Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MHub / GC - Add LUNA22 ISMI baseline model implementation #46

Closed

Conversation

silvandeleemput
Copy link
Contributor

@silvandeleemput silvandeleemput commented Aug 29, 2023

This PR adds the GC LUNA22 ISMI baseline model (from the LUNA22 challenge) to MHub.
GitHub Repo: https://github.com/DIAGNijmegen/bodyct-luna22-ismi-algorithm-baseline
GC page: https://grand-challenge.org/algorithms/luna22-ismi-baseline/

Algorithm I/O

  • Input should be a volume from a CT Lung image (MHA) centered around a single nodule (This MHub implementation expects a Dicom which is converted to MHA using MhaConverter)
  • Outputs are:
    • A JSON file with the following output scores:
      • malignancy risk
      • lung nodule type
  • Test images for this algorithm can be downloaded from here: https://zenodo.org/record/6559584

Caveats

  • The PR target is main, but should be something like m-gc-luna22-ismi-baseline
  • In the Dockerfile the MHub model repo integration is currently marked TODO since it requires the creation of the appropriate branch for this code first.
  • Added a TODO to the MHAConverter since it doesn't have the panimg backend yet.

@silvandeleemput
Copy link
Contributor Author

This algorithm/model should not be added since it is not very suitable as a MHub model, due to it being intended for students. Also, the algorithm focuses on small volumes around nodules, requiring additional preprocessing. Hence we will replace this algorithm with #60, which is a better candidate.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Incompatible
Development

Successfully merging this pull request may close these issues.

1 participant