Skip to main content

Table 6 Test classification performance results obtained in Test 3

From: Automated classifiers for early detection and diagnosis of retinopathy in diabetic eyes

TH vs. FD

RNFL (eye/scans)

GCL + IPL. (eye/scans)

INL (eye/scans)

OPL (eye/scans)

ONL + IS (eye/scans)

OS (eye/scans)

RPE (eye/scans)

TP

18/108

18/108

15/90

4/24

10/60

18/108

20/120

FN

5/30

5/30

8/48

19/114

13/78

5/30

3/18

TN

30/180

26/156

32/192

28/168

26/162

31/186

33/198

FP

8/48

12/72

6/36

10/60

12/72

7/42

5/30

PPV

0.69

0.60

0.71

0.29

0.45

0.72

0.80*

Sensitivity

0.78

0.78

0.65

0.17

0.43

0.78

0.87*

Specificity

0.79

0.68

0.84

0.74

0.68

0.82

0.87*

  1. *denotes the intraretinal layer for which the sensitivity, specificity and PPV are greater than 80%.
  2. Sensitivity, specificity, predictive values (TP, FN, TN, FP) and positive predictive values (PPV) obtained when training the Bayesian radial basis function network using the thickness (TH) and fractal dimension (FD) as the input and target features, respectively.