Table 6 Comparison results of different segmentation algorithms in STARE,[Key: Best, Second Best].

From: TCDDU-Net: combining transformer and convolutional dual-path decoding U-Net for retinal vessel segmentation

Methods

F1

Acc

AUC

Sp

Se

Yu44

–

96.13

97.87

98.22

78.37

DUNet45

81.43

96.41

98.32

98.78

75.95

Yan46

–

96.38

98.33

98.57

77.35

U-Net++47

78.59

97.57

97.63

–

–

CTF-Net48

–

–

–

–

–

CcNet49

–

96.33

97.00

98.48

77.09

Yang30

–

96.26

–

98.21

79.46

Xu28

–

96.92

98.12

97.90

85.04

Ours (w/o background decoder)

81.10 ± 4.41

97.18 ± 0.49

98.60 ± 0.73

98.37 ± 0.50

82.24 ± 8.15

Ours (TCDDU-Net)

81.63 ± 5.53

97.40 ± 0.64

98.56 ± 0.88

98.84 ± 0.32

79.20 ± 9.41

  1. Significant values are in bold and underline.