Slide-Level Subtyping on TCGA-BRCA 100% (train)
87.4Macro AUCHIPT
Evaluation results
| Method | Links | |
|---|---|---|
| HIPTArchitecture=HIPT, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 87.4 | |
| CLAM-SBArchitecture=CLAM-SB, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 85.8 | |
| GCN-MILArchitecture=GCN-MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 84 | |
| DS-MILArchitecture=DS-MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 83.8 | |
| DeepAttnMISLArchitecture=DeepAttnMISL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 78.4 | |
| MILArchitecture=MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 77.8 | |
| ViT_4096-256 (Mean)Architecture=ViT_4096-256, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 77.5 | |
| ViT_256-16 (Mean)Architecture=ViT_256-16, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 72.5 | |
| ResNet-50IN (Mean)Architecture=ResNet-50IN, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 66.7 |