GAN-Enhanced Brain Slice Images for Detecting Alzheimer’s Disease

Alzheimer’s Disease (AD) is a progressive neurological disorder marked by cognitive decline, memory loss, and impaired reasoning, affecting millions globally. Early and accurate diagnosis of AD is crucial for managing the disease, yet traditional diagnostic methods such as clinical assessments and Magnetic Resonance Imaging (MRI) face significant challenges. This research proposes a novel approach to enhance the diagnostic process by using Generative Adversarial Networks (GANs) to improve brain MRI image quality, thereby aiding automated detection of AD. It involves preprocessing brain MRI scans, designing a GAN for image enhancement, and utilizing these enhanced images in a Convolutional Neural Network (CNN) for detecting AD. The effectiveness of method is evaluated using key metrics such as accuracy, sensitivity, and specificity, comparing its performance to baseline methods using non-enhanced images. Cross-validation and testing with external datasets are conducted to ensure the model’s robustness and generalizability. The integrated GAN-CNN framework demonstrated a remarkable accuracy of 99.9 % in predicting AD using MRI images from the OASIS dataset.