Alzheimer’s disease (AD) is a serious neurological condition that leads to significant cognitive decline in millions of patients worldwide. This research intends to enhance AD classification using advanced machine-learning techniques applied to medical imaging data. We aim to increase diagnostic accuracy and support early detection with an advanced image-processing pipeline and complex machine-learning algorithms. This approach promotes early intervention thus enhancing patient outcomes using diagnosis and classification. Our work showcases unique techniques for the fusion of important characteristics of both Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) scans to provide new strategies for the early diagnosis of AD. This study aims to enhance the accuracy of feature extraction and analysis through artifact elimination, noise reduction and other sophisticated techniques. Our project will also evaluate the performance of the multimodal system in terms of various metrics. Key targets of the project include early perception of the disease, the fusion of data from both MRI and PET scans and the classification of individuals into specific stages of the disease.