Skip to main content

Table 2 Comparison of the segmentation performances of three SOTA networks and ours on the local ultrasound breast images 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 (h)↓

TransUNet

0.869240

8.963769

4

U-Net [12]

0.825394

10.121881

3

DeepLab V3 + [40]

0.843596

9.281189

3.25

Proposed

0.875815

5.820322

2.75