Table 1.
We compare the results of different rate combinations and introduce scSE into the multiscale feature before and after fusion. It is used to compare the impact of single and composite feature maps on global accuracy.
| Methods (scSE) (r1, r2, r3, r4, r5) | Dice | IoU |
|---|---|---|
| MSFA-Net (I and II) (1,2,3,15,21) | 0.9066 | 0.8311 |
| MSFA-Net (I and II) (1,2,3,9,15) | 0.9129 | 0.9112 |
| MSFA-Net (I and II) (1,3,6,12,18) | 0.9248 | 0.8852 |
| MSFA-Net (I) (1,2,3,15,21) | 0.9020 | 0.8374 |
| MSFA-Net (I) (1,2,3,9,15) | 0.9026 | 0.8228 |
| MSFA-Net (I) (1,3,6,12,18) | 0.9075 | 0.8653 |
| MSFA-Net (II) (1,2,3,15,21) | 0.8520 | 0.7972 |
| MSFA-Net (II) (1,2,3,9,15) | 0.9199 | 0.8573 |
| MSFA-Net (II) (1,3,6,12,18) | 0.9271 | 0.9128 |