miccaiif / dgmil Goto Github PK

Thank you for your great work!

The paper mentioned that "For bag-level classification, we only use the simple mean- pooling approach to aggregate the positive scores of all instances in a bag." How do you set the threshold value to distinguish between negative and positive bags in the testing set?

Thanks for your nice work!
When will the code be updated?

We have encountered challenges in replicating the FROC score calculations. To ensure accuracy and consistency, we would greatly appreciate your assistance with the following inquiries:

• Could you kindly provide us with the complete pipeline code you used to calculate the FROC score?

If not could you please guide us on:

• How did you determine the coordinates of the points used in the calculations?

• If clustering was involved in the selection of coordinates, could you elaborate on the process? For instance, did you extract the count of clusters from the XML file containing tumor region coordinates before doing the clustering on model probability scores? Additionally, was the center of each cluster chosen for calculations?

• Could you specify the number of coordinates you chose for the FROC score calculations (or if it's not constant how you choose this number)?

Thanks for the great work and codes! I wonder how to calculate FROC metrics for patch-level localization for details？

您好，我看到论文中DSMIL (CVPR’21) 的 Slide ACC 只有 0.7359，而 DSMIL 原始论文中Slide ACC 可以达到 0.8682，请问造成结果差异的原因是什么？感谢！

Hi! Thanks for your great work!
I noticed that there is no completely negative slide in the TCGA dataset. They are only labeled as LUAD or LUSC. May I ask how did you train the "Pseudo Label-Based Feature Space Refinement" part with TCGA data? Thanks so much!

Thank you for your greate work!
Is it possible to implement this method on multi-class classification task?

Could you please let me know how to patch the camelyon16 dataset with the same settings as yours?

Could you also let me know how to get 130 slides for testing? When I tried downloading the camelyon16 dataset, I only got 129 slides

I didn't find the model of mae,and the function of mae is a projection,the same as projection768