Table 2 Comparison results of DSC (%) and HD95 (mm) metrics on the BraTS2019 Validation set.

From: Generative adversarial DacFormer network for MRI brain tumor segmentation

Methods

DSC \(\uparrow\)

HD95 \(\downarrow\)

ET

WT

TC

MEAN

ET

WT

TC

MEAN

MBANet25

78.2

89.8

83.0

83.7

3.08

5.88

5.09

4.68

SMRAU-Net26

74.2

88.5

81.0

81.2

6.67

10.83

10.25

9.25

AMMGS23

76.8

89.3

81.1

82.4

5.18

8.22

7.23

6.88

SPA-Net27

77.1

89.6

83.3

83.3

−

−

−

−

TransBTS17

78.9

90.0

81.9

83.6

3.73

5.64

6.05

5.14

IncompleteMriSeg28

78.3

90.3

83.1

83.9

5.55

4.82

6.93

5.76

GMetaNet16

78.4

90.2

82.5

83.7

−

−

−

−

GAU-Net29

76.7

89.7

79.0

81.8

8.40

6.92

4.61

6.64

GVAT-Net30

75.2

89.9

81.5

82.2

12.56

7.39

8.06

9.34

GDacFormer (Ours)

77.9

90.9*

84.6*

84.5*

2.83*

4.42*

6.58

4.61*

  1. *Denotes significant difference compared with SOTA by Wilcoxon signed rank test (p value < 0.05).