Effects of non-neuronal components for functional connectivity analysis from resting-state functional MRI toward automated diagnosis of schizophrenia

Junghoe Kim, Jong-Hwan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A functional connectivity (FC) analysis from resting-state functional MRI (rsfMRI) is gaining its popularity toward the clinical application such as diagnosis of neuropsychiatric disease. To delineate the brain networks from rsfMRI data, non-neuronal components including head motions and physiological artifacts mainly observed in cerebrospinal fluid (CSF), white matter (WM) along with a global brain signal have been regarded as nuisance variables in calculating the FC level. However, it is still unclear how the non-neuronal components can affect the performance toward diagnosis of neuropsychiatric disease. In this study, a systematic comparison of classification performance of schizophrenia patients was provided employing the partial correlation coefficients (CCs) as feature elements. Pair-wise partial CCs were calculated between brain regions, in which six combinatorial sets of nuisance variables were considered. The partial CCs were used as candidate feature elements followed by feature selection based on the statistical significance test between two groups in the training set. Once a linear support vector machine was trained using the selected features from the training set, the classification performance was evaluated using the features from the test set (i.e. leaveone- out cross validation scheme). From the results, the error rate using all non-neuronal components as nuisance variables (12.4%) was significantly lower than those using remaining combination of non-neuronal components as nuisance variables (13.8 ~ 20.0%). In conclusion, the non-neuronal components substantially degraded the automated diagnosis performance, which supports our hypothesis that the non-neuronal components are crucial in controlling the automated diagnosis performance of the neuropsychiatric disease using an fMRI modality.

Original languageEnglish
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
PublisherSPIE
Volume9038
ISBN (Print)9780819498311
DOIs
Publication statusPublished - 2014 Jan 1
EventMedical Imaging 2014: Biomedical Applications in Molecular, Structural, and Functional Imaging - San Diego, CA, United States
Duration: 2014 Feb 162014 Feb 18

Other

OtherMedical Imaging 2014: Biomedical Applications in Molecular, Structural, and Functional Imaging
CountryUnited States
CitySan Diego, CA
Period14/2/1614/2/18

Fingerprint

schizophrenia
functional analysis
Functional analysis
Schizophrenia
Magnetic Resonance Imaging
Brain
correlation coefficients
brain
Cerebrospinal fluid
Statistical tests
education
Artifacts
cerebrospinal fluid
Support vector machines
Cerebrospinal Fluid
Feature extraction
Head
artifacts

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Effects of non-neuronal components for functional connectivity analysis from resting-state functional MRI toward automated diagnosis of schizophrenia. / Kim, Junghoe; Lee, Jong-Hwan.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 9038 SPIE, 2014. 903808.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, J & Lee, J-H 2014, Effects of non-neuronal components for functional connectivity analysis from resting-state functional MRI toward automated diagnosis of schizophrenia. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 9038, 903808, SPIE, Medical Imaging 2014: Biomedical Applications in Molecular, Structural, and Functional Imaging, San Diego, CA, United States, 14/2/16. https://doi.org/10.1117/12.2042980
@inproceedings{6480054595d4466f9a79c4a70332dc95,
title = "Effects of non-neuronal components for functional connectivity analysis from resting-state functional MRI toward automated diagnosis of schizophrenia",
abstract = "A functional connectivity (FC) analysis from resting-state functional MRI (rsfMRI) is gaining its popularity toward the clinical application such as diagnosis of neuropsychiatric disease. To delineate the brain networks from rsfMRI data, non-neuronal components including head motions and physiological artifacts mainly observed in cerebrospinal fluid (CSF), white matter (WM) along with a global brain signal have been regarded as nuisance variables in calculating the FC level. However, it is still unclear how the non-neuronal components can affect the performance toward diagnosis of neuropsychiatric disease. In this study, a systematic comparison of classification performance of schizophrenia patients was provided employing the partial correlation coefficients (CCs) as feature elements. Pair-wise partial CCs were calculated between brain regions, in which six combinatorial sets of nuisance variables were considered. The partial CCs were used as candidate feature elements followed by feature selection based on the statistical significance test between two groups in the training set. Once a linear support vector machine was trained using the selected features from the training set, the classification performance was evaluated using the features from the test set (i.e. leaveone- out cross validation scheme). From the results, the error rate using all non-neuronal components as nuisance variables (12.4{\%}) was significantly lower than those using remaining combination of non-neuronal components as nuisance variables (13.8 ~ 20.0{\%}). In conclusion, the non-neuronal components substantially degraded the automated diagnosis performance, which supports our hypothesis that the non-neuronal components are crucial in controlling the automated diagnosis performance of the neuropsychiatric disease using an fMRI modality.",
keywords = "Diagnosis, Functional connectivity, Partial correlation coefficients, Resting state fMRI, Schizophrenia",
author = "Junghoe Kim and Jong-Hwan Lee",
year = "2014",
month = "1",
day = "1",
doi = "10.1117/12.2042980",
language = "English",
isbn = "9780819498311",
volume = "9038",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",

