Table 3 Comparison of the segmentation performances using three SOTA networks and ours on the public ultrasound breast dataset with the best results in bold
From: A neural network with a human learning paradigm for breast fibroadenoma segmentation in sonography
Network | DSC ↑ | HD (mm) ↓ | Time (hr)↓ |
|---|---|---|---|
TransUNet | 0.849274 | 38.664333 | 2.5 |
U-Net | 0.832526 | 37.099123 | 2.25 |
DeepLab V3 +  | 0.852061 | 35.231811 | 2 |
Proposed | 0.852804 | 33.796840 | 2.25 |