Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI

Youngoh Bae, Kunaraj Kumarasamy, Issa M. Ali, Panagiotis Korfiatis, Zeynettin Akkus, Bradley J Erickson

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Schizophrenia has been proposed to result from impairment of functional connectivity. We aimed to use machine learning to distinguish schizophrenic subjects from normal controls using a publicly available functional MRI (fMRI) data set. Global and local parameters of functional connectivity were extracted for classification. We found decreased global and local network connectivity in subjects with schizophrenia, particularly in the anterior right cingulate cortex, the superior right temporal region, and the inferior left parietal region as compared to healthy subjects. Using support vector machine and 10-fold cross-validation, nine features reached 92.1% prediction accuracy, respectively. Our results suggest that there are significant differences between control and schizophrenic subjects based on regional brain activity detected with fMRI.

Original languageEnglish (US)
Pages (from-to)1-10
Number of pages10
JournalJournal of Digital Imaging
DOIs
StateAccepted/In press - Sep 18 2017

Fingerprint

Schizophrenia
Magnetic Resonance Imaging
Parietal Lobe
Gyrus Cinguli
Temporal Lobe
Support vector machines
Learning systems
Brain
Healthy Volunteers
Machine Learning
Datasets
Support Vector Machine

Keywords

  • fMRI
  • Machine learning
  • Network properties
  • Schizophrenia

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI. / Bae, Youngoh; Kumarasamy, Kunaraj; Ali, Issa M.; Korfiatis, Panagiotis; Akkus, Zeynettin; Erickson, Bradley J.

In: Journal of Digital Imaging, 18.09.2017, p. 1-10.

Research output: Contribution to journalArticle

@article{5de6353602f5425e8f057aea475b978b,
title = "Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI",
abstract = "Schizophrenia has been proposed to result from impairment of functional connectivity. We aimed to use machine learning to distinguish schizophrenic subjects from normal controls using a publicly available functional MRI (fMRI) data set. Global and local parameters of functional connectivity were extracted for classification. We found decreased global and local network connectivity in subjects with schizophrenia, particularly in the anterior right cingulate cortex, the superior right temporal region, and the inferior left parietal region as compared to healthy subjects. Using support vector machine and 10-fold cross-validation, nine features reached 92.1{\%} prediction accuracy, respectively. Our results suggest that there are significant differences between control and schizophrenic subjects based on regional brain activity detected with fMRI.",
keywords = "fMRI, Machine learning, Network properties, Schizophrenia",
author = "Youngoh Bae and Kunaraj Kumarasamy and Ali, {Issa M.} and Panagiotis Korfiatis and Zeynettin Akkus and Erickson, {Bradley J}",
year = "2017",
month = "9",
day = "18",
doi = "10.1007/s10278-017-0020-4",
language = "English (US)",
pages = "1--10",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",

}

TY - JOUR

T1 - Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI

AU - Bae, Youngoh

AU - Kumarasamy, Kunaraj

AU - Ali, Issa M.

AU - Korfiatis, Panagiotis

AU - Akkus, Zeynettin

AU - Erickson, Bradley J

PY - 2017/9/18

Y1 - 2017/9/18

N2 - Schizophrenia has been proposed to result from impairment of functional connectivity. We aimed to use machine learning to distinguish schizophrenic subjects from normal controls using a publicly available functional MRI (fMRI) data set. Global and local parameters of functional connectivity were extracted for classification. We found decreased global and local network connectivity in subjects with schizophrenia, particularly in the anterior right cingulate cortex, the superior right temporal region, and the inferior left parietal region as compared to healthy subjects. Using support vector machine and 10-fold cross-validation, nine features reached 92.1% prediction accuracy, respectively. Our results suggest that there are significant differences between control and schizophrenic subjects based on regional brain activity detected with fMRI.

AB - Schizophrenia has been proposed to result from impairment of functional connectivity. We aimed to use machine learning to distinguish schizophrenic subjects from normal controls using a publicly available functional MRI (fMRI) data set. Global and local parameters of functional connectivity were extracted for classification. We found decreased global and local network connectivity in subjects with schizophrenia, particularly in the anterior right cingulate cortex, the superior right temporal region, and the inferior left parietal region as compared to healthy subjects. Using support vector machine and 10-fold cross-validation, nine features reached 92.1% prediction accuracy, respectively. Our results suggest that there are significant differences between control and schizophrenic subjects based on regional brain activity detected with fMRI.

KW - fMRI

KW - Machine learning

KW - Network properties

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85029583461&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029583461&partnerID=8YFLogxK

U2 - 10.1007/s10278-017-0020-4

DO - 10.1007/s10278-017-0020-4

M3 - Article

C2 - 28924878

AN - SCOPUS:85029583461

SP - 1

EP - 10

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

ER -