Multiclass Classification of Alzheimer’s Disease using Ensembling of Deep Learning Models

Alzheimer's Disease (AD) is a cognitive illness that poses significant challenges in its early detection and classification. AD diagnosis and classification represent crucial challenges in neurodegenerative research. In this work, we present a unique method for multiclass AD classification that combines deep learning models and ensemble approaches. Our methodology integrates convolutional neural networks (CNNs) and various pre-trained models to extract features from MRI scans. Further, through ensembling strategy, we combine the predictions of multiple deep learning models to enhance classification accuracy. Our experiments on a comprehensive dataset comprising AD patients at different stages shows how well the suggested method works for correctly classifying AD patients. In addition, the results underscore the potential of ensembling deep learning models for improving AD classification accuracy, which could facilitate early diagnosis and intervention strategies in clinical settings.