Deep Learning-Based Early Detection of Alzheimer’s Disease Using MRI Scans

Abstract

Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by progressive cognitive decline, posing a significant burden on healthcare systems globally. Early diagnosis is crucial for effective management and potential interventions. Recent advancements in deep learning (DL) techniques have demonstrated remarkable potential in medical imaging for disease detection. In this study, we propose a convolutional neural network (CNN)-based framework for the early detection of Alzheimer’s disease using magnetic resonance imaging (MRI) scans. The proposed model employs a transfer learning approach combined with fine-tuning to achieve high sensitivity and specificity. By leveraging pre-trained models, we address the challenges posed by limited datasets. Our results, validated on a publicly available ADNI dataset, indicate that the proposed method achieves state-of-the-art performance with an accuracy of 94.7%, outperforming existing methods. The study highlights the importance of feature extraction in distinguishing between healthy and pathological brain states. Further, we employ Grad-CAM for interpretability, providing clinicians with insights into the decision-making process. This research underscores the transformative potential of deep learning in enabling accurate, non-invasive, and timely diagnosis of Alzheimer’s disease.

DOI - https://doi.org/10.65525/SVUP.9788199778009.2026.70-76