An approach to apply the proposed segmentation region from an ML model to DICOM data

Hi all,
I would like to create a new extension which can do the following task:

  • Click a point on a DICOM data on Slicer (e.g. a point in a specific human organ)
  • Get that point and image, then pass them to the ML model. The model will output a proposed region for segmentation.
  • Pass the model’s output to Slicer and segment the region on Slicer.

I highly appreciate if you guys can recommend an approach to do those task. Thank you!

Sounds reasonable. You should review MONAI Label and TotalSegmentator to see what’s already possible. Then read the programming tutorials and read through the script repository.

1 Like