Table 13.

Performance results of ResNet50 on internal dataset

	KFold	Accuracy	Precision	Recall	Specificity	F1-score
Without GAN	Fold1	0.9710	0.9719	0.9688	0.9731	0.9704
	Fold2	0.9771	0.9752	0.9782	0.9760	0.9767
	Fold3	0.9832	0.9844	0.9813	0.9850	0.9828
	Fold4	0.9817	0.9874	0.9751	0.9880	0.9812
	Fold5	0.9863	0.9906	0.9813	0.9910	0.9859
	Overall	0.9798	0.9819	0.9769	0.9826	0.9794
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	0.9939	1.0000	0.9875	1.0000	0.9937
	Fold4	0.9893	0.9968	0.9813	0.9970	0.9890
	Fold5	0.9893	0.9968	0.9813	0.9970	0.9890
	Overall	0.9911	0.9969	0.9850	0.9970	0.9909