Table 2 Performance comparison of different models on the GlaS dataset. Evaluation metrics include IoU, Dice coefficient, Precision, and Recall, where higher values indicate better performance. The best result in each column is highlighted in bold.

From: Multi-module UNet++ for colon cancer histopathological image segmentation

Methods

IoU (%)

Dice (%)

Pre. (%)

Rec. (%)

U-Net5

72.11

79.70

80.76

87.25

UNet++8

73.35

81.83

83.32

83.61

Residual-Attention UNet++16

74.91

82.43

85.11

86.01

DenseRes-UNet12

75.19

82.96

84.27

87.01

nnUNet14

75.90

83.05

87.15

85.70

RPAU-Net++

76.34

83.20

88.17

85.67