Table 3.
Comparison of liver segmentation results.
| Model | VOE (%) | RVD (%) | ASD (mm) | RMSD (mm) | DICE (%) |
|---|---|---|---|---|---|
| UNet (Chlebus et al., 2017) | 14.21 ± 5.71 | –0.05 ± 0.10 | 4.33 ± 3.39 | 8.35 ± 7.54 | 0.923 ± 0.03 |
| ResNet (Han, 2017) | 11.65 ± 4.06 | –0.03 ± 0.06 | 3.91 ± 3.95 | 8.11 ± 9.68 | 0.938 ± 0.02 |
| Christ (Christ et al., 2016) | 10.7 | −1.4 | 1.5 | 24.0 | 0.943 |
| X. Li et al. (Li et al., 2018b) | 10.20 ± 3.44 | −0.01 ± 0.05 | 4.06 ± 3.85 | 9.63 ± 10.41 | 0.947 ± 0.01 |
| H. Jiang et al. (Jiang et al., 2019) | – | – | – | – | 0.945 ± 0.02 |
| Ours | 9.52 ± 4.65 | −0.02 ± 0.07 | 8.43 ± 9.39 | 14.21 ± 5.71 | 0.946 ± 0.03 |
| Li et al. + (Li et al., 2015) | 9.15 ± 1.44 | −0.07 ± 3.63 | 1.55 ± 0.39 | 3.15 ± 0.98 | – |
| Moghbel + (Moghbel et al., 2016) | 5.95 | 7.49 | – | – | 0.911 |
| Lu et al. + (Lu et al., 2017) | 9.36 ± 3.34 | 0.97 ± 3.26 | 1.89 ± 1.08 | 4.15 ± 3.16 | – |
| X. Li et al. + (Li et al., 2018b) | 3.57 ± 1.66 | 0.01 ± 0.02 | 1.28 ± 2.02 | 3.58 ± 6.58 | 0.982 ± 0.01 |
| Ours + | 4.02 ± 1.42 | −0.02 ± 0.03 | 1.24 ± 1.02 | 3.48 ± 4.16 | 0.984 ± 0.01 |
+ denotes the method using augmented training dataset; - denotes the unreported result.