Table 1. Classification results for two classes—control and Alzheimer’s disease.

The best results for each test metric is indicated in bold italics.

Model	Train accuracy	Validation accuracy	Test accuracy	Test sensitivity	Test specificity
Siamese 3D	0.9844	0.8646	0.7448	0.6776	0.5943
ViT	0.7804	0.9203	0.8902	0.8902	0.7401
DenseNet	0.9656	0.8854	0.7448	0.6322	0.5905
EfficientNet B7	0.9672	0.8750	0.8542	0.8085	0.6835