Alzheimer’s Disease Prediction Using Deep Learning Techniques

The brain anatomy is studied by Magnetic resonance imaging (MRI). In order to take preventive measures that are necessary, early diagnosis of patients affected by Alzheimer’s disease(AD) is more essential. The most prevalent illness affecting the old people is AD. For the diagnosis of AD, numerous, intricate segmentation methods have been presented. Deep Learning (DL) techniques have attracted interest for the technique of segmenting the anatomy of the brain and categorizing AD because they can produce efficient results over a vast data collection. How the knowledge of brain anatomy can be used to identify AD using concepts from convolutional neural networks are explained. New methods, their outcomes on public datasets, and the advantages of MRI segmentation of brain for classification of AD is described. This work investigates the potential use of DL techniques to enhance and strengthen early diagnosis, predict AD phases as mild, moderate, low, or medium, and investigate strategies for strengthening overall performance analysis.