Table 15.

Performance results of ResNet50v2 on internal dataset

	KFold	Accuracy	Precision	Recall (Sensitivity)	Specificity	F1-score
Without GAN	Fold1	0.9847	0.9968	0.9720	0.9970	0.9842
	Fold2	0.9847	0.9968	0.9720	0.9970	0.9842
	Fold3	0.9863	0.9906	0.9813	0.9910	0.9859
	Fold4	0.9847	0.9905	0.9782	0.9910	0.9843
	Fold5	0.9893	0.9906	0.9875	0.9910	0.9891
	Overall	0.9860	0.9931	0.9782	0.9934	0.9856
With GAN	Fold1	0.9908	0.9937	0.9875	0.9940	0.9906
	Fold2	0.9924	0.9969	0.9875	0.9970	0.9922
	Fold3	0.9954	0.9969	0.9938	0.9970	0.9953
	Fold4	0.9954	1.0000	0.9907	1.0000	0.9953
	Fold5	0.9969	1.0000	0.9938	1.0000	0.9969
	Overall	0.9942	0.9975	0.9907	0.9976	0.9941