Table 2 Performance comparison of the proposed architectures with counterparts.

From: Stages prediction of Alzheimer’s disease with shallow 2D and 3D CNNs from intelligently selected neuroimaging data

Study

Architecture

No. of Subjects

Parameters

No. of Models

Accuracy

(%)

41

2D CNN

509

1,227,731

123

84.05

25

2D VGG-19

300

138,423,208

1

87.15

Proposed

2D CNN

2186

1,152,115

3

93

24

3D CNN

988

10,467,315

1

84.57

35

3D DenseNet-121

3512

7,628,484

1

84

Proposed

3D CNN

2186

1,091,475

1

96.5

Back to article page