Guillaume Jaume

Hi, do you have a CPU or GPU memory issue? Also are you able to identify what part of the code is creating it?

Hi, Can you try to follow this example instead https://github.com/histocartography/histocartography/blob/main/examples/stain_normalization.py. Let me know if you still get the same error. Guillaume

Hi, What module would require multi-gpu? In some cases, you could have a wrapper around an existing module that includes multi-threading.

Apologies for the late reply. Evaluating survival on very small cohorts is hard. All strategies have flaws. In SurvPath and following previous works, we didn't use a val set. The...

What kind of tissue segmentation are you facing with HunCRC?

Apologies for the very late reply. We followed a strategy similar to https://github.com/mahmoodlab/MMP/blob/main/src/preprocess_pancancer_TCGA_normalized_RNA.ipynb. Long story short, we took data from the Xena portal, here: https://xenabrowser.net/datapages/

Apologies for the late reply. In linear probing, we used logistic regression with sklearn default L2 regularization (set to 1.0) and lbfgs solver. We set the maximum number of training...

Feel free to refer to our new trident repo for WSI image processing: https://github.com/mahmoodlab/trident You can directly set the mag and patch size, the rest is handled internally.

Apologies for the late reply. Short answer is: it depends. What are you trying to achieve? If you want risk scores, you need to transform the logits "S", using the...

Please refer to our new repo trident for titan/conchv1.5 feature extraction: https://github.com/mahmoodlab/trident. However, the Titan official documentation states ‘TITAN-preview is a vision-lanuage model trained on CONCH v1.5 patch features with...