Skip to content

Conversation

naga-karthik
Copy link
Collaborator

This PR adds a script to create a list of difficult cases. This list of subjects could be used for benchmarking our segmentation models.

Resolves #131

@naga-karthik naga-karthik marked this pull request as ready for review January 27, 2025 20:13
Copy link
Member

@jcohenadad jcohenadad left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i would change the name of the function-- it is misleading-- eg: create_folder_of_difficult_subjects.py

Copy link
Member

@jcohenadad jcohenadad left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i don't think this script will be very useful in the long term-- the idea is:

  • for each project (in this case, contrast-agnostic), identify the subjects based on:
    • BIDS dataset root and subj (eg: data/xxx/sub-xxx)
    • concatenate those into a YAML that goes as input into sct_run_batch
    • in the future we can run sct_run_batch -include-list
  • What if subjects span across multiple BIDS datasets?
    • solution 1: create a loop (eg in shell or python) that splits the subjs across roots datasets and then run sct_run_batch
    • solution 2: post feature request in SCT to accept running across BIDS datasets: spinalcordtoolbox/spinalcordtoolbox#4658

@naga-karthik naga-karthik added the wontfix This will not be worked on label Apr 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

wontfix This will not be worked on

Projects

None yet

Development

Successfully merging this pull request may close these issues.

create list of problematic subjects used for qualitative testing

2 participants