Please use this identifier to cite or link to this item: https://doi.org/10.1371/journal.pone.0117295
DC FieldValue
dc.titleMRI-based intelligence quotient (IQ) estimation with sparse learning
dc.contributor.authorWang L.
dc.contributor.authorWee C.-Y.
dc.contributor.authorSuk H.-I.
dc.contributor.authorTang X.
dc.contributor.authorShen D.
dc.date.accessioned2019-11-07T04:59:48Z
dc.date.available2019-11-07T04:59:48Z
dc.date.issued2015
dc.identifier.citationWang L., Wee C.-Y., Suk H.-I., Tang X., Shen D. (2015). MRI-based intelligence quotient (IQ) estimation with sparse learning. PLoS ONE 10 (3) : e0117295. ScholarBank@NUS Repository. https://doi.org/10.1371/journal.pone.0117295
dc.identifier.issn19326203
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/161736
dc.description.abstractIn this paper, we propose a novel framework for IQ estimation using Magnetic Resonance Imaging (MRI) data. In particular, we devise a new feature selection method based on an extended dirty model for jointly considering both element-wise sparsity and group-wise sparsity. Meanwhile, due to the absence of large dataset with consistent scanning protocols for the IQ estimation, we integrate multiple datasets scanned from different sites with different scanning parameters and protocols. In this way, there is large variability in these different datasets. To address this issue, we design a two-step procedure for 1) first identifying the possible scanning site for each testing subject and 2) then estimating the testing subject's IQ by using a specific estimator designed for that scanning site. We perform two experiments to test the performance of our method by using the MRI data collected from 164 typically developing children between 6 and 15 years old. In the first experiment, we use a multi-kernel Support Vector Regression (SVR) for estimating IQ values, and obtain an average correlation coefficient of 0.718 and also an average root mean square error of 8.695 between the true IQs and the estimated ones. In the second experiment, we use a singlekernel SVR for IQ estimation, and achieve an average correlation coefficient of 0.684