Table 41.

Performance results of DenseNet169 without GAN on external dataset

	KFold	Accuracy	Precision	Recall	Specificity	F1-score
Without GAN	Fold1	0.9071	0.7987	0.9165	0.9032	0.8536
	Fold2	0.9085	0.8041	0.9123	0.9069	0.8548
	Fold3	0.9016	0.7963	0.8960	0.9039	0.8432
	Fold4	0.8966	0.7899	0.8853	0.9013	0.8349
	Fold5	0.9022	0.8018	0.8885	0.9079	0.8429
	Overall	0.9032	0.7982	0.8997	0.9046	0.8459
With GAN	Fold1	0.9342	0.8618	0.9258	0.9378	0.8926
	Fold2	0.9363	0.8664	0.9273	0.9401	0.8958
	Fold3	0.9306	0.8605	0.9130	0.9380	0.8860
	Fold4	0.9302	0.8609	0.9108	0.9383	0.8851
	Fold5	0.9283	0.8623	0.9013	0.9397	0.8813
	Overall	0.9319	0.8624	0.9156	0.9388	0.8882