Update SNOMED-CT mapping #324
Draft
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fedorov
force-pushed
the
update-snomed-mapping
branch
from
ad2ba69 to
e2666ee
Compare
fedorov
force-pushed
the
update-snomed-mapping
branch
4 times, most recently
from
eb4d616 to
81af678
Compare
|
@lassoan I think it is ready for you. |
|
@fedorov the column names are still the long ones (it should be Category.CodingSchemeDesignator instead of SegmentedPropertyCategoryCodeSequence.CodingSchemeDesignator etc.) and I don't see the color columns. |
|
I am sorry, I lost track of the many files and sheets ... let me fix it. |
fedorov
force-pushed
the
update-snomed-mapping
branch
4 times, most recently
from
b0a25cc to
c48536a
Compare
|
@lassoan it should be ready now. |
|
@lassoan this one is still waiting for you! |
|
Thank you for the reminder! I'll finalize this. I don't remember if we added the total_mr segments as well? |
|
Yes! You can confirm this from the notebook I used for processing: https://colab.research.google.com/drive/16sKS1W6Z9LbwHhZMM_I0xwkv0ZBCj8Lg?usp=sharing |
Done |
The updated mapping should now include all of the structures listed in totalsegmentator/map_to_binary.py. To create this map, the content of the original SNOMED mapping CSV was merged with the exhaustive list of the labels from map_to_binary.py, and the mapping for the missing structures was populated.
Colors added were originally contributed in https://github.com/ImagingDataCommons/CloudSegmentator/blob/main/workflows/TotalSegmentator/resources/totalsegmentator_snomed_mapping_with_partial_colors.csv and are optimized to improve contrast between the neighboring structures for the purposes of visual review of TotalSegmentator results. Also, amended the column names to make them more readable. Specifically, the specific DICOM attributes used in DICOM Segmentation that were used as column names earlier were replaced by shorter names as follows: - SegmentedPropertyCategoryCodeSequence -> Category - SegmentedPropertyTypeCodeSequence -> Type - SegmentedPropertyTypeModifierCodeSequence -> TypeModifier - AnatomicRegionSequence > AnatomicRegion - AnatomicRegionModifierSequence > AnatomicRegionModifier Co-authored-by: Vamsi Thiriveedhi <[email protected]> Co-authored-by: Deepa Krishnaswamy <[email protected]> Co-authored-by: Andras Lasso <[email protected]>
fedorov
force-pushed
the
update-snomed-mapping
branch
from
c48536a to
dad35aa
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The updated mapping should now include all of the structures listed in totalsegmentator/map_to_binary.py.
To create this map, the content of the original SNOMED mapping CSV was merged with the exhaustive list of the labels from map_to_binary.py, and the mapping for the missing structures was populated.
Here's a google sheet in case anyone wants to review and comment in an easier manner than PR comments: https://docs.google.com/spreadsheets/d/1oEzXCmraoLgbbb5lNxWiHuYDza86aXxKqSUmUetwI7M/edit?usp=sharing.
Script I used to merge various things together, for the sake of historical perspective: https://colab.research.google.com/drive/16sKS1W6Z9LbwHhZMM_I0xwkv0ZBCj8Lg?usp=sharing
cc: @lassoan