Medical Image Segmentation on MSD Liver (5-fold CV)
95.43Dice (Label 1)ensemble 3D U-Net + 3D U-Net (U-Net Cascade)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ensemble 3D U-Net + 3D U-Net (U-Net Cascade)Ensemble=3D U-Net + 3D U-Net (Cascade)2018.09 | 95.43 | 61.82 | |
| 3D U-Net (U-Net Cascade)Architecture=3D U-Net, Pipeline=U-Net Cascade2018.09 | 95.38 | 58.49 | |
| ensemble 2D U-Net + 3D U-Net (U-Net Cascade)Ensemble=2D U-Net + 3D U-Net (Cascade)2018.09 | 95.31 | 60.09 | |
| 3D U-Net stage1 onlyArchitecture=3D U-Net, Pipeline=U-Net Cascade, Stage=1 only2018.09 | 94.69 | 47.01 | |
| 2D U-NetArchitecture=2D U-Net2018.09 | 94.37 | 53.94 | |
| ensemble 2D U-Net + 3D U-NetEnsemble=2D U-Net + 3D U-Net2018.09 | 94.3 | 60.24 | |
| 3D U-NetArchitecture=3D U-Net2018.09 | 94.11 | 61.74 |