession number",
+        modality,
+        study.message.study_uid,
+    )
+    return await orthanc_raw.query_remote(
+        study.orthanc_query_dict,
+        modality=modality,
+    )
+
+
+def _is_daytime() -> bool:
+    """Check if the current time is between 8 am and 8 pm."""
+    timezone = ZoneInfo(config("TZ"))
+    after_8am = datetime.time(8, 00) <= datetime.datetime.now(tz=timezone).time()
+    before_8pm = datetime.datetime.now(tz=timezone).time() <= datetime.time(20, 00)
+    return after_8am and before_8pm
+
+
+def _is_weekend() -> bool:
+    """Check if it's the weekend."""
+    timezone = ZoneInfo(config("TZ"))
+    saturday = 5
+    sunday = 6
+    return datetime.datetime.now(tz=timezone).weekday() in (saturday, sunday)
 
-    if different_project:
-        await _add_project_to_study(project_name, orthanc_raw, different_project)
-        return True
-    await orthanc_raw.send_existing_study_to_anon(existing_resources[0]["ID"])
-    return True
+
+async def _retrieve_study(orthanc_raw: Orthanc, study_query_id: str) -> None:
+    """Retrieve all instances for a study from the VNA / PACS."""
+    job_id = await orthanc_raw.retrieve_study_from_remote(query_id=study_query_id)  # C-Move
+    await orthanc_raw.wait_for_job_success_or_raise(
+        job_id, "c-move", timeout=orthanc_raw.dicom_timeout
+    )
 
 
-async def _add_project_to_study(
-    project_name: str, orthanc_raw: PIXLRawOrthanc, studies: list[str]
+async def _retrieve_missing_instances(
+    resources: list[str],
+    orthanc_raw: Orthanc,
+    study: ImagingStudy,
+    study_query_id: str,
+    modality: str,
 ) -> None:
-    if len(studies) > 1:
-        logger.error(
-            "Got {} studies with matching accession number and patient ID, expected 1",
-            studies,
+    """Retrieve missing instances for a study from the VNA / PACS."""
+    missing_instance_uids = await _get_missing_instances(
+        orthanc_raw=orthanc_raw, study=study, resources=resources, study_query_id=study_query_id
+    )
+    if not missing_instance_uids:
+        return
+    logger.debug(
+        "Retrieving {} missing instances for study {}",
+        len(missing_instance_uids),
+        study.message.identifier,
+    )
+    job_id = await orthanc_raw.retrieve_instances_from_remote(modality, missing_instance_uids)
+    await orthanc_raw.wait_for_job_success_or_raise(
+        job_id, "c-move for missing instances", timeout=orthanc_raw.dicom_timeout
+    )
+
+
+async def _get_missing_instances(
+    orthanc_raw: Orthanc, study: ImagingStudy, resources: list[str], study_query_id: str
+) -> list[dict[str, str]]:
+    """
+    Check if any study instances are missing from Orthanc Raw.
+
+    Return a list of missing instance UIDs (empty if none missing)
+    """
+    missing_instances: list[dict[str, str]] = []
+
+    # First query the VNA / PACS for the study instances
+    study_query_answers = await orthanc_raw.get_remote_query_answers(study_query_id)
+    instances_queries_and_answers = []
+    for answer_id in study_query_answers:
+        instances_query_id = await orthanc_raw.get_remote_query_answer_instances(
+            query_id=study_query_id, answer_id=answer_id
         )
-    for study in studies:
-        logger.debug("Adding private tag to study ID {}", study)
-        await orthanc_raw.modify_private_tags_by_study(
-            study_id=study,
-            private_creator=DICOM_TAG_PROJECT_NAME.creator_string,
-            tag_replacement={
-                # The tag here needs to be defined in orthanc's dictionary
-                DICOM_TAG_PROJECT_NAME.tag_nickname: project_name,
-            },
+        instances_query_answers = await orthanc_raw.get_remote_query_answers(instances_query_id)
+        instances_queries_and_answers.extend(
+            [(instances_query_id, answer) for answer in instances_query_answers]
+        )
+    num_remote_instances = len(instances_queries_and_answers)
+
+    num_local_instances = 0
+    for resource in resources:
+        study_statistics = await orthanc_raw.get_local_study_statistics(study_id=resource)
+        num_local_instances += int(study_statistics["CountInstances"])
+
+    if num_remote_instances == num_local_instances:
+        logger.debug("No missing instances for study {}", study.message.study_uid)
+        return missing_instances
+
+    # Get all SOPInstanceUIDs for the study that are in Orthanc Raw
+    orthanc_raw_sop_instance_uids = []
+    for resource in resources:
+        study_instances = await orthanc_raw.get_local_study_instances(study_id=resource)
+        orthanc_raw_sop_instance_uids.extend(
+            [instance["MainDicomTags"]["0008,0018"] for instance in study_instances]
         )
 
+    # If the SOPInstanceUID is not in the list of instances in Orthanc Raw
+    # retrieve the instance from the VNA / PACS
+    query_tags = ["0020,000d", "0020,000e", "0008,0018"]
+    for instances_query_id, instance_query_answer in instances_queries_and_answers:
+        instance_query_answer_content = await orthanc_raw.get_remote_query_answer_content(
+            query_id=instances_query_id,
+            answer_id=instance_query_answer,
+        )
+        uids_for_query = {
+            instance_query_answer_content[x]["Name"]: instance_query_answer_content[x]["Value"]
+            for x in query_tags
+        }
+        sop_instance_uid = uids_for_query["SOPInstanceUID"]
+        if sop_instance_uid in orthanc_raw_sop_instance_uids:
+            continue
+
+        logger.trace(
+            "Instance {} is missing from study {}",
+            sop_instance_uid,
+            study.message.study_uid,
+        )
+        missing_instances.append(uids_for_query)
 
-async def _find_study_in_vna_or_raise(orthanc_raw: Orthanc, study: ImagingStudy) -> str:
-    """Query the VNA for the study, raise exception if it doesn't exist"""
-    query_id = await orthanc_raw.query_remote(
-        study.orthanc_query_dict, modality=config("VNAQR_MODALITY")
-    )
-    if query_id is None:
-        msg = "Failed to find in the VNA"
-        raise PixlDiscardError(msg)
-    return query_id
+    return missing_instances
 
 
 @dataclass
@@ -161,29 +353,45 @@ def from_message(cls, message: Message) -> ImagingStudy:
         return ImagingStudy(message=message)
 
     @property
-    def orthanc_query_dict(self) -> dict:
-        """Build a dictionary to query a study."""
+    def orthanc_uid_query_dict(self) -> dict:
+        """Build a dictionary to query a study with a study UID."""
         return {
             "Level": "Study",
             "Query": {
-                "PatientID": self.message.mrn,
-                "AccessionNumber": self.message.accession_number,
+                "StudyInstanceUID": self.message.study_uid,
             },
         }
 
     @property
-    def orthanc_dict_with_project_name(self) -> dict:
-        """Dictionary to query a study, returning the PIXL_PROJECT tags for each study."""
+    def orthanc_query_dict(self) -> dict:
+        """Build a dictionary to query a study on MRN and accession number."""
         return {
-            **self.orthanc_query_dict,
-            "RequestedTags": [DICOM_TAG_PROJECT_NAME.tag_nickname],
-            "Expand": True,
+            "Level": "Study",
+            "Query": {
+                "PatientID": self.message.mrn,
+                "AccessionNumber": self.message.accession_number,
+            },
         }
 
-    async def query_local(self, node: Orthanc, *, project_tag: bool = False) -> Any:
-        """Does this study exist in an Orthanc instance/node, optionally query for project tag."""
-        query_dict = self.orthanc_query_dict
-        if project_tag:
-            query_dict = self.orthanc_dict_with_project_name
+    async def query_local(self, node: Orthanc) -> Any:
+        """Does this study exist in an Orthanc instance/node."""
+        if self.message.study_uid:
+            uid_query = self.orthanc_uid_query_dict
+
+            query_response = await node.query_local(uid_query)
+            if query_response:
+                return query_response
+
+            logger.trace(
+                "No study found locally with UID, trying MRN and accession number. {}",
+                self.orthanc_query_dict,
+            )
+        else:
+            logger.trace(
+                "study_uid is empty, trying MRN and accession number. {}",
+                self.orthanc_query_dict,
+            )
+
+        mrn_accession_query = self.orthanc_query_dict
 
-        return await node.query_local(query_dict)
+        return await node.query_local(mrn_accession_query)
diff --git a/pixl_imaging/src/pixl_imaging/main.py b/pixl_imaging/src/pixl_imaging/main.py
index 94f3ac62d..7e612ecfc 100644
--- a/pixl_imaging/src/pixl_imaging/main.py
+++ b/pixl_imaging/src/pixl_imaging/main.py
@@ -26,9 +26,10 @@
 from fastapi.responses import JSONResponse
 from loguru import logger
 
-from ._processing import process_message
+from ._processing import DicomModality, process_message
 
-QUEUE_NAME = "imaging"
+QUEUE_NAME = "imaging-primary"
+SECONDARY_QUEUE_NAME = "imaging-secondary"
 
 app = FastAPI(
     title="imaging-api",
@@ -57,10 +58,24 @@ async def startup_event() -> None:
     the task is consumer.run and the callback is _processing.process_message
     """
     background_tasks = set()
-    async with PixlConsumer(
-        QUEUE_NAME, token_bucket=state.token_bucket, callback=process_message
-    ) as consumer:
-        task = asyncio.create_task(consumer.run())
+    async with (
+        PixlConsumer(
+            QUEUE_NAME,
+            token_bucket=state.token_bucket,
+            token_bucket_key="primary",  # noqa: S106
+            callback=lambda message: process_message(message, archive=DicomModality.primary),
+        ) as primary_consumer,
+        PixlConsumer(
+            SECONDARY_QUEUE_NAME,
+            token_bucket=state.token_bucket,
+            token_bucket_key="secondary",  # noqa: S106
+            callback=lambda message: process_message(message, archive=DicomModality.secondary),
+        ) as secondary_consumer,
+    ):
+        task = asyncio.create_task(primary_consumer.run())
+        background_tasks.add(task)
+        task.add_done_callback(background_tasks.discard)
 
+        task = asyncio.create_task(secondary_consumer.run())
         background_tasks.add(task)
         task.add_done_callback(background_tasks.discard)
diff --git a/pixl_imaging/tests/conftest.py b/pixl_imaging/tests/conftest.py
index 1f025b8e4..ed1c38071 100644
--- a/pixl_imaging/tests/conftest.py
+++ b/pixl_imaging/tests/conftest.py
@@ -16,12 +16,9 @@
 import os
 import shlex
 import subprocess
-from collections.abc import Generator
 from pathlib import Path
 
 import pytest
-from _pytest.monkeypatch import MonkeyPatch
-from loguru import logger
 from pytest_pixl.helpers import run_subprocess
 
 os.environ["TEST"] = "true"
@@ -30,32 +27,30 @@
 os.environ["RABBITMQ_USERNAME"] = "guest"
 os.environ["RABBITMQ_HOST"] = "queue"
 os.environ["RABBITMQ_PORT"] = "5672"
+os.environ["ORTHANC_ANON_URL"] = "unused"
+os.environ["ORTHANC_ANON_USERNAME"] = "unused"
+os.environ["ORTHANC_ANON_PASSWORD"] = "unused"
+os.environ["ORTHANC_ANON_AE_TITLE"] = "PIXLRAW"
 os.environ["ORTHANC_RAW_URL"] = "http://localhost:8044"
 os.environ["ORTHANC_RAW_USERNAME"] = "orthanc"
 os.environ["ORTHANC_RAW_PASSWORD"] = "orthanc"
 os.environ["ORTHANC_RAW_AE_TITLE"] = "PIXLRAW"
+os.environ["ORTHANC_AUTOROUTE_RAW_TO_ANON"] = "False"
 os.environ["ORTHANC_VNA_URL"] = "http://localhost:8043"
 os.environ["ORTHANC_VNA_USERNAME"] = "orthanc"
 os.environ["ORTHANC_VNA_PASSWORD"] = "orthanc"
-os.environ["ORTHANC_VNA_AE_TITLE"] = "VNAQR"
-os.environ["VNAQR_MODALITY"] = "UCVNAQR"
+os.environ["ORTHANC_PACS_URL"] = "http://localhost:8045"
+os.environ["ORTHANC_PACS_USERNAME"] = "orthanc"
+os.environ["ORTHANC_PACS_PASSWORD"] = "orthanc"
+os.environ["PRIMARY_DICOM_SOURCE_MODALITY"] = "UCPRIMARYQR"
+os.environ["PRIMARY_DICOM_SOURCE_AE_TITLE"] = "PRIMARYQR"
+os.environ["SECONDARY_DICOM_SOURCE_MODALITY"] = "UCSECONDARYQR"
+os.environ["SECONDARY_DICOM_SOURCE_AE_TITLE"] = "SECONDARYQR"
+os.environ["PIXL_QUERY_TIMEOUT"] = "10"
 os.environ["PIXL_DICOM_TRANSFER_TIMEOUT"] = "30"
 os.environ["SKIP_ALEMBIC"] = "true"
 os.environ["PIXL_MAX_MESSAGES_IN_FLIGHT"] = "20"
-os.environ["ORTHANC_AUTOROUTE_RAW_TO_ANON"] = "false"
-
-
-@pytest.fixture(autouse=True)
-def _patch_send_existing_study_to_anon(monkeypatch: Generator[MonkeyPatch, None, None]) -> None:
-    """Patch send_existing_study_to_anon in Orthanc as orthanc raw doesn't use the pixl plugin."""
-
-    async def patched_send(self, resource_id: str) -> None:
-        """Replaces send_existing_study_to_anon."""
-        logger.info("Intercepted request to send '{}' to anon", resource_id)
-
-    monkeypatch.setattr(
-        "pixl_imaging._orthanc.PIXLRawOrthanc.send_existing_study_to_anon", patched_send
-    )
+os.environ["TZ"] = "Europe/London"
 
 
 TEST_DIR = Path(__file__).parent
@@ -67,7 +62,7 @@ def run_containers() -> subprocess.CompletedProcess[bytes]:
     yield run_subprocess(
         shlex.split("docker compose up --build --wait"),
         TEST_DIR,
-        timeout=180,
+        timeout=240,
     )
     run_subprocess(
         shlex.split("docker compose down --volumes"),
diff --git a/pixl_imaging/tests/docker-compose.yml b/pixl_imaging/tests/docker-compose.yml
index bf318b794..3aded6e04 100644
--- a/pixl_imaging/tests/docker-compose.yml
+++ b/pixl_imaging/tests/docker-compose.yml
@@ -33,38 +33,61 @@ services:
     vna-qr:
         image: orthancteam/orthanc:24.3.3
         environment:
-            ORTHANC_NAME: "VNAQR"
+            ORTHANC_NAME: "PRIMARYQR"
             ORTHANC_USERNAME: "orthanc"
             ORTHANC_PASSWORD: "orthanc"
-            ORTHANC_AE_TITLE: "VNAQR"
+            ORTHANC_AE_TITLE: "PRIMARYQR"
             RAW_AE_TITLE: "PIXLRAW"
             RAW_DICOM_PORT: "4242"
             RAW_IP_ADDR: "orthanc-raw" # aka. hostname
+            TZ: ${TZ:-Europe/London}
         ports:
             - "127.0.0.1:4243:4242"
             - "127.0.0.1:8043:8042"
         volumes:
             - ../../test/vna_config/:/run/secrets:ro
         <<: *orthanc-healthcheck
+    pacs-qr:
+        image: orthancteam/orthanc:24.3.3
+        environment:
+            ORTHANC_NAME: "SECONDARYQR"
+            ORTHANC_USERNAME: "orthanc"
+            ORTHANC_PASSWORD: "orthanc"
+            ORTHANC_AE_TITLE: "SECONDARYQR"
+            RAW_AE_TITLE: "PIXLRAW"
+            RAW_DICOM_PORT: "4242"
+            RAW_IP_ADDR: "orthanc-raw" # aka. hostname
+            TZ: ${TZ:-Europe/London}
+        ports:
+            - "127.0.0.1:4245:4242"
+            - "127.0.0.1:8045:8042"
+        volumes:
+            - ../../test/vna_config/:/run/secrets:ro
+        <<: *orthanc-healthcheck
 
     orthanc-raw:
         build:
             context: ../../
             dockerfile: ./docker/orthanc/Dockerfile
             target: pixl_orthanc_raw
+            args:
+                PIXL_DICOM_TRANSFER_TIMEOUT: 30
         environment:
             ORTHANC_NAME: "PIXL: Raw"
             ORTHANC_USERNAME: "orthanc"
             ORTHANC_PASSWORD: "orthanc"
             ORTHANC_AE_TITLE: "PIXLRAW"
-            VNAQR_AE_TITLE: "VNAQR"
-            VNAQR_DICOM_PORT: "4242"
-            VNAQR_IP_ADDR: "vna-qr"
+            PRIMARY_DICOM_SOURCE_AE_TITLE: "PRIMARYQR"
+            PRIMARY_DICOM_SOURCE_PORT: "4242"
+            PRIMARY_DICOM_SOURCE_IP_ADDR: "vna-qr"
+            SECONDARY_DICOM_SOURCE_AE_TITLE: "SECONDARYQR"
+            SECONDARY_DICOM_SOURCE_PORT: "4242"
+            SECONDARY_DICOM_SOURCE_IP_ADDR: "pacs-qr"
             ORTHANC_ANON_AE_TITLE: "unused"
             ORTHANC_ANON_DICOM_PORT: "4242"
             ORTHANC_ANON_HOSTNAME: "orthanc-anon"
-            ORTHANC_AUTOROUTE_RAW_TO_ANON: "false"
             PROJECT_CONFIGS_DIR: "/projects/configs"
+            TZ: "Europe/London"
         ports:
             - "127.0.0.1:4244:4242"
             - "127.0.0.1:8044:8042"
diff --git a/pixl_imaging/tests/orthanc_raw_config/dicom.json b/pixl_imaging/tests/orthanc_raw_config/dicom.json
index 4e3b20af9..75d89a507 100644
--- a/pixl_imaging/tests/orthanc_raw_config/dicom.json
+++ b/pixl_imaging/tests/orthanc_raw_config/dicom.json
@@ -1,19 +1,96 @@
 {
   "DicomAet" : "${ORTHANC_AE_TITLE}",
-  "DicomAlwaysAllowEcho" : true,
-  "DicomCheckModalityHost" : true,
+
   "DicomModalities" : {
-    "UCVNAQR" : {
-      "AET" : "${VNAQR_AE_TITLE}",
-      "Port" : "${VNAQR_DICOM_PORT}",
-      "Host" : "${VNAQR_IP_ADDR}",
-      "Manufacturer" : "Generic"
+    "UCPRIMARYQR" : {
+      "AET" : "${PRIMARY_DICOM_SOURCE_AE_TITLE}",
+      "Port" : "${PRIMARY_DICOM_SOURCE_PORT}",
+      "Host" : "${PRIMARY_DICOM_SOURCE_IP_ADDR}",
+      "Manufacturer" : "Generic",
+      "AllowEcho" : true,
+      "AllowFind" : false,
+      "AllowFindWorklist" : false,
+      "AllowGet"  : false,
+      "AllowMove" : false,
+      "AllowStore" : true,
+      "AllowStorageCommitment" : false,
+      "AllowTranscoding" : true,
+      "UseDicomTls" : false,
+      "Timeout" : 60
     },
-    "PIXLR" : {
-      "AET" : "${ORTHANC_AE_TITLE}",
-      "Port" : "4242",
-      "Host" : "127.0.0.1",
-      "Manufacturer" : "Generic"
+    "UCSECONDARYQR" : {
+      "AET" : "${SECONDARY_DICOM_SOURCE_AE_TITLE}",
+      "Port" : "${SECONDARY_DICOM_SOURCE_PORT}",
+      "Host" : "${SECONDARY_DICOM_SOURCE_IP_ADDR}",
+      "Manufacturer" : "Generic",
+      "AllowEcho" : true,
+      "AllowFind" : false,
+      "AllowFindWorklist" : false,
+      "AllowGet"  : false,
+      "AllowMove" : false,
+      "AllowStore" : true,
+      "AllowStorageCommitment" : false,
+      "AllowTranscoding" : true,
+      "UseDicomTls" : false,
+      "Timeout" : 60
     }
-  }
+  },
+
+  // Check whether the called AET corresponds to the AET of Orthanc
+  // during an incoming DICOM SCU request
+  "DicomCheckCalledAet" : true,
+
+  // Whether Orthanc accepts to act as C-STORE SCP for unknown storage
+  // SOP classes (aka. "promiscuous mode")
+  "UnknownSopClassAccepted" : true,
+
+  // Whether the Orthanc SCP allows incoming C-ECHO requests, even
+  // from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above). Orthanc 1.3.0
+  // is the only version to behave as if this argument were set to "false".
+  "DicomAlwaysAllowEcho" : true,
+
+  // Whether the Orthanc SCP allows incoming C-STORE requests, even
+  // from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above)
+  "DicomAlwaysAllowStore" : true,
+
+  // Whether the Orthanc SCP allows incoming C-FIND requests, even
+  // from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above). Setting this
+  // option to "true" implies security risks. (new in Orthanc 1.9.0)
+  // Note: From Orthanc 1.10.0, this option only applies to C-FIND
+  // requests for patients/studies/series/instances. Use option
+  // "DicomAlwaysAllowFindWorklist" for worklists.
+  "DicomAlwaysAllowFind" : false,
+
+  // Whether the Orthanc SCP allows incoming C-FIND requests for worklists, 
+  // even from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above). Setting this
+  // option to "true" implies security risks. (new in Orthanc 1.10.0)
+  "DicomAlwaysAllowFindWorklist" : false,
+
+  // Whether the Orthanc SCP allows incoming C-GET requests, even
+  // from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above). Setting this
+  // option to "true" implies security risks. (new in Orthanc 1.9.0)
+  "DicomAlwaysAllowGet" : false,
+
+  // Whether the Orthanc SCP allows incoming C-MOVE requests, even
+  // from SCU modalities it does not know about (i.e. that are not
+  // listed in the "DicomModalities" option above). Setting this
+  // option to "true" implies security risks. (new in Orthanc 1.9.7)
+  "DicomAlwaysAllowMove" : false,
+
+  // Whether Orthanc checks the IP/hostname address of the remote
+  // modality initiating a DICOM connection (as listed in the
+  // "DicomModalities" option above). If this option is set to
+  // "false", Orthanc only checks the AET of the remote modality.
+  "DicomCheckModalityHost" : false,
+
+  // Overwrite instances with the same UID
+  // This allows us to set the project name tag in-place without modifying the
+  //StudyInstanceUID, SeriesInstanceUID, and SOPInstanceUID
+  "OverwriteInstance": true
+  
 }
diff --git a/pixl_imaging/tests/orthanc_raw_config/orthanc.json b/pixl_imaging/tests/orthanc_raw_config/orthanc.json
index e2c6a767e..00cc51049 100644
--- a/pixl_imaging/tests/orthanc_raw_config/orthanc.json
+++ b/pixl_imaging/tests/orthanc_raw_config/orthanc.json
@@ -1,11 +1,31 @@
 {
-  "Dictionary": {
-    "000d,1001": ["LO", "UCLHPIXLProjectName", 1, 1, "UCLH PIXL"]
-  },
   "DefaultPrivateCreator" : "UCLH PIXL",
   "Name" : "${ORTHANC_NAME}",
   "RemoteAccessAllowed" : true,
   "RegisteredUsers": {
       "${ORTHANC_USERNAME}": "${ORTHANC_PASSWORD}"
-    }
+    },
+
+// Path to the directory that holds the heavyweight files (i.e. the
+  // raw DICOM instances). Backslashes must be either escaped by
+  // doubling them, or replaced by forward slashes "/".
+  "StorageDirectory" : "/var/lib/orthanc/db",
+
+  // Limit the maximum storage size
+  "MaximumPatientCount" : 0, // no limit
+  "MaximumStorageSize" : 100, // MB
+  "MaximumStorageMode" : "Recycle",
+  // Enable concurrency
+  "JobsHistorySize": 100,
+  "ConcurrentJobs" : 20,
+  // overwrite instances with the same UID if we get them for a second time
+  "OverwriteInstances" : true,
+    "StableAge" : 30,
+  // Defines the number of threads that are used to execute each type of
+  // jobs (for the jobs that can be parallelized).
+  // A value of "0" indicates to use all the available CPU logical cores
+  "JobsEngineThreadsCount" : {
+    "ResourceModification": 5  // for /anonymize, /modify
+  }
+
 }
\ No newline at end of file
diff --git a/pixl_imaging/tests/test_imaging_processing.py b/pixl_imaging/tests/test_imaging_processing.py
index 24645e95d..b4821960e 100644
--- a/pixl_imaging/tests/test_imaging_processing.py
+++ b/pixl_imaging/tests/test_imaging_processing.py
@@ -16,38 +16,135 @@
 from __future__ import annotations
 
 import datetime
+import os
 import pathlib
 import shlex
+from typing import TYPE_CHECKING
 
 import pytest
+from core.exceptions import PixlDiscardError, PixlOutOfHoursError, PixlStudyNotInPrimaryArchiveError
 from core.patient_queue.message import Message
 from decouple import config
 from pixl_imaging._orthanc import Orthanc, PIXLRawOrthanc
-from pixl_imaging._processing import ImagingStudy, process_message
+from pixl_imaging._processing import DicomModality, ImagingStudy, process_message
 from pydicom import dcmread
 from pydicom.data import get_testdata_file
+from pydicom.uid import generate_uid
+from pytest_check import check
 from pytest_pixl.helpers import run_subprocess
 
