Table 4 Classification results obtained when the models are run (5 slices manually).

From: Improving early detection of Alzheimer’s disease through MRI slice selection and deep learning techniques

Models

Accuracy

Precision

Recall

F1 Score

AUC

MCC

EfficientNetB2

0.9177

0.8244

0.7478

0.7834

0.9569

0.7823

InceptionV3

0.8788

0.7148

0.6556

0.6864

0.9381

0.6972

RegNetx006

0.9712

0.9345

0.9203

0.9268

0.9929

0.9375

Basic ViT

0.8898

0.7678

0.6981

0.7302

0.9482

0.7394

EfficientNetB2 + FPN (Our Model)

0.9473

0.9315

0.9029

0.9167

0.9714

0.9098

ViT + EfficientNetB2 + FPN (Our model)

0.9091

0.9082

0.7089

0.7978

0.9021

0.8236

Back to article page