Table 4 Segmentation performance of different models on the SEED dataset
From: CFG-MambaNet: Contextual and Frequency-Guided Mamba Network for medical image segmentation
Model | Dice (%) ↑ | IoU (%) ↑ | ASD ↓ | SP (%) ↑ |
|---|---|---|---|---|
U-Net32 | 75.67 | 66.61 | 12.98 | 91.99 |
nnUNet33 | 82.98 | 75.05 | 11.42 | 88.78 |
AttUNet12 | 79.15 | 70.08 | 12.95 | 89.07 |
MISSFormer37 | 82.02 | 73.61 | 11.71 | 90.72 |
FSCA-Net40 | 81.96 | 73.57 | 11.01 | 91.07 |
Rolling-unet34 | 81.85 | 73.53 | 19.67 | 76.99 |
H2Former36 | 78.94 | 70.23 | 14.26 | 85.05 |
UCTransNet35 | 79.08 | 70.35 | 19.34 | 78.39 |
EMCAD41 | 83.46 | 75.22 | 10.69 | 91.60 |
Hetero-UNet38 | 80.49 | 71.83 | 14.01 | 89.86 |
GH_UNet42 | 83.92 | 76.15 | 17.46 | 84.79 |
Swin-UMamba39 | 83.68 | 75.54 | 9.92 | 92.12 |
Ours | 86.52 | 79.34 | 8.69 | 92.90 |
