Table 3 Performance comparisons of our model with those of other studies reported in the literature for AD vs. MCI vs. NC and AD vs. NC binary classifications.

From: Early diagnosis of Alzheimer’s disease using a group self-calibrated coordinate attention network based on multimodal MRI

Train

Test

Tasks

Method

ACC (%)

SEN (%)

SPE (%)

AUC

  

AD

vs.

MCI

vs.

NC

3D-CNN41

59.73

-

-

-

  

THAN42

62.90

64.50

81.80

0.65

  

STNet33

71.76

-

-

-

  

LSTM-Robust43

75.96

-

-

-

ADNI

In-house dataset

Our study

83.33

-

-

0.92

  

AD

vs.

NC

BB + pA-blocks (A) + Bili44

90.70

88.77

92.44

0.94

  

3D-ResAttNet3445

91.30

91.00

92.00

98.40

  

THAN42

92.00

90.30

93.10

0.96

  

PT DCN26

92.00

89.10

94.00

0.96

  

DenseCNN246

92.52

88.20

94.95

0.98

ADNI

In-house dataset

Our study

92.81

96.22

90.68

0.95

Back to article page