Cancer Classification on RSNA Cancer
92.5AUCMIL-PF (MedSigLIP) AT: max
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MIL-PF (MedSigLIP) AT: max# Trainable Params (M)=0.04, Level=Breast2026.03 | 92.5 | 83 | 73.3 | |
| MIL-PF (DINOv2) AT: attn# Trainable Params (M)=0.05, Level=Breast2026.03 | 92.3 | 82.8 | 70.9 | |
| MIL-PF (MedSigLIP) AT: attn# Trainable Params (M)=0.04, Level=Breast2026.03 | 92.3 | 83.5 | 75.7 | |
| FPN-AbMIL (mean)# Trainable Params (M)=1.76, Level=Breast2026.03 | 91.4 | 82.6 | 68.7 | |
| FPN-AbMIL (max)# Trainable Params (M)=5.38, Level=Breast2026.03 | 90.2 | 78.5 | 66.4 | |
| FPN-SetTrans (mean)# Trainable Params (M)=1.76, Level=Breast2026.03 | 90.2 | 82.5 | 74.7 | |
| MIL-PF (DINOv2) AT: max# Trainable Params (M)=0.05, Level=Breast2026.03 | 90.1 | 81.5 | 66.9 | |
| GMIC-ResNet18# Trainable Params (M)=22.49, Level=Image2026.03 | 89.9 | 75.4 | 68.4 | |
| FPN-SetTrans (max)# Trainable Params (M)=5.38, Level=Breast2026.03 | 89.6 | 77.3 | 69.3 | |
| FPN-AbMIL# Trainable Params (M)=1.76, Level=Image2026.03 | 89.1 | 79.3 | 62.8 | |
| ES-Att# Trainable Params (M)=22.89, Level=Case2026.03 | 89 | 79.9 | 64.2 | |
| FPN-SetTrans# Trainable Params (M)=5.38, Level=Image2026.03 | 87.4 | 77.3 | 65.6 | |
| GMIC# Trainable Params (M)=14.11, Level=Image2026.03 | 77.3 | 69.9 | 43.4 |