}

TY - GEN

T1 - Effects of non-neuronal components for functional connectivity analysis from resting-state functional MRI toward automated diagnosis of schizophrenia

AU - Kim, Junghoe

AU - Lee, Jong-Hwan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - A functional connectivity (FC) analysis from resting-state functional MRI (rsfMRI) is gaining its popularity toward the clinical application such as diagnosis of neuropsychiatric disease. To delineate the brain networks from rsfMRI data, non-neuronal components including head motions and physiological artifacts mainly observed in cerebrospinal fluid (CSF), white matter (WM) along with a global brain signal have been regarded as nuisance variables in calculating the FC level. However, it is still unclear how the non-neuronal components can affect the performance toward diagnosis of neuropsychiatric disease. In this study, a systematic comparison of classification performance of schizophrenia patients was provided employing the partial correlation coefficients (CCs) as feature elements. Pair-wise partial CCs were calculated between brain regions, in which six combinatorial sets of nuisance variables were considered. The partial CCs were used as candidate feature elements followed by feature selection based on the statistical significance test between two groups in the training set. Once a linear support vector machine was trained using the selected features from the training set, the classification performance was evaluated using the features from the test set (i.e. leaveone- out cross validation scheme). From the results, the error rate using all non-neuronal components as nuisance variables (12.4%) was significantly lower than those using remaining combination of non-neuronal components as nuisance variables (13.8 ~ 20.0%). In conclusion, the non-neuronal components substantially degraded the automated diagnosis performance, which supports our hypothesis that the non-neuronal components are crucial in controlling the automated diagnosis performance of the neuropsychiatric disease using an fMRI modality.

AB - A functional connectivity (FC) analysis from resting-state functional MRI (rsfMRI) is gaining its popularity toward the clinical application such as diagnosis of neuropsychiatric disease. To delineate the brain networks from rsfMRI data, non-neuronal components including head motions and physiological artifacts mainly observed in cerebrospinal fluid (CSF), white matter (WM) along with a global brain signal have been regarded as nuisance variables in calculating the FC level. However, it is still unclear how the non-neuronal components can affect the performance toward diagnosis of neuropsychiatric disease. In this study, a systematic comparison of classification performance of schizophrenia patients was provided employing the partial correlation coefficients (CCs) as feature elements. Pair-wise partial CCs were calculated between brain regions, in which six combinatorial sets of nuisance variables were considered. The partial CCs were used as candidate feature elements followed by feature selection based on the statistical significance test between two groups in the training set. Once a linear support vector machine was trained using the selected features from the training set, the classification performance was evaluated using the features from the test set (i.e. leaveone- out cross validation scheme). From the results, the error rate using all non-neuronal components as nuisance variables (12.4%) was significantly lower than those using remaining combination of non-neuronal components as nuisance variables (13.8 ~ 20.0%). In conclusion, the non-neuronal components substantially degraded the automated diagnosis performance, which supports our hypothesis that the non-neuronal components are crucial in controlling the automated diagnosis performance of the neuropsychiatric disease using an fMRI modality.

KW - Diagnosis

KW - Functional connectivity

KW - Partial correlation coefficients

KW - Resting state fMRI

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=84901791949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901791949&partnerID=8YFLogxK

U2 - 10.1117/12.2042980

DO - 10.1117/12.2042980

M3 - Conference contribution

AN - SCOPUS:84901791949

SN - 9780819498311

VL - 9038

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

ER -