Skip to main content
Journal of Big Data

Table 8 Comparison of performance measures using ISIC-2020 with state-of-the-art

From: Skin-Net: a novel deep residual network for skin lesions classification using multilevel feature extraction and cross-channel correlation with detection of outlier

 

Method

Classification

Pre-processing (enhancement and/or segmentation and/or Augmentation)

Performance measures

Accuracy (%)

Specificity (%)

Sensitivity (%)

Precision (%)

F-Score (%)

[57]

Transfer learning to VGG19

Binary

yes

80.67

–

–

–

–

[26]

Fuzzy C-means and Red Fox Optimization

Binary

yes

90.5

92.1

89.5

–

–

[58]

SqueezeNet optimized by bald eagle search

Binary

yes

98.37

96.74

100

–

98.39

Proposed methods

RDNN

Multiclass (7)

No

98.69

99.28

95.43

95.43

93.79

  1. The proposed method for ISIC 2020 obtained the highest values for accuracy, specificity, and precision only compared with methods [26, 57, 58].
Back to article page