Table 1 Summarized results of the metrics of the seven models evaluated in a pilot test to support the decision-making process for the selection of a network.

CNN model	Architecture	K-fold 5	Loss	Metrics
CNN model	Architecture	K-fold 5	Loss	Accuracy	F₁-score	Precision	Recall	Specificity
DenseNet121 100 epochs Batch size=32	TL	Fold 1	0.7780	0.8327	0.8193	0.8203	0.8185	0.9213
		Fold 2	0.6892	0.8227	0.7920	0.7920	0.7920	0.9112
		Fold 3	0.6635	0.8114	0.7804	0.7808	0.7800	0.9121
		Fold 4	0.7392	0.8162	0.8159	0.8169	0.8149	0.9320
		Fold 5	0.6757	0.8262	0.8242	0.8261	0.8224	0.9334
		Average	0.7091	0.8218	0.8064	0.8072	0.8056	0.9220
InceptionV3 100 epochs Batch size=16	TL	Fold 1	0.8517	0.7640	0.7608	0.7649	0.7573	0.9037
		Fold 2	0.5928	0.7640	0.7564	0.7615	0.7524	0.8953
		Fold 3	0.7088	0.7503	0.7437	0.7464	0.7414	0.8988
		Fold 4	0.6979	0.7712	0.7673	0.7715	0.7637	0.9095
		Fold 5	0.6236	0.7599	0.7588	0.7679	0.7512	0.9043
		Average	0.6950	0.7619	0.7574	0.7625	0.7532	0.9023
Xception 100 epochs Batch size=32	TL	Fold 1	0.9429	0.7852	0.7749	0.7758	0.7740	0.9084
		Fold 2	0.7903	0.8039	0.7732	0.7736	0.7728	0.9071
		Fold 3	1.0323	0.7702	0.7603	0.7610	0.7596	0.9034
		Fold 4	0.8688	0.8087	0.8079	0.8083	0.8075	0.9312
		Fold 5	0.9424	0.7875	0.7871	0.7882	0.7862	0.9233
		Average	0.9154	0.7911	0.7807	0.7814	0.7800	0.9147
InceptionResNetV2 100 epochs Batch size=32	TL	Fold 1	0.9598	0.7915	0.7618	0.7629	0.7608	0.9053
		Fold 2	0.9619	0.8127	0.8007	0.8024	0.7992	0.9142
		Fold 3	0.9329	0.8064	0.7950	0.7955	0.7944	0.9132
		Fold 4	0.8800	0.7962	0.7965	0.7968	0.7962	0.9272
		Fold 5	0.7088	0.8324	0.8324	0.8336	0.8312	0.9387
		Average	0.8886	0.8078	0.7973	0.7982	0.7964	0.9197

CNN model	Architecture	K-fold 5	Loss	Metrics
CNN model	Architecture	K-fold 5	Loss	Accuracy	F₁-score	Precision	Recall	Specificity
ResNet50 100 epochs Batch size=32	TL	Fold 1	0.9303	0.7915	0.7626	0.7645	0.7608	0.9041
		Fold 2	1.0381	0.8002	0.7881	0.7903	0.7860	0.9118
		Fold 3	0.8592	0.8177	0.7872	0.7872	0.7872	0.9109
		Fold 4	0.9334	0.8062	0.8066	0.8071	0.8062	0.9297
		Fold 5	0.7910	0.8062	0.8072	0.8082	0.8062	0.9304
		Average	0.9104	0.8043	0.7903	0.7915	0.7893	0.9174
ResNet101 100 epochs Batch size=32	TL	Fold 1	0.9598	0.8014	0.7712	0.7721	0.7704	0.9064
		Fold 2	0.8728	0.8102	0.7977	0.7987	0.7968	0.9175
		Fold 3	0.9338	0.7952	0.7819	0.7827	0.7812	0.9110
		Fold 4	0.8091	0.7962	0.7968	0.7989	0.7950	0.9229
		Fold 5	0.8373	0.8075	0.8064	0.8067	0.8062	0.9308
		Average	0.8826	0.8021	0.7908	0.7918	0.7899	0.9177
MobileNetV2 100 epochs Batch size=32	TL	Fold 1	0.7950	0.7990	0.7682	0.7710	0.7656	0.9043
		Fold 2	1.0042	0.7777	0.7501	0.7516	0.7487	0.8989
		Fold 3	1.0015	0.7865	0.7752	0.7752	0.7752	0.9075
		Fold 4	0.8395	0.7837	0.7838	0.7838	0.7837	0.9228
		Fold 5	0.6802	0.8075	0.8086	0.8098	0.8075	0.9248
		Average	0.8641	0.7909	0.7772	0.7783	0.7761	0.9117
VGG16 100 epochs Batch size=32	TL	Fold 1	0.6843	0.8064	0.7769	0.7775	0.7764	0.9071
		Fold 2	0.6431	0.8439	0.8125	0.8125	0.8125	0.9197
		Fold 3	0.5552	0.8064	0.7949	0.7954	0.7944	0.9105
		Fold 4	0.5840	0.7362	0.7376	0.7509	0.7262	0.8727
		Fold 5	0.6014	0.7024	0.6990	0.7064	0.6924	0.8725
		Average	0.6136	0.7791	0.7642	0.7685	0.7604	0.8965

Search