Deep Learning Classification using MRI for Alzheimer’s Disease Detection

Abstract

Alzheimer's disease is an incurable, progressive brain disorder that gradually destroys memory and cognitive function, and eventually the ability to perform even te most basic tasks. It is now considered to be one of the most common illnesses worldwide. Furthermore, there is no known cure for Alzheimer's disease. Convolutional Neural Networks (CNNs), a type of deep learning technique, are used to work on interaction for the identification of Alzheimer's infection. CNN has made great strides recently in the analysis of MRI images and medical research. Much research has been done to determine the exact location of Alzheimer's disease based on brain MRI images that are processed by CNN. However, a fundamental limitation is that there was no demonstration of a valid link between a suggested model and pre-trained models. Thus, utilizing the ADNI MRI dataset, we present a 6-layer CNN model for binary classification in this study to identify Alzheimer's. Our model's presentation is compared to a few other CNN-based models in terms of review, F1 score, ROC bend, and accuracy, precision, and accuracy on the Alzheimer Disease Neuroimaging Initiative (ADNI) dataset. The focus of the paper is our CNN model, which has an accuracy of 98.83%, better than the other previously proposed CNN-based models that are provided on the ADNI. The trial output demonstrates our model's supremacy over the other models. Keywords: CNN, MRI, ADNI, Alzheimer, Deep Learning, Machine Learning.