Automated Identification of Alzheimer’s Disease Stages Based on Magnetic Resonance Imaging Scans Using Artificial Intelligence Techniques

Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by progressive cognitive decline. Early and accurate identification of AD stages is crucial for timely intervention. This study proposes an automated approach using artificial intelligence (AI) techniques to classify MRI scans into different stages of AD. A dataset comprising 6400 preprocessed MRI images representing non-demented (ND), very mild demented (VMD), mild demented (MD), and moderate demented (ModD) stages was utilized. The study focuses on addressing class imbalance through data preprocessing and augmentation techniques. Various AI algorithms, such as MobileNetV2, DenseNet-201, ResNet-50, and VGG-19 in conjunction with several machine learning algorithms including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Gradient Boosting (GB), Random Forest (RF), Decision Tree (DT), and Gaussian Naïve Bayes (GNB), were employed to classify MRI scans under different dataset conditions. The Equalized Balanced Dataset yielded the highest accuracy of 99.6% in classifying AD stages. Results were compared with existing literature, demonstrating improved accuracy over previous methodologies. This research contributes to enhancing the efficiency and accuracy of AD classification using MRI scans, aiding in early diagnosis.