ALZHEIMER'S DIAGNOSIS USING ADAPTIVE NEURO CLUSTERING

Alzheimer’s disease (AD) is one of the most common neurodegenerative disorders affecting millions of elderly individuals worldwide. It gradually damages brain cells, resulting in memory loss, cognitive decline, and behavioural changes that significantly impact daily life. Early and accurate diagnosis of Alzheimer’s disease is essential for effective treatment planning and slowing disease progression. However, conventional diagnostic techniques mainly depend on clinical examinations and manual analysis of brain imaging data, which are often timeconsuming and subject to human error. In recent years, machine learning and artificial intelligence techniques have shown promising potential for improving the accuracy and efficiency of neurological disease diagnosis. This study proposes an intelligent system for Alzheimer’s diagnosis using Adaptive Neuro Clustering techniques applied to Magnetic Resonance Imaging (MRI) data. The proposed system integrates several image processing and machine learning methods to automatically detect structural brain changes associated with Alzheimer’s disease. Initially, MRI images undergo preprocessing operations such as noise removal, skull stripping, and intensity normalization to improve image quality. After preprocessing, texture features are extracted using the Gray Level Co-occurrence Matrix (GLCM), which captures spatial relationships among pixels in brain images. To reduce computational complexity and retain important information, Principal Component Analysis (PCA) is applied for dimensionality reduction. The core component of the system uses an Adaptive Moving SelfOrganizing Map (AMSOM) combined with KMeans clustering to classify brain images into Normal, Mild Cognitive Impairment (MCI), and Alzheimer’s Disease categories. Experimental results indicate that the proposed system improves classification accuracy and provides a reliable decision-support tool for medical professionals. This automated approach helps neurologists detect Alzheimer’s disease at an early stage and contributes to improved patient management and healthcare outcomes.