From: Deep learning approach for automatic segmentation of ulna and radius in dual-energy X-ray imaging
Methods | Validation set (Dice) | Testing set (Dice) | ||
---|---|---|---|---|
Ulna | Radius | Ulna | Radius | |
U-Net | 0.9753 ± 0.0291 | 0.9832 ± 0.0126 | 0.9751 ± 0.0309 | 0.9828 ± 0.0133 |
with Resblock | 0.9782 ± 0.0214 | 0.9850 ± 0.0103 | 0.9785 ± 0.0214 | 0.9852 ± 0.0100 |
 | Validation set (Jaccard) | Testing set (Jaccard) | ||
---|---|---|---|---|
Ulna | Radius | Ulna | Radius | |
U-Net | 0.9534 ± 0.0481 | 0.9670 ± 0.0233 | 0.9532 ± 0.0488 | 0.9665 ± 0.0242 |
with Resblock | 0.9581 ± 0.0368 | 0.9707 ± 0.0192 | 0.9589 ± 0.0369 | 0.9711 ± 0.0186 |