A CNN Model: Earlier Diagnosis and Classification of Alzheimer Disease using MRI

Alzheimer 's Disease (AD) is the most common form of dementia that can lead to a neurological brain disorder that causes progressive memory loss as a result of damaging the brain cells and the ability to perform daily activities. Using MRI (Magnetic Resonance Imaging) scan brain images, we can get the help of Artificial intelligence (AI) technology for detection and prediction of this disease and classify the AD patients whether they have or may not have this deadly disease in future. The main purpose of doing all this is to make the best prediction and detection tools for the help of radiologists, doctors, caregivers to save time, cost, and help the patient suffering from this disease. In recent years, the Deep Learning (DL) algorithms are very useful for the diagnosis of AD as DL algorithms work well with large datasets. In this paper, we have implemented Convolutional Neural Network (CNN) for the earlier diagnosis and classification of AD using MRI images, the ADNI 3 class of images with the total number of 1512 mild, 2633 normal and 2480 AD were used. A significant accuracy of 99% achieved in which the model performed well as we compared with many other related works. Furthermore, we also compared the result with our previous work on which ma-chine learning algorithms were applied using OASIS dataset and it showed that when dealing with large amount of data like medical data the deep learning approaches can be a better option over the traditional machine learning techniques.