Table 10 A comparative evaluation analysis of the developed Skin-DeepNet architecture against state-of-the-art systems on the ISIC 2019 and HAM1000 datasets.

From: A deep learning framework for automated early diagnosis and classification of skin cancer lesions in dermoscopy images

Approaches

ISIC 2019

HAM1000

AR

Pr.

Re.

F1

AUC

AR

Pr.

Re.

F1

AUC

Adegun and Viriri44

–

–

–

–

–

98.3

98

98.5

98

99

Banerjee et al.36

97.86

94.99

96.06

–

–

–

–

–

–

–

Singh et al.37

98.04

95.82

96.67

96.24

97.59

–

–

–

–

–

Krishnan et al.42

96.03

96.68

96.03

96.03

–

96.36

97.07

96.36

96.44

–

Monica et al.41

–

–

–

–

–

99.98

 

99.97

99.90

–

Imranet al.18

93.50

94

87

92

–

–

–

–

–

–

Radhika and Chandana43

98.77

98.56

98.42

98.76

–

–

–

–

–

–

Naeem and Anees45

98.32

98.23

98.23

98.19

98.90

–

–

–

–

–

Himel et al.38

–

–

–

–

–

96.15

96.95

95.30

96.12

99.49

Alwakid et al.46

–

–

–

–

–

86

84

86

86

 

Ali et al.47

–

–

–

–

–

87.91

88

88

87

97.53

Kousis et al.48

–

–

–

–

–

92.25

92.95

93.59

93.27

–

Skin-DeepNet system

99.65

99.51

99.56

99.54

99.94

100

99.92

100

99.96

99.97