Skip to main content

Table 2 The comparison of evaluation scores (precision, recall (sensitivity), specificity, f-measure and accuracy) of DePicT Melanoma CLASS/Deep-CLASS

From: DePicT Melanoma Deep-CLASS: a deep convolutional neural networks approach to classify skin lesion images

Classification and retrieval

TP

TN

FP

FN

Pre.

Rec.(Sen.)

Spec.

F-m.

Acc.

1st test: k-NN (300, 100)

30

34

16

20

0.65

0.6

0.68

0.62

0.64

1st test: SVM (300. 100)

25

37

13

25

0.66

0.5

0.74

0.57

0.62

2nd test: k-NN (1346, 450)

124

178

47

101

0.73

0.55

0.79

0.63

0.67

2nd test: SVM (1346. 450)

105

149

76

120

0.58

0.47

0.66

0.52

0.56

3rd test: CNN (300,100)

35

33

17

15

0.67

0.70

0.66

0.68

0.68

4th test: CNN (1346,450)

164

175

50

61

0.77

0.73

0.78

0.75

0.75