Residual Cancer Burden Prediction on Residual Cancer Burden (held-out set)
56Weighted F1MOOZY
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MOOZYEvaluation Protocol=Frozen model evaluated with MLP probe2026.03 | 56 | 0.74 | 51 | |
| MOOZYEvaluation Protocol=Frozen-feature MLP probe2026.03 | 56 | 0.74 | 51 | |
| MadeleineEvaluation Protocol=Frozen-feature MLP probe2026.03 | 51 | 0.63 | 48 | |
| CONCH v1.5Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 47 | 0.61 | 42 | |
| BackboneEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 46 | 0.6 | 44 | |
| CHIEFEvaluation Protocol=Frozen-feature MLP probe2026.03 | 46 | 0.6 | 44 | |
| PRISMEvaluation Protocol=Frozen-feature MLP probe2026.03 | 46 | 0.58 | 43 | |
| Giga PathEvaluation Protocol=Frozen-feature MLP probe2026.03 | 45 | 0.55 | 40 | |
| UNI v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 44 | 0.6 | 40 | |
| MUSKEvaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 44 | 0.59 | 40 | |
| TITANEvaluation Protocol=Frozen-feature MLP probe2026.03 | 43 | 0.58 | 38 | |
| Phikon v2Evaluation Protocol=Aggregator trained from scratch on frozen features, Aggregator=Mean over five MIL architectures (MeanMIL, ABMIL, CLAM, DSMIL, TransMIL)2026.03 | 42 | 0.59 | 39 |