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+
 pytest_plugins = ("pytest_asyncio",)
 
 ACCESSION_NUMBER = "abc"
 PATIENT_ID = "a_patient"
-message = Message(
-    mrn=PATIENT_ID,
-    accession_number=ACCESSION_NUMBER,
-    study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
-        tzinfo=datetime.timezone.utc
-    ),
-    procedure_occurrence_id=234,
-    project_name="test project",
-    extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
-)
+STUDY_UID = generate_uid(entropy_srcs=["12345678"])
+SERIES_UID = generate_uid(entropy_srcs=["12345678.1"])
+SOP_INSTANCE_UID = "1.1.1.1.1.1.1111.1.1.1.1.1.11111111111111.11111"
+SOP_INSTANCE_UID_2 = "2.2.2.2.2.2.2222.2.2.2.2.2.22222222222222.22222"
+
+PACS_ACCESSION_NUMBER = "def"
+PACS_PATIENT_ID = "another_patient"
+PACS_STUDY_UID = "87654321"
+
+MISSING_ACCESSION_NUMBER = "ghi"
+MISSING_PATIENT_ID = "missing_patient"
+MISSING_STUDY_UID = "00000000"
+
+
+@pytest.fixture(scope="module")
+def message() -> Message:
+    """A Message with a valid study_uid."""
+    return Message(
+        mrn=PATIENT_ID,
+        accession_number=ACCESSION_NUMBER,
+        study_uid=STUDY_UID,
+        study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
+            tzinfo=datetime.timezone.utc
+        ),
+        procedure_occurrence_id=234,
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
+    )
+
+
+@pytest.fixture(scope="module")
+def no_uid_message() -> Message:
+    """A Message with a valid study_uid."""
+    return Message(
+        mrn=PATIENT_ID,
+        accession_number=ACCESSION_NUMBER,
+        study_uid="",
+        study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
+            tzinfo=datetime.timezone.utc
+        ),
+        procedure_occurrence_id=234,
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
+    )
+
+
+@pytest.fixture(scope="module")
+def pacs_message() -> Message:
+    """A Message with a valid study_uid for a study that exists in PACS but not VNA."""
+    return Message(
+        mrn=PACS_PATIENT_ID,
+        accession_number=PACS_ACCESSION_NUMBER,
+        study_uid=PACS_STUDY_UID,
+        study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
+            tzinfo=datetime.timezone.utc
+        ),
+        procedure_occurrence_id=234,
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
+    )
+
+
+@pytest.fixture(scope="module")
+def pacs_no_uid_message() -> Message:
+    """A Message without a valid study_uid for a study that exists in PACS but not the VNA."""
+    return Message(
+        mrn=PACS_PATIENT_ID,
+        accession_number=PACS_ACCESSION_NUMBER,
+        study_uid="ialsodontexist",
+        study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
+            tzinfo=datetime.timezone.utc
+        ),
+        procedure_occurrence_id=234,
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
+    )
+
+
+@pytest.fixture(scope="module")
+def missing_message() -> Message:
+    """A Message for a study that does not exist in PACS nor the VNA."""
+    return Message(
+        mrn=MISSING_PATIENT_ID,
+        accession_number=MISSING_ACCESSION_NUMBER,
+        study_uid=MISSING_STUDY_UID,
+        study_date=datetime.datetime.strptime("01/01/1234 01:23:45", "%d/%m/%Y %H:%M:%S").replace(
+            tzinfo=datetime.timezone.utc
+        ),
+        procedure_occurrence_id=345,
+        project_name="test project",
+        extract_generated_timestamp=datetime.datetime.fromisoformat("1234-01-01 00:00:00"),
+    )
 
 
 class WritableOrthanc(Orthanc):
-    @property
-    def aet(self) -> str:
-        return "VNAQR"
+    def __init__(self, url: str, username: str, password: str, aet: str) -> None:
+        super().__init__(
+            url=url,
+            username=username,
+            password=password,
+            http_timeout=config("PIXL_QUERY_TIMEOUT", cast=int),
+            dicom_timeout=config("PIXL_DICOM_TRANSFER_TIMEOUT", cast=int),
+            aet=aet,
+        )
 
     def upload(self, filename: str) -> None:
         run_subprocess(
@@ -59,21 +156,61 @@ def upload(self, filename: str) -> None:
 
 
 @pytest.fixture(scope="module")
-def _add_image_to_fake_vna(run_containers) -> None:
+def _add_image_to_fake_vna(run_containers) -> Generator[None]:
     """Add single fake image to VNA."""
+    vna = WritableOrthanc(
+        aet="PRIMARYQR",
+        url=config("ORTHANC_VNA_URL"),
+        username=config("ORTHANC_VNA_USERNAME"),
+        password=config("ORTHANC_VNA_PASSWORD"),
+    )
+
     image_filename = "test.dcm"
-    path = get_testdata_file("CT_small.dcm")
+    path = str(get_testdata_file("CT_small.dcm"))
     ds = dcmread(path)
     ds.AccessionNumber = ACCESSION_NUMBER
     ds.PatientID = PATIENT_ID
+    ds.StudyInstanceUID = STUDY_UID
+    ds.SeriesInstanceUID = SERIES_UID
+    ds.SOPInstanceUID = SOP_INSTANCE_UID
     ds.save_as(image_filename)
 
     vna = WritableOrthanc(
+        aet="PRIMARYQR",
         url=config("ORTHANC_VNA_URL"),
         username=config("ORTHANC_VNA_USERNAME"),
         password=config("ORTHANC_VNA_PASSWORD"),
     )
     vna.upload(image_filename)
+
+    instance_2_image_filename = "test_2.dcm"
+    ds.SOPInstanceUID = SOP_INSTANCE_UID_2
+    ds.save_as(instance_2_image_filename)
+    vna.upload(instance_2_image_filename)
+
+    yield
+    pathlib.Path(image_filename).unlink(missing_ok=True)
+    pathlib.Path(instance_2_image_filename).unlink(missing_ok=True)
+
+
+@pytest.fixture(scope="module")
+def _add_image_to_fake_pacs(run_containers) -> Generator[None]:
+    """Add single fake image to PACS."""
+    image_filename = "test-mr.dcm"
+    path = str(get_testdata_file("MR_small.dcm"))
+    ds = dcmread(path)
+    ds.AccessionNumber = PACS_ACCESSION_NUMBER
+    ds.PatientID = PACS_PATIENT_ID
+    ds.StudyInstanceUID = PACS_STUDY_UID
+    ds.save_as(image_filename)
+
+    pacs = WritableOrthanc(
+        aet="SECONDARYQR",
+        url=config("ORTHANC_PACS_URL"),
+        username=config("ORTHANC_PACS_USERNAME"),
+        password=config("ORTHANC_PACS_PASSWORD"),
+    )
+    pacs.upload(image_filename)
     yield
     pathlib.Path(image_filename).unlink(missing_ok=True)
 
@@ -93,7 +230,7 @@ async def orthanc_raw(run_containers) -> PIXLRawOrthanc:
 @pytest.mark.processing()
 @pytest.mark.asyncio()
 @pytest.mark.usefixtures("_add_image_to_fake_vna")
-async def test_image_saved(orthanc_raw) -> None:
+async def test_image_saved(orthanc_raw, message: Message) -> None:
     """
     Given the VNA has images, and orthanc raw has no images
     When we run process_message
@@ -104,14 +241,75 @@ async def test_image_saved(orthanc_raw) -> None:
     orthanc = await orthanc_raw
 
     assert not await study.query_local(orthanc)
-    await process_message(message)
+    await process_message(message, archive=DicomModality.primary)
+
+    studies = await study.query_local(orthanc)
+    assert len(studies) == 1
+
+    study_info = await orthanc._get(f"/studies/{studies[0]}")
+    with check:
+        assert study_info["MainDicomTags"]["AccessionNumber"] == ACCESSION_NUMBER
+        assert study_info["PatientMainDicomTags"]["PatientID"] == PATIENT_ID
+        assert study_info["MainDicomTags"]["StudyInstanceUID"] == STUDY_UID
+
+    series_info = await orthanc._get(f"/series/{study_info['Series'][0]}")
+    with check:
+        assert series_info["MainDicomTags"]["SeriesInstanceUID"] == SERIES_UID
+
+    instance_info = await orthanc._get(f"/instances/{series_info['Instances'][0]}")
+    with check:
+        assert instance_info["MainDicomTags"]["SOPInstanceUID"] in (
+            SOP_INSTANCE_UID,
+            SOP_INSTANCE_UID_2,
+        )
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+@pytest.mark.usefixtures("_add_image_to_fake_vna")
+async def test_partial_retrieve(orthanc_raw, message: Message, caplog) -> None:
+    """
+    Given the VNA has a single study with 2 instances, and orthanc raw has the same study with
+    1 instance
+    When we run process_message
+    Then orthanc raw will contain both instances after retrieving only the missing instance
+    """
+    study = ImagingStudy.from_message(message)
+
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+    await process_message(message, archive=DicomModality.primary)
     assert await study.query_local(orthanc)
 
+    all_instances = await orthanc._get("/instances")
+    assert len(all_instances) == 2
+
+    instance_info = {}
+
+    with check:
+        for instance in all_instances:
+            instance_info = await orthanc._get(f"/instances/{instance}")
+            sop_instance_uid = instance_info["MainDicomTags"]["SOPInstanceUID"]
+            assert sop_instance_uid in (SOP_INSTANCE_UID, SOP_INSTANCE_UID_2)
+
+    await orthanc.delete(f"/instances/{instance_info['ID']}")
+
+    await process_message(message, archive=DicomModality.primary)
+    all_instances = await orthanc._get("/instances")
+    assert len(all_instances) == 2
+
+    expected_msg = (
+        f"Instance {instance_info['MainDicomTags']['SOPInstanceUID']}"
+        f" is missing from study {STUDY_UID}"
+    )
+    assert expected_msg in caplog.text
+
 
 @pytest.mark.processing()
 @pytest.mark.asyncio()
 @pytest.mark.usefixtures("_add_image_to_fake_vna")
-async def test_existing_message_sent_twice(orthanc_raw) -> None:
+async def test_existing_message_sent_twice(orthanc_raw, message: Message) -> None:
     """
     Given the VNA has images, and orthanc raw has no images
     When we run process_message on the same message twice
@@ -120,16 +318,237 @@ async def test_existing_message_sent_twice(orthanc_raw) -> None:
     study = ImagingStudy.from_message(message)
     orthanc = await orthanc_raw
 
-    await process_message(message)
+    await process_message(message, archive=DicomModality.primary)
     assert await study.query_local(orthanc)
 
     query_for_update_time = {**study.orthanc_query_dict, "Expand": True}
     first_processing_resource = await orthanc.query_local(query_for_update_time)
     assert len(first_processing_resource) == 1
 
-    await process_message(message)
+    await process_message(message, archive=DicomModality.primary)
     second_processing_resource = await orthanc.query_local(query_for_update_time)
     assert len(second_processing_resource) == 1
 
     # Check update time hasn't changed
     assert first_processing_resource[0]["LastUpdate"] == second_processing_resource[0]["LastUpdate"]
+
+    studies = await study.query_local(orthanc)
+    assert len(studies) == 1
+
+    study_info = await orthanc._get(f"/studies/{studies[0]}")
+    with check:
+        assert study_info["MainDicomTags"]["AccessionNumber"] == ACCESSION_NUMBER
+        assert study_info["PatientMainDicomTags"]["PatientID"] == PATIENT_ID
+        assert study_info["MainDicomTags"]["StudyInstanceUID"] == STUDY_UID
+
+    series_info = await orthanc._get(f"/series/{study_info['Series'][0]}")
+    with check:
+        assert series_info["MainDicomTags"]["SeriesInstanceUID"] == SERIES_UID
+
+    instance_info = await orthanc._get(f"/instances/{series_info['Instances'][0]}")
+    with check:
+        assert instance_info["MainDicomTags"]["SOPInstanceUID"] in (
+            SOP_INSTANCE_UID,
+            SOP_INSTANCE_UID_2,
+        )
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+@pytest.mark.usefixtures("_add_image_to_fake_vna")
+async def test_querying_without_uid(orthanc_raw, caplog, no_uid_message: Message) -> None:
+    """
+    Given a message with non-existent study_uid
+    When we query the VNA
+    Then the querying falls back to using the MRN and accession number
+    """
+    study = ImagingStudy.from_message(no_uid_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+    await process_message(no_uid_message, archive=DicomModality.primary)
+    assert await study.query_local(orthanc)
+
+    expected_msg = (
+        f"No study found in modality UCPRIMARYQR with UID '{study.message.study_uid}', "
+        "trying MRN and accession number"
+    )
+    assert expected_msg in caplog.text
+
+
+class Monday2AM(datetime.datetime):
+    @classmethod
+    def now(cls, tz=None) -> datetime.datetime:
+        return cls(2024, 1, 1, 2, 0, tzinfo=tz)
+
+
+class Monday11AM(datetime.datetime):
+    @classmethod
+    def now(cls, tz=None) -> datetime.datetime:
+        return cls(2024, 1, 1, 11, 0, tzinfo=tz)
+
+
+class Saturday2AM(datetime.datetime):
+    @classmethod
+    def now(cls, tz=None) -> datetime.datetime:
+        return datetime.datetime(2024, 1, 6, 2, 0, tzinfo=tz)
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+@pytest.mark.usefixtures("_add_image_to_fake_pacs")
+async def test_querying_pacs_with_uid(
+    orthanc_raw, caplog, monkeypatch, pacs_message: Message
+) -> None:
+    """
+    Given a message with study_uid exists in PACS but not VNA,
+    When we query the archives
+    Then the querying finds the study in PACS with the study_uid
+    """
+    study = ImagingStudy.from_message(pacs_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+
+    # PACS is not queried during the daytime nor at the weekend.
+    # Set today to be a Monday at 2 am.
+    with monkeypatch.context() as mp:
+        mp.setattr(datetime, "datetime", Monday2AM)
+        match = "sending message to secondary imaging queue."
+        with pytest.raises(PixlStudyNotInPrimaryArchiveError, match=match):
+            await process_message(pacs_message, archive=DicomModality.primary)
+        await process_message(pacs_message, archive=DicomModality.secondary)
+
+    assert await study.query_local(orthanc)
+
+    expected_msg = (
+        f"No study found in modality UCPRIMARYQR with UID '{study.message.study_uid}', "
+        "trying MRN and accession number"
+    )
+    assert expected_msg in caplog.text
+
+    unexpected_msg = (
+        f"No study found in modality UCSECONDARYQR with UID '{study.message.study_uid}', "
+        "trying MRN and accession number"
+    )
+    assert unexpected_msg not in caplog.text
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+@pytest.mark.usefixtures("_add_image_to_fake_pacs")
+async def test_querying_pacs_without_uid(
+    orthanc_raw, caplog, monkeypatch, pacs_no_uid_message: Message
+) -> None:
+    """
+    Given a message with non-existent study_uid exists in PACS but not VNA,
+    When we query the archives
+    Then the querying falls back to using the MRN and accession number and finds the study in PACS
+    """
+    study = ImagingStudy.from_message(pacs_no_uid_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+
+    # PACS is not queried during the daytime nor at the weekend.
+    # Set today to be a Monday at 2 am.
+    with monkeypatch.context() as mp:
+        mp.setattr(datetime, "datetime", Monday2AM)
+        match = "sending message to secondary imaging queue."
+        with pytest.raises(PixlStudyNotInPrimaryArchiveError, match=match):
+            await process_message(pacs_no_uid_message, archive=DicomModality.primary)
+        await process_message(pacs_no_uid_message, archive=DicomModality.secondary)
+
+    assert await study.query_local(orthanc)
+
+    expected_msg = "No study found in modality UCPRIMARYQR with UID"
+    assert expected_msg in caplog.text
+
+    expected_msg = (
+        f"No study found in modality UCSECONDARYQR with UID '{study.message.study_uid}', "
+        "trying MRN and accession number"
+    )
+    assert expected_msg in caplog.text
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+async def test_querying_missing_image(orthanc_raw, monkeypatch, missing_message: Message) -> None:
+    """
+    Given a message for a study that is missing in both the VNA and PACS,
+    When we query the archives within the window of Monday-Friday 8pm to 8am,
+    Then the querying tries both the VNA and PACS and raises a PixlDiscardError
+    """
+    study = ImagingStudy.from_message(missing_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+
+    # PACS is not queried during the daytime nor at the weekend.
+    # Set today to be a Monday at 2 am.
+    primary_match = "sending message to secondary imaging queue."
+    secondary_match = "Failed to find study .* in primary or secondary archive."
+    with (  # noqa: PT012
+        monkeypatch.context() as mp,
+        pytest.raises(PixlStudyNotInPrimaryArchiveError, match=primary_match),
+        pytest.raises(PixlDiscardError, match=secondary_match),
+    ):
+        mp.setattr(datetime, "datetime", Monday2AM)
+        await process_message(missing_message, archive=DicomModality.primary)
+        await process_message(missing_message, archive=DicomModality.secondary)
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+@pytest.mark.parametrize(
+    "query_date",
+    [
+        (Monday11AM),
+        (Saturday2AM),
+    ],
+)
+async def test_querying_pacs_during_working_hours(
+    orthanc_raw, query_date, monkeypatch, missing_message: Message
+) -> None:
+    """
+    Given a message for a study that is missing in both the VNA and PACS,
+    When we query the archives outside of Monday-Friday 8pm-8am,
+    Then the querying tries only the VNA and raises a PixlDiscardError
+    """
+    study = ImagingStudy.from_message(missing_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+
+    match = "Not querying secondary archive during the daytime or on the weekend."
+    with monkeypatch.context() as mp, pytest.raises(PixlOutOfHoursError, match=match):  # noqa: PT012
+        mp.setattr(datetime, "datetime", query_date)
+        await process_message(missing_message, archive=DicomModality.secondary)
+
+
+@pytest.mark.processing()
+@pytest.mark.asyncio()
+async def test_querying_pacs_not_defined(
+    orthanc_raw, monkeypatch, missing_message: Message
+) -> None:
+    """
+    Given a message for a study that is missing in the VNA and the SECONDARY_DICOM_SOURCE_AE_TITLE
+    is the same as the PRIMARY_DICOM_SOURCE_AE_TITLE
+    When we query the archive,
+    Then the querying tries the VNA and then raises a PixlDiscardError
+    """
+    study = ImagingStudy.from_message(missing_message)
+    orthanc = await orthanc_raw
+
+    assert not await study.query_local(orthanc)
+
+    match = (
+        "Failed to find study .* in primary archive "
+        "and SECONDARY_DICOM_SOURCE_AE_TITLE is the same as PRIMARY_DICOM_SOURCE_AE_TITLE."
+    )
+    with (  # noqa: PT012
+        monkeypatch.context() as mp,
+        pytest.raises(PixlDiscardError, match=match),
+    ):
+        mp.setenv("SECONDARY_DICOM_SOURCE_AE_TITLE", os.environ["PRIMARY_DICOM_SOURCE_AE_TITLE"])
+        await process_message(missing_message, archive=DicomModality.primary)
diff --git a/projects/configs/ms-pinpoint-internal-only.yaml b/projects/configs/ms-pinpoint.yaml
similarity index 87%
rename from projects/configs/ms-pinpoint-internal-only.yaml
rename to projects/configs/ms-pinpoint.yaml
index 67247be86..a68258adf 100644
--- a/projects/configs/ms-pinpoint-internal-only.yaml
+++ b/projects/configs/ms-pinpoint.yaml
@@ -13,14 +13,15 @@
 #  limitations under the License.
 
 project:
-    name: "ms-pinpoint-internal-only"
+    name: "ms-pinpoint"
     modalities: ["MR"]
 
 tag_operation_files:
     base:
+        - "base.yaml" #Expected base config file for any project
         - "mri.yaml"
         - "ms-pinpoint.yaml"
-    manufacturer_overrides: null
+    manufacturer_overrides: ["mri.yaml"]
 
