Skip to main content

Table 4 A description of methods employed in the study

From: 3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities

Serial #

Methods

1

AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using fivefold CV approach

2

AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using tenfold CV approach

3

AD/NC(SPECT)/PD classification with combined augmentations in the spatial domain using tenfold CV approach

4

AD/NC(SPECT)/PD classification with random zoomed in/out augmentation in the frequency domain using fivefold CV approach

5

AD/NC(SPECT)/PD classification with combined augmentations in the frequency domain using tenfold CV approach

6

AD/NC(SPECT)/PD classification with random zoomed in/out augmentation in the spatial domain using fivefold CV approach

7

AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the frequency domain using fivefold CV approach

8

AD/NC(SPECT)/PD classification with combined augmentations in the spatial domain using fivefold CV approach

9

AD/NC(SPECT)/PD classification with random zoomed in/out augmentation in the spatial domain using tenfold CV approach

10

AD/NC(SPECT)/PD classification with combined augmentations in the frequency domain using fivefold CV approach

11

AD/NC(SPECT)/PD classification without augmentation in the frequency domain using fivefold CV approach

12

AD/NC(SPECT)/PD classification without augmentation in the frequency domain using tenfold CV approach

13

AD/NC(SPECT)/PD classification without augmentation in the spatial domain using fivefold CV approach

14

AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the frequency domain using tenfold CV approach

15

AD/NC(SPECT)/PD classification with random zoomed in/out augmentation in the frequency domain using tenfold CV approach

16

AD/NC(SPECT)/PD classification without augmentation in the spatial domain using tenfold CV approach

17

AD/NC(PET)/PD classification without augmentation in the spatial domain using fivefold CV approach

18

AD/NC(PET)/PD classification without augmentation in the spatial domain using tenfold CV approach

19

AD/NC(PET)/PD classification without augmentation in the frequency domain using fivefold CV approach

20

AD/NC(PET)/PD classification without augmentation in the frequency domain using tenfold CV approach