Goal: Detect Alzheimer's disease from structural brain MRI (Magnetic resonance imaging).
This project aims to predict Alzheimer's disease, specifically distinguishing between Mild Cognitive Impairment (MCI) and Cognitively Normal (CN) individuals, using structural brain MRI scans. We propose a deep learning-based approach, utilizing a Convolutional Neural Network (CNN) to extract relevant features from the MRI scans and classify the subjects. Additionally, we explore a hybrid model that combines the feature extraction capabilities of the CNN with the predictive power of the XGBoost algorithm, incorporating both imaging features and demographic information (age and sex) to enhance the model's performance. Our goal is to develop an accurate and reliable prediction model that can assist in the early detection of Alzheimer's disease, ultimately leading to timely intervention and improved patient outcomes.