Main Article Content

Abstract

Alzheimer Disease (AD) is one of the brain disorders which progressively expand over the years. It gradually harms the reasoning ability and memory of the affected person. Earlier identification can keep away the severity of the disease and can advance the feature of life. Alzheimer's disease diagnosis using image processing is an important but challenging problem around medical science since image processing made hard by noise, low contrast and other imaging ambiguities. There are many methods that exist in medical image analysis, which includes preprocessing, feature extraction, image segmentation and classification. Although several models have been widely used, there is a need to implement a system with more accuracy. A comparative analysis for the segmentation which comprises FCM and K-means clustering methods and classification of AD using SVM and CNN performed. These methods are used for segmentation and classification, which calculates the accuracy and consolidates their advantages. Finally analyzing efficient for the diagnosis of AD.

Keywords

Alzheimer Disease (AD) FCM (Fuzzy–C Means) ); CNN (Convolutional Neural Network) SVM (Support Vector Machine)

Article Details

How to Cite
Pushpa B.R, Nayana.P.Kamal, & Amal P.S. (2019). A comparative study on different segmentation and classification methods for the diagnosis of Alzheimer Disease. International Journal of Research in Pharmaceutical Sciences, 10(3), 2058-2070. https://doi.org/10.26452/ijrps.v10i3.1422