Table 6 Comparisons on LiTS17 challenge.

From: Deep supervision and atrous inception-based U-Net combining CRF for automatic liver segmentation from CT

Method

Dimension

Model

DPC (%)

DG (%)

Roth et al.10

2D

U-Net

95.0

94.0

Kaluva et al.7

FCN

91.2

92.3

Liu et al.33

GIU-Net

–

95.05

Song et al.31

BS U-Net

96.1

96.4

Li et al.11

3D

H-DenseUNet

96.1

96.5

Jin et al.12

RA U-Net

96.3

96.1

Rafiei et al.32

U-Net

–

92.8

Ours

DA-UNet

95.3

95.8

  1. Significant values are in bold.
Back to article page