 series_filters:
     - "localizer"
diff --git a/projects/configs/prognosis-ai.yaml b/projects/configs/prognosis-ai.yaml
new file mode 100644
index 000000000..f1292856e
--- /dev/null
+++ b/projects/configs/prognosis-ai.yaml
@@ -0,0 +1,34 @@
+#  Copyright (c) 2024 University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+project:
+    name: "prognosis-ai"
+    modalities: ["MR"]
+
+tag_operation_files:
+    base:
+        - "base.yaml" #Expected base config file for any project
+        - "mri.yaml"
+        - "ion-neuro-db.yaml"
+    manufacturer_overrides: ["mri.yaml"]
+
+series_filters:
+    - "localizer"
+    - "localiser"
+    - "scout"
+    - "positioning"
+
+destination:
+    dicom: "none"
+    parquet: "none"
diff --git a/projects/configs/tag-operations/base.yaml b/projects/configs/tag-operations/base.yaml
new file mode 100644
index 000000000..d5271ab15
--- /dev/null
+++ b/projects/configs/tag-operations/base.yaml
@@ -0,0 +1,375 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+# Default `base.yaml` configuration file with commented links to their respective image modalities
+# `base.yaml` configuration file is expected to be part of all projects configuration files
+
+#################################### 0008 Group ###################################
+#
+#
+- name: "Specific Character Set"
+  group: 0x0008
+  element: 0x0005
+  op: "keep"
+#CT, MR, US, RT
+- name: "Image Type"
+  group: 0x0008
+  element: 0x0008
+  op: "keep"
+#CT, MR, US, RT
+- name: "Instance Creator UID"
+  group: 0x0008
+  element: 0x0014
+  op: "replace_UID"
+#CT, MR, US, RT
+- name: "SOP Class UID"
+  group: 0x0008
+  element: 0x0016
+  op: "keep"
+#CT, MR, US, RT
+- name: "SOP Instance UID"
+  group: 0x0008
+  element: 0x0018
+  op: "replace_UID"
+#CT, MR, US, RT
+- name: "Accession Number"
+  group: 0x0008
+  element: 0x0050
+  op: "replace"
+- name: "Study Date"
+  group: 0x0008
+  element: 0x0020
+  op: "replace"
+- name: "General Study"
+  group: 0x0008
+  element: 0x0030
+  op: "replace"
+- name: "Modality"
+  group: 0x0008
+  element: 0x0060
+  op: "keep"
+- name: "Modalities In Study"
+  group: 0x0008
+  element: 0x0061
+  op: "keep"
+- name: "Manufacturer"
+  group: 0x0008
+  element: 0x0070
+  op: "keep"
+- name: "Referring Physician's Name"
+  group: 0x0008
+  element: 0x0090
+  op: "replace"
+- name: "Study Description"
+  group: 0x0008
+  element: 0x1030
+  op: "keep"
+- name: "Series Description"
+  group: 0x0008
+  element: 0x103e
+  op: "keep"
+- name: "Manufacturers Model Name"
+  group: 0x0008
+  element: 0x1090
+  op: "keep"
+- name: "Referenced Series Sequence"
+  group: 0x0008
+  element: 0x1155
+  op: "replace_UID"
+- name: "Referenced Frame Number"
+  group: 0x0008
+  element: 0x1160
+  op: "keep"
+- name: "Pixel Presentation"
+  group: 0x0008
+  element: 0x9205
+  op: "keep"
+#################################### 0010 Group ###################################
+#
+#
+- name: "Patients Name"
+  group: 0x0010
+  element: 0x0010
+  op: "replace"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Patient ID"
+  group: 0x0010
+  element: 0x0020
+  op: "secure-hash"
+- name: "Patient's Birth Date"
+  group: 0x0010
+  element: 0x0030
+  op: "replace"
+- name: "Patient's Sex"
+  group: 0x0010
+  element: 0x0040
+  op: "keep"
+#################################### 0013 Group ###################################
+- name: "VR OB Creator"
+  group: 0x0013
+  element: 0x0010
+  op: "keep"
+- name: "VR OB sequence"
+  group: 0x0013
+  element: 0x1010
+  op: "replace"
+#################################### 0018 Group ###################################
+#
+#
+- name: "Scan Options Attribute"
+  group: 0x0018
+  element: 0x0022
+  op: "replace"
+#CT, MR, X-Ray
+- name: "Software Version"
+  group: 0x0018
+  element: 0x1020
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Focal Spot"
+  group: 0x0018
+  element: 0x1190
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Patient Position"
+  group: 0x0018
+  element: 0x5100
+  op: "replace"
+#CT, MR, PET, US, X-Ray, and RT Images
+#################################### 0020 Group ###################################
+#
+#
+- name: "Study Instance UID"
+  group: 0x0020
+  element: 0x000d
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Series Instance UID"
+  group: 0x0020
+  element: 0x000e
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Study ID"
+  group: 0x0020
+  element: 0x0010
+  op: "replace"
+#CT, MR, US, and RT Images
+- name: "Series Number"
+  group: 0x0020
+  element: 0x0011
+  op: "keep"
+#RT Image
+- name: "Acquisition Number"
+  group: 0x0020
+  element: 0x0012
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Instance Number"
+  group: 0x0020
+  element: 0x0013
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Patient Orientation"
+  group: 0x0020
+  element: 0x0020
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Image Position (Patient)"
+  group: 0x0020
+  element: 0x0032
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Image Orientation (Patient)"
+  group: 0x0020
+  element: 0x0037
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Image Laterality"
+  group: 0x0020
+  element: 0x0062
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Frame of Reference UID"
+  group: 0x0020
+  element: 0x0052
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Synchronization Frame of Reference UID"
+  group: 0x0020
+  element: 0x0200
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Position Reference Indicator"
+  group: 0x0020
+  element: 0x1040
+  op: "replace"
+#CT, MR, PET, US, X-Ray, and RT Images
+#################################### 0028 Group ###################################
+#
+#
+- name: "Samples Per Pixel"
+  group: 0x0028
+  element: 0x0002
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Photometric Interpretation"
+  group: 0x0028
+  element: 0x0004
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Planar Configuration"
+  group: 0x0028
+  element: 0x0006
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Rows"
+  group: 0x0028
+  element: 0x0010
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Columns"
+  group: 0x0028
+  element: 0x0011
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Pixel Spacing"
+  group: 0x0028
+  element: 0x0030
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Bits Allocated"
+  group: 0x0028
+  element: 0x0100
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Bits Stored"
+  group: 0x0028
+  element: 0x0101
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "High Bit"
+  group: 0x0028
+  element: 0x0102
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Pixel Representation"
+  group: 0x0028
+  element: 0x0103
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Burned In Annotation"
+  group: 0x0028
+  element: 0x0301
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Recognizable Visual Features"
+  group: 0x0028
+  element: 0x0302
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Window Center"
+  group: 0x0028
+  element: 0x1050
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Window Width"
+  group: 0x0028
+  element: 0x1051
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Rescale Intercept"
+  group: 0x0028
+  element: 0x1052
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Rescale Slope"
+  group: 0x0028
+  element: 0x1053
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Rescale Type"
+  group: 0x0028
+  element: 0x1054
+  op: "keep"
+#CT, MR, US, RT, X-ray
+- name: "Window Center And Width Explanation"
+  group: 0x0028
+  element: 0x1055
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Lossy Image Compression"
+  group: 0x0028
+  element: 0x2110
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "VOI LUT Sequence"
+  group: 0x0028
+  element: 0x3010
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+#################################### 0040 Group ###################################
+#
+#
+- name: "UID Attribute"
+  group: 0x0040
+  element: 0xA124
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+- name: "Real World Value Intercept"
+  group: 0x0040
+  element: 0x9224
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+- name: "Real World Value Slope"
+  group: 0x0040
+  element: 0x9225
+  op: "keep"
+#CT, MR, US, RT, PET, X-ray
+#################################### 0054 Group ###################################
+#
+#
+- name: "View Code Sequence"
+  group: 0x0054
+  element: 0x0220
+  op: "keep"
+#CT, MR, PET, US, X-Ray, and RT Images
+#################################### 0088 Group ###################################
+#
+#
+- name: "Storage Media File-set UID"
+  group: 0x0088
+  element: 0x0140
+  op: "replace_UID"
+#CT, MR, PET, US, X-Ray, and RT Images
+#################################### 3006 Group ###################################
+#
+#
+- name: "Referenced Frame of Reference UID"
+  group: 0x3006
+  element: 0x0024
+  op: "replace_UID"
+#RT
+- name: "Related Frame of Reference UID"
+  group: 0x3006
+  element: 0x00C2
+  op: "replace_UID"
+#NOTE cannot find any imaging for this one
+#################################### 7FE0 Group ###################################
+#
+#
+- name: "Pixel Data"
+  group: 0x7fe0
+  element: 0x0010
+  op: "keep"
+#CT, US, and RT Images
\ No newline at end of file
diff --git a/projects/configs/tag-operations/diffusion-weighted-mri.yaml b/projects/configs/tag-operations/diffusion-weighted-mri.yaml
index dbf64a449..ca80aabe4 100644
--- a/projects/configs/tag-operations/diffusion-weighted-mri.yaml
+++ b/projects/configs/tag-operations/diffusion-weighted-mri.yaml
@@ -12,7 +12,7 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-# Extra common public tags for diffusion weighted MRI
+# Common public tags for diffusion weighted MRI
 
 - name: "DiffusionGradientOrientation"
   group: 0x0018
diff --git a/pixl_dcmd/bin/run-tests.sh b/projects/configs/tag-operations/ion-neuro-db.yaml
old mode 100755
new mode 100644
similarity index 80%
rename from pixl_dcmd/bin/run-tests.sh
rename to projects/configs/tag-operations/ion-neuro-db.yaml
index 770867555..ad15c76cb
--- a/pixl_dcmd/bin/run-tests.sh
+++ b/projects/configs/tag-operations/ion-neuro-db.yaml
@@ -1,4 +1,3 @@
-#!/usr/bin/env bash
 #  Copyright (c) University College London Hospitals NHS Foundation Trust
 #
 #  Licensed under the Apache License, Version 2.0 (the "License");
@@ -12,10 +11,12 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-set -euxo pipefail
 
-BIN_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-PACKAGE_DIR="${BIN_DIR%/*}"
-cd "$PACKAGE_DIR"
+# Specific tag operations for ion-neuro-db project
+
+- name: "Acquisition Date"
+  group: 0x0008
+  element: 0x0022
+  op: "keep"
+
 
-pytest tests
diff --git a/projects/configs/tag-operations/manufacturer-overrides/mri-diffusion.yaml b/projects/configs/tag-operations/manufacturer-overrides/mri-diffusion.yaml
index 89bc1e2db..76d850e19 100644
--- a/projects/configs/tag-operations/manufacturer-overrides/mri-diffusion.yaml
+++ b/projects/configs/tag-operations/manufacturer-overrides/mri-diffusion.yaml
@@ -13,28 +13,45 @@
 #  limitations under the License.
 
 # Example tags obtained from https://github.com/rordenlab/dcm2niix/blob/master/Philips/README.md#diffusion-direction
+# https://www.documents.philips.com/doclib/enc/fetch/8554818/DICOM_Conformance_Statement_MR_Applications_on_IntelliSpace_Portal_V4.0.pdf
 - manufacturer: ^philips
   tags:
-    - group: 0x2001
+    - name: "Private Creator Group 2001"
+      group: 0x2001
+      element: 0x0010
+      op: "keep"
+    - name: "Private Creator Group 2001 (90)"
+      group: 0x2001
+      element: 0x0090
+      op: "keep"
+    - name: "Diffusion B-Factor"
+      group: 0x2001
       element: 0x1003
       op: "keep"
-    - name: "ScaleSlope" # may need to have this for all MRs rather than just DW?
+    - name: "Private Creator Group 2005"
       group: 0x2005
-      element: 0x100e
+      element: 0x0010
       op: "keep"
-    - group: 0x2005
+    - name: "Diffusion Direction RL"
+      group: 0x2005
       element: 0x10b0
       op: "keep"
-    - group: 0x2005
+    - name: "Diffusion Direction AP"
+      group: 0x2005
       element: 0x10b1
       op: "keep"
-    - group: 0x2005
+    - name: "Diffusion Direction FH"
+      group: 0x2005
       element: 0x10b2
       op: "keep"
 
 # Example tags obtained from https://github.com/rordenlab/dcm2niix/blob/master/Siemens/README.md#siemens-x-series
 - manufacturer: ^siemens
   tags:
+    - name: "SIEMENS MR HEADER private creator Group"
+      group: 0x0019
+      element: 0x0010
+      op: "keep"
     - name: "SiemensDiffusionBValue"
       group: 0x0019
       element: 0x100c
@@ -43,6 +60,14 @@
       group: 0x0019
       element: 0x100e
       op: "keep"
+    - name: "SIEMENS CSA HEADER private creator"
+      group: 0x0029
+      element: 0x0010
+      op: "keep"
+    - name: "SIEMENS MEDCOM HEADER2  private creator"
+      group: 0x0029
+      element: 0x0011
+      op: "keep"
     - name: "CSA Image Header Info"
       group: 0x0029
       element: 0x1010
diff --git a/projects/configs/tag-operations/manufacturer-overrides/mri.yaml b/projects/configs/tag-operations/manufacturer-overrides/mri.yaml
new file mode 100644
index 000000000..d3ad9c4d0
--- /dev/null
+++ b/projects/configs/tag-operations/manufacturer-overrides/mri.yaml
@@ -0,0 +1,41 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+# https://www.documents.philips.com/doclib/enc/fetch/8554818/DICOM_Conformance_Statement_MR_Applications_on_IntelliSpace_Portal_V4.0.pdf
+- manufacturer: ^philips
+  tags:
+    - name: "Private Creator Group 2001"
+      group: 0x2001
+      element: 0x0010
+      op: "keep"
+    - name: "Private Creator Group 2001 (90)"
+      group: 0x2001
+      element: 0x0090
+      op: "keep"
+    - name: "Flip angle" # public version can have rounding issues
+      group: 0x2001
+      element: 0x1023
+      op: "keep"
+    - name: "Private Creator Group 2005"
+      group: 0x2005
+      element: 0x0010
+      op: "keep"
+    - name: "Scale Slope"
+      group: 0x2005
+      element: 0x100e
+      op: "keep"
+    - name: "Repetition Time" # public version can have rounding issues
+      group: 0x2005
+      element: 0x1030
+      op: "keep"
\ No newline at end of file
diff --git a/projects/configs/tag-operations/mr-spectroscopy.yaml b/projects/configs/tag-operations/mr-spectroscopy.yaml
new file mode 100644
index 000000000..5042d9979
--- /dev/null
+++ b/projects/configs/tag-operations/mr-spectroscopy.yaml
@@ -0,0 +1,190 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+- name: Device Serial Number
+  group: 0x0018
+  element: 0x1000
+  op: keep
+- name: Content Qualification
+  group: 0x0018
+  element: 0x9004
+  op: keep
+- name: Pulse Sequence Name
+  group: 0x0018
+  element: 0x9005
+  op: keep
+- name: Echo Pulse Sequence
+  group: 0x0018
+  element: 0x9008
+  op: keep
+- name: Multi-planar Excitation
+  group: 0x0018
+  element: 0x9012
+  op: keep
+- name: Steady State Pulse Sequence
+  group: 0x0018
+  element: 0x9017
+  op: keep
+- name: Echo Planar Pulse Sequence
+  group: 0x0018
+  element: 0x9018
+  op: keep
+- name: Spectrally Selected Suppression
+  group: 0x0018
+  element: 0x9025
+  op: keep
+- name: Geometry of k-Space Traversal
+  group: 0x0018
+  element: 0x9032
+  op: keep
+- name: Segmented k-Space Traversal
+  group: 0x0018
+  element: 0x9033
+  op: keep
+- name: Spectral Width
+  group: 0x0018
+  element: 0x9052
+  op: keep
+- name: Chemical Shift Reference
+  group: 0x0018
+  element: 0x9053
+  op: keep
+- name: Volume Localization Technique
+  group: 0x0018
+  element: 0x9054
+  op: keep
+- name: De-coupling
+  group: 0x0018
+  element: 0x9059
+  op: keep
+- name: k-space Filtering
+  group: 0x0018
+  element: 0x9064
+  op: keep
+- name: Time Domain Filtering
+  group: 0x0018
+  element: 0x9065
+  op: keep
+- name: Number of Zero Fills
+  group: 0x0018
+  element: 0x9066
+  op: keep
+- name: Baseline Correction
+  group: 0x0018
+  element: 0x9067
+  op: keep
+- name: Acquisition Duration
+  group: 0x0018
+  element: 0x9073
+  op: keep
+- name: Number of k-Space Trajectories
+  group: 0x0018
+  element: 0x9093
+  op: keep
+- name: Transmitter Frequency
+  group: 0x0018
+  element: 0x9098
+  op: keep
+- name: Resonant Nucleus
+  group: 0x0018
+  element: 0x9100
+  op: keep
+- name: Frequency Correction
+  group: 0x0018
+  element: 0x9101
+  op: keep
+- name: Slab Thickness
+  group: 0x0018
+  element: 0x9104
+  op: keep
+- name: Slab Orientation
+  group: 0x0018
+  element: 0x9105
+  op: keep
+- name: Mid Slab Position
+  group: 0x0018
+  element: 0x9106
+  op: keep
+- name: Multiple Spin Echo
+  group: 0x0018
+  element: 0x9011
+  op: keep
+- name: Volume Localization Sequence
+  group: 0x0018
+  element: 0x9126
+  op: keep
+- name: Applicable Safety Standard Agency
+  group: 0x0018
+  element: 0x9174
+  op: keep
+- name: First Order Phase Correction
+  group: 0x0018
+  element: 0x9198
+  op: keep
+- name: Water Referenced Phase Correction
+  group: 0x0018
+  element: 0x9199
+  op: keep
+- name: MR Spectroscopy Acquisition Type
+  group: 0x0018
+  element: 0x9200
+  op: keep
+- name: Dimension Organization UID
+  group: 0x0020
+  element: 0x9164
+  op: keep
+- name: Dimension Index Pointer
+  group: 0x0020
+  element: 0x9165
+  op: keep
+- name: Dimension Organization Sequence
+  group: 0x0020
+  element: 0x9221
+  op: keep
+- name: Dimension Index Sequence
+  group: 0x0020
+  element: 0x9222
+  op: keep
+- name: Number of Frames
+  group: 0x0028
+  element: 0x0008
+  op: keep
+- name: Data Point Rows
+  group: 0x0028
+  element: 0x9001
+  op: keep
+- name: Data Point Columns
+  group: 0x0028
+  element: 0x9002
+  op: keep
+- name: Signal Domain Columns
+  group: 0x0028
+  element: 0x9003
+  op: keep
+- name: Data Representation
+  group: 0x0028
+  element: 0x9108
+  op: keep
+- name: Acquisition Context Sequence
+  group: 0x0040
+  element: 0x0555
+  op: keep
+- name: Shared Functional Groups Sequence
+  group: 0x5200
+  element: 0x9229
+  op: keep
+- name: Spectroscopy Data
+  group: 0x5600
+  element: 0x0020
+  op: keep
diff --git a/projects/configs/tag-operations/mri.yaml b/projects/configs/tag-operations/mri.yaml
index d5f3b7140..77415f15f 100644
--- a/projects/configs/tag-operations/mri.yaml
+++ b/projects/configs/tag-operations/mri.yaml
@@ -12,81 +12,31 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-# Default configuration for Standard MR Image
+# Default configuration for Standard MR Image with commented links of resepctive tags
+# See further details at:
+# https://dicom.innolitics.com/ciods/mr-image
+# https://dicom.nema.org/medical/dicom/current/output/chtml/part03/sect_A.4.3.html#table_A.4-1
 
-- name: "Private Creator Data Element"
-  group: 0x000d
-  element: 0x0010
-  op: "keep"
-- name: "UCLH Project Name"
-  group: 0x000d
-  element: 0x1001
-  op: "keep"
-- name: "Specific Character Set"
-  group: 0x0008
-  element: 0x0005
-  op: "keep"
-- name: "Image Type"
-  group: 0x0008
-  element: 0x0008
-  op: "keep"
-- name: "Instance Creator UID"
-  group: 0x0008
-  element: 0x0014
-  op: "replace_UID"
-- name: "SOP Class UID"
-  group: 0x0008
-  element: 0x0016
-  op: "keep"
-- name: "SOP Instance UID"
-  group: 0x0008
-  element: 0x0018
-  op: "replace_UID"
-- name: "Accession Number"
-  group: 0x0008
-  element: 0x0050
-  op: "replace"
-- name: "Modality"
-  group: 0x0008
-  element: 0x0060
-  op: "keep"
-- name: "Modalities In Study"
-  group: 0x0008
-  element: 0x0061
-  op: "keep"
-- name: "Manufacturer"
-  group: 0x0008
-  element: 0x0070
-  op: "keep"
-- name: "Study Description"
-  group: 0x0008
-  element: 0x1030
-  op: "keep"
-- name: "Series Description"
-  group: 0x0008
-  element: 0x103e
-  op: "keep"
-- name: "Manufacturers Model Name"
-  group: 0x0008
-  element: 0x1090
-  op: "keep"
-- name: "Referenced Series Sequence"
+################################### 0008 Group ###################################
+#
+#
+- name: Acquisition DateTime
   group: 0x0008
-  element: 0x1155
-  op: "replace_UID"
-- name: "Referenced Frame Number"
+  element: 0x002A
+  op: replace
+- name: Content Date
   group: 0x0008
-  element: 0x1160
-  op: "keep"
-- name: "Pixel Presentation"
+  element: 0x0023
+  op: replace
+- name: Content Time
   group: 0x0008
-  element: 0x9205
-  op: "keep"
+  element: 0x0033
+  op: replace
 - name: "Volumetric Properties"
   group: 0x0008
   element: 0x9206
   op: "keep"
-- name: "Volume Based Calculation Technique Attribute"
+- name: "Volume Based Calculation Technique"
   group: 0x0008
   element: 0x9207
   op: "keep"
@@ -98,14 +48,9 @@
   group: 0x0008
   element: 0x9209
   op: "keep"
-- name: "Patients Name"
-  group: 0x0010
-  element: 0x0010
-  op: "replace"
-- name: "Patient ID"
-  group: 0x0010
-  element: 0x0020
-  op: "secure-hash"
+#################################### 0018 Group ###################################
+#
+#
 - name: "Scanning Sequence"
   group: 0x0018
   element: 0x0020
@@ -118,6 +63,9 @@
   group: 0x0018
   element: 0x0023
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00180023
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/mr-pulse-sequence/00180023
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/mr-pulse-sequence/00180023
 - name: "Sequence Name"
   group: 0x0018
   element: 0x0024
@@ -130,6 +78,8 @@
   group: 0x0018
   element: 0x0080
   op: "keep"
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009229/00189112/00180080
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189112/00180080
 - name: "Echo Time"
   group: 0x0018
   element: 0x0081
@@ -142,30 +92,42 @@
   group: 0x0018
   element: 0x0083
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00180083
+#https://dicom.innolitics.com/ciods/mr-spectroscopy/mr-spectroscopy-multi-frame-functional-groups/52009229/00189119/00180083
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009230/00189119/00180083
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189119/00180083
 - name: "Magnetic Field Strength"
   group: 0x0018
   element: 0x0087
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00180087
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image/00180087
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-image/00180087
+#https://dicom.innolitics.com/ciods/legacy-converted-enhanced-mr-image/enhanced-mr-image/00180087
 - name: "Spacing Between Slices"
   group: 0x0018
   element: 0x0088
   op: "keep"
+#https://dicom.innolitics.com/ciods/ct-image/image-plane/00180088
+#https://dicom.innolitics.com/ciods/mr-image/image-plane/00180088
+#https://dicom.innolitics.com/ciods/x-ray-3d-angiographic-image/x-ray-3d-angiographic-image-multi-frame-functional-groups/52009229/00289110/00180088
+#https://dicom.innolitics.com/ciods/x-ray-3d-craniofacial-image/x-ray-3d-craniofacial-image-multi-frame-functional-groups/52009229/00289110/00180088
 - name: "Echo train length"
   group: 0x0018
   element: 0x0091
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00180091
+#https://dicom.innolitics.com/ciods/mr-spectroscopy/mr-spectroscopy-multi-frame-functional-groups/52009229/00189112/00180091
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009229/00189112/00180091
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189112/00180091
 - name: "Percent Phase Field of View"
   group: 0x0018
   element: 0x0094
   op: "keep"
-- name: "Software Version"
-  group: 0x0018
-  element: 0x1020
-  op: "keep"
-- name: "Protocol Name"
-  group: 0x0018
-  element: 0x1030
-  op: "delete"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00180094
+#https://dicom.innolitics.com/ciods/mr-spectroscopy/mr-spectroscopy-multi-frame-functional-groups/52009229/00189103/00180094
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009229/00189125/00180094
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189125/00180094
 - name: "Field Of View Dimension"
   group: 0x0018
   element: 0x1149
@@ -178,207 +140,36 @@
   group: 0x0018
   element: 0x1166
   op: "keep"
-- name: "Focal Spot"
-  group: 0x0018
-  element: 0x1190
-  op: "keep"
 - name: "Receive Coil Name"
   group: 0x0018
   element: 0x1250
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00181250
+#https://dicom.innolitics.com/ciods/mr-spectroscopy/mr-spectroscopy-multi-frame-functional-groups/52009229/00189042/00181250
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009230/00189042/00181250
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189042/00181250
 - name: "Transmit Coil Name"
   group: 0x0018
   element: 0x1251
   op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00181251
+#https://dicom.innolitics.com/ciods/mr-spectroscopy/mr-spectroscopy-multi-frame-functional-groups/52009229/00189049/00181251
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009230/00189049/00181251
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189049/00181251
 - name: "Flip Angle"
   group: 0x0018
   element: 0x1314
   op: "keep"
-- name: "SAR"
-  group: 0x0018
-  element: 0x1316
-  op: "keep"
-- name: "Acquisition Device Processing Description"
-  group: 0x0018
-  element: 0x1400
-  op: "keep"
+#https://dicom.innolitics.com/ciods/mr-image/mr-image/00181314
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009230/00189112/00181314
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189112/00181314
 - name: "MR Acquisition Frequency Encoding Steps"
   group: 0x0018
   element: 0x9058
   op: "keep"
+#https://dicom.innolitics.com/ciods/enhanced-mr-image/enhanced-mr-image-multi-frame-functional-groups/52009230/00189125/00189058
+#https://dicom.innolitics.com/ciods/enhanced-mr-color-image/enhanced-mr-color-image-multi-frame-functional-groups/52009229/00189125/00189058
 - name: "MR Acquisition Phase Encoding Steps in-plane"
   group: 0x0018
   element: 0x9231
   op: "keep"
-- name: "Study Instance UID"
-  group: 0x0020
-  element: 0x000d
-  op: "replace_UID"
-- name: "Series Instance UID"
-  group: 0x0020
-  element: 0x000e
-  op: "replace_UID"
-- name: "Study ID"
-  group: 0x0020
-  element: 0x0010
-  op: "replace"
-- name: "Series Number"
-  group: 0x0020
-  element: 0x0011
-  op: "keep"
-- name: "Acquisition Number"
-  group: 0x0020
-  element: 0x0012
-  op: "keep"
-- name: "Instance Number"
-  group: 0x0020
-  element: 0x0013
-  op: "keep"
-- name: "Patient Orientation"
-  group: 0x0020
-  element: 0x0020
-  op: "keep"
-- name: "Image Position (Patient)"
-  group: 0x0020
-  element: 0x0032
-  op: "keep"
-- name: "Image Orientation (Patient)"
-  group: 0x0020
-  element: 0x0037
-  op: "keep"
-- name: "Image Laterality"
-  group: 0x0020
-  element: 0x0062
-  op: "keep"
-- name: "Frame of Reference UID"
-  group: 0x0020
-  element: 0x0052
-  op: "replace_UID"
-- name: "Synchronization Frame of Reference UID"
-  group: 0x0020
-  element: 0x0200
-  op: "replace_UID"
-- name: "Samples Per Pixel"
-  group: 0x0028
-  element: 0x0002
-  op: "keep"
-- name: "Photometric Interpretation"
-  group: 0x0028
-  element: 0x0004
-  op: "keep"
-- name: "Planar Configuration"
-  group: 0x0028
-  element: 0x0006
-  op: "keep"
-- name: "Rows"
-  group: 0x0028
-  element: 0x0010
-  op: "keep"
-- name: "Columns"
-  group: 0x0028
-  element: 0x0011
-  op: "keep"
-- name: "Pixel Spacing"
-  group: 0x0028
-  element: 0x0030
-  op: "keep"
-- name: "Bits Stored"
-  group: 0x0028
-  element: 0x0101
-  op: "keep"
-- name: "High Bit"
-  group: 0x0028
-  element: 0x0102
-  op: "keep"
-- name: "Pixel Representation"
-  group: 0x0028
-  element: 0x0103
-  op: "keep"
-- name: "Burned In Annotation"
-  group: 0x0028
-  element: 0x0301
-  op: "keep"
-- name: "Pixel Spacing Calibration Type"
-  group: 0x0028
-  element: 0x0a02
-  op: "keep"
-- name: "Pixel Spacing Calibration Description"
-  group: 0x0028
-  element: 0x0a04
-  op: "keep"
-- name: "Pixel Intensity Relationship"
-  group: 0x0028
-  element: 0x1040
-  op: "keep"
-- name: "Pixel Intensity Relationship Sign"
-  group: 0x0028
-  element: 0x1041
-  op: "keep"
-- name: "Window Center"
-  group: 0x0028
-  element: 0x1050
-  op: "keep"
-- name: "Window Width"
-  group: 0x0028
-  element: 0x1051
-  op: "keep"
-- name: "Rescale Intercept"
-  group: 0x0028
-  element: 0x1052
-  op: "keep"
-- name: "Rescale Slope"
-  group: 0x0028
-  element: 0x1053
-  op: "keep"
-- name: "Rescale Type"
-  group: 0x0028
-  element: 0x1054
-  op: "keep"
-- name: "Window Center And Width Explanation"
-  group: 0x0028
-  element: 0x1055
-  op: "keep"
-- name: "Lossy Image Compression"
-  group: 0x0028
-  element: 0x2110
-  op: "keep"
-- name: "VOI LUT Sequence"
-  group: 0x0028
-  element: 0x3010
-  op: "keep"
-- name: "Current Patient Location"
-  group: 0x0038
-  element: 0x0300
-  op: "delete"
-- name: "UID"
-  group: 0x0040
-  element: 0xA124
-  op: "replace_UID"
-- name: "Real World Value Intercept"
-  group: 0x0040
-  element: 0x9924
-  op: "replace_UID"
-- name: "Real World Value Slope"
-  group: 0x0040
-  element: 0x9925
-  op: "replace_UID"
-- name: "View Code Sequence"
-  group: 0x0054
-  element: 0x0220
-  op: "keep"
-- name: "Storage Media File-set UID"
-  group: 0x0088
-  element: 0x0140
-  op: "replace_UID"
-- name: "Referenced Frame of Reference UID"
-  group: 0x3006
-  element: 0x0024
-  op: "replace_UID"
-- name: "Related Frame of Reference UID"
-  group: 0x3006
-  element: 0x00C2
-  op: "replace_UID"
-- name: "Pixel Data"
-  group: 0x7fe0
-  element: 0x0010
-  op: "keep"
diff --git a/projects/configs/tag-operations/ms-pinpoint.yaml b/projects/configs/tag-operations/ms-pinpoint.yaml
index d69a84eeb..a64ee7e13 100644
--- a/projects/configs/tag-operations/ms-pinpoint.yaml
+++ b/projects/configs/tag-operations/ms-pinpoint.yaml
@@ -13,6 +13,7 @@
 #  limitations under the License.
 
