Table 4 Comparison of experimental results on synapse dataset.
From: Boundary-enhanced sparse transformer for generalizable and accurate medical image segmentation
Models | Average | Dice | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Dice | HD | Aorta | GB | KL | KR | Liver | PC | SP | SM | |
TransUNet9 | 78.02 | 30.69 | 87.23 | 63.13 | 81.87 | 77.02 | 94.08 | 58.04 | 87.06 | 75.75 |
TransCASCADE48 | 81.88 | 18.05 | 86.89 | 68.75 | 85.31 | 82.05 | 94.21 | 65.77 | 91.62 | 80.41 |
Swin-Unet10 | 77.55 | 27.42 | 81.66 | 65.85 | 82.42 | 79.32 | 93.63 | 53.71 | 88.14 | 75.69 |
RWKV-Unet49 | 82.71 | 17.24 | 86.73 | 68.38 | 87.76 | 84.56 | 94.53 | 65.44 | 90.89 | 83.41 |
VM-Unet50 | 81.15 | 19.41 | 86.47 | 69.31 | 86.56 | 82.76 | 94.27 | 58.90 | 89.42 | 81.50 |
EMCAD51 | 83.68 | 15.58 | 88.24 | 68.97 | 88.18 | 84.2 | 95.36 | 68.61 | 92.07 | 83.82 |
MISSFormer27 | 82.56 | 15.8 | 89.46 | 67.59 | 84.21 | 79.16 | 95.47 | 69.28 | 90.95 | 84.39 |
MT-UNet46 | 78.59 | 26.59 | 87.92 | 64.99 | 81.47 | 77.29 | 93.06 | 59.46 | 87.75 | 76.81 |
PVT-CASCADE12 | 81.06 | 20.23 | 83.01 | 70.59 | 82.23 | 80.37 | 94.08 | 64.43 | 90.10 | 83.69 |
Our Model | 84.54 | 14.59 | 88.31 | 71.34 | 88.22 | 84.73 | 95.83 | 68.96 | 92.86 | 86.03 |
