A better and stronger pre-trained model was built for various histopathological image applications. This model outperforms ImageNet pre-trained features by a large margin. We release our best model and invite researchers to test it on your computational pathology tasks.
- 128GB of RAM
- 32*Nvidia V100 32G GPUs
1.Download all TCGA 32000 WSIs.
2.Download all PAIP 2,457 WSIs. So, there will be about 15,000,000 images(~100T). It costs us $400,000 to advance the progress of digital pathology.
This pre-train model is here
It is the most obvious and direct way to evaluate the distinctive power of the provided features.
TissueNet | ||||
---|---|---|---|---|
Acc@1 | Acc@3 | Acc@5 | mMV@5 | |
ImageNet | 50.35 | 77.65 | 87.68 | 46.15 |
CCL (ours) | 67.09 | 87.81 | 93.4 | 70.1 |
UniToPatho | ||||
---|---|---|---|---|
Acc@1 | Acc@3 | Acc@5 | mMV@5 | |
ImageNet | 58.17 | 82.89 | 89.45 | 59.01 |
CCL (ours) | 66.55 | 84.32 | 90.31 | 68.35 |
This task is currently based on ImageNet pretrained features, which can also verify the superiority of our feature extractor.
TCGA-NSCLC | ||
---|---|---|
Accuracy | AUC | |
ABMIL | 0.7719 | 0.8656 |
MIL-RNN | 0.8619 | 0.9107 |
DSMIL | 0.8058 | 0.8925 |
TransMIL | 0.8835 | 0.9603 |
CLAM | 0.8422 | 0.9377 |
CLAM+CCL (ours) | 0.911 | 0.967 |
This task follows KimiaNet
Colorectal cancer dataset | |
---|---|
Accuracy | |
Combined features | 87.40 |
Fine-tuned VGG-19 | 86.19 |
Ensemble of CNNs | 92.83 |
KamiaNet | 96.80 |
CCL (ours) | 98.40 |
If you want to compute the features.
python get_feature.py
It is recommended to first try to extract features at 1.0mpp, and then try other magnifications
If you want to fine-tune model.
python resnet_lincls.py
RetCCL is released under the Apache 2.0 license.
Please use below to cite this paper if you find our work useful in your research.
@inproceedings{wang2022RetCCL,
title={RetCCL: Clustering-guided Contrastive Learning for Whole-slide Image Retrieval}
}