Table 2 Summary of fivefold cross-validation and holdout test the data distribution of FAZ binary mask images.

From: Enhancing foveal avascular zone analysis for Alzheimer’s diagnosis with AI segmentation and machine learning using multiple radiomic features

Method

Fivefold cross-validation

Holdout test

Data type

Training set (n = 85)

Holdout test set (n = 45)

Split

Train

Test

Test

Fold 1

70

15

45 (64%)

Fold 2

68

17

Fold 3

69

16

Fold 4

67

18

Fold 5

66

19

Back to article page