Medical Image Segmentation on BraTS PED 2023
52.55Dice (ET)Swin UNETR (Tang et al., 2022)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Swin UNETR (Tang et al., 2022)Pre-training Method=Medical SSL, Backbone=Swin UNETR2026.05 | 52.55 | 84.75 | 86.28 | 74.53 | |
| SwinMM (Wang et al., 2023c)Pre-training Method=Medical SSL, Backbone=Swin UNETR2026.05 | 51.99 | 84.71 | 85.55 | 74.08 | |
| Swin UNETRPre-training Method=From Scratch, Backbone=Swin UNETR2026.05 | 51.11 | 86.86 | 88.15 | 75.37 | |
| S2DC (Pan et al., 2025)Pre-training Method=Medical SSL, Backbone=Swin UNETR2026.05 | 51.04 | 87.46 | 88.64 | 75.71 | |
| TACOPre-training Method=Medical SSL, Backbone=Swin UNETR2026.05 | 50.58 | 88.69 | 89.38 | 76.22 | |
| VoCo (Wu et al., 2024)Pre-training Method=Medical SSL, Backbone=Swin UNETR2026.05 | 50.52 | 84.22 | 85.91 | 73.55 | |
| BrainMVP (Rui et al., 2025)Pre-training Method=Medical SSL, Backbone=UniFormer2026.05 | 49.89 | 85.25 | 87.52 | 74.22 | |
| UniFormerPre-training Method=From Scratch, Backbone=UniFormer2026.05 | 47.81 | 82.34 | 83.82 | 71.32 | |
| M3AE (Liu et al., 2023)Pre-training Method=Medical SSL, Backbone=UNET3D2026.05 | 47.57 | 84.62 | 85.78 | 72.66 | |
| UNETRPre-training Method=From Scratch, Backbone=UNETR2026.05 | 46.97 | 78.02 | 81.73 | 68.9 | |
| UNET3DPre-training Method=From Scratch, Backbone=UNET3D2026.05 | 46.12 | 84.92 | 86.63 | 72.55 |