Alzheimer's Disease Prediction Using VGG16 and Transfer Learning

Alzheimer's Disease (AD) prediction is essential for early detection and effective treatment. In this paper, a hybrid deep learning model has been proposed for predicting Alzheimer's Disease in a patient in their early years. The dataset consists of Magnetic Resonance Imaging (MRI) scans that have four classes namely, non-demented, very mild demented, mildly demented, and moderately demented. In this hybrid model, fine-tuned VGG16 and transfer learning models were used with hyperparameter tuning to adapt it to Alzheimer's Disease prediction. The simulation results show that the proposed hybrid model outperforms the existing VGG16 model with an accuracy of 97.23%