File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Distinguishing Adolescents With Conduct Disorder From Typically Developing Youngsters Based on Pattern Classification of Brain Structural MRI

TitleDistinguishing Adolescents With Conduct Disorder From Typically Developing Youngsters Based on Pattern Classification of Brain Structural MRI
Authors
KeywordsClassification
Conduct disorder
Structural MRI
Support vector machine
Voxel-based morphometry
Issue Date2018
PublisherFrontiers Research Foundation. The Journal's web site is located at http://www.frontiersin.org/humanneuroscience/
Citation
Frontiers in Human Neuroscience, 2018, v. 12, p. 152:1-152:9 How to Cite?
AbstractBackground: Conduct disorder (CD) is a mental disorder diagnosed in childhood or adolescence that presents antisocial behaviors, and is associated with structural alterations in brain. However, whether these structural alterations can distinguish CD from healthy controls (HCs) remains unknown. Here, we quantified these structural differences and explored the classification ability of these quantitative features based on machine learning (ML). Materials and Methods: High-resolution 3D structural magnetic resonance imaging (sMRI) was acquired from 60 CD subjects and 60 age-matched HCs. Voxel-based morphometry (VBM) was used to assess the regional gray matter (GM) volume difference. The significantly different regional GM volumes were then extracted as features, and input into three ML classifiers: logistic regression, random forest and support vector machine (SVM). We trained and tested these ML models for classifying CD from HCs by using fivefold cross-validation (CV). Results: Eight brain regions with abnormal GM volumes were detected, which mainly distributed in the frontal lobe, parietal lobe, anterior cingulate, cerebellum posterior lobe, lingual gyrus, and insula areas. We found that these ML models achieved comparable classification performance, with accuracy of 77.9 ∼ 80.4%, specificity of 73.3 ∼ 80.4%, sensitivity of 75.4 ∼ 87.5%, and area under the receiver operating characteristic curve (AUC) of 0.76 ∼ 0.80.
Persistent Identifierhttp://hdl.handle.net/10722/259651
ISSN
2023 Impact Factor: 2.4
2023 SCImago Journal Rankings: 0.787
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, J-
dc.contributor.authorLiu, W-
dc.contributor.authorZhang, J-
dc.contributor.authorWu, Q-
dc.contributor.authorGao, Y-
dc.contributor.authorJiang, Y-
dc.contributor.authorGao, J-
dc.contributor.authorYao, S-
dc.contributor.authorHuang, B-
dc.date.accessioned2018-09-03T04:11:30Z-
dc.date.available2018-09-03T04:11:30Z-
dc.date.issued2018-
dc.identifier.citationFrontiers in Human Neuroscience, 2018, v. 12, p. 152:1-152:9-
dc.identifier.issn1662-5161-
dc.identifier.urihttp://hdl.handle.net/10722/259651-
dc.description.abstractBackground: Conduct disorder (CD) is a mental disorder diagnosed in childhood or adolescence that presents antisocial behaviors, and is associated with structural alterations in brain. However, whether these structural alterations can distinguish CD from healthy controls (HCs) remains unknown. Here, we quantified these structural differences and explored the classification ability of these quantitative features based on machine learning (ML). Materials and Methods: High-resolution 3D structural magnetic resonance imaging (sMRI) was acquired from 60 CD subjects and 60 age-matched HCs. Voxel-based morphometry (VBM) was used to assess the regional gray matter (GM) volume difference. The significantly different regional GM volumes were then extracted as features, and input into three ML classifiers: logistic regression, random forest and support vector machine (SVM). We trained and tested these ML models for classifying CD from HCs by using fivefold cross-validation (CV). Results: Eight brain regions with abnormal GM volumes were detected, which mainly distributed in the frontal lobe, parietal lobe, anterior cingulate, cerebellum posterior lobe, lingual gyrus, and insula areas. We found that these ML models achieved comparable classification performance, with accuracy of 77.9 ∼ 80.4%, specificity of 73.3 ∼ 80.4%, sensitivity of 75.4 ∼ 87.5%, and area under the receiver operating characteristic curve (AUC) of 0.76 ∼ 0.80.-
dc.languageeng-
dc.publisherFrontiers Research Foundation. The Journal's web site is located at http://www.frontiersin.org/humanneuroscience/-
dc.relation.ispartofFrontiers in Human Neuroscience-
dc.rightsThis Document is Protected by copyright and was first published by Frontiers. All rights reserved. It is reproduced with permission.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectClassification-
dc.subjectConduct disorder-
dc.subjectStructural MRI-
dc.subjectSupport vector machine-
dc.subjectVoxel-based morphometry-
dc.titleDistinguishing Adolescents With Conduct Disorder From Typically Developing Youngsters Based on Pattern Classification of Brain Structural MRI-
dc.typeArticle-
dc.identifier.emailGao, J: galeng@hku.hk-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.3389/fnhum.2018.00152-
dc.identifier.pmcidPMC5925967-
dc.identifier.scopuseid_2-s2.0-85046888973-
dc.identifier.hkuros287829-
dc.identifier.volume12-
dc.identifier.spage152:1-
dc.identifier.epage152:9-
dc.identifier.isiWOS:000430586100001-
dc.publisher.placeSwitzerland-
dc.identifier.issnl1662-5161-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats