harmonzie labels for longitudinal lesions - WIP

[frheault]

Quick description

This script takes in multiple lesions file (labels) from a single subject (could be scan-rescan, longitudinal, etc.) and relabel the lesions so the overlapping, temporally consistent lesions will have the same labels.

Based on:
https://www.sciencedirect.com/science/article/pii/S2213158218303711?via%3Dihub

...

Type of change

Check the relevant options.

• 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

Provide data, screenshots, command line to test (if relevant)

...

Checklist

• My code follows the style guidelines of this project (run autopep8)
• I added relevant citations to scripts, modules and functions docstrings and descriptions
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I moved all functions from the script file (except the argparser and main) to scilpy modules
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[pep8speaks]

Hello @frheault, Thank you for updating !

• In the file scilpy/image/labels.py:

Line 13:80: E501 line too long (88 > 79 characters)
Line 517:80: E501 line too long (80 > 79 characters)
Line 563:80: E501 line too long (86 > 79 characters)
Line 579:80: E501 line too long (81 > 79 characters)

• In the file scripts/scil_lesions_harmonize_labels.py:

Line 104:80: E501 line too long (81 > 79 characters)

Comment last updated at 2024-10-29 15:43:26 UTC

[frheault]

@Manonedde @ThoumyreStanislas If you have real data (co-registered), this could be tested.

If there are corner cases or problems, I will fix them before adding tests.

[codecov]

Codecov Report

Attention: Patch coverage is 3.19149% with 91 lines in your changes missing coverage. Please review.

Project coverage is 68.52%. Comparing base (b95593b) to head (34b73b3).

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #1039      +/-   ##
==========================================
- Coverage   68.79%   68.52%   -0.28%     
==========================================
  Files         432      433       +1     
  Lines       22456    22550      +94     
  Branches     3038     3057      +19     
==========================================
+ Hits        15449    15452       +3     
- Misses       5709     5800      +91     
  Partials     1298     1298              

Components	Coverage Δ
Scripts	69.44% <0.00%> (-0.23%)	⬇️
Library	67.21% <5.76%> (-0.35%)	⬇️

[Manonedde]

Here are test data from MS myelo-inferno subjects. Lesion masks are coregistered to session 1: sub-004_ms_test_harmonize_lesion.tar.gz

The results seem coherent but for the newly labelled lesion 160 (parahip lesion, green-yellow colors), for session 4 it is labelled 169 (in red) whereas it is close to lesion 160 (session 2, 3 and 5). Here are the results: Harmonize_labels.tar.gz

Harmonize_labels.tar.gz
sub-004_ms_test_harmonize_lesion.tar.gz

[Manonedde]

@frheault
Coregister_lesions.zip