framework v1

[casperdcl]

one example notebook

1. download data https://github.com/TomographicImaging/SyneRBI-Challenge/blob/nema-data/src/SIRF_data_preparation/try_data_preparation.py
2. run NEMA reconstruction (BSREM Algorithm) https://github.com/SyneRBI/SIRF-Contribs/blob/master/src/notebooks/BSREM_illustration.ipynb
3. get ROIs https://github.com/SyneRBI/SIRF-Contribs/blob/master/src/Python/sirf/contrib/NEMA/generate_nema_rois.py
4. run metrics https://github.com/TomographicImaging/Hackathon-000-Stochastic-QualityMetrics/blob/cil_callback/img_quality_cil_stir/image_quality_callback.py
   • Challenge metrics.docx
5. dummy Algorithm for users to implement custom reconstruction with

submissions & leaderboard

1. template repo (this one)
2. README instructions
   • must use SIRF projectors
   • must use CIL Algorithm
   • max binary size 1GB (e.g. pretrained CNN weights)
3. one private fork per team (maybe hosted by us + we manually give write access to GH usernames)
4. GH workflow to evaluate metrics & update leaderboard
   • on: push: quick basic tests
   • on: tag: full run one dataset
   • after submission deadline: full run on more datasets (maybe only on top 30%)

ideas/TODO

• Callback in Algorithm TomographicImaging/CIL#1584
• example notebook #2, Nema data preparation #3, ...?
  • adding script for NEMA ROI generation SIRF-Contribs#10, adding BGR ROI as sphere number 7 SIRF-Contribs#12 -> https://github.com/SyneRBI/SIRF-Contribs/blob/master/src/Python/sirf/contrib/NEMA/generate_nema_rois.py
  • https://github.com/TomographicImaging/Hackathon-000-Stochastic-QualityMetrics
  • re-use existing cil.optimisation.algorithms.Algorithm functionality in main.py
• running
  • docker docker-stacks and jupyterhub SIRF-SuperBuild#718
    • fix fix docker deploy SIRF-SuperBuild#866
  • devcontainers? add devcontainer spec SIRF-SuperBuild#865
• GitHub Action to evaluate metrics & update leaderboard
  • self-hosted runner