Multi-Orientation Hippocampus-Centered 3D CNN with Attention Mechanism for Alzheimer’s Disease Classification from MRI Scans

Alzheimer’s disease detection faces challenges in capturing hippocampal atrophy across multiple anatomical orientations. This study presents a multi-orientation hippocampus-centered 3D CNN with attention mechanism for automated classification. The architecture processes three parallel 40×128×128×1 volumes from sagittal, axial, and coronal orientations. Each branch employs Conv3D layers with dilated convolutions and attention-based feature fusion. Training on ADNI dataset (1008 subjects: 652 normal, 356 Alzheimer’s) using focal loss achieves AUC-PR values of 0.982-0.990 across five-fold cross-validation. The hippocampus-centered preprocessing uses MNI152 registration and FIRST segmentation. Results demonstrate superior performance with interpretable attention weights for clinical deployment.