Volumetric Histogram-Based Alzheimer's Disease Detection Using Support Vector Machine

Heba Elshatoury; Egils Avots; Gholamreza Anbarjafari; Alzheimer’s Disease Neuroimaging Initiative

doi:10.3233/JAD-190704

Volumetric Histogram-Based Alzheimer's Disease Detection Using Support Vector Machine

J Alzheimers Dis. 2019;72(2):515-524. doi: 10.3233/JAD-190704.

Authors

Heba Elshatoury¹, Egils Avots¹, Gholamreza Anbarjafari^{1

2}; Alzheimer’s Disease Neuroimaging Initiative

Affiliations

¹ iCV Research Lab, Institute of Technology, University of Tartu, Tartu, Estonia.
² Department of Electrical and Electronic Engineering, Hasan Kalyoncu University, Gaziantep, Turkey.

PMID: 31609690
DOI: 10.3233/JAD-190704

Abstract

In this research work, machine learning techniques are used to classify magnetic resonance imaging brain scans of people with Alzheimer's disease. This work deals with binary classification between Alzheimer's disease and cognitively normal. Supervised learning algorithms were used to train classifiers in which the accuracies are being compared. The database used is from The Alzheimer's Disease Neuroimaging Initiative (ADNI). Histogram is used for all slices of all images. Based on the highest performance, specific slices were selected for further examination. Majority voting and weighted voting is applied in which the accuracy is calculated and the best result is 69.5% for majority voting.

Keywords: Alzheimer’s disease; computer vision; feature extraction; individual grey matter; machine learning; magnetic resonance imaging.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Alzheimer Disease / diagnosis*
Alzheimer Disease / diagnostic imaging
Databases, Factual
Decision Trees
Humans
Image Interpretation, Computer-Assisted
Machine Learning
Magnetic Resonance Imaging
Neuroimaging
Positron-Emission Tomography
Reproducibility of Results
Support Vector Machine*