Table 8 Performance metrics for each individual class in the ISIC 2019 dataset using the Skin-DeepNet system.

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

Class

Pr.

Re.

Specificity

F1

Melanoma

98.1

97.5

99.8

97.8

Melanocytic nevi

99.7

99.9

99.2

99.8

Basal cell carcinoma

99.4

98.9

99.6

99.1

Squamous cell carcinoma

96.5

79.2

99.5

87.1

Vascular lesions

94.6

81.5

99.4

87.5

Dermatofibroma

97.3

86.4

99.7

91.5

Actinic keratosis

96.1

89.7

99.3

92.8

Benign keratosis

98.8

97.4

99.1

98.1