Table 7. Training results when models run.

1 vs All	Models	Accuracy	Precision	Recall	Auc	F1 score	Validation accuracy
MCI/CNAD	EfficientNetB0	0.9984	0.9976	0.9976	0.9998	0.9976	0.9790
	DenseNet121	0.9970	0.9970	0.9970	0.9999	0.9969	0.9796
	AlexNet	0.9969	0.9953	0.9953	0.9993	0.9953	0.9233
AD/CNMCI	EfficientNetB0	0.9929	0.9894	0.9894	0.9991	0.9893	0.9915
	DenseNet121	0.9983	0.9983	0.9983	0.9999	0.9982	0.9915
	AlexNet	0.9990	0.9985	0.9985	0.9999	0.9985	0.9972
CN/MCIAD	EfficientNetB0	0.9973	0.9959	0.9959	0.9998	0.9959	0.9807
	DenseNet121	0.9853	0.9853	0.9853	0.9980	0.9852	0.9702
	AlexNet	0.9988	0.9982	0.9982	0.9999	0.9982	0.9776