 # Specific tag operations for ms-pinpoint project
+
 - name: "Acquisition Date"
   group: 0x0008
   element: 0x0022
diff --git a/projects/configs/tag-operations/test-external-user.yaml b/projects/configs/tag-operations/test-external-user.yaml
new file mode 100644
index 000000000..b979a95f8
--- /dev/null
+++ b/projects/configs/tag-operations/test-external-user.yaml
@@ -0,0 +1,408 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+# Configuration of Standard MR Image for external user
+
+- name: "Specific Character Set"
+  group: 0x0008
+  element: 0x0005
+  op: "keep"
+- name: "Image Type"
+  group: 0x0008
+  element: 0x0008
+  op: "keep"
+- name: "Instance Creator UID"
+  group: 0x0008
+  element: 0x0014
+  op: "replace_UID"
+- name: "SOP Class UID"
+  group: 0x0008
+  element: 0x0016
+  op: "keep"
+- name: "SOP Instance UID"
+  group: 0x0008
+  element: 0x0018
+  op: "replace_UID"
+- name: "Study Date"
+  group: 0x0008
+  element: 0x0020
+  op: "replace"
+- name: "Study Time"
+  group: 0x0008
+  element: 0x0030
+  op: "replace"
+- name: "Accession Number"
+  group: 0x0008
+  element: 0x0050
+  op: "replace"
+- name: "Modality"
+  group: 0x0008
+  element: 0x0060
+  op: "keep"
+- name: "Modalities In Study"
+  group: 0x0008
+  element: 0x0061
+  op: "keep"
+- name: "Manufacturer"
+  group: 0x0008
+  element: 0x0070
+  op: "keep"
+- name: "Referring Clinician's Name"
+  group: 0x0008
+  element: 0x0090
+  op: "replace"
+- name: "Study Description"
+  group: 0x0008
+  element: 0x1030
+  op: "keep"
+- name: "Series Description"
+  group: 0x0008
+  element: 0x103e
+  op: "keep"
+- name: "Manufacturers Model Name"
+  group: 0x0008
+  element: 0x1090
+  op: "keep"
+- name: "Referenced Series Sequence"
+  group: 0x0008
+  element: 0x1155
+  op: "replace_UID"
+- name: "Referenced Frame Number"
+  group: 0x0008
+  element: 0x1160
+  op: "keep"
+- name: "Pixel Presentation"
+  group: 0x0008
+  element: 0x9205
+  op: "keep"
+- name: "Volumetric Properties"
+  group: 0x0008
+  element: 0x9206
+  op: "keep"
+- name: "Volume Based Calculation Technique"
+  group: 0x0008
+  element: 0x9207
+  op: "keep"
+- name: "Complex Image Component"
+  group: 0x0008
+  element: 0x9208
+  op: "keep"
+- name: "Acquisition Contrast"
+  group: 0x0008
+  element: 0x9209
+  op: "keep"
+- name: "Patients Name"
+  group: 0x0010
+  element: 0x0010
+  op: "replace"
+- name: "Patient ID"
+  group: 0x0010
+  element: 0x0020
+  op: "replace"
+- name: "Patient's Birth Date"
+  group: 0x0010
+  element: 0x0030
+  op: "replace"
+- name: "Patient's Sex"
+  group: 0x0010
+  element: 0x0040
+  op: "keep"
+- name: "Scanning Sequence"
+  group: 0x0018
+  element: 0x0020
+  op: "keep"
+- name: "Sequence Variant"
+  group: 0x0018
+  element: 0x0021
+  op: "keep"
+- name: "Scan Options"
+  group: 0x0018
+  element: 0x0022
+  op: "keep"
+- name: "MR Acquisition Type"
+  group: 0x0018
+  element: 0x0023
+  op: "keep"
+- name: "Sequence Name"
+  group: 0x0018
+  element: 0x0024
+  op: "keep"
+- name: "Slice Thickness"
+  group: 0x0018
+  element: 0x0050
+  op: "keep"
+- name: "Repetition Time"
+  group: 0x0018
+  element: 0x0080
+  op: "keep"
+- name: "Echo Time"
+  group: 0x0018
+  element: 0x0081
+  op: "keep"
+- name: "Inversion Time"
+  group: 0x0018
+  element: 0x0082
+  op: "keep"
+- name: "Number of Averages"
+  group: 0x0018
+  element: 0x0083
+  op: "keep"
+- name: "Magnetic Field Strength"
+  group: 0x0018
+  element: 0x0087
+  op: "keep"
+- name: "Spacing Between Slices"
+  group: 0x0018
+  element: 0x0088
+  op: "keep"
+- name: "Echo train length"
+  group: 0x0018
+  element: 0x0091
+  op: "keep"
+- name: "Percent Phase Field of View"
+  group: 0x0018
+  element: 0x0094
+  op: "keep"
+- name: "Patient Position"
+  group: 0x0018
+  element: 0x5100
+  op: "keep"
+- name: "Software Version"
+  group: 0x0018
+  element: 0x1020
+  op: "keep"
+- name: "Field Of View Dimension"
+  group: 0x0018
+  element: 0x1149
+  op: "keep"
+- name: "Imager Pixel Spacing"
+  group: 0x0018
+  element: 0x1164
+  op: "keep"
+- name: "Grid"
+  group: 0x0018
+  element: 0x1166
+  op: "keep"
+- name: "Focal Spot"
+  group: 0x0018
+  element: 0x1190
+  op: "keep"
+- name: "Receive Coil Name"
+  group: 0x0018
+  element: 0x1250
+  op: "keep"
+- name: "Transmit Coil Name"
+  group: 0x0018
+  element: 0x1251
+  op: "keep"
+- name: "Flip Angle"
+  group: 0x0018
+  element: 0x1314
+  op: "keep"
+- name: "SAR"
+  group: 0x0018
+  element: 0x1316
+  op: "keep"
+- name: "Acquisition Device Processing Description"
+  group: 0x0018
+  element: 0x1400
+  op: "keep"
+- name: "MR Acquisition Frequency Encoding Steps"
+  group: 0x0018
+  element: 0x9058
+  op: "keep"
+- name: "MR Acquisition Phase Encoding Steps in-plane"
+  group: 0x0018
+  element: 0x9231
+  op: "keep"
+- name: "Study Instance UID"
+  group: 0x0020
+  element: 0x000d
+  op: "replace_UID"
+- name: "Series Instance UID"
+  group: 0x0020
+  element: 0x000e
+  op: "replace_UID"
+- name: "Study ID"
+  group: 0x0020
+  element: 0x0010
+  op: "replace"
+- name: "Series Number"
+  group: 0x0020
+  element: 0x0011
+  op: "keep"
+- name: "Acquisition Number"
+  group: 0x0020
+  element: 0x0012
+  op: "keep"
+- name: "Instance Number"
+  group: 0x0020
+  element: 0x0013
+  op: "keep"
+- name: "Patient Orientation"
+  group: 0x0020
+  element: 0x0020
+  op: "keep"
+- name: "Image Position (Patient)"
+  group: 0x0020
+  element: 0x0032
+  op: "keep"
+- name: "Image Orientation (Patient)"
+  group: 0x0020
+  element: 0x0037
+  op: "keep"
+- name: "Image Laterality"
+  group: 0x0020
+  element: 0x0062
+  op: "keep"
+- name: "Frame of Reference UID"
+  group: 0x0020
+  element: 0x0052
+  op: "replace_UID"
+- name: "Position Reference Indicator"
+  group: 0x0020
+  element: 0x1040
+  op: "keep"
+- name: "Synchronization Frame of Reference UID"
+  group: 0x0020
+  element: 0x0200
+  op: "replace_UID"
+- name: "Samples Per Pixel"
+  group: 0x0028
+  element: 0x0002
+  op: "keep"
+- name: "Photometric Interpretation"
+  group: 0x0028
+  element: 0x0004
+  op: "keep"
+- name: "Planar Configuration"
+  group: 0x0028
+  element: 0x0006
+  op: "keep"
+- name: "Rows"
+  group: 0x0028
+  element: 0x0010
+  op: "keep"
+- name: "Columns"
+  group: 0x0028
+  element: 0x0011
+  op: "keep"
+- name: "Pixel Spacing"
+  group: 0x0028
+  element: 0x0030
+  op: "keep"
+- name: "Bits Allocated"
+  group: 0x0028
+  element: 0x0100
+  op: "keep"
+- name: "Bits Stored"
+  group: 0x0028
+  element: 0x0101
+  op: "keep"
+- name: "High Bit"
+  group: 0x0028
+  element: 0x0102
+  op: "keep"
+- name: "Pixel Representation"
+  group: 0x0028
+  element: 0x0103
+  op: "keep"
+- name: "Burned In Annotation"
+  group: 0x0028
+  element: 0x0301
+  op: "keep"
+- name: "LUTDescriptor"
+  group: 0x0028
+  element: 0x0302
+  op: "keep"
+- name: "Pixel Spacing Calibration Type"
+  group: 0x0028
+  element: 0x0a02
+  op: "keep"
+- name: "Pixel Spacing Calibration Description"
+  group: 0x0028
+  element: 0x0a04
+  op: "keep"
+- name: "Pixel Intensity Relationship"
+  group: 0x0028
+  element: 0x1040
+  op: "keep"
+- name: "Pixel Intensity Relationship Sign"
+  group: 0x0028
+  element: 0x1041
+  op: "keep"
+- name: "Window Center"
+  group: 0x0028
+  element: 0x1050
+  op: "keep"
+- name: "Window Width"
+  group: 0x0028
+  element: 0x1051
+  op: "keep"
+- name: "Rescale Intercept"
+  group: 0x0028
+  element: 0x1052
+  op: "keep"
+- name: "Rescale Slope"
+  group: 0x0028
+  element: 0x1053
+  op: "keep"
+- name: "Rescale Type"
+  group: 0x0028
+  element: 0x1054
+  op: "keep"
+- name: "Window Center And Width Explanation"
+  group: 0x0028
+  element: 0x1055
+  op: "keep"
+- name: "Lossy Image Compression"
+  group: 0x0028
+  element: 0x2110
+  op: "keep"
+- name: "VOI LUT Sequence"
+  group: 0x0028
+  element: 0x3010
+  op: "keep"
+- name: "UID"
+  group: 0x0040
+  element: 0xA124
+  op: "replace_UID"
+- name: "Real World Value Intercept"
+  group: 0x0040
+  element: 0x9924
+  op: "replace_UID"
+- name: "Real World Value Slope"
+  group: 0x0040
+  element: 0x9925
+  op: "replace_UID"
+- name: "View Code Sequence"
+  group: 0x0054
+  element: 0x0220
+  op: "keep"
+- name: "Storage Media File-set UID"
+  group: 0x0088
+  element: 0x0140
+  op: "replace_UID"
+- name: "Referenced Frame of Reference UID"
+  group: 0x3006
+  element: 0x0024
+  op: "replace_UID"
+- name: "Related Frame of Reference UID"
+  group: 0x3006
+  element: 0x00C2
+  op: "replace_UID"
+- name: "Pixel Data"
+  group: 0x7fe0
+  element: 0x0010
+  op: "keep"
diff --git a/projects/configs/tag-operations/test-extract-uclh-omop-cdm.yaml b/projects/configs/tag-operations/test-extract-uclh-omop-cdm.yaml
index 54aed8f2f..f31e7af13 100644
--- a/projects/configs/tag-operations/test-extract-uclh-omop-cdm.yaml
+++ b/projects/configs/tag-operations/test-extract-uclh-omop-cdm.yaml
@@ -11,591 +11,14 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
-- name: "Specific Character Set"
-  group: 0x0008
-  element: 0x0005
-  op: "keep"
-- name: "Image Type"
-  group: 0x0008
-  element: 0x0008
-  op: "keep"
-- name: "SOP Class UID"
-  group: 0x0008
-  element: 0x0016
-  op: "keep"
-- name: "SOP Instance UID"
-  group: 0x0008
-  element: 0x0018
-  op: "replace_UID"
-- name: "Study Date"
-  group: 0x0008
-  element: 0x0020
-  op: "delete"
-- name: "Series Date"
-  group: 0x0008
-  element: 0x0021
-  op: "delete"
-- name: "Acquisition Date"
-  group: 0x0008
-  element: 0x0022
-  op: "delete"
-- name: "Image Date"
-  group: 0x0008
-  element: 0x0023
-  op: "delete"
-- name: "Acquisition Date Time"
-  group: 0x0008
-  element: 0x002a
-  op: "delete"
-- name: "Study Time"
-  group: 0x0008
-  element: 0x0030
-  op: "delete"
-- name: "Series Time"
-  group: 0x0008
-  element: 0x0031
-  op: "delete"
-- name: "Acquisition Time"
-  group: 0x0008
-  element: 0x0032
-  op: "delete"
-- name: "Image Time"
-  group: 0x0008
-  element: 0x0033
-  op: "delete"
-- name: "Accession Number"
-  group: 0x0008
-  element: 0x0050
-  op: "replace"
-- name: "Modality"
-  group: 0x0008
-  element: 0x0060
-  op: "keep"
-- name: "Modalities In Study"
-  group: 0x0008
-  element: 0x0061
-  op: "keep"
-- name: "Presentation Intent Type"
-  group: 0x0008
-  element: 0x0068
-  op: "delete"
-- name: "Manufacturer"
-  group: 0x0008
-  element: 0x0070
-  op: "keep"
-- name: "Institution Name"
-  group: 0x0008
-  element: 0x0080
-  op: "delete"
-- name: "Institution Address"
-  group: 0x0008
-  element: 0x0081
-  op: "delete"
-- name: "Referring Physicians Name"
-  group: 0x0008
-  element: 0x0090
-  op: "delete"
-- name: "Station Name"
-  group: 0x0008
-  element: 0x1010
-  op: "delete"
-- name: "Study Description"
-  group: 0x0008
-  element: 0x1030
-  op: "keep"
-- name: "Series Description"
-  group: 0x0008
-  element: 0x103e
-  op: "keep"
-- name: "Institutional Department Name"
-  group: 0x0008
-  element: 0x1040
-  op: "delete"
-- name: "Performing Physicians Name"
-  group: 0x0008
-  element: 0x1050
-  op: "delete"
-- name: "Operators Name"
-  group: 0x0008
-  element: 0x1070
-  op: "delete"
-- name: "Manufacturers Model Name"
-  group: 0x0008
-  element: 0x1090
-  op: "keep"
-- name: "Referenced Study Sequence"
-  group: 0x0008
-  element: 0x1110
-  op: "delete"
-- name: "Referenced Patient Sequence"
-  group: 0x0008
-  element: 0x1120
-  op: "delete"
-- name: "Source Image Sequence"
-  group: 0x0008
-  element: 0x2112
-  op: "delete"
-- name: "Anatomic Region Sequence"
-  group: 0x0008
-  element: 0x2218
-  op: "delete"
-- name: "Irradiation Event UID"
-  group: 0x0008
-  element: 0x3010
-  op: "delete"
-- name: "Patients Name"
-  group: 0x0010
+
+# Configuration for extracting data from UCLH OMOP CDM DICOM files
+
+- name: "VR OB Creator"
+  group: 0x0013
   element: 0x0010
-  op: "replace"
-- name: "Patient ID"
-  group: 0x0010
-  element: 0x0020
-  op: "secure-hash"
-- name: "Issuer Of Patient ID"
-  group: 0x0010
-  element: 0x0021
-  op: "delete"
-- name: "Patients Birth Date"
-  group: 0x0010
-  element: 0x0030
-  op: "delete"
-- name: "Patients Birth Time"
-  group: 0x0010
-  element: 0x0032
-  op: "delete"
-- name: "Patients Sex"
-  group: 0x0010
-  element: 0x0040
-  op: "delete"
-- name: "Other Patient IDs"
-  group: 0x0010
-  element: 0x1000
-  op: "delete"
-- name: "Other Patient Names"
-  group: 0x0010
-  element: 0x1001
-  op: "delete"
-- name: "Patients Age"
-  group: 0x0010
-  element: 0x1010
-  op: "delete"
-- name: "Patients Size"
-  group: 0x0010
-  element: 0x1020
-  op: "keep"
-- name: "Patients Weight"
-  group: 0x0010
-  element: 0x1030
-  op: "keep"
-- name: "Patients Address"
-  group: 0x0010
-  element: 0x1040
-  op: "delete"
-- name: "Medical Alerts"
-  group: 0x0010
-  element: 0x2000
-  op: "delete"
-- name: "Contrast Allergies"
-  group: 0x0010
-  element: 0x2110
-  op: "delete"
-- name: "Patient Comments"
-  group: 0x0010
-  element: 0x4000
-  op: "delete"
-- name: "Private Creator Data Element"
-  group: 0x0011
-  element: 0x0010
-  op: "delete"
-- name: "Body Part Examined"
-  group: 0x0018
-  element: 0x0015
-  op: "keep"
-- name: "kVp"
-  group: 0x0018
-  element: 0x0060
-  op: "keep"
-- name: "Software Version"
-  group: 0x0018
-  element: 0x1020
-  op: "keep"
-- name: "Protocol Name"
-  group: 0x0018
-  element: 0x1030
-  op: "delete"
-- name: "Field Of View Dimension"
-  group: 0x0018
-  element: 0x1149
-  op: "keep"
-- name: "Exposure Time"
-  group: 0x0018
-  element: 0x1150
-  op: "keep"
-- name: "X Ray Tube Current"
-  group: 0x0018
-  element: 0x1151
-  op: "keep"
-- name: "Exposure"
-  group: 0x0018
-  element: 0x1152
-  op: "keep"
-- name: "Exposure In Uas"
-  group: 0x0018
-  element: 0x1153
-  op: "keep"
-- name: "Image Area Dose Product"
-  group: 0x0018
-  element: 0x115e
-  op: "keep"
-- name: "Imager Pixel Spacing"
-  group: 0x0018
-  element: 0x1164
-  op: "keep"
-- name: "Grid"
-  group: 0x0018
-  element: 0x1166
-  op: "keep"
-- name: "Focal Spot"
-  group: 0x0018
-  element: 0x1190
-  op: "keep"
-- name: "Acquisition Device Processing Description"
-  group: 0x0018
-  element: 0x1400
-  op: "keep"
-- name: "Exposure Index"
-  group: 0x0018
-  element: 0x1411
-  op: "keep"
-- name: "Target Exposure Index"
-  group: 0x0018
-  element: 0x1412
-  op: "keep"
-- name: "Deviation Index"
-  group: 0x0018
-  element: 0x1413
-  op: "keep"
-- name: "Positioner Type"
-  group: 0x0018
-  element: 0x1508
-  op: "keep"
-- name: "Collemator Shape"
-  group: 0x0018
-  element: 0x1700
-  op: "keep"
-- name: "Vertices Of The Polygonal Collimator"
-  group: 0x0018
-  element: 0x1720
-  op: "keep"
-- name: "View Position"
-  group: 0x0018
-  element: 0x5101
-  op: "keep"
-- name: "Sensitivity"
-  group: 0x0018
-  element: 0x6000
-  op: "keep"
-- name: "Detector Temperature"
-  group: 0x0018
-  element: 0x7001
-  op: "keep"
-- name: "Detector Type"
-  group: 0x0018
-  element: 0x7004
-  op: "keep"
-- name: "Detector Configuration"
-  group: 0x0018
-  element: 0x7005
-  op: "keep"
-- name: "Detector ID"
-  group: 0x0018
-  element: 0x700a
-  op: "keep"
-- name: "Detector Binning"
-  group: 0x0018
-  element: 0x701a
-  op: "keep"
-- name: "Detector Element Physical Size"
-  group: 0x0018
-  element: 0x7020
-  op: "keep"
-- name: "Detector Element Spacing"
-  group: 0x0018
-  element: 0x7022
-  op: "keep"
-- name: "Detector Active Shape"
-  group: 0x0018
-  element: 0x7024
   op: "keep"
-- name: "Detector Active Dimensions"
-  group: 0x0018
-  element: 0x7026
-  op: "keep"
-- name: "Field Of View Origin"
-  group: 0x0018
-  element: 0x7030
-  op: "keep"
-- name: "Field Of View Rotation"
-  group: 0x0018
-  element: 0x7032
-  op: "keep"
-- name: "Field Of View Horizontal Flip"
-  group: 0x0018
-  element: 0x7034
-  op: "keep"
-- name: "Grid Focal Distance"
-  group: 0x0018
-  element: 0x704c
-  op: "keep"
-- name: "Exposure Control Mode"
-  group: 0x0018
-  element: 0x7060
-  op: "keep"
-- name: "Study Instance UID"
-  group: 0x0020
-  element: 0x000d
-  op: "replace_UID"
-- name: "Series Instance UID"
-  group: 0x0020
-  element: 0x000e
-  op: "replace_UID"
-- name: "Study ID"
-  group: 0x0020
-  element: 0x0010
+- name: "VR OB sequence"
+  group: 0x0013
+  element: 0x1010
   op: "replace"
-- name: "Series Number"
-  group: 0x0020
-  element: 0x0011
-  op: "keep"
-- name: "Image Number"
-  group: 0x0020
-  element: 0x0013
-  op: "keep"
-- name: "Patient Orientation"
-  group: 0x0020
-  element: 0x0020
-  op: "keep"
-- name: "Image Laterality"
-  group: 0x0020
-  element: 0x0062
-  op: "keep"
-- name: "Number Of Study Related Images"
-  group: 0x0020
-  element: 0x1208
-  op: "delete"
-- name: "Samples Per Pixel"
-  group: 0x0028
-  element: 0x0002
-  op: "keep"
-- name: "Photometric Interpretation"
-  group: 0x0028
-  element: 0x0004
-  op: "keep"
-- name: "Rows"
-  group: 0x0028
-  element: 0x0010
-  op: "keep"
-- name: "Columns"
-  group: 0x0028
-  element: 0x0011
-  op: "keep"
-- name: "Pixel Spacing"
-  group: 0x0028
-  element: 0x0030
-  op: "keep"
-- name: "Bits Allocated"
-  group: 0x0028
-  element: 0x0100
-  op: "keep"
-- name: "Bits Stored"
-  group: 0x0028
-  element: 0x0101
-  op: "keep"
-- name: "High Bit"
-  group: 0x0028
-  element: 0x0102
-  op: "keep"
-- name: "Pixel Representation"
-  group: 0x0028
-  element: 0x0103
-  op: "keep"
-- name: "Quality Control Image"
-  group: 0x0028
-  element: 0x0300
-  op: "keep"
-- name: "Burned In Annotation"
-  group: 0x0028
-  element: 0x0301
-  op: "keep"
-- name: "Pixel Spacing Calibration Type"
-  group: 0x0028
-  element: 0x0a02
-  op: "keep"
-- name: "Pixel Spacing Calibration Description"
-  group: 0x0028
-  element: 0x0a04
-  op: "keep"
-- name: "Pixel Intensity Relationship"
-  group: 0x0028
-  element: 0x1040
-  op: "keep"
-- name: "Pixel Intensity Relationship Sign"
-  group: 0x0028
-  element: 0x1041
-  op: "keep"
-- name: "Window Center"
-  group: 0x0028
-  element: 0x1050
-  op: "keep"
-- name: "Window Width"
-  group: 0x0028
-  element: 0x1051
-  op: "keep"
-- name: "Rescale Intercept"
-  group: 0x0028
-  element: 0x1052
-  op: "keep"
-- name: "Rescale Slope"
-  group: 0x0028
-  element: 0x1053
-  op: "keep"
-- name: "Rescale Type"
-  group: 0x0028
-  element: 0x1054
-  op: "keep"
-- name: "Window Center And Width Explanation"
-  group: 0x0028
-  element: 0x1055
-  op: "keep"
-- name: "Lossy Image Compression"
-  group: 0x0028
-  element: 0x2110
-  op: "keep"
-- name: "VOI LUT Sequence"
-  group: 0x0028
-  element: 0x3010
-  op: "keep"
-- name: "Current Patient Location"
-  group: 0x0038
-  element: 0x0300
-  op: "delete"
-- name: "Patient State"
-  group: 0x0038
-  element: 0x0500
-  op: "delete"
-- name: "Performed Procedure Start Date"
-  group: 0x0040
-  element: 0x0244
-  op: "delete"
-- name: "Performed Procedure Start Time"
-  group: 0x0040
-  element: 0x0245
-  op: "delete"
-- name: "Performed Procedure Step ID"
-  group: 0x0040
-  element: 0x0253
-  op: "delete"
-- name: "Performed Procedure Step Description"
-  group: 0x0040
-  element: 0x0254
-  op: "delete"
-- name: "Performed Action Item Sequence"
-  group: 0x0040
-  element: 0x0260
-  op: "delete"
-- name: "Request Attributes Sequence"
-  group: 0x0040
-  element: 0x0275
-  op: "delete"
-- name: "Acquisition Context Sequence"
-  group: 0x0040
-  element: 0x0555
-  op: "delete"
-- name: "Confidentiality Code"
-  group: 0x0040
-  element: 0x1008
-  op: "delete"
-- name: "Private Creator Data Element"
-  group: 0x0045
-  element: 0x0010
-  op: "delete"
-- name: "View Code Sequence"
-  group: 0x0054
-  element: 0x0220
-  op: "keep"
-- name: "Image Comments"
-  group: 0x0020
-  element: 0x4000
-  op: "delete"
-- name: "Instance Creator UID"
-  group: 0x0008
-  element: 0x0014
-  op: "replace_UID"
-- name: "Referenced SOP Instance UID"
-  group: 0x0008
-  element: 0x1155
-  op: "replace_UID"
-- name: "Frame of Reference UID"
-  group: 0x0020
-  element: 0x0052
-  op: "replace_UID"
-- name: "Synchronization Frame of Reference UID"
-  group: 0x0020
-  element: 0x0200
-  op: "replace_UID"
-- name: "Storage Media File-set UID"
-  group: 0x0088
-  element: 0x0140
-  op: "replace_UID"
-- name: "Referenced Frame of Reference UID"
-  group: 0x3006
-  element: 0x0024
-  op: "replace_UID"
-- name: "Related Frame of Reference UID"
-  group: 0x3006
-  element: 0x00C2
-  op: "replace_UID"
-- name: "UID"
-  group: 0x0040
-  element: 0xA124
-  op: "replace_UID"
-- name: "Study Comments [Retired]"
-  group: 0x0032
-  element: 0x4000
-  op: "delete"
-- name: "Ethnic Group"
-  group: 0x0010
-  element: 0x2160
-  op: "delete"
-- name: "Physicians Of Record"
-  group: 0x0008
-  element: 0x1048
-  op: "delete"
-- name: "Name Of Physicians Reading Study"
-  group: 0x0008
-  element: 0x1060
-  op: "delete"
-- name: "Device Serial Number"
-  group: 0x0018
-  element: 0x1000
-  op: "delete"
-- name: "Additional Patient History"
-  group: 0x0010
-  element: 0x21b0
-  op: "delete"
-- name: "Pregnancy Status"
-  group: 0x0010
-  element: 0x21c0
-  op: "delete"
-- name: "Pixel Data"
-  group: 0x7fe0
-  element: 0x0010
-  op: "keep"
-- name: "Private Creator Data Element"
-  group: 0x000d
-  element: 0x0010
-  op: "keep"
-- name: "UCLH Project Name"
-  group: 0x000d
-  element: 0x1001
-  op: "keep"
diff --git a/projects/configs/tag-operations/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml b/projects/configs/tag-operations/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
index 54aed8f2f..718d2fecf 100644
--- a/projects/configs/tag-operations/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
+++ b/projects/configs/tag-operations/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
@@ -11,6 +11,9 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+
+# Configuration for extracting data from UCLH Nasogastric Tube Project DICOM files
+
 - name: "Specific Character Set"
   group: 0x0008
   element: 0x0005
@@ -30,39 +33,15 @@
 - name: "Study Date"
   group: 0x0008
   element: 0x0020
-  op: "delete"
-- name: "Series Date"
-  group: 0x0008
-  element: 0x0021
-  op: "delete"
-- name: "Acquisition Date"
-  group: 0x0008
-  element: 0x0022
-  op: "delete"
-- name: "Image Date"
-  group: 0x0008
-  element: 0x0023
-  op: "delete"
-- name: "Acquisition Date Time"
+  op: "replace"
+- name: "Instance Creator UID"
   group: 0x0008
-  element: 0x002a
-  op: "delete"
+  element: 0x0014
+  op: "replace_UID"
 - name: "Study Time"
   group: 0x0008
   element: 0x0030
-  op: "delete"
-- name: "Series Time"
-  group: 0x0008
-  element: 0x0031
-  op: "delete"
-- name: "Acquisition Time"
-  group: 0x0008
-  element: 0x0032
-  op: "delete"
-- name: "Image Time"
-  group: 0x0008
-  element: 0x0033
-  op: "delete"
+  op: "replace"
 - name: "Accession Number"
   group: 0x0008
   element: 0x0050
@@ -75,30 +54,14 @@
   group: 0x0008
   element: 0x0061
   op: "keep"
-- name: "Presentation Intent Type"
-  group: 0x0008
-  element: 0x0068
-  op: "delete"
 - name: "Manufacturer"
   group: 0x0008
   element: 0x0070
   op: "keep"
-- name: "Institution Name"
-  group: 0x0008
-  element: 0x0080
-  op: "delete"
-- name: "Institution Address"
-  group: 0x0008
-  element: 0x0081
-  op: "delete"
 - name: "Referring Physicians Name"
   group: 0x0008
   element: 0x0090
-  op: "delete"
-- name: "Station Name"
-  group: 0x0008
-  element: 0x1010
-  op: "delete"
+  op: "replace"
 - name: "Study Description"
   group: 0x0008
   element: 0x1030
@@ -107,42 +70,14 @@
   group: 0x0008
   element: 0x103e
   op: "keep"
-- name: "Institutional Department Name"
-  group: 0x0008
-  element: 0x1040
-  op: "delete"
-- name: "Performing Physicians Name"
-  group: 0x0008
-  element: 0x1050
-  op: "delete"
-- name: "Operators Name"
-  group: 0x0008
-  element: 0x1070
-  op: "delete"
 - name: "Manufacturers Model Name"
   group: 0x0008
   element: 0x1090
   op: "keep"
-- name: "Referenced Study Sequence"
-  group: 0x0008
-  element: 0x1110
-  op: "delete"
-- name: "Referenced Patient Sequence"
-  group: 0x0008
-  element: 0x1120
-  op: "delete"
-- name: "Source Image Sequence"
-  group: 0x0008
-  element: 0x2112
-  op: "delete"
-- name: "Anatomic Region Sequence"
-  group: 0x0008
-  element: 0x2218
-  op: "delete"
-- name: "Irradiation Event UID"
+- name: "Referenced SOP Instance UID"
   group: 0x0008
-  element: 0x3010
-  op: "delete"
+  element: 0x1155
+  op: "replace_UID"
 - name: "Patients Name"
   group: 0x0010
   element: 0x0010
@@ -151,34 +86,14 @@
   group: 0x0010
   element: 0x0020
   op: "secure-hash"
-- name: "Issuer Of Patient ID"
-  group: 0x0010
-  element: 0x0021
-  op: "delete"
 - name: "Patients Birth Date"
   group: 0x0010
   element: 0x0030
-  op: "delete"
-- name: "Patients Birth Time"
-  group: 0x0010
-  element: 0x0032
-  op: "delete"
+  op: "replace"
 - name: "Patients Sex"
   group: 0x0010
   element: 0x0040
-  op: "delete"
-- name: "Other Patient IDs"
-  group: 0x0010
-  element: 0x1000
-  op: "delete"
-- name: "Other Patient Names"
-  group: 0x0010
-  element: 0x1001
-  op: "delete"
-- name: "Patients Age"
-  group: 0x0010
-  element: 0x1010
-  op: "delete"
+  op: "keep"
 - name: "Patients Size"
   group: 0x0010
   element: 0x1020
@@ -187,42 +102,46 @@
   group: 0x0010
   element: 0x1030
   op: "keep"
-- name: "Patients Address"
-  group: 0x0010
-  element: 0x1040
-  op: "delete"
-- name: "Medical Alerts"
-  group: 0x0010
-  element: 0x2000
-  op: "delete"
-- name: "Contrast Allergies"
-  group: 0x0010
-  element: 0x2110
-  op: "delete"
-- name: "Patient Comments"
-  group: 0x0010
-  element: 0x4000
-  op: "delete"
-- name: "Private Creator Data Element"
-  group: 0x0011
-  element: 0x0010
-  op: "delete"
 - name: "Body Part Examined"
   group: 0x0018
   element: 0x0015
   op: "keep"
+- name: "Scanning Sequence"
+  group: 0x0018
+  element: 0x0020
+  op: "keep"
+- name: "Scanning Variant"
+  group: 0x0018
+  element: 0x0021
+  op: "keep"
+- name: "Scan Options"
+  group: 0x0018
+  element: 0x0022
+  op: "keep"
+- name: "MR Acquisition Type"
+  group: 0x0018
+  element: 0x0023
+  op: "keep"
+- name: "Slice Thickness"
+  group: 0x0018
+  element: 0x0050
+  op: "keep"
 - name: "kVp"
   group: 0x0018
   element: 0x0060
   op: "keep"
+- name: "Echo Time"
+  group: 0x0018
+  element: 0x0081
+  op: "keep"
+- name: "Echo Train Length"
+  group: 0x0018
+  element: 0x0091
+  op: "keep"
 - name: "Software Version"
   group: 0x0018
   element: 0x1020
   op: "keep"
-- name: "Protocol Name"
-  group: 0x0018
-  element: 0x1030
-  op: "delete"
 - name: "Field Of View Dimension"
   group: 0x0018
   element: 0x1149
@@ -287,6 +206,10 @@
   group: 0x0018
   element: 0x1720
   op: "keep"
+- name: "Patient Position"
+  group: 0x0018
+  element: 0x5100
+  op: "keep"
 - name: "View Position"
   group: 0x0018
   element: 0x5101
@@ -375,14 +298,26 @@
   group: 0x0020
   element: 0x0020
   op: "keep"
+- name: "Image Position (Patient)"
+  group: 0x0020
+  element: 0x0032
+  op: "keep"
+- name: "Image Orientation (Patient)"
+  group: 0x0020
+  element: 0x0037
+  op: "keep"
+- name: "Position Reference Indicator"
+  group: 0x0020
+  element: 0x1040
+  op: "keep"
+- name: "Patient Orientation Code Sequence"
+  group: 0x0054
+  element: 0x0410
+  op: "keep"
 - name: "Image Laterality"
   group: 0x0020
   element: 0x0062
   op: "keep"
-- name: "Number Of Study Related Images"
-  group: 0x0020
-  element: 0x1208
-  op: "delete"
 - name: "Samples Per Pixel"
   group: 0x0028
   element: 0x0002
@@ -475,66 +410,10 @@
   group: 0x0028
   element: 0x3010
   op: "keep"
-- name: "Current Patient Location"
-  group: 0x0038
-  element: 0x0300
-  op: "delete"
-- name: "Patient State"
-  group: 0x0038
-  element: 0x0500
-  op: "delete"
-- name: "Performed Procedure Start Date"
-  group: 0x0040
-  element: 0x0244
-  op: "delete"
-- name: "Performed Procedure Start Time"
-  group: 0x0040
-  element: 0x0245
-  op: "delete"
-- name: "Performed Procedure Step ID"
-  group: 0x0040
-  element: 0x0253
-  op: "delete"
-- name: "Performed Procedure Step Description"
-  group: 0x0040
-  element: 0x0254
-  op: "delete"
-- name: "Performed Action Item Sequence"
-  group: 0x0040
-  element: 0x0260
-  op: "delete"
-- name: "Request Attributes Sequence"
-  group: 0x0040
-  element: 0x0275
-  op: "delete"
-- name: "Acquisition Context Sequence"
-  group: 0x0040
-  element: 0x0555
-  op: "delete"
-- name: "Confidentiality Code"
-  group: 0x0040
-  element: 0x1008
-  op: "delete"
-- name: "Private Creator Data Element"
-  group: 0x0045
-  element: 0x0010
-  op: "delete"
 - name: "View Code Sequence"
   group: 0x0054
   element: 0x0220
   op: "keep"
-- name: "Image Comments"
-  group: 0x0020
-  element: 0x4000
-  op: "delete"
-- name: "Instance Creator UID"
-  group: 0x0008
-  element: 0x0014
-  op: "replace_UID"
-- name: "Referenced SOP Instance UID"
-  group: 0x0008
-  element: 0x1155
-  op: "replace_UID"
 - name: "Frame of Reference UID"
   group: 0x0020
   element: 0x0052
@@ -547,6 +426,10 @@
   group: 0x0088
   element: 0x0140
   op: "replace_UID"
+- name: "UID"
+  group: 0x0040
+  element: 0xA124
+  op: "replace_UID"
 - name: "Referenced Frame of Reference UID"
   group: 0x3006
   element: 0x0024
@@ -555,47 +438,7 @@
   group: 0x3006
   element: 0x00C2
   op: "replace_UID"
-- name: "UID"
-  group: 0x0040
-  element: 0xA124
-  op: "replace_UID"
-- name: "Study Comments [Retired]"
-  group: 0x0032
-  element: 0x4000
-  op: "delete"
-- name: "Ethnic Group"
-  group: 0x0010
-  element: 0x2160
-  op: "delete"
-- name: "Physicians Of Record"
-  group: 0x0008
-  element: 0x1048
-  op: "delete"
-- name: "Name Of Physicians Reading Study"
-  group: 0x0008
-  element: 0x1060
-  op: "delete"
-- name: "Device Serial Number"
-  group: 0x0018
-  element: 0x1000
-  op: "delete"
-- name: "Additional Patient History"
-  group: 0x0010
-  element: 0x21b0
-  op: "delete"
-- name: "Pregnancy Status"
-  group: 0x0010
-  element: 0x21c0
-  op: "delete"
 - name: "Pixel Data"
   group: 0x7fe0
   element: 0x0010
   op: "keep"
-- name: "Private Creator Data Element"
-  group: 0x000d
-  element: 0x0010
-  op: "keep"
-- name: "UCLH Project Name"
-  group: 0x000d
-  element: 0x1001
-  op: "keep"
diff --git a/projects/configs/tag-operations/xray.yaml b/projects/configs/tag-operations/xray.yaml
new file mode 100644
index 000000000..947b0879a
--- /dev/null
+++ b/projects/configs/tag-operations/xray.yaml
@@ -0,0 +1,89 @@
+#  Copyright (c) University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+# Default configuration to extend base for x-rays
+
+- name: "Volumetric Properties"
+  group: 0x0008
+  element: 0x9206
+  op: "keep"
+- name: "Volume Based Calculation Technique"
+  group: 0x0008
+  element: 0x9207
+  op: "keep"
+- name: "Field Of View Dimension"
+  group: 0x0018
+  element: 0x1149
+  op: "keep"
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/dx-detector/00181149
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/dx-detector/00181149
+#https://dicom.innolitics.com/ciods/x-ray-radiofluoroscopic-image/x-ray-acquisition/00181149
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/x-ray-acquisition/00181149
+#https://dicom.innolitics.com/ciods/digital-x-ray-image/dx-detector/00181149
+#https://dicom.innolitics.com/ciods/digital-mammography-x-ray-image/dx-detector/00181149
+#https://dicom.innolitics.com/ciods/digital-intra-oral-x-ray-image/dx-detector/00181149
+- name: "Imager Pixel Spacing"
+  group: 0x0018
+  element: 0x1164
+  op: "keep"
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/dx-detector/00181164
+#https://dicom.innolitics.com/ciods/x-ray-radiofluoroscopic-image/x-ray-acquisition/00181164
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/x-ray-acquisition/00181164
+#https://dicom.innolitics.com/ciods/digital-x-ray-image/dx-detector/00181164
+#https://dicom.innolitics.com/ciods/digital-mammography-x-ray-image/dx-detector/00181164
+#https://dicom.innolitics.com/ciods/digital-intra-oral-x-ray-image/dx-detector/00181164
+- name: "Grid"
+  group: 0x0018
+  element: 0x1166
+  op: "keep"
+#https://dicom.innolitics.com/ciods/x-ray-radiofluoroscopic-image/x-ray-acquisition/00181166
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/x-ray-acquisition/00181166
+#https://dicom.innolitics.com/ciods/digital-x-ray-image/x-ray-grid/00181166
+#https://dicom.innolitics.com/ciods/digital-mammography-x-ray-image/x-ray-grid/00181166
+#https://dicom.innolitics.com/ciods/digital-intra-oral-x-ray-image/x-ray-grid/00181166
+#https://dicom.innolitics.com/ciods/x-ray-3d-craniofacial-image/x-ray-3d-craniofacial-acquisition/00189507/00181166
+#https://dicom.innolitics.com/ciods/x-ray-3d-angiographic-image/x-ray-3d-angiographic-acquisition/00189507/00181166
+#https://dicom.innolitics.com/ciods/breast-projection-x-ray-image/breast-projection-x-ray-image-multi-frame-functional-groups/52009229/00189555/00181166
+- name: "Acquisition Device Processing Description"
+  group: 0x0018
+  element: 0x1400
+  op: "keep"
+#https://dicom.innolitics.com/ciods/x-ray-radiofluoroscopic-image/x-ray-image/00181400
+#https://dicom.innolitics.com/ciods/x-ray-angiographic-image/x-ray-image/00181400
+#https://dicom.innolitics.com/ciods/digital-x-ray-image/dx-image/00181400
+#https://dicom.innolitics.com/ciods/digital-mammography-x-ray-image/dx-image/00181400
+#https://dicom.innolitics.com/ciods/digital-intra-oral-x-ray-image/dx-image/00181400
+#https://dicom.innolitics.com/ciods/x-ray-3d-craniofacial-image/x-ray-3d-craniofacial-image-contributing-sources/00189506/00181400
+#https://dicom.innolitics.com/ciods/x-ray-3d-angiographic-image/x-ray-3d-angiographic-image-contributing-sources/00189506/00181400
+#https://dicom.innolitics.com/ciods/breast-projection-x-ray-image/breast-projection-x-ray-image-multi-frame-functional-groups/52009229/00189412/00181400
+- name: "Pixel Spacing Calibration Type"
+  group: 0x0028
+  element: 0x0a02
+  op: "keep"
+#RT, X-Ray
+- name: "Pixel Spacing Calibration Description"
+  group: 0x0028
+  element: 0x0a04
+  op: "keep"
+#X-Ray
+- name: "Pixel Intensity Relationship"
+  group: 0x0028
+  element: 0x1040
+  op: "keep"
+#X-Ray
+- name: "Pixel Intensity Relationship Sign"
+  group: 0x0028
+  element: 0x1041
+  op: "keep"
+#X-Ray
diff --git a/projects/configs/test-external-user.yaml b/projects/configs/test-external-user.yaml
new file mode 100644
index 000000000..ad4734d07
--- /dev/null
+++ b/projects/configs/test-external-user.yaml
@@ -0,0 +1,34 @@
+#  Copyright (c) 2022 University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+project:
+    name: "test-external-user"
+    modalities: ["MR"]
+
+tag_operation_files:
+    base:
+        - "base.yaml" #Expected base config file for any project
+        - "test-external-user.yaml"
+        - "diffusion-weighted-mri.yaml"
+    manufacturer_overrides: ["mri-diffusion.yaml"]
+
+series_filters:
+    - "localizer"
+    - "localiser"
+    - "scout"
+    - "positioning"
+
+destination:
+    dicom: "none"
+    parquet: "none"
diff --git a/projects/configs/test-extract-uclh-omop-cdm-dicomweb.yaml b/projects/configs/test-extract-uclh-omop-cdm-dicomweb.yaml
index 5e8868963..bec9c9bc3 100644
--- a/projects/configs/test-extract-uclh-omop-cdm-dicomweb.yaml
+++ b/projects/configs/test-extract-uclh-omop-cdm-dicomweb.yaml
@@ -19,8 +19,9 @@ project:
 
