Application of pattern recognition and graph theoretical approaches to analysis of brain network in Alzheimer's disease

Ali Khazaee, Ata Ebrahimzadeh, Abbas Babajani-Feremi

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We used resting-state functional magnetic resonance imaging (fMRI) data to study functional brain network alteration in patients with Alzheimer's disease (AD). We combine graph theoretical approaches with advanced machine learning methods to automatically classify patients with AD from healthy subjects. Our method was applied on the resting-state fMRI data of twenty patients with AD and twenty age and gender matched healthy subjects. After preprocessing of data, signals from 90 brain regions, parcelated based on the automated anatomical labeling (AAL) atlas, were extracted and edges of the graph were calculated using the correlation between the signals of all pairs of the brain regions. Then a weighted undirected graph was constructed and graph measures were calculated. Extracted network-based features were fed to different feature selection algorithms to choose most significant features. Support vector machine (SVM) was used to explore the ability of graph measures in diagnosis of AD. Using the selected features, we were able to accurately classify patients with AD from healthy control ones with accuracy of 97.5%.

Original languageEnglish (US)
Pages (from-to)1145-1155
Number of pages11
JournalJournal of Medical Imaging and Health Informatics
Volume5
Issue number6
DOIs
StatePublished - Dec 1 2015

Fingerprint

Alzheimer Disease
Brain
Healthy Volunteers
Magnetic Resonance Imaging
Aptitude
Atlases

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging
  • Health Informatics

Cite this

Application of pattern recognition and graph theoretical approaches to analysis of brain network in Alzheimer's disease. / Khazaee, Ali; Ebrahimzadeh, Ata; Babajani-Feremi, Abbas.

In: Journal of Medical Imaging and Health Informatics, Vol. 5, No. 6, 01.12.2015, p. 1145-1155.

Research output: Contribution to journalArticle

@article{d2b5c726709d425e92d8ca19e2cb3c8e,
title = "Application of pattern recognition and graph theoretical approaches to analysis of brain network in Alzheimer's disease",
abstract = "We used resting-state functional magnetic resonance imaging (fMRI) data to study functional brain network alteration in patients with Alzheimer's disease (AD). We combine graph theoretical approaches with advanced machine learning methods to automatically classify patients with AD from healthy subjects. Our method was applied on the resting-state fMRI data of twenty patients with AD and twenty age and gender matched healthy subjects. After preprocessing of data, signals from 90 brain regions, parcelated based on the automated anatomical labeling (AAL) atlas, were extracted and edges of the graph were calculated using the correlation between the signals of all pairs of the brain regions. Then a weighted undirected graph was constructed and graph measures were calculated. Extracted network-based features were fed to different feature selection algorithms to choose most significant features. Support vector machine (SVM) was used to explore the ability of graph measures in diagnosis of AD. Using the selected features, we were able to accurately classify patients with AD from healthy control ones with accuracy of 97.5{\%}.",
author = "Ali Khazaee and Ata Ebrahimzadeh and Abbas Babajani-Feremi",
year = "2015",
month = "12",
day = "1",
doi = "10.1166/jmihi.2015.1513",
language = "English (US)",
volume = "5",
pages = "1145--1155",
journal = "Journal of Medical Imaging and Health Informatics",
issn = "2156-7018",
publisher = "American Scientific Publishers",
number = "6",

}

TY - JOUR

T1 - Application of pattern recognition and graph theoretical approaches to analysis of brain network in Alzheimer's disease

AU - Khazaee, Ali

AU - Ebrahimzadeh, Ata

AU - Babajani-Feremi, Abbas

PY - 2015/12/1

Y1 - 2015/12/1

N2 - We used resting-state functional magnetic resonance imaging (fMRI) data to study functional brain network alteration in patients with Alzheimer's disease (AD). We combine graph theoretical approaches with advanced machine learning methods to automatically classify patients with AD from healthy subjects. Our method was applied on the resting-state fMRI data of twenty patients with AD and twenty age and gender matched healthy subjects. After preprocessing of data, signals from 90 brain regions, parcelated based on the automated anatomical labeling (AAL) atlas, were extracted and edges of the graph were calculated using the correlation between the signals of all pairs of the brain regions. Then a weighted undirected graph was constructed and graph measures were calculated. Extracted network-based features were fed to different feature selection algorithms to choose most significant features. Support vector machine (SVM) was used to explore the ability of graph measures in diagnosis of AD. Using the selected features, we were able to accurately classify patients with AD from healthy control ones with accuracy of 97.5%.

AB - We used resting-state functional magnetic resonance imaging (fMRI) data to study functional brain network alteration in patients with Alzheimer's disease (AD). We combine graph theoretical approaches with advanced machine learning methods to automatically classify patients with AD from healthy subjects. Our method was applied on the resting-state fMRI data of twenty patients with AD and twenty age and gender matched healthy subjects. After preprocessing of data, signals from 90 brain regions, parcelated based on the automated anatomical labeling (AAL) atlas, were extracted and edges of the graph were calculated using the correlation between the signals of all pairs of the brain regions. Then a weighted undirected graph was constructed and graph measures were calculated. Extracted network-based features were fed to different feature selection algorithms to choose most significant features. Support vector machine (SVM) was used to explore the ability of graph measures in diagnosis of AD. Using the selected features, we were able to accurately classify patients with AD from healthy control ones with accuracy of 97.5%.

UR - http://www.scopus.com/inward/record.url?scp=85000350880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85000350880&partnerID=8YFLogxK

U2 - 10.1166/jmihi.2015.1513

DO - 10.1166/jmihi.2015.1513

M3 - Article

VL - 5

SP - 1145

EP - 1155

JO - Journal of Medical Imaging and Health Informatics

JF - Journal of Medical Imaging and Health Informatics

SN - 2156-7018

IS - 6

ER -