Medical Image Segmentation on DDTI
90.3DSCPruned E-BayesSAM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Pruned E-BayesSAMZero-shot=true, Uncertainty Estimation=T-VBI, Architecture=SO-KAN, Pruning=Applied2025.08 | 90.3 | — | |
| MedSAMZero-shot=true2025.08 | 90 | — | |
| BayesMedSAMZero-shot=true, Uncertainty Estimation=T-VBI2025.08 | 89.8 | — | |
| E-BayesSAMZero-shot=true, Uncertainty Estimation=T-VBI, Architecture=SO-KAN2025.08 | 89.4 | — | |
| JointTrain2026.06 | 83.35 | — | |
| C2GR2026.06 | 82.25 | — | |
| SR-DSFW2026.06 | 82.06 | — | |
| Hiera-based adaptive framework2025.03 | 81.52 | 26.68 | |
| UltraUPConvNetInteraction Mode=Automatic, Params=60.48M2025.09 | 80.55 | — | |
| MedSeqFT2026.06 | 79.73 | — | |
| UltraUPConvNet w/o promptInteraction Mode=Automatic, Params=60.44M, Prompting=w/o prompt2025.09 | 79.25 | — | |
| GR2026.06 | 78.68 | — | |
| CoNuSeg2026.06 | 77.86 | — | |
| SAMUS2025.03 | 77.48 | 33.53 | |
| FineTune2026.06 | 77.27 | — | |
| Scratch2026.06 | 74.49 | — | |
| nnUNet2025.03 | 73.26 | 40.43 | |
| MedNeXt2025.03 | 71.59 | 40.02 | |
| SwinUNETR2025.03 | 70.59 | 41.76 | |
| SAMUSInteraction Mode=Interactive, Params=130.10M2025.09 | 69.7 | — | |
| MedSAM22025.03 | 69.69 | 39.02 | |
| UniUSNetInteraction Mode=Automatic, Params=86.29M2025.09 | 66.06 | — | |
| UNet2025.03 | 48.43 | 52.6 |