 tag_operation_files:
     base:
-        - "test-extract-uclh-omop-cdm.yaml"
-    manufacturer_overrides: "manufacturer-overrides/mri-diffusion.yaml"
+        - "base.yaml" #Expected base config file for any project
+        - "mri.yaml"
+    manufacturer_overrides: ["mri.yaml", "mri-diffusion.yaml"]
 
 series_filters:
     - "localizer"
diff --git a/projects/configs/test-extract-uclh-omop-cdm-xnat.yaml b/projects/configs/test-extract-uclh-omop-cdm-xnat.yaml
new file mode 100644
index 000000000..9db5648d5
--- /dev/null
+++ b/projects/configs/test-extract-uclh-omop-cdm-xnat.yaml
@@ -0,0 +1,38 @@
+#  Copyright (c) 2024 University College London Hospitals NHS Foundation Trust
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+
+project:
+    name: "test-extract-uclh-omop-cdm-xnat"
+    azure_kv_alias: "test"
+    modalities: ["DX", "CR", "MR"]
+
+tag_operation_files:
+    base:
+        - "base.yaml" #Expected base config file for any project
+        - "mri.yaml"
+    manufacturer_overrides: ["mri.yaml", "mri-diffusion.yaml"]
+
+series_filters:
+    - "localizer"
+    - "localiser"
+    - "scout"
+    - "positioning"
+
+destination:
+    dicom: "xnat"
+    parquet: "none"
+
+xnat_destination_options:
+    overwrite: "none"
+    destination: "/archive"
diff --git a/projects/configs/test-extract-uclh-omop-cdm.yaml b/projects/configs/test-extract-uclh-omop-cdm.yaml
index 5a13f6692..7ff106a1f 100644
--- a/projects/configs/test-extract-uclh-omop-cdm.yaml
+++ b/projects/configs/test-extract-uclh-omop-cdm.yaml
@@ -19,8 +19,10 @@ project:
 
 tag_operation_files:
     base:
+        - "base.yaml" #Expected base config file for any project
+        - "mri.yaml"
         - "test-extract-uclh-omop-cdm.yaml"
-    manufacturer_overrides: "manufacturer-overrides/mri-diffusion.yaml"
+    manufacturer_overrides: ["mri-diffusion.yaml"]
 
 series_filters:
     - "localizer"
diff --git a/pixl_dcmd/tests/__init__.py b/projects/configs/test-mr-spectroscopy.yaml
similarity index 63%
rename from pixl_dcmd/tests/__init__.py
rename to projects/configs/test-mr-spectroscopy.yaml
index a61138626..6571deb1e 100644
--- a/pixl_dcmd/tests/__init__.py
+++ b/projects/configs/test-mr-spectroscopy.yaml
@@ -11,3 +11,25 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+
+project:
+    name: "test-mr-spectroscopy"
+    modalities: ["MR"]
+
+tag_operation_files:
+    base:
+        - "base.yaml"
+        - "mri.yaml"
+        - "mr-spectroscopy.yaml"
+    manufacturer_overrides:
+        - "mri.yaml"
+
+series_filters:
+    - "localizer"
+    - "localiser"
+    - "scout"
+    - "positioning"
+
+destination:
+    dicom: "none"
+    parquet: "none"
diff --git a/projects/configs/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml b/projects/configs/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
index 2aa75ed31..6b49a09e5 100644
--- a/projects/configs/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
+++ b/projects/configs/uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml
@@ -19,6 +19,7 @@ project:
 
 tag_operation_files:
     base:
+        - "base.yaml" #Expected base config file for any project
         - "uclh-nasogastric-tube-project-ngt-only-full-dataset.yaml"
     manufacturer_overrides: null
 destination:
diff --git a/projects/configs/uclh-prostate-mri-validation-dataset.yaml b/projects/configs/uclh-prostate-mri-external-dataset.yaml
similarity index 78%
rename from projects/configs/uclh-prostate-mri-validation-dataset.yaml
rename to projects/configs/uclh-prostate-mri-external-dataset.yaml
index ba78bd730..326e94c92 100644
--- a/projects/configs/uclh-prostate-mri-validation-dataset.yaml
+++ b/projects/configs/uclh-prostate-mri-external-dataset.yaml
@@ -13,14 +13,15 @@
 #  limitations under the License.
 
 project:
-    name: "uclh-prostate-mri-validation-dataset"
+    name: "uclh-prostate-mri-external-dataset"
     modalities: ["MR"]
 
 tag_operation_files:
     base:
+        - "base.yaml" #Expected base config file for any project
         - "mri.yaml"
         - "diffusion-weighted-mri.yaml"
-    manufacturer_overrides: "manufacturer-overrides/mri-diffusion.yaml"
+    manufacturer_overrides: ["mri.yaml", "mri-diffusion.yaml"]
 destination:
-    dicom: "none"
-    parquet: "none"
+    dicom: "ftps"
+    parquet: "ftps"
diff --git a/pytest-pixl/README.md b/pytest-pixl/README.md
index 6111973b7..4c4e9666e 100644
--- a/pytest-pixl/README.md
+++ b/pytest-pixl/README.md
@@ -2,6 +2,17 @@
 
 Installable `pytest` plugin module providing common test fixtures used throughout PIXL.
 
