Table 3.
Deep learning models for segmentation.
| Purpose (Type of image) |
Model | Number of Training Set Images | Number of Test Set Images | Result | Study |
|---|---|---|---|---|---|
| Segmentation of breast lesions (B-mode image) |
RDAU-NET | 857 | 205 | Precision rate: 88.58% Recall rate: 83.19% F1 score: 84.78 |
[53] |
| Segmentation of breast lesions (B-mode image) |
Combining DFCN with a PBAC model | 400 | 170 | Dice similarity coefficient: 88.97% Hausdorff distance: 35.54 pixels Mean absolute deviation: 7.67 pixels |
[54] |
| Segmentation of breast lesions (B-mode image) |
Multi U-net algorithm | 372 | 61 | Mean Dice coefficient: 0.82 True positive fraction: 0.84 False positive fraction: 0.01 |
[55] |
CAD, computer-assisted diagnosis; RDAU-NET, Residual-Dilated-Attention-Gate-U-net; DFCN, dilated fully convolutional network; PBAC, phase-based active contour; AUC, area under the curve.