Research Article
WBC Image Segmentation Based on Residual Networks and Attentional Mechanisms
Table 4
Comparison of segmentation results of different models on the BCISC dataset.
| Model | Dice (%) | mIOU (%) | PPV (%) | SE (%) | HD |
| FCN-8s | 96.84 | 93.90 | 97.47 | 96.38 | 8.14 | FCN-16s | 96.79 | 93.76 | 97.16 | 97.53 | 8.76 | FCN-32s | 96.55 | 93.27 | 93.77 | 99.53 | 9.02 | U-Net | 97.65 | 95.34 | 97.69 | 97.65 | 4.22 | Ours | 98.13 | 96.36 | 98.23 | 98.06 | 3.52 |
|
|