EARLY DIAGNOSIS OF ALZHEIMER’S DISEASE (AD) USING DEEP LEARNING TECHNIQUES

Abstract

Alzheimer's disease is a neurodegenerative disorder that progresses slowly and affects memory, and it is therefore important to diagnose it as early as possible to ensure it does not progress. Conventional diagnostic methods often fail to identify subtle structural and functional brain changes in the initial stages. To address this challenge, this research proposes a DL-based structure that employs a CNN for automated feature extraction and classification from MRI and fMRI scans. CNN effectively captures discriminative spatial patterns associated with early AD, enabling accurate differentiation between normal, mild cognitive impairment, and Alzheimer-affected brains. The performance of the model was evaluated by employing standard metrics. It is observed that the experimental results show the proposed CNN framework’s 94.2% accuracy is better than the traditional methods. This proves the robust nature of the CNN models in the early stages of AD. Furthermore, this approach offers a practical diagnostic tool that can support clinicians in timely interventions, with potential for further improvement through integration of multimodal neuroimaging and clinical data.