Table 1 Segmentation results of methods on the test set
From: U-Net combined with multi-scale attention mechanism for liver segmentation in CT images
Method | DSC [%] | IOU [%] | Precision [%] | Recall [%] |
|---|---|---|---|---|
UNet [13] | 89.23 ± 4.98 | 80.93 ± 8.12 | 92.97 ± 3.87 | 86.49 ± 9.59 |
UNet++ [2] | 92.10 ± 3.62 | 85.56 ± 6.04 | 93.49 ± 4.96 | 91.23 ± 6.34 |
DeepLabv3+ [34] | 96.94 ± 2.85 | 94.19 ± 4.45 | 95.42 ± 4.37 | 98.63 ± 1.22 |
CE-Net [33] | 97.67 ± 0.81 | 95.46 ± 1.53 | 96.76 ± 1.45 | 98.61 ± 1.22 |
MSA-UNet | 98.00 ± 0.38 | 96.08 ± 0.74 | 97.17 ± 0.85 | 98.85 ± 0.70 |