Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

Table 3

Performance metrics for the cubic SVM classifier trained with ResNet-50 +DenseNet-201 + DarkNet-53 + DWT-A + LBP features.

Class	Specificity	Sensitivity	Precision	F1-score
ak	0.9979	0.9674	0.98765	0.9768
bcc	0.9979	0.9874	0.9874	0.9874
blk	0.9918	0.9799	0.9555	0.9675
df	1	1	1	1
mel	0.999	0.9865	0.9946	0.9905
nv	0.9992	0.9971	0.9952	0.9962
vasc	1	1	1	1
mean	0.9969	0.9854	0.9884	0.9883