MACHINELEARNING AND DEEP LEARNING TECHNIQUES IN DIAGNOSING ALZHEIMERS DISEASE-A REVIEW

Abstract

The disease progressively damages the memory cells and mental functions - Alzheimer’s disorder, which leads to the mental illness. The early identification of this disease is really difficult; to solve this problem researchers developed deep convolutional neural networks (CNN) method to identify and solve a range of troubles associated with brain imaging data analysis. MRI diagnosing method is currently commonly used for AD identification. For exact categorization of mental illness stages, we require extremely selective features attained from MRI scanning. CNN effectively showed their precision. The machine learning techniques are surveyed under three main categories: first one is support vector machine, second one is artificial neural web system and DL and combined methods. Compared with already available methods DL is performing well to identify complex configuration in difficult highly complicated data. Recently this advantage of CNN is used for the early diagnosis and categorization of AD. A quick development in neuro imaging methods has produced extensive multimodal neuro imaging data. In this review, we can see more details about the process of DL approaches performance and neuro imaging data for analytical categorization of AD.