+## Installation
+
+```bash
+python -m pip install -e ../pixl_core -e ".[test]"
+```
+
+## pytest-cov’s engine
+```
+COV_CORE_SOURCE=src COV_CORE_CONFIG=.coveragerc COV_CORE_DATAFILE=.coverage.eager pytest --cov=src --cov-append --cov-report=xml --cov-report=term-missing
+```
+
 ## Available fixtures
 
 ### `ftps_server`
diff --git a/pytest-pixl/pyproject.toml b/pytest-pixl/pyproject.toml
index df00c1e77..2f7e1c232 100644
--- a/pytest-pixl/pyproject.toml
+++ b/pytest-pixl/pyproject.toml
@@ -1,9 +1,7 @@
 [project]
 name = "pytest-pixl"
-version = "0.0.1"
-authors = [
-  { name="PIXL core functionality" },
-]
+version = "0.2.0rc0"
+authors = [{ name = "PIXL authors" }]
 description = "Pytest plugin for PIXL"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -12,27 +10,52 @@ classifiers = [
 ]
 dependencies = [
     "pydicom==2.4.4",
-    "pyftpdlib==1.5.9",
-    "python-decouple==3.6",
-    "pyOpenSSL==24.0.0",
-    "requests==2.31.0",
+    "pyftpdlib==2.0.1",
+    "pyOpenSSL==24.3.0",
+    "python-decouple==3.8",
+    "pytest-loguru==0.4.0",
+    "requests==2.32.3",
 ]
 
 [project.optional-dependencies]
 test = [
-    "core", # pixl_core
-    "pytest==7.4.2",
+    "core==0.2.0rc0",
+    "pytest==8.3.4",
 ]
 dev = [
-    "mypy",
-    "pre-commit",
-    "ruff",
+    "core[dev]==0.2.0rc0",
 ]
 
 [build-system]
 requires = ["setuptools>=61.0", "setuptools-scm>=8.0"]
 build-backend = "setuptools.build_meta"
 
+
+[tool.coverage.report]
+exclude_also = [
+    # Don't complain about missing debug-only code:
+    "def __repr__",
+    "if self.debug:",
+
+    # Don't complain if tests don't hit defensive assertion code:
+    "raise AssertionError",
+    "raise NotImplementedError",
+
+    # Don't complain if non-runnable code isn't run:
+    "if 0:",
+    "if __name__ == .__main__.:",
+
+    # Don't complain about abstract methods, they aren't run:
+    "@(abc\\.)?abstractmethod",
+
+    # Others
+    "if settings.DEBUG",
+    "except subprocess.CalledProcessError as exception:",
+    "if TYPE_CHECKING:",
+    "if typing.TYPE_CHECKING",
+    "class .*\\bProtocol\\):",
+]
+
 [tool.setuptools.package-data]
 pytest_pixl = ["*.key", "*.crt"]
 
@@ -43,4 +66,4 @@ extend = "../ruff.toml"
 "./tests/**" = ["D100"]
 
 [project.entry-points.pytest11]
-pytest_pixl = "pytest_pixl.plugin"
+pytest_pixl = "pytest_pixl.plugin"
\ No newline at end of file
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/batch_input.csv b/pytest-pixl/src/pytest_pixl/data/omop-resources/batch_input.csv
new file mode 100644
index 000000000..b2440897a
--- /dev/null
+++ b/pytest-pixl/src/pytest_pixl/data/omop-resources/batch_input.csv
@@ -0,0 +1,4 @@
+procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date,study_uid,participant_id
+1,mrn,123,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,1.2.3,
+2,mrn,234,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,2.3.4,
+3,mrn,345,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,3.4.5,
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/duplicate_input.csv b/pytest-pixl/src/pytest_pixl/data/omop-resources/duplicate_input.csv
new file mode 100644
index 000000000..c4b38f497
--- /dev/null
+++ b/pytest-pixl/src/pytest_pixl/data/omop-resources/duplicate_input.csv
@@ -0,0 +1,7 @@
+procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date,study_uid,participant_id
+1,mrn,123,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,1.2.3,
+2,mrn,234,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,2.3.4,
+3,mrn,345,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,3.4.5,
+4,mrn,123,i-am-a-project,2024-01-01T00:00:00Z,2023-01-01,1.2.3,
+5,mrn,234,i-am-a-project,2024-01-01T00:00:00Z,2023-01-01,2.3.4,
+6,mrn,345,i-am-a-project,2024-01-01T00:00:00Z,2023-01-01,3.4.5,
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/multiple_projects.csv b/pytest-pixl/src/pytest_pixl/data/omop-resources/multiple_projects.csv
new file mode 100644
index 000000000..846c7d213
--- /dev/null
+++ b/pytest-pixl/src/pytest_pixl/data/omop-resources/multiple_projects.csv
@@ -0,0 +1,7 @@
+procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date,study_uid,participant_id
+1,mrn,123,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,1.2.3,
+2,mrn,234,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,2.3.4,
+3,mrn,345,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,3.4.5,
+4,mrn,123,i-am-another-project,2023-01-01T00:00:00Z,2023-01-01,1.2.3,
+5,mrn,234,i-am-another-project,2023-01-01T00:00:00Z,2023-01-01,2.3.4,
+6,mrn,345,i-am-another-project,2023-01-01T00:00:00Z,2023-01-01,3.4.5,
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet b/pytest-pixl/src/pytest_pixl/data/omop-resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet
index f4a1d6370..c1c49f80d 100644
Binary files a/pytest-pixl/src/pytest_pixl/data/omop-resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet and b/pytest-pixl/src/pytest_pixl/data/omop-resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet differ
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/participant_id.csv b/pytest-pixl/src/pytest_pixl/data/omop-resources/participant_id.csv
new file mode 100644
index 000000000..57555de63
--- /dev/null
+++ b/pytest-pixl/src/pytest_pixl/data/omop-resources/participant_id.csv
@@ -0,0 +1,4 @@
+procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date,study_uid,participant_id
+1,mrn,123,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,1.2.3,AAA00
+2,mrn,234,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,2.3.4,BBB11
+3,mrn,345,i-am-a-project,2023-01-01T00:00:00Z,2023-01-01,3.4.5,CCC22
diff --git a/pytest-pixl/src/pytest_pixl/data/omop-resources/test.csv b/pytest-pixl/src/pytest_pixl/data/omop-resources/test.csv
index b520add67..367736831 100644
--- a/pytest-pixl/src/pytest_pixl/data/omop-resources/test.csv
+++ b/pytest-pixl/src/pytest_pixl/data/omop-resources/test.csv
@@ -1,2 +1,2 @@
-procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date
-0,patient_identifier,123456789,ms-pinpoint-test,01/01/2022 00:01,01/01/2022 00:01
\ No newline at end of file
+procedure_id,mrn,accession_number,project_name,extract_generated_timestamp,study_date,study_uid,participant_id
+0,patient_identifier,123456789,ms-pinpoint-test,2023-01-01T00:01:00Z,2022-01-01,1.2.3.4.5.6.7.8,
diff --git a/pytest-pixl/src/pytest_pixl/helpers.py b/pytest-pixl/src/pytest_pixl/helpers.py
index ecbcbf122..dc59b3779 100644
--- a/pytest-pixl/src/pytest_pixl/helpers.py
+++ b/pytest-pixl/src/pytest_pixl/helpers.py
@@ -39,11 +39,11 @@ def run_subprocess(
     """
     logger.info("Running command {}", cmd)
     try:
-        cp = subprocess.run(
+        cp = subprocess.run(  # noqa: S603 input is trusted
             cmd,
             check=True,
             cwd=working_dir,
-            shell=shell,  # noqa: S603 input is trusted
+            shell=shell,
             timeout=timeout,
             capture_output=True,
         )
diff --git a/pytest-pixl/tests/test_ftpserver_fixture.py b/pytest-pixl/tests/test_ftpserver_fixture.py
index de9951e25..9f7833907 100644
--- a/pytest-pixl/tests/test_ftpserver_fixture.py
+++ b/pytest-pixl/tests/test_ftpserver_fixture.py
@@ -11,11 +11,30 @@
 #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
+import os
+from pathlib import Path
+
 import pytest
+from conftest import TEST_DIR
+from pytest_pixl.dicom import _create_default_json
+from pytest_pixl.plugin import FtpHostAddress
 
 
-@pytest.mark.pytester_example_path("tests/samples_for_fixture_tests/test_ftpserver_fixture")
+@pytest.mark.pytester_example_path(f"{TEST_DIR}/samples_for_fixture_tests/test_ftpserver_fixture")
 def test_ftpserver_connection(pytester):
     """Test whether we can connect to the FTP server fixture"""
     pytester.copy_example("test_ftpserver_login.py")
     pytester.runpytest("-k", "test_ftpserver_login")
+
+
+def test_create_default_json_file():
+    """Test whether we can create a default JSON file"""
+    filename_to_create = "test_json_file.json"
+    _create_default_json(filename_to_create)
+    assert Path(filename_to_create).exists()
+    os.remove(filename_to_create)  # noqa: PTH107
+
+
+def test_ftp_host_address():
+    """Run FTP on localhost - docker containers do not need to access it"""
+    assert FtpHostAddress.DOCKERHOST == FtpHostAddress.DOCKERHOST
diff --git a/pytest.ini b/pytest.ini
index 8096b9b62..be8f67715 100644
--- a/pytest.ini
+++ b/pytest.ini
@@ -1,10 +1,11 @@
 [pytest]
 minversion=6.0
-addopts = -ra -q
+addopts = -ra -q --cov --cov-append
 testpaths =
     pixl_core/tests
     cli/tests
     pixl_export/tests
     pixl_imaging/tests
     pixl_dcmd/tests
-# pixl_dcmd and hasher conftests clash, so can only add one of the two
+    pytest-pixl/tests
+# pixl_dcmd and hasher conftests clash, so can only add one of the two
\ No newline at end of file
diff --git a/ruff.toml b/ruff.toml
index 99b8cd438..36ba9768c 100644
--- a/ruff.toml
+++ b/ruff.toml
@@ -48,7 +48,13 @@ lint.mccabe.max-complexity = 18
 exclude=["scripts"]
 
