Alzheimer’s Disease Diagnosis using Deep Learning Approach

Alzheimer's Disease (AD) is a long-term neurodegenerative condition that kills brain cells, leading to dementia and irreversible decline in cognitive abilities. There is no cure for it, and its underlying causes are still poorly understood. However, neuro imaging tools now help with clinical diagnosis, and deep learning techniques have lately developed as a crucial paradigm applied with these tools. Machine learning algorithms, in particular analytical modelling and sample detection in biomedical sciences from the deliverance of drugs to medicinal visioning; have emerged as the one among the key techniques that are helping researchers to gain a deeper accepting of the overall problem and to solve challenging clinical issues. Deep learning is a dominant machine learning approach for classifying and retrieving the characteristics. In this paper, the distinction between a brain affected by Alzheimer's disease and a healthy brain has been made using Convolutional Neural Networks (CNN). The significance of categorising this type of medical information is to ultimately establish a expect form or model to distinguish the kind of illness from healthy people or to expect the state of the illness. This study has effectively identified MRI data of individuals with Alzheimer's disease (AD) by using Convolutional Neural Network (CNN) and the well-known architecture of LeNet-5 model has been utilized on the trained data to obtain the maximum accuracy of distinguishing the AD affected brain and normally functioning brain.