Research Article
A Semiautomated Deep Learning Approach for Pancreas Segmentation
Table 3
Comparison with other segmentation methods on the NIH dataset (DSC%). Bold denotes the best.
| Method | Min DSC | Max DSC | Mean DSC |
| Roth et al., MICCAI’2015 [16] | 23.99 | 86.29 | 71.42 10.11 | Roth et al., MICCAI’2016 [17] | 34.11 | 88.65 | 78.01 8.20 | Zhou et al., MICCAI’2017 [14] | 62.43 | 90.85 | 82.37 5.68 | Cai et al., 2019 [21] | 59.00 | 91.00 | 83.70 5.10 | Liu et al., IEEE access 2019 [22] | N/A | N/A | 84.10 4.91 | Zhu et al., 3DV’2018 [24] | 69.62 | 91.45 | 84.59 4.86 | Man et al., IEEE T MED IMAGING 2019 [23] | 74.32 | 91.34 | 86.93 4.92 | DUNet(Ours) | 77.03 | 93.29 | 87.25 ± 3.27 |
|
|