search

miccaiif / DGMIL

Official PyTorch implementation of our MICCAI 2022 paper: DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification.
32 stars 3 forks source link

Camelyon16 Patching #4

Closed bryanwong17 closed 1 year ago

bryanwong17 commented 1 year ago

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

bryanwong17 commented 1 year ago

Hi @miccaiif, for extracting CAMELYON16 patches for 5x magnification, did you follow the default settings on the DSMIL GitHub page?

python .\deepzoom_tiler.py -m 0 -b 5

HardworkingLittlequ commented 1 year ago

Hello! Thanks for your attention! You can use DSMIL Github page to generate patches.

HardworkingLittlequ commented 1 year ago

Compared with DSMIL, for considerations of computational efficiency and resources, we used 5x (vs. DSMIL 20x) in our experiments. We used a patch size of 512 (vs DSMIL 224), and a patch is labeled as positive if it contains 25% or more cancer areas (not specified in DSMIL). These different settings may result in the difference between the metrics reported by us and those reported by DSMIL.