Enhancing Alzheimer's Detection Using a Multi-Modal Approach Hybrid Features Extraction Technique from MRI Images

Abstract

The neurodegenerative illness Alzheimer's, which affects millions of people worldwide, poses significant obstacles to early detection and efficient treatment. The non-invasive technique of magnetic resonance imaging (MRI) has shown promise in identifying structural abnormalities in the brain linked to Alzheimer's disease. To address the complexity of Alzheimer's detection and enhance accuracy, this study proposes a novel hybrid feature extraction method that combines Convolutional Neural Networks (CNN), Local Binary Patterns (LBP), and Scale-Invariant Feature Transform (SIFT). After the feature extraction, PSO (Particle Swarm Optimization) and ABC (Ant Bee Colony) were applied for optimization. In this research, a dataset comprising MRI brain images from healthy individuals and Alzheimer's patients was curated. Preprocessing techniques were applied to enhance image quality and remove noise. The hybrid feature extraction method was then employed to extract distinctive and complementary features from the MRI images.