An artificial intelligence-based framework for Alzheimer's disease diagnosis from magnetic resonance imaging volumes via video vision transformer.

Objective: Alzheimer's disease (AD) is a progressive neurodegenerative disorder that leads to cognitive decline and memory impairment, posing a public health concern in aging populations. Early and accurate detection of AD using non-invasive imaging biomarkers remains a critical clinical need for timely intervention and disease management. This study aims to develop an advanced artificial intelligence (AI)-based diagnostic framework, ViTranZheimer, that leverages video vision transformers to analyze magnetic resonance imaging (MRI) and improve the accuracy of AD classification. Methods: This study presents 'ViTranZheimer,' an AD diagnosis approach that leverages video transformers to analyze MRI volumes. Our proposed deep learning framework aims to improve the accuracy and sensitivity of AD diagnosis, equipping clinicians with a tool for early detection and intervention. We exploit the temporal dependencies between slices by treating the MRI volumes as videos to capture intricate structural relationships. We evaluated ViTranZheimer on the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI): Complete 3Yr 3T data collection, which includes 351 T1-weighted MRI scans categorized into normal controls (NC = 129), mild cognitive impairment (MCI = 145), and AD = 77 groups. Each MRI volume was preprocessed using spatial normalization and skull stripping, then modeled as a video sequence for input to a Video Vision Transformer (ViViT). The model was trained from scratch using 10-fold stratified cross-validation and optimized with the Adam optimizer over 500 epochs. Classification performance was evaluated using accuracy, precision, recall, F1-score, and area under the ROC curve (AUC). Statistical comparison was conducted using the Wilcoxon signed-rank test against two baseline models: a convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM), and a vision transformer with bidirectional long short-term memory (ViT-BiLSTM). Results: The proposed ViTranZheimer model achieved 98.6% accuracy in classifying NC, MCI, and AD cases, outperforming CNN-BiLSTM (96.5%) and ViT-BiLSTM (97.5%). It also attained superior precision, recall, F1-score (all 0.97), and an AUC of 0.99. Performance differences were statistically significant based on the Wilcoxon signed-rank test ( Conclusion: ViTranZheimer demonstrates strong potential for accurate and early Alzheimer's disease diagnosis using non-invasive MRI data. By leveraging video vision transformers, the model provides a promising tool for clinical decision support in neurodegenerative disease detection.