 [lint.extend-per-file-ignores]
-"**/test*/*" = ["PLR2004"] #  Magic value used in comparison
+"**/test*/*" = [
+    "PLR2004", #  Magic value used in comparison
+    "S105"  # harcoded password
+]
+"test/conftest.py" = [
+    "E402" # Module level import not at the top of the file
+]
 "hasher/tests/*" = ["ARG001"] #  unused function argument
 "env.py" = ["INP001", "E402", "ERA001"]
 "alembic/versions/*" = ["D103", "INP001"]
diff --git a/schemas/github-issue-forms.json b/schemas/github-issue-forms.json
new file mode 100644
index 000000000..815289757
--- /dev/null
+++ b/schemas/github-issue-forms.json
@@ -0,0 +1,2377 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+
+  "$id": "https://json.schemastore.org/github-issue-forms.json",
+
+  "$comment": "https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms",
+
+  "additionalProperties": true,
+
+  "definitions": {
+    "type": {
+      "description": "A form item type\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#keys",
+
+      "type": "string",
+
+      "enum": ["checkboxes", "dropdown", "input", "markdown", "textarea"]
+    },
+
+    "id": {
+      "type": "string",
+
+      "pattern": "^[a-zA-Z0-9_-]+$",
+
+      "examples": ["SampleId"]
+    },
+
+    "validations": {
+      "title": "validation options",
+
+      "type": "object",
+
+      "properties": {
+        "required": {
+          "description": "Specify whether require a form item",
+
+          "type": "boolean",
+
+          "default": false
+        }
+      },
+
+      "additionalProperties": false
+    },
+
+    "assignee": {
+      "type": "string",
+
+      "maxLength": 39,
+
+      "pattern": "^[a-zA-Z0-9](-?[a-zA-Z0-9])*$",
+
+      "examples": ["SampleAssignee"]
+    },
+
+    "label": {
+      "type": "string",
+
+      "minLength": 1,
+
+      "examples": ["Sample label"]
+    },
+
+    "description": {
+      "type": "string",
+
+      "default": "",
+
+      "examples": ["Sample description"]
+    },
+
+    "placeholder": {
+      "type": "string",
+
+      "default": "",
+
+      "examples": ["Sample placeholder"]
+    },
+
+    "value": {
+      "type": "string",
+
+      "minLength": 1,
+
+      "examples": ["Sample value"]
+    },
+
+    "form_item": {
+      "title": "form item",
+
+      "description": "A form item\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#about-githubs-form-schema",
+
+      "type": "object",
+
+      "required": ["type"],
+
+      "properties": {
+        "type": {
+          "$ref": "#/definitions/type"
+        }
+      },
+
+      "allOf": [
+        {
+          "if": {
+            "properties": {
+              "type": {
+                "const": "markdown"
+              }
+            }
+          },
+
+          "then": {
+            "$comment": "For `additionalProperties` to work `type` must also be present here.",
+
+            "title": "markdown",
+
+            "description": "Markdown\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#markdown",
+
+            "type": "object",
+
+            "required": ["type", "attributes"],
+
+            "properties": {
+              "type": {
+                "$ref": "#/definitions/type"
+              },
+
+              "attributes": {
+                "title": "markdown attributes",
+
+                "description": "Markdown attributes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes",
+
+                "type": "object",
+
+                "required": ["value"],
+
+                "properties": {
+                  "value": {
+                    "description": "A markdown code\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes",
+
+                    "type": "string",
+
+                    "minLength": 1,
+
+                    "examples": ["Sample code"]
+                  }
+                },
+
+                "additionalProperties": false
+              }
+            },
+
+            "additionalProperties": false
+          }
+        },
+
+        {
+          "if": {
+            "properties": {
+              "type": {
+                "const": "textarea"
+              }
+            }
+          },
+
+          "then": {
+            "$comment": "For `additionalProperties` to work `type` must also be present here.",
+
+            "title": "textarea",
+
+            "description": "Textarea\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#textarea",
+
+            "type": "object",
+
+            "required": ["type", "attributes"],
+
+            "properties": {
+              "type": {
+                "$ref": "#/definitions/type"
+              },
+
+              "id": {
+                "$ref": "#/definitions/id",
+
+                "description": "A textarea id\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#keys"
+              },
+
+              "attributes": {
+                "title": "textarea attributes",
+
+                "description": "Textarea attributes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1",
+
+                "type": "object",
+
+                "required": ["label"],
+
+                "properties": {
+                  "label": {
+                    "$ref": "#/definitions/label",
+
+                    "description": "A short textarea description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1"
+                  },
+
+                  "description": {
+                    "$ref": "#/definitions/description",
+
+                    "description": "A long textarea description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1"
+                  },
+
+                  "placeholder": {
+                    "$ref": "#/definitions/placeholder",
+
+                    "description": "A textarea placeholder\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1"
+                  },
+
+                  "value": {
+                    "$ref": "#/definitions/value",
+
+                    "description": "A textarea value\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1"
+                  },
+
+                  "render": {
+                    "description": "A textarea syntax highlighting mode\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-1",
+
+                    "type": "string",
+
+                    "enum": [
+                      "1C Enterprise",
+
+                      "4D",
+
+                      "ABAP CDS",
+
+                      "ABAP",
+
+                      "ABNF",
+
+                      "AFDKO",
+
+                      "AGS Script",
+
+                      "AIDL",
+
+                      "AL",
+
+                      "AMPL",
+
+                      "ANTLR",
+
+                      "API Blueprint",
+
+                      "APL",
+
+                      "ASL",
+
+                      "ASN.1",
+
+                      "ASP.NET",
+
+                      "ATS",
+
+                      "ActionScript",
+
+                      "Ada",
+
+                      "Alloy",
+
+                      "Alpine Abuild",
+
+                      "Altium Designer",
+
+                      "AngelScript",
+
+                      "Ant Build System",
+
+                      "ApacheConf",
+
+                      "Apex",
+
+                      "Apollo Guidance Computer",
+
+                      "AppleScript",
+
+                      "Arc",
+
+                      "AsciiDoc",
+
+                      "AspectJ",
+
+                      "Assembly",
+
+                      "Astro",
+
+                      "Asymptote",
+
+                      "Augeas",
+
+                      "AutoHotkey",
+
+                      "AutoIt",
+
+                      "AutoIt3",
+
+                      "AutoItScript",
+
+                      "Avro IDL",
+
+                      "Awk",
+
+                      "BASIC",
+
+                      "Ballerina",
+
+                      "Batchfile",
+
+                      "Beef",
+
+                      "Befunge",
+
+                      "BibTeX",
+
+                      "Bicep",
+
+                      "Bison",
+
+                      "BitBake",
+
+                      "Blade",
+
+                      "BlitzBasic",
+
+                      "BlitzMax",
+
+                      "Boo",
+
+                      "Boogie",
+
+                      "Brainfuck",
+
+                      "Brightscript",
+
+                      "Browserslist",
+
+                      "C",
+
+                      "C#",
+
+                      "C++",
+
+                      "C-ObjDump",
+
+                      "C2hs Haskell",
+
+                      "CIL",
+
+                      "CLIPS",
+
+                      "CMake",
+
+                      "COBOL",
+
+                      "CODEOWNERS",
+
+                      "COLLADA",
+
+                      "CSON",
+
+                      "CSS",
+
+                      "CSV",
+
+                      "CUE",
+
+                      "CWeb",
+
+                      "Cabal Config",
+
+                      "Cabal",
+
+                      "Cap'n Proto",
+
+                      "Carto",
+
+                      "CartoCSS",
+
+                      "Ceylon",
+
+                      "Chapel",
+
+                      "Charity",
+
+                      "ChucK",
+
+                      "Cirru",
+
+                      "Clarion",
+
+                      "Classic ASP",
+
+                      "Clean",
+
+                      "Click",
+
+                      "Clojure",
+
+                      "Closure Templates",
+
+                      "Cloud Firestore Security Rules",
+
+                      "CoNLL",
+
+                      "CoNLL-U",
+
+                      "CoNLL-X",
+
+                      "ColdFusion CFC",
+
+                      "ColdFusion",
+
+                      "Common Lisp",
+
+                      "Common Workflow Language",
+
+                      "Component Pascal",
+
+                      "Containerfile",
+
+                      "Cool",
+
+                      "Coq",
+
+                      "Cpp-ObjDump",
+
+                      "Crystal",
+
+                      "Csound Document",
+
+                      "Csound Score",
+
+                      "Csound",
+
+                      "Cuda",
+
+                      "Cue Sheet",
+
+                      "Cycript",
+
+                      "Cython",
+
+                      "D-ObjDump",
+
+                      "DIGITAL Command Language",
+
+                      "DM",
+
+                      "DTrace",
+
+                      "Dafny",
+
+                      "Darcs Patch",
+
+                      "Dart",
+
+                      "DataWeave",
+
+                      "Dhall",
+
+                      "Diff",
+
+                      "Dlang",
+
+                      "Dockerfile",
+
+                      "Dogescript",
+
+                      "Dylan",
+
+                      "E",
+
+                      "E-mail",
+
+                      "EBNF",
+
+                      "ECL",
+
+                      "ECLiPSe",
+
+                      "EJS",
+
+                      "EQ",
+
+                      "Eagle",
+
+                      "Earthly",
+
+                      "Easybuild",
+
+                      "Ecere Projects",
+
+                      "EditorConfig",
+
+                      "Eiffel",
+
+                      "Elixir",
+
+                      "Elm",
+
+                      "Emacs Lisp",
+
+                      "EmberScript",
+
+                      "Erlang",
+
+                      "F#",
+
+                      "F*",
+
+                      "FIGfont",
+
+                      "FIGlet Font",
+
+                      "FLUX",
+
+                      "Factor",
+
+                      "Fancy",
+
+                      "Fantom",
+
+                      "Faust",
+
+                      "Fennel",
+
+                      "Filebench WML",
+
+                      "Filterscript",
+
+                      "Fluent",
+
+                      "Formatted",
+
+                      "Forth",
+
+                      "Fortran Free Form",
+
+                      "Fortran",
+
+                      "FreeBasic",
+
+                      "Frege",
+
+                      "Futhark",
+
+                      "G-code",
+
+                      "GAML",
+
+                      "GAMS",
+
+                      "GAP",
+
+                      "GCC Machine Description",
+
+                      "GDB",
+
+                      "GDScript",
+
+                      "GEDCOM",
+
+                      "GLSL",
+
+                      "GN",
+
+                      "Game Maker Language",
+
+                      "Gemfile.lock",
+
+                      "Genie",
+
+                      "Genshi",
+
+                      "Gentoo Eclass",
+
+                      "Gerber Image",
+
+                      "Gettext Catalog",
+
+                      "Gherkin",
+
+                      "Git Config",
+
+                      "Glyph Bitmap Distribution Format",
+
+                      "Glyph",
+
+                      "Gnuplot",
+
+                      "Go Checksums",
+
+                      "Go Module",
+
+                      "Go",
+
+                      "Golo",
+
+                      "Gosu",
+
+                      "Grace",
+
+                      "Gradle",
+
+                      "Grammatical Framework",
+
+                      "Graph Modeling Language",
+
+                      "GraphQL",
+
+                      "Graphviz (DOT)",
+
+                      "Groovy Server Pages",
+
+                      "Groovy",
+
+                      "HAProxy",
+
+                      "HCL",
+
+                      "HTML",
+
+                      "HTML+ECR",
+
+                      "HTML+EEX",
+
+                      "HTML+ERB",
+
+                      "HTML+PHP",
+
+                      "HTML+Razor",
+
+                      "HTTP",
+
+                      "HXML",
+
+                      "Hack",
+
+                      "Haml",
+
+                      "Handlebars",
+
+                      "Harbour",
+
+                      "HashiCorp Configuration Language",
+
+                      "Haskell",
+
+                      "Haxe",
+
+                      "HiveQL",
+
+                      "HolyC",
+
+                      "Hy",
+
+                      "IDL",
+
+                      "IGOR Pro",
+
+                      "IPython Notebook",
+
+                      "Idris",
+
+                      "Ignore List",
+
+                      "ImageJ Macro",
+
+                      "Inform 7",
+
+                      "Io",
+
+                      "Ioke",
+
+                      "Isabelle ROOT",
+
+                      "Isabelle",
+
+                      "J",
+
+                      "JAR Manifest",
+
+                      "JFlex",
+
+                      "JSON with Comments",
+
+                      "JSON",
+
+                      "JSON5",
+
+                      "JSONLD",
+
+                      "JSONiq",
+
+                      "Jasmin",
+
+                      "Java Properties",
+
+                      "Java Server Pages",
+
+                      "Java",
+
+                      "JavaScript",
+
+                      "JavaScript+ERB",
+
+                      "Jest Snapshot",
+
+                      "Jinja",
+
+                      "Jison Lex",
+
+                      "Jison",
+
+                      "Jolie",
+
+                      "Jsonnet",
+
+                      "Julia",
+
+                      "Jupyter Notebook",
+
+                      "Kaitai Struct",
+
+                      "KakouneScript",
+
+                      "KiCad Layout",
+
+                      "KiCad Legacy Layout",
+
+                      "KiCad Schematic",
+
+                      "Kit",
+
+                      "Kotlin",
+
+                      "Kusto",
+
+                      "LFE",
+
+                      "LLVM",
+
+                      "LOLCODE",
+
+                      "LSL",
+
+                      "LTspice Symbol",
+
+                      "LabVIEW",
+
+                      "Lark",
+
+                      "Lasso",
+
+                      "Lean",
+
+                      "Less",
+
+                      "Lex",
+
+                      "LilyPond",
+
+                      "Limbo",
+
+                      "Linker Script",
+
+                      "Linux Kernel Module",
+
+                      "Liquid",
+
+                      "Literate Agda",
+
+                      "Literate CoffeeScript",
+
+                      "Literate Haskell",
+
+                      "LiveScript",
+
+                      "Logos",
+
+                      "Logtalk",
+
+                      "LookML",
+
+                      "LoomScript",
+
+                      "Lua",
+
+                      "M",
+
+                      "M4",
+
+                      "M4Sugar",
+
+                      "MATLAB",
+
+                      "MAXScript",
+
+                      "MLIR",
+
+                      "MQL4",
+
+                      "MQL5",
+
+                      "MTML",
+
+                      "MUF",
+
+                      "Macaulay2",
+
+                      "Makefile",
+
+                      "Mako",
+
+                      "Markdown",
+
+                      "Marko",
+
+                      "Mathematica",
+
+                      "Max",
+
+                      "Mercury",
+
+                      "Meson",
+
+                      "Metal",
+
+                      "Microsoft Developer Studio Project",
+
+                      "Microsoft Visual Studio Solution",
+
+                      "MiniD",
+
+                      "Mirah",
+
+                      "Modelica",
+
+                      "Modula-2",
+
+                      "Modula-3",
+
+                      "Module Management System",
+
+                      "Monkey",
+
+                      "Moocode",
+
+                      "MoonScript",
+
+                      "Motoko",
+
+                      "Motorola 68K Assembly",
+
+                      "Muse",
+
+                      "Myghty",
+
+                      "NASL",
+
+                      "NCL",
+
+                      "NEON",
+
+                      "NPM Config",
+
+                      "NSIS",
+
+                      "NWScript",
+
+                      "Nearley",
+
+                      "Nemerle",
+
+                      "NeoSnippet",
+
+                      "NetLinx",
+
+                      "NetLinx+ERB",
+
+                      "NetLogo",
+
+                      "NewLisp",
+
+                      "Nextflow",
+
+                      "Nginx",
+
+                      "Ninja",
+
+                      "Nit",
+
+                      "Nix",
+
+                      "NumPy",
+
+                      "Nunjucks",
+
+                      "ObjDump",
+
+                      "Object Data Instance Notation",
+
+                      "ObjectScript",
+
+                      "Objective-C",
+
+                      "Objective-C++",
+
+                      "Objective-J",
+
+                      "Odin",
+
+                      "Omgrofl",
+
+                      "Opa",
+
+                      "Opal",
+
+                      "Open Policy Agent",
+
+                      "OpenCL",
+
+                      "OpenEdge ABL",
+
+                      "OpenQASM",
+
+                      "OpenRC runscript",
+
+                      "OpenSCAD",
+
+                      "OpenStep Property List",
+
+                      "OpenType Feature File",
+
+                      "Org",
+
+                      "Ox",
+
+                      "Oxygene",
+
+                      "Oz",
+
+                      "P4",
+
+                      "PEG.js",
+
+                      "PHP",
+
+                      "PLpgSQL",
+
+                      "POV-Ray SDL",
+
+                      "Pan",
+
+                      "Papyrus",
+
+                      "Parrot Assembly",
+
+                      "Parrot Internal Representation",
+
+                      "Parrot",
+
+                      "Pascal",
+
+                      "Pawn",
+
+                      "Pep8",
+
+                      "Perl",
+
+                      "Pickle",
+
+                      "PicoLisp",
+
+                      "PigLatin",
+
+                      "Pike",
+
+                      "PlantUML",
+
+                      "Pod 6",
+
+                      "Pod",
+
+                      "PogoScript",
+
+                      "Pony",
+
+                      "PostCSS",
+
+                      "PostScript",
+
+                      "PowerShell",
+
+                      "Prisma",
+
+                      "Processing",
+
+                      "Proguard",
+
+                      "Prolog",
+
+                      "Promela",
+
+                      "Propeller Spin",
+
+                      "Protocol Buffer",
+
+                      "Protocol Buffers",
+
+                      "Public Key",
+
+                      "Pug",
+
+                      "Puppet",
+
+                      "Pure Data",
+
+                      "PureBasic",
+
+                      "PureScript",
+
+                      "Python",
+
+                      "Q#",
+
+                      "QMake",
+
+                      "Qt Script",
+
+                      "Quake",
+
+                      "R",
+
+                      "RAML",
+
+                      "RDoc",
+
+                      "REALbasic",
+
+                      "REXX",
+
+                      "RMarkdown",
+
+                      "RPC",
+
+                      "RPM Spec",
+
+                      "Racket",
+
+                      "Ragel",
+
+                      "Raw token data",
+
+                      "ReScript",
+
+                      "Readline Config",
+
+                      "Reason",
+
+                      "Rebol",
+
+                      "Record Jar",
+
+                      "Red",
+
+                      "Redirect Rules",
+
+                      "Regular Expression",
+
+                      "RenderScript",
+
+                      "Rich Text Format",
+
+                      "Ring",
+
+                      "Riot",
+
+                      "RobotFramework",
+
+                      "Roff",
+
+                      "Rouge",
+
+                      "Rscript",
+
+                      "Ruby",
+
+                      "Rust",
+
+                      "SAS",
+
+                      "SCSS",
+
+                      "SELinux Kernel Policy Language",
+
+                      "SELinux Policy",
+
+                      "SMT",
+
+                      "SPARQL",
+
+                      "SQF",
+
+                      "SQL",
+
+                      "SQLPL",
+
+                      "SRecode Template",
+
+                      "SSH Config",
+
+                      "STON",
+
+                      "SVG",
+
+                      "SWIG",
+
+                      "Sage",
+
+                      "SaltStack",
+
+                      "Sass",
+
+                      "Scala",
+
+                      "Scaml",
+
+                      "Scheme",
+
+                      "Scilab",
+
+                      "Self",
+
+                      "ShaderLab",
+
+                      "Shell",
+
+                      "ShellCheck Config",
+
+                      "Sieve",
+
+                      "Singularity",
+
+                      "Slash",
+
+                      "Slice",
+
+                      "Slim",
+
+                      "SmPL",
+
+                      "Smalltalk",
+
+                      "SnipMate",
+
+                      "Solidity",
+
+                      "Soong",
+
+                      "SourcePawn",
+
+                      "Spline Font Database",
+
+                      "Squirrel",
+
+                      "Stan",
+
+                      "Standard ML",
+
+                      "Starlark",
+
+                      "StringTemplate",
+
+                      "Stylus",
+
+                      "SubRip Text",
+
+                      "SugarSS",
+
+                      "SuperCollider",
+
+                      "Svelte",
+
+                      "Swift",
+
+                      "SystemVerilog",
+
+                      "TI Program",
+
+                      "TLA",
+
+                      "TOML",
+
+                      "TSQL",
+
+                      "TSV",
+
+                      "TSX",
+
+                      "TXL",
+
+                      "Tcl",
+
+                      "Tcsh",
+
+                      "TeX",
+
+                      "Tea",
+
+                      "Terra",
+
+                      "Texinfo",
+
+                      "Text",
+
+                      "TextMate Properties",
+
+                      "Textile",
+
+                      "Thrift",
+
+                      "Turing",
+
+                      "Turtle",
+
+                      "Twig",
+
+                      "Type Language",
+
+                      "TypeScript",
+
+                      "UltiSnip",
+
+                      "UltiSnips",
+
+                      "Unified Parallel C",
+
+                      "Unity3D Asset",
+
+                      "Unix Assembly",
+
+                      "Uno",
+
+                      "UnrealScript",
+
+                      "Ur",
+
+                      "Ur/Web",
+
+                      "UrWeb",
+
+                      "V",
+
+                      "VBA",
+
+                      "VCL",
+
+                      "VHDL",
+
+                      "Vala",
+
+                      "Valve Data Format",
+
+                      "Verilog",
+
+                      "Vim Help File",
+
+                      "Vim Script",
+
+                      "Vim Snippet",
+
+                      "Visual Basic .NET",
+
+                      "Vue",
+
+                      "Wavefront Material",
+
+                      "Wavefront Object",
+
+                      "Web Ontology Language",
+
+                      "WebAssembly",
+
+                      "WebVTT",
+
+                      "Wget Config",
+
+                      "Wikitext",
+
+                      "Windows Registry Entries",
+
+                      "Wollok",
+
+                      "World of Warcraft Addon Data",
+
+                      "X BitMap",
+
+                      "X Font Directory Index",
+
+                      "X PixMap",
+
+                      "X10",
+
+                      "XC",
+
+                      "XCompose",
+
+                      "XML Property List",
+
+                      "XML",
+
+                      "XPages",
+
+                      "XProc",
+
+                      "XQuery",
+
+                      "XS",
+
+                      "XSLT",
+
+                      "Xojo",
+
+                      "Xonsh",
+
+                      "Xtend",
+
+                      "YAML",
+
+                      "YANG",
+
+                      "YARA",
+
+                      "YASnippet",
+
+                      "Yacc",
+
+                      "ZAP",
+
+                      "ZIL",
+
+                      "Zeek",
+
+                      "ZenScript",
+
+                      "Zephir",
+
+                      "Zig",
+
+                      "Zimpl",
+
+                      "abl",
+
+                      "abuild",
+
+                      "acfm",
+
+                      "aconf",
+
+                      "actionscript 3",
+
+                      "actionscript3",
+
+                      "ada2005",
+
+                      "ada95",
+
+                      "adobe composite font metrics",
+
+                      "adobe multiple font metrics",
+
+                      "advpl",
+
+                      "ags",
+
+                      "ahk",
+
+                      "altium",
+
+                      "amfm",
+
+                      "amusewiki",
+
+                      "apache",
+
+                      "apkbuild",
+
+                      "arexx",
+
+                      "as3",
+
+                      "asm",
+
+                      "asp",
+
+                      "aspx",
+
+                      "aspx-vb",
+
+                      "ats2",
+
+                      "au3",
+
+                      "autoconf",
+
+                      "b3d",
+
+                      "bash session",
+
+                      "bash",
+
+                      "bat",
+
+                      "batch",
+
+                      "bazel",
+
+                      "blitz3d",
+
+                      "blitzplus",
+
+                      "bmax",
+
+                      "bplus",
+
+                      "bro",
+
+                      "bsdmake",
+
+                      "byond",
+
+                      "bzl",
+
+                      "c++-objdump",
+
+                      "c2hs",
+
+                      "cURL Config",
+
+                      "cake",
+
+                      "cakescript",
+
+                      "cfc",
+
+                      "cfm",
+
+                      "cfml",
+
+                      "chpl",
+
+                      "clipper",
+
+                      "coccinelle",
+
+                      "coffee",
+
+                      "coffee-script",
+
+                      "coldfusion html",
+
+                      "console",
+
+                      "cperl",
+
+                      "cpp",
+
+                      "csharp",
+
+                      "csound-csd",
+
+                      "csound-orc",
+
+                      "csound-sco",
+
+                      "cucumber",
+
+                      "curlrc",
+
+                      "cwl",
+
+                      "dcl",
+
+                      "delphi",
+
+                      "desktop",
+
+                      "dircolors",
+
+                      "django",
+
+                      "dosbatch",
+
+                      "dosini",
+
+                      "dpatch",
+
+                      "dtrace-script",
+
+                      "eC",
+
+                      "ecr",
+
+                      "editor-config",
+
+                      "edn",
+
+                      "eeschema schematic",
+
+                      "eex",
+
+                      "elisp",
+
+                      "emacs muse",
+
+                      "emacs",
+
+                      "email",
+
+                      "eml",
+
+                      "erb",
+
+                      "fb",
+
+                      "fish",
+
+                      "flex",
+
+                      "foxpro",
+
+                      "fsharp",
+
+                      "fstar",
+
+                      "ftl",
+
+                      "fundamental",
+
+                      "gf",
+
+                      "git-ignore",
+
+                      "gitattributes",
+
+                      "gitconfig",
+
+                      "gitignore",
+
+                      "gitmodules",
+
+                      "go mod",
+
+                      "go sum",
+
+                      "go.mod",
+
+                      "go.sum",
+
+                      "golang",
+
+                      "groff",
+
+                      "gsp",
+
+                      "hbs",
+
+                      "heex",
+
+                      "help",
+
+                      "html+django",
+
+                      "html+jinja",
+
+                      "html+ruby",
+
+                      "htmlbars",
+
+                      "htmldjango",
+
+                      "hylang",
+
+                      "i7",
+
+                      "ignore",
+
+                      "igor",
+
+                      "igorpro",
+
+                      "ijm",
+
+                      "inc",
+
+                      "inform7",
+
+                      "inputrc",
+
+                      "irc logs",
+
+                      "irc",
+
+                      "java server page",
+
+                      "jq",
+
+                      "jruby",
+
+                      "js",
+
+                      "jsonc",
+
+                      "jsp",
+
+                      "kak",
+
+                      "kakscript",
+
+                      "keyvalues",
+
+                      "ksy",
+
+                      "lassoscript",
+
+                      "latex",
+
+                      "leex",
+
+                      "lhaskell",
+
+                      "lhs",
+
+                      "lisp",
+
+                      "litcoffee",
+
+                      "live-script",
+
+                      "ls",
+
+                      "m2",
+
+                      "m68k",
+
+                      "mIRC Script",
+
+                      "macruby",
+
+                      "mail",
+
+                      "make",
+
+                      "man page",
+
+                      "man",
+
+                      "man-page",
+
+                      "manpage",
+
+                      "markojs",
+
+                      "max/msp",
+
+                      "maxmsp",
+
+                      "mbox",
+
+                      "mcfunction",
+
+                      "mdoc",
+
+                      "mediawiki",
+
+                      "mf",
+
+                      "mma",
+
+                      "mumps",
+
+                      "mupad",
+
+                      "nanorc",
+
+                      "nasm",
+
+                      "ne-on",
+
+                      "nesC",
+
+                      "nette object notation",
+
+                      "nginx configuration file",
+
+                      "nixos",
+
+                      "njk",
+
+                      "node",
+
+                      "npmrc",
+
+                      "nroff",
+
+                      "nush",
+
+                      "nvim",
+
+                      "obj-c",
+
+                      "obj-c++",
+
+                      "obj-j",
+
+                      "objc",
+
+                      "objc++",
+
+                      "objectivec",
+
+                      "objectivec++",
+
+                      "objectivej",
+
+                      "objectpascal",
+
+                      "objj",
+
+                      "octave",
+
+                      "odin-lang",
+
+                      "odinlang",
+
+                      "oncrpc",
+
+                      "ooc",
+
+                      "openedge",
+
+                      "openrc",
+
+                      "osascript",
+
+                      "pandoc",
+
+                      "pasm",
+
+                      "pcbnew",
+
+                      "perl-6",
+
+                      "perl6",
+
+                      "pir",
+
+                      "plain text",
+
+                      "posh",
+
+                      "postscr",
+
+                      "pot",
+
+                      "pov-ray",
+
+                      "povray",
+
+                      "progress",
+
+                      "protobuf",
+
+                      "pwsh",
+
+                      "pycon",
+
+                      "pyrex",
+
+                      "python3",
+
+                      "q",
+
+                      "ql",
+
+                      "qsharp",
+
+                      "ragel-rb",
+
+                      "ragel-ruby",
+
+                      "rake",
+
+                      "raw",
+
+                      "razor",
+
+                      "rb",
+
+                      "rbx",
+
+                      "reStructuredText",
+
+                      "readline",
+
+                      "red/system",
+
+                      "redirects",
+
+                      "regex",
+
+                      "regexp",
+
+                      "renpy",
+
+                      "rhtml",
+
+                      "robots txt",
+
+                      "robots",
+
+                      "robots.txt",
+
+                      "rpcgen",
+
+                      "rs",
+
+                      "rs-274x",
+
+                      "rss",
+
+                      "rst",
+
+                      "rusthon",
+
+                      "salt",
+
+                      "saltstate",
+
+                      "sed",
+
+                      "sepolicy",
+
+                      "sh",
+
+                      "shell-script",
+
+                      "shellcheckrc",
+
+                      "sml",
+
+                      "snippet",
+
+                      "sourcemod",
+
+                      "soy",
+
+                      "specfile",
+
+                      "splus",
+
+                      "squeak",
+
+                      "terraform",
+
+                      "tl",
+
+                      "tm-properties",
+
+                      "troff",
+
+                      "ts",
+
+                      "udiff",
+
+                      "vb .net",
+
+                      "vb.net",
+
+                      "vb6",
+
+                      "vbnet",
+
+                      "vdf",
+
+                      "vim",
+
+                      "vimhelp",
+
+                      "viml",
+
+                      "visual basic 6",
+
+                      "visual basic for applications",
+
+                      "visual basic",
+
+                      "vlang",
+
+                      "wasm",
+
+                      "wast",
+
+                      "wdl",
+
+                      "wgetrc",
+
+                      "wiki",
+
+                      "winbatch",
+
+                      "wisp",
+
+                      "wl",
+
+                      "wolfram lang",
+
+                      "wolfram language",
+
+                      "wolfram",
+
+                      "wsdl",
+
+                      "xBase",
+
+                      "xbm",
+
+                      "xdr",
+
+                      "xhtml",
+
+                      "xml+genshi",
+
+                      "xml+kid",
+
+                      "xpm",
+
+                      "xsd",
+
+                      "xsl",
+
+                      "xten",
+
+                      "yas",
+
+                      "yml",
+
+                      "zsh"
+                    ]
+                  }
+                },
+
+                "additionalProperties": false
+              },
+
+              "validations": {
+                "$ref": "#/definitions/validations",
+
+                "title": "textarea validations",
+
+                "description": "Textarea validations\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#validations"
+              }
+            },
+
+            "additionalProperties": false
+          }
+        },
+
+        {
+          "if": {
+            "properties": {
+              "type": {
+                "const": "input"
+              }
+            }
+          },
+
+          "then": {
+            "$comment": "For `additionalProperties` to work `type` must also be present here.",
+
+            "title": "input",
+
+            "description": "Input\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#input",
+
+            "type": "object",
+
+            "required": ["type", "attributes"],
+
+            "properties": {
+              "type": {
+                "$ref": "#/definitions/type"
+              },
+
+              "id": {
+                "$ref": "#/definitions/id",
+
+                "description": "An input id\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#keys"
+              },
+
+              "attributes": {
+                "title": "input attributes",
+
+                "description": "Input attributes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-2",
+
+                "type": "object",
+
+                "required": ["label"],
+
+                "properties": {
+                  "label": {
+                    "$ref": "#/definitions/label",
+
+                    "description": "A short input description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-2"
+                  },
+
+                  "description": {
+                    "$ref": "#/definitions/description",
+
+                    "description": "A long input description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-2"
+                  },
+
+                  "placeholder": {
+                    "$ref": "#/definitions/placeholder",
+
+                    "description": "An input placeholder\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-2"
+                  },
+
+                  "value": {
+                    "$ref": "#/definitions/value",
+
+                    "description": "An input value\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-2"
+                  }
+                },
+
+                "additionalProperties": false
+              },
+
+              "validations": {
+                "$ref": "#/definitions/validations",
+
+                "title": "input validations",
+
+                "description": "Input validations\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#validations-1"
+              }
+            },
+
+            "additionalProperties": false
+          }
+        },
+
+        {
+          "if": {
+            "properties": {
+              "type": {
+                "const": "dropdown"
+              }
+            }
+          },
+
+          "then": {
+            "$comment": "For `additionalProperties` to work `type` must also be present here.",
+
+            "title": "dropdown",
+
+            "description": "dropdown\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#dropdown",
+
+            "type": "object",
+
+            "required": ["type", "attributes"],
+
+            "properties": {
+              "type": {
+                "$ref": "#/definitions/type"
+              },
+
+              "id": {
+                "$ref": "#/definitions/id",
+
+                "description": "A dropdown id\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#keys"
+              },
+
+              "attributes": {
+                "title": "dropdown attributes",
+
+                "description": "Dropdown attributes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3",
+
+                "type": "object",
+
+                "required": ["label", "options"],
+
+                "properties": {
+                  "label": {
+                    "$ref": "#/definitions/label",
+
+                    "description": "A short dropdown description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3"
+                  },
+
+                  "description": {
+                    "$ref": "#/definitions/description",
+
+                    "description": "A long dropdown description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3"
+                  },
+
+                  "multiple": {
+                    "description": "Specify whether allow a multiple choices\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3",
+
+                    "type": "boolean",
+
+                    "default": false
+                  },
+
+                  "options": {
+                    "description": "Dropdown choices\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3",
+
+                    "type": "array",
+
+                    "minItems": 1,
+
+                    "uniqueItems": true,
+
+                    "items": {
+                      "type": "string",
+
+                      "minLength": 1,
+
+                      "examples": ["Sample choice"]
+                    }
+                  },
+
+                  "default": {
+                    "description": "Index of the default option\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-3",
+
+                    "type": "integer",
+
+                    "examples": [0]
+                  }
+                },
+
+                "additionalProperties": false
+              },
+
+              "validations": {
+                "$ref": "#/definitions/validations",
+
+                "title": "dropdown validations",
+
+                "description": "Dropdown validations\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#validations-2"
+              }
+            },
+
+            "additionalProperties": false
+          }
+        },
+
+        {
+          "if": {
+            "properties": {
+              "type": {
+                "const": "checkboxes"
+              }
+            }
+          },
+
+          "then": {
+            "$comment": "For `additionalProperties` to work `type` must also be present here.",
+
+            "title": "checkboxes",
+
+            "description": "Checkboxes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#checkboxes",
+
+            "type": "object",
+
+            "required": ["type", "attributes"],
+
+            "properties": {
+              "type": {
+                "$ref": "#/definitions/type"
+              },
+
+              "id": {
+                "$ref": "#/definitions/id",
+
+                "description": "Checkbox list id\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#keys"
+              },
+
+              "attributes": {
+                "title": "checkbox list attributes",
+
+                "description": "Checkbox list attributes\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4",
+
+                "type": "object",
+
+                "required": ["label", "options"],
+
+                "properties": {
+                  "label": {
+                    "$ref": "#/definitions/label",
+
+                    "description": "A short checkbox list description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4"
+                  },
+
+                  "description": {
+                    "$ref": "#/definitions/description",
+
+                    "description": "A long checkbox list description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4"
+                  },
+
+                  "options": {
+                    "description": "Checkbox list choices\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4",
+
+                    "type": "array",
+
+                    "minItems": 1,
+
+                    "items": {
+                      "title": "checkbox list choice",
+
+                      "description": "Checkbox list choice\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4",
+
+                      "type": "object",
+
+                      "required": ["label"],
+
+                      "properties": {
+                        "label": {
+                          "description": "A short checkbox list choice description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4",
+
+                          "type": "string",
+
+                          "minLength": 1,
+
+                          "examples": ["Sample label"]
+                        },
+
+                        "required": {
+                          "description": "Specify whether a choice is required\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-githubs-form-schema#attributes-4",
+
+                          "type": "boolean",
+
+                          "default": false
+                        }
+                      },
+
+                      "additionalProperties": false
+                    }
+                  }
+                },
+
+                "additionalProperties": false
+              }
+            },
+
+            "additionalProperties": false
+          }
+        }
+      ]
+    }
+  },
+
+  "properties": {
+    "name": {
+      "description": "An issue template name\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "type": "string",
+
+      "minLength": 1,
+
+      "examples": ["Sample name"]
+    },
+
+    "description": {
+      "description": "An issue template description\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "type": "string",
+
+      "minLength": 1,
+
+      "examples": ["Sample description"]
+    },
+
+    "body": {
+      "description": "An issue template body\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "type": "array",
+
+      "minItems": 1,
+
+      "items": {
+        "$ref": "#/definitions/form_item"
+      }
+    },
+
+    "assignees": {
+      "description": "An issue template assignees\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "oneOf": [
+        {
+          "$ref": "#/definitions/assignee"
+        },
+
+        {
+          "type": "array",
+
+          "minItems": 1,
+
+          "uniqueItems": true,
+
+          "items": {
+            "$ref": "#/definitions/assignee"
+          }
+        }
+      ]
+    },
+
+    "labels": {
+      "description": "An issue template labels\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "type": "array",
+
+      "minItems": 1,
+
+      "uniqueItems": true,
+
+      "items": {
+        "type": "string",
+
+        "minLength": 1,
+
+        "examples": [
+          "Sample label",
+
+          "bug",
+
+          "documentation",
+
+          "duplicate",
+
+          "enhancement",
+
+          "good first issue",
+
+          "help wanted",
+
+          "invalid",
+
+          "question",
+
+          "wontfix"
+        ]
+      }
+    },
+
+    "title": {
+      "description": "An issue template title\nhttps://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/syntax-for-issue-forms#top-level-syntax",
+
+      "type": "string",
+
+      "minLength": 1,
+
+      "examples": ["Sample title", "Bug: ", "Feature: "]
+    }
+  },
+
+  "required": ["name", "description", "body"],
+
+  "title": "GitHub issue forms config file schema",
+
+  "type": "object"
+}
diff --git a/template_config.yaml b/template_config.yaml
index f90291a43..223c11fe9 100644
--- a/template_config.yaml
+++ b/template_config.yaml
@@ -23,5 +23,5 @@ tag_operation_files: # DICOM tag anonymisation operations
     manufacturer_overrides: none # Manufactuer-dependendent overrides
 
 destination:
-    dicom: "ftps" # alternatives: "dicomweb", "none"
+    dicom: "ftps" # alternatives: "dicomweb", "xnat", "none"
     parquet: "ftps" # alternatives: "none"
diff --git a/test/.env b/test/.env
index e5ff8ec9f..ad9b56d91 100644
--- a/test/.env
+++ b/test/.env
@@ -1,8 +1,11 @@
 ENV=test
 DEBUG=True
-PIXL_DICOM_TRANSFER_TIMEOUT=120
-PIXL_QUERY_TIMEOUT=120
-PIXL_MAX_MESSAGES_IN_FLIGHT=20
+LOG_LEVEL=DEBUG
+PIXL_DICOM_TRANSFER_TIMEOUT=100
+PIXL_QUERY_TIMEOUT=20
+CLI_RETRY_SECONDS=90
+PIXL_MAX_MESSAGES_IN_FLIGHT=5
+TZ=Europe/London
 
