search

khuhm / deep-kidney-cancer

Deep Learning for End-to-End Kidney Cancer Diagnosis on Multi-Phase Abdominal Computed Tomography
MIT License
15 stars 0 forks source link

Cannot find code for segmentation #2

Open SamsungApple opened 2 years ago

SamsungApple commented 2 years ago

Thank you for opening the code available. There are several questions to ask.

  1. From the paper, classification was done after segmentation and registration. But from the code available seems to only show train and evaluation of classification code. Is there other repesitory for segmentation and registration?

  2. Is the classification model trained from the output of segmentation model (3D U-Net) or from manually drawn mask?

Thank you.

khuhm commented 2 years ago

Sorry for the late reply.

  1. We use the open repository for segmentation (https://github.com/MIC-DKFZ/nnUNet). The registration code is not opened as they are not clean.

  2. The classification model is trained from the output of the segmentation model.

Thank you.