Medical Image Segmentation on MoNu
82.43DiceAutoSAM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AutoSAM2023.06 | 82.43 | 70.17 | |
| MedAdaptor-SAMPrompting Strategy=GT points2023.06 | 80.34 | 67.33 | |
| 3P-SEGBackbone=Hardnet-852023.06 | 80.3 | 67.19 | |
| UCTransNet2023.06 | 79.87 | 66.68 | |
| MedT2023.06 | 79.55 | 66.17 | |
| FCN-Hardnet85Backbone=Hardnet-852023.06 | 79.52 | 66.06 | |
| U-Net++2023.06 | 79.49 | 66.04 | |
| Res-UNet2023.06 | 79.49 | 66.07 | |
| U-Net2023.06 | 79.43 | 65.99 | |
| Axial Attention2023.06 | 76.83 | 62.49 | |
| Lightweight decoder h(g(I))2023.06 | 76.75 | 62.32 | |
| SAMPrompting Strategy=AutoSAM output as mask prompt2023.06 | 58.1 | 41.26 | |
| SAMPrompting Strategy=GT mask as prompt2023.06 | 30.24 | 18.21 | |
| SAMPrompting Strategy=GT point prompt2023.06 | 29.65 | 17.52 | |
| FCN2023.06 | 28.84 | 28.71 |