 # PIXL PostgreSQL instance
 PIXL_DB_HOST=postgres
@@ -12,14 +15,6 @@ PIXL_DB_USER=pixl_db_username
 PIXL_DB_PASSWORD=pixl_db_password
 SKIP_ALEMBIC=false
 
-# EMAP UDS
-EMAP_UDS_HOST=star
-EMAP_UDS_PORT=5432
-EMAP_UDS_NAME=emap
-EMAP_UDS_USER=postgres
-EMAP_UDS_PASSWORD=postgres
-EMAP_UDS_SCHEMA_NAME=star
-
 # Exposed ports
 HASHER_API_PORT=7010
 POSTGRES_PORT=7001
@@ -55,21 +50,24 @@ ORTHANC_RAW_RECORD_HEADERS=true
 ORTHANC_RAW_HEADER_LOG_PATH=/tmp/headers.csv
 
 # PIXL Orthanc anon instance
+ORTHANC_ANON_URL=http://orthanc-anon:8042
 ORTHANC_ANON_USERNAME=orthanc_anon_username
 ORTHANC_ANON_PASSWORD=orthanc_anon_password
 ORTHANC_ANON_AE_TITLE=ORTHANCANON
 ORTHANC_ANON_HTTP_TIMEOUT=60
 ENABLE_DICOM_WEB=true
 ORTHANC_AUTOROUTE_ANON_TO_ENDPOINT=true
-PIXL_DICOM_TRANSFER_TIMEOUT=240
 STUDY_TIME_OFFSET=0
 LOCAL_SALT_VALUE=PIXL
 
 # UCVNAQR DICOM node information
-VNAQR_AE_TITLE=VNAQR
-VNAQR_DICOM_PORT=4242
-VNAQR_IP_ADDR=vna-qr
-VNAQR_MODALITY=UCVNAQR
+PRIMARY_DICOM_SOURCE_AE_TITLE=PRIMARYQR
+PRIMARY_DICOM_SOURCE_PORT=4242
+PRIMARY_DICOM_SOURCE_IP_ADDR=vna-qr
+PRIMARY_DICOM_SOURCE_MODALITY=UCPRIMARYQR
+
+# UCVNAQR DICOM node information
+SECONDARY_DICOM_SOURCE_MODALITY=UCSECONDARYQR
 
 # RabbitMQ
 RABBITMQ_HOST=localhost
diff --git a/test/README.md b/test/README.md
index 15d8f704a..2a3723cca 100644
--- a/test/README.md
+++ b/test/README.md
@@ -3,14 +3,12 @@
 This directory contains a system/integration test that runs locally and aims to test the essential
 functionality of the full PIXL system.
 
-**Given** a DICOM image in an Orthanc instance (mocked vendor neutral archive, VNA) and a single
-patient with the same identifier in a postgres instance (mocked EMAP database, star schema).
+**Given** a DICOM image in an Orthanc instance (mocked vendor neutral archive, VNA)
 
 **When** a message containing the patient and study identifier is added to the queue and the
 consumers started.
 
-**Then** a row in the "anon" EMAP data instance of the PIXL postgres instance exists and the DICOM
-study exists in the "anon" PIXL Orthanc instance.
+**Then** the DICOM study exists in the "anon" PIXL Orthanc instance.
 
 After setting up your [.secrets.env](../README.md#project-secrets)), you can run the system test with:
 
diff --git a/test/conftest.py b/test/conftest.py
index a25b1b70b..79cb460d7 100644
--- a/test/conftest.py
+++ b/test/conftest.py
@@ -14,17 +14,29 @@
 """System/E2E test setup"""
 
 # ruff: noqa: C408 dict() makes test data easier to read and write
+import os
 from collections.abc import Generator
 from pathlib import Path
 from typing import Any
 
+from core.db.models import Base
+from sqlalchemy import URL, create_engine
+from sqlalchemy.orm import sessionmaker
+
+# Setting env variables before loading modules
+os.environ["PIXL_DB_HOST"] = "localhost"
+os.environ["PIXL_DB_PORT"] = "7001"
+os.environ["PIXL_DB_USER"] = "pixl_db_username"
+os.environ["PIXL_DB_PASSWORD"] = "pixl_db_password"
+os.environ["PIXL_DB_NAME"] = "pixl"
+
 import pytest
 import requests
 from pytest_pixl.dicom import generate_dicom_dataset
 from pytest_pixl.ftpserver import PixlFTPServer
 from pytest_pixl.helpers import run_subprocess
 from pytest_pixl.plugin import FtpHostAddress
-from utils import wait_for_stable_orthanc_anon
+from utils import wait_for_images_to_be_exported
 
 pytest_plugins = "pytest_pixl"
 
@@ -39,6 +51,7 @@ def host_export_root_dir() -> Path:
 RESOURCES_DIR = TEST_DIR / "resources"
 RESOURCES_OMOP_DIR = RESOURCES_DIR / "omop"
 RESOURCES_OMOP_DICOMWEB_DIR = RESOURCES_DIR / "omop-dicomweb"
+SECONDS_TO_WAIT_FOR_EXPORT = 301
 
 
 def _upload_to_vna(image_filename: Path) -> None:
@@ -58,12 +71,6 @@ def _populate_vna(tmp_path_factory: pytest.TempPathFactory) -> None:
     # more detailed series testing is found in pixl_dcmd tests, but here
     # we just stick an instance to each study, one of which is expected to be propagated through
 
-    # studies are also defined by the StudyID, the StudyInstanceUID
-    def study_instance_uid(offset: int) -> dict[str, str]:
-        baseline = "1.3.46.670589.11.38023.5.0.14068.2023012517090166000"
-        offset_str = f"{offset:04d}"
-        return dict(StudyInstanceUID=baseline[: -len(offset_str)] + offset_str)
-
     def series_instance_uid(offset: int) -> dict[str, str]:
         baseline = "1.3.46.670589.11.38023.5.0.7404.2023012517551898153"
         offset_str = f"{offset:04d}"
@@ -78,13 +85,13 @@ def sop_instance_uid(offset: int) -> dict[str, str]:
         AccessionNumber="AA12345601",
         PatientID="987654321",
         StudyID="12340001",
-        **study_instance_uid(1),
+        StudyInstanceUID="1.3.6.1.4.1.14519.5.2.1.99.1071.12985477682660597455732044031486",
     )
     study_2 = dict(
         AccessionNumber="AA12345605",
         PatientID="987654321",
         StudyID="12340002",
-        **study_instance_uid(2),
+        StudyInstanceUID="1.2.276.0.7230010.3.1.2.929116473.1.1710754859.579485",
     )
 
     # Series are also defined by the SeriesInstanceUID and SeriesNumber.
@@ -137,9 +144,13 @@ def _upload_dicom_instance(dicom_dir: Path, **kwargs: Any) -> None:
 @pytest.fixture(scope="session")
 def _setup_pixl_cli(ftps_server: PixlFTPServer, _populate_vna: None) -> Generator:
     """Run pixl populate/start. Cleanup intermediate export dir on exit."""
-    run_subprocess(["pixl", "populate", str(RESOURCES_OMOP_DIR.absolute())], TEST_DIR)
-    # poll here for two minutes to check for imaging to be processed, printing progress
-    wait_for_stable_orthanc_anon(121, 5, 15, min_instances=3)
+    run_subprocess(
+        ["pixl", "populate", "--num-retries", "0", str(RESOURCES_OMOP_DIR.absolute())],
+        TEST_DIR,
+        timeout=600,
+    )
+    # poll here to check for imaging to be processed, printing progress
+    wait_for_images_to_be_exported(SECONDS_TO_WAIT_FOR_EXPORT, 5, 15)
     yield
     run_subprocess(
         [
@@ -157,9 +168,13 @@ def _setup_pixl_cli(ftps_server: PixlFTPServer, _populate_vna: None) -> Generato
 @pytest.fixture(scope="session")
 def _setup_pixl_cli_dicomweb(_populate_vna: None) -> Generator:
     """Run pixl populate/start. Cleanup intermediate export dir on exit."""
-    run_subprocess(["pixl", "populate", str(RESOURCES_OMOP_DICOMWEB_DIR.absolute())], TEST_DIR)
-    # poll here for two minutes to check for imaging to be processed, printing progress
-    wait_for_stable_orthanc_anon(121, 5, 15, min_instances=3)
+    run_subprocess(
+        ["pixl", "populate", "--num-retries", "0", str(RESOURCES_OMOP_DICOMWEB_DIR.absolute())],
+        TEST_DIR,
+        timeout=600,
+    )
+    # poll here to check for imaging to be processed, printing progress
+    wait_for_images_to_be_exported(SECONDS_TO_WAIT_FOR_EXPORT, 5, 15)
     yield
     run_subprocess(
         [
@@ -187,3 +202,28 @@ def _export_patient_data(_setup_pixl_cli) -> None:  # type: ignore [no-untyped-d
     is synchronous (whether that is itself wise is another matter).
     """
     run_subprocess(["pixl", "export-patient-data", str(RESOURCES_OMOP_DIR.absolute())], TEST_DIR)
+
+
+@pytest.fixture(scope="session", autouse=True)
+def _cleanup_database() -> Generator:
+    """
+    Remove the test data from the database so we can re-run the tests.
+
+    If the database is not cleaned, the data will not be exported when the
+    tests are re-run, which results in `wait_for_condition` timing out.
+    """
+    yield
+    url = URL.create(
+        drivername="postgresql+psycopg2",
+        username=os.environ["PIXL_DB_USER"],
+        password=os.environ["PIXL_DB_PASSWORD"],
+        host="localhost",
+        port=os.environ["PIXL_DB_PORT"],
+        database=os.environ["PIXL_DB_NAME"],
+    )
+    engine = create_engine(url)
+    PixlSession = sessionmaker(engine)
+    with PixlSession() as session:
+        for table in reversed(Base.metadata.sorted_tables):
+            session.execute(table.delete())
+        session.commit()
diff --git a/test/docker-compose.yml b/test/docker-compose.yml
index 71f186b72..f123709fc 100644
--- a/test/docker-compose.yml
+++ b/test/docker-compose.yml
@@ -22,13 +22,14 @@ services:
         image: orthancteam/orthanc:24.3.3
         platform: linux/amd64
         environment:
-            ORTHANC_NAME: ${VNAQR_AE_TITLE}
+            ORTHANC_NAME: ${PRIMARY_DICOM_SOURCE_AE_TITLE}
             ORTHANC_USERNAME: "orthanc"
             ORTHANC_PASSWORD: "orthanc"
-            ORTHANC_AE_TITLE: "VNAQR"
+            ORTHANC_AE_TITLE: "PRIMARYQR"
             RAW_AE_TITLE: ${ORTHANC_RAW_AE_TITLE}
             RAW_DICOM_PORT: "4242"
             RAW_IP_ADDR: "orthanc-raw" # aka. hostname
+            TZ: ${TZ:-Europe/London}
         ports:
             - "127.0.0.1:4243:4242"
             - "127.0.0.1:8043:8042"
@@ -54,6 +55,7 @@ services:
             RAW_DICOM_PORT: "4242"
             RAW_IP_ADDR: "dicomweb-server" # aka. hostname
             DICOM_WEB_PLUGIN_ENABLED: true
+            TZ: ${TZ:-Europe/London}
         ports:
             - "127.0.0.1:4244:4242"
             - "127.0.0.1:8044:8042"
diff --git a/test/resources/omop-dicomweb/private/PROCEDURE_OCCURRENCE_LINKS.parquet b/test/resources/omop-dicomweb/private/PROCEDURE_OCCURRENCE_LINKS.parquet
index f4a1d6370..c1c49f80d 100644
Binary files a/test/resources/omop-dicomweb/private/PROCEDURE_OCCURRENCE_LINKS.parquet and b/test/resources/omop-dicomweb/private/PROCEDURE_OCCURRENCE_LINKS.parquet differ
diff --git a/test/resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet b/test/resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet
index f4a1d6370..c1c49f80d 100644
Binary files a/test/resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet and b/test/resources/omop/private/PROCEDURE_OCCURRENCE_LINKS.parquet differ
diff --git a/test/run-system-test.sh b/test/run-system-test.sh
index 01cdf3645..da7c71fd7 100755
--- a/test/run-system-test.sh
+++ b/test/run-system-test.sh
@@ -18,8 +18,11 @@ PACKAGE_DIR="${BIN_DIR%/*}"
 cd "${PACKAGE_DIR}/test"
 
 setup() {
+    # NOTE: the `pixl dc` command only work when run from the PIXL project root.
+    # However, doing so will fail unless a valid .env file with all the necessary environment 
+    # variables is present.
     docker compose --env-file .env -p system-test down --volumes
-    #
+
     # Note: cannot run as single docker compose command due to different build contexts
     docker compose --env-file .env -p system-test up --wait -d --build --remove-orphans
     # Warning: Requires to be run from the project root
diff --git a/test/system_test.py b/test/system_test.py
index 6d7ae6171..6fc53b0c0 100644
--- a/test/system_test.py
+++ b/test/system_test.py
@@ -14,26 +14,28 @@
 """Replacement for the 'interesting' bits of the system/E2E test"""
 
 from pathlib import Path
-from typing import Any
 
 import pandas as pd
 import pydicom
 import pytest
 import requests
-from core.dicom_tags import DICOM_TAG_PROJECT_NAME
 from loguru import logger
+from pydicom.uid import UID
+from pytest_check import check
 from pytest_pixl.ftpserver import PixlFTPServer
 from pytest_pixl.helpers import run_subprocess, wait_for_condition
 
 pytest_plugins = "pytest_pixl"
 
+SECONDS_TO_WAIT_FOR_CONDITION = 251
+
 
 @pytest.fixture()
-def expected_studies() -> dict[str, Any]:
+def expected_studies() -> dict[int, dict]:
     """Expected study metadata post-anonymisation."""
     return {
-        "d40f0639105babcdec043f1acf7330a8ebd64e64f13f7d0d4745f0135ddee0cd": {
-            "procedure_occurrence_id": 4,
+        4: {
+            "original_study_instance_uid": "1.3.46.670589.11.38023.5.0.14068.2023012517090160001",
             "instances": {
                 # tuple made up of (AccessionNumber, SeriesDescription)
                 # for AA12345601
@@ -41,8 +43,8 @@ def expected_studies() -> dict[str, Any]:
                 ("ANONYMIZED", "AP"),
             },
         },
-        "7ff25b0b438d23a31db984f49b0d6ca272104eb3d20c82f30e392cff5446a9c3": {
-            "procedure_occurrence_id": 5,
+        5: {
+            "original_study_instance_uid": "1.3.46.670589.11.38023.5.0.14068.2023012517090160002",
             "instances": {
                 # for AA12345605,
                 ("ANONYMIZED", "include123"),
@@ -99,15 +101,16 @@ def test_ftps_radiology_linker_upload(self, expected_studies: dict) -> None:
             TestFtpsUpload.expected_public_parquet_dir / "radiology" / "IMAGE_LINKER.parquet"
         )
         po_col = radiology_linker_data["procedure_occurrence_id"]
-        for study_id, studies in expected_studies.items():
-            expected_po_id = studies["procedure_occurrence_id"]
+        for procedure_occurrence_id, studies in expected_studies.items():
+            expected_po_id = procedure_occurrence_id
             row = radiology_linker_data[po_col == expected_po_id].iloc[0]
-            assert row.hashed_identifier == study_id
+            assert UID(row.pseudo_study_uid).is_valid
+            assert row.pseudo_study_uid != studies["original_study_instance_uid"]
 
         assert radiology_linker_data.shape[0] == 2
         assert set(radiology_linker_data.columns) == {
             "procedure_occurrence_id",
-            "hashed_identifier",
+            "pseudo_study_uid",
         }
 
     @pytest.mark.usefixtures("_export_patient_data")
@@ -128,21 +131,26 @@ def two_zip_files_present() -> bool:
 
         wait_for_condition(
             two_zip_files_present,
-            seconds_max=121,
+            seconds_max=SECONDS_TO_WAIT_FOR_CONDITION,
             seconds_interval=5,
             seconds_condition_stays_true_for=15,
             progress_string_fn=zip_file_list,
         )
         assert zip_files
+        radiology_linker_data = pd.read_parquet(
+            TestFtpsUpload.expected_public_parquet_dir / "radiology" / "IMAGE_LINKER.parquet"
+        )
+        radiology_linker_data = radiology_linker_data.set_index("pseudo_study_uid")
         for z in zip_files:
             unzip_dir = tmp_path_factory.mktemp("unzip_dir", numbered=True)
-            self._check_dcm_tags_from_zip(z, unzip_dir, expected_studies)
+            procedure = radiology_linker_data.loc[z.stem]["procedure_occurrence_id"]
+            logger.info("Checking tags in zip file {} for procedure {}", z, procedure)
+            self._check_dcm_tags_from_zip(z, unzip_dir, expected_studies[procedure])
 
     def _check_dcm_tags_from_zip(
-        self, zip_path: Path, unzip_dir: Path, expected_studies: dict
+        self, zip_path: Path, unzip_dir: Path, expected_study: dict
     ) -> None:
         """Check that private tag has survived anonymisation with the correct value."""
-        expected_instances = expected_studies[zip_path.stem]["instances"]
         run_subprocess(
             ["unzip", zip_path],
             working_dir=unzip_dir,
@@ -156,26 +164,13 @@ def _check_dcm_tags_from_zip(
         for dcm_file in dicom_in_zip:
             dcm = pydicom.dcmread(dcm_file)
             # The actual dicom filename and dir structure isn't checked - should it be?
-            assert dcm.get("PatientID") == zip_path.stem  # PatientID stores study id post anon
+            assert (
+                dcm.get("StudyInstanceUID") == zip_path.stem
+            )  # StudyInstanceUID stores the pseudo study id post anon
             actual_instances.add((dcm.get("AccessionNumber"), dcm.get("SeriesDescription")))
-            block = dcm.private_block(
-                DICOM_TAG_PROJECT_NAME.group_id, DICOM_TAG_PROJECT_NAME.creator_string
-            )
-            tag_offset = DICOM_TAG_PROJECT_NAME.offset_id
-            private_tag = block[tag_offset]
-            assert private_tag is not None
-            if isinstance(private_tag.value, bytes):
-                # Allow this for the time being, until it has been investigated
-                # See https://github.com/UCLH-Foundry/PIXL/issues/363
-                logger.error(
-                    "TEMPORARILY IGNORE: tag value {} should be of type str, but is of type bytes",
-                    private_tag.value,
-                )
-                assert private_tag.value.decode() == TestFtpsUpload.project_slug
-            else:
-                assert private_tag.value == TestFtpsUpload.project_slug
         # check the basic info about the instances exactly matches
-        assert actual_instances == expected_instances
+        with check:
+            assert actual_instances == expected_study["instances"]
 
 
 @pytest.mark.usefixtures("_setup_pixl_cli_dicomweb")
@@ -201,7 +196,7 @@ def two_studies_present_on_dicomweb() -> bool:
 
     wait_for_condition(
         two_studies_present_on_dicomweb,
-        seconds_max=121,
+        seconds_max=SECONDS_TO_WAIT_FOR_CONDITION,
         seconds_interval=10,
         progress_string_fn=dicomweb_studies_list,
     )
diff --git a/test/utils.py b/test/utils.py
index 10ac4161d..b512d8d46 100644
--- a/test/utils.py
+++ b/test/utils.py
@@ -14,48 +14,49 @@
 
 """Utilities for the system test"""
 
-import json
-import shlex
-import subprocess
 from functools import partial, update_wrapper
+from typing import cast
 
+from core.db.models import Image
+from core.db.queries import engine
 from pytest_pixl.helpers import wait_for_condition
+from sqlalchemy import not_
+from sqlalchemy.orm import sessionmaker
 
 
-def wait_for_stable_orthanc_anon(
+def wait_for_images_to_be_exported(
     seconds_max: int,
     seconds_interval: int,
     seconds_condition_stays_true_for: int,
-    min_instances: int = 3,
+    min_studies: int = 2,
 ) -> None:
     """
-    Query the orthanc-anon REST API to check that the correct number of instances
-    have been received.
+    Query pixl DB to ensure that images have been processed and exported.
     If they haven't within the time limit, raise a TimeoutError
     """
-    instances = []
+    studies: list[Image] = []
 
-    def at_least_n_intances(n_intances: int) -> bool:
-        nonlocal instances
-        instances_cmd = shlex.split(
-            "docker exec system-test-orthanc-anon-1 "
-            'curl -u "orthanc_anon_username:orthanc_anon_password" '
-            "http://orthanc-anon:8042/instances"
-        )
-        instances_output = subprocess.run(instances_cmd, capture_output=True, check=True, text=True)  # noqa: S603
-        instances = json.loads(instances_output.stdout)
-        return len(instances) >= n_intances
+    def at_least_n_studies_exported(n_studies: int) -> bool:
+        nonlocal studies
 
-    condition = partial(at_least_n_intances, min_instances)
-    update_wrapper(condition, at_least_n_intances)
+        PixlSession = sessionmaker(engine)
+        with PixlSession() as session:
+            studies = cast(
+                list[Image],
+                session.query(Image).filter(not_(Image.exported_at.is_(None))).all(),
+            )
+        return len(studies) >= n_studies
 
-    def list_instances() -> str:
-        return f"Expecting at least {min_instances} instances.\northanc-anon instances: {instances}"
+    condition = partial(at_least_n_studies_exported, min_studies)
+    update_wrapper(condition, at_least_n_studies_exported)
+
+    def list_studies() -> str:
+        return f"Expecting at least {min_studies} studies.\nexported studies: {studies}"
 
     wait_for_condition(
         condition,
         seconds_max=seconds_max,
         seconds_interval=seconds_interval,
-        progress_string_fn=list_instances,
+        progress_string_fn=list_studies,
         seconds_condition_stays_true_for=seconds_condition_stays_true_for,
     )