Alzheimer’s disease (AD) is the most prevalent form of dementia and a major cause of mortality among older adults. Magnetic resonance imaging (MRI) and positron emission tomography (PET) are commonly used for AD diagnosis. Despite extensive research, the accuracy of automated detection methods remains limited. This study proposes a highly accurate AD classification model by integrating complementary information from MRI and PET scans. The images are fused using a discrete wavelet transform (DWT), augmented, and subsequently classified using a Vision Transformer (ViT). Comprehensive evaluation across nine performance metrics shows that the proposed ViT-based framework achieves 97.68\% accuracy, surpassing benchmark transfer learning models and state-of-the-art methods. Ablation studies and comparative analysis further confirm the robustness and reliability of the proposed approach for AD detection.
Dum et al. (Wed,) studied this question.