Table 3 Quantitative comparison of the independent testing set among different methods
From: Deep learning approach for automatic segmentation of ulna and radius in dual-energy X-ray imaging
Methods | Independent testing set (Dice) | Independent testing set (Jaccard) | ||
|---|---|---|---|---|
Ulna | Radius | Ulna | Radius | |
U-Net | 0.9767 ± 0.0258 | 0.9836 ± 0.0114 | 0.9557 ± 0.0444 | 0.9681 ± 0.0213 |
FCN | 0.9755 ± 0.0113 | 0.9824 ± 0.0070 | 0.9525 ± 0.0212 | 0.9655 ± 0.0134 |
Ours | 0.9806 ± 0.0164 | 0.9860 ± 0.0076 | 0.9624 ± 0.0295 | 0.9725 ± 0.0142 |