search

AIM-Harvard / foundation-cancer-image-biomarker

Code and evaluation repository for the paper
https://aim-harvard.github.io/foundation-cancer-image-biomarker/
MIT License
83 stars 10 forks source link

Extracting Features #310

Closed AlexNmSED closed 3 days ago

AlexNmSED commented 1 week ago

Hello,

Our data is already an ROI file （.nii.gz / .dcm） for the tumor region, so there is no seed point data. Can I just use your model to extract the features of ROI directly.

surajpaib commented 6 days ago

Hi @AlexNmSED

You can use the ROI file to extract the seed point data as shown in the notebook here: https://github.com/AIM-Harvard/foundation-cancer-image-biomarker/blob/master/tutorials/get_seed_from_mask.ipynb

We alternatively have WIP to support native DICOM formats through mhub.ai here https://github.com/MHubAI/models/pull/99 which should be available in the next couple of days

AlexNmSED commented 4 days ago

Thank you for your help.