Table 1 Mono-modal liver segmentation accuracy, trainable parameters (in millions), and run-time comparison for the Anatomy3 and SilverCopus datasets.
From: Deep action learning enables robust 3D segmentation of body organs in various CT and MRI images
Dataset | No. | Algorithm | Dice | Parameters | Runtime |
|---|---|---|---|---|---|
[%] | [M] | [s] | |||
AVG ± STD | |||||
Anatomy3 | 20 | Our method | 90.8 ± 0.7 | 2.7 | 1 |
CT | 3D U-Net | 90.5 ± 3.6 | 16.1 | 60 | |
SilverCopus | 51 | Our method | 89.9 ± 0.6 | 2.7 | 1 |
CT | 3D U-Net | 89.1 ± 3.9 | 16.1 | 60 |
