Table 2 Segmentation results of compare models on the ACDC dataset.

From: Medical image segmentation by combining feature enhancement Swin Transformer and UperNet

Model

PA (%)

Dice (%)

HD

ResNet50+DeepLabV3+38

85.35

82.48

30.13

ResNet50+UPernet39

88.21

85.87

28.32

TransUNet40

87.79

86.12

22.65

DCL-Net43

89.30

87.60

25.87

ASF-LKUNet44

88.75

89.45

19.24

FE-SwinUper

89.83

90.15

18.29

Back to article page