Slide-Level Subtyping on TCGA-NSCLC 100% (train)
0.952Macro-averaged AUCHIPT
Evaluation results
| Method | Links | |
|---|---|---|
| HIPTArchitecture=HIPT, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.952 | |
| CLAM-SBArchitecture=CLAM-SB, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.928 | |
| DS-MILArchitecture=DS-MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.92 | |
| MILArchitecture=MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.892 | |
| ViT_4096-256 (Mean)Architecture=ViT_4096-256, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 0.889 | |
| GCN-MILArchitecture=GCN-MIL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.831 | |
| ResNet-50IN (Mean)Architecture=ResNet-50IN, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 0.794 | |
| DeepAttnMISLArchitecture=DeepAttnMISL, Evaluation Protocol=Weakly-supervised Fine-tuning2022.06 | 0.778 | |
| ViT_256-16 (Mean)Architecture=ViT_256-16, Evaluation Protocol=K-Nearest Neighbors (KNN), Aggregation Method=Mean Pooling2022.06 | 0.742 |