Identification and Analysis of Alzheimer’s Disease using DenseNet Architecture with Minimum Path Length Between Input and Output Layers

Abstract

Alzheimer’s Disease is a neurological brain disorder that damages the cells in brain and reduce the ability of the brain from the regular activities. It is a representation of the most common form of adult-onset dementias. Earlier detection of Alzheimer’s disease can be more helpful in predetermining the symptomatic conditions of patients suffering with this problem. By diagnosing the consequences of this disease, with the help of medical scan images, it would be more useful in classifying the patients whether they are suffering from this deadly disease. Machine Learning tends to be more beneficial in diagnosing diseases and implementation of this technique, to Magnetic Resonance Imaging (MRI) inputs in identification of Alzheimer’s disease, resulted in faster prediction of the disease and in the contribution of the evolution of the disease. Carrying out this technique, it is possible to diagnose and predict the individual dementia of adults by screening data of Alzheimer’s disease and inducing Machine Learning classifiers. This work focuses on building an evolving framework to detect Alzheimer’s disease efficiently with the help of neuroimaging technologies and prediction at a very earlier stage by using the data stacked up for Alzheimer’s disease patients.