Analysing of Alzheimer Diseases Using Data Augmentation and CNN

Alzheimer’s disease is the most prevalent form of dementia, characterized by a progressive decline in cognitive function. It typically begins with mild memory impairment and gradually leads to severe neurological deterioration, affecting an individual's ability to converse, interact, and respond to their environment. This irreversible condition involves critical regions of the brain responsible for thought processes, memory retention, and decision-making. The growing prevalence of Alzheimer’s disease worldwide underscores the importance of timely diagnosis and effective interventions to enhance patients’ quality of life and explore more efficient therapeutic strategies. Advanced diagnostic methods using imaging technologies, such as Magnetic Resonance Imaging (MRI), have revolutionized the early detection of Alzheimer’s disease. These scans provide critical insights into the structural changes in the brain, enabling researchers to differentiate between healthy individuals and those with neurodegenerative conditions. However, manual analysis of these imaging data is time-consuming and prone to variability, necessitating automated and robust computational approaches for accurate diagnosis. In this research, we propose a novel framework for classifying MRI scans using Principal Component Analysis (PCA) for feature extraction, data augmentation techniques for expanding the dataset, and a 2D Convolutional Neural Network (2D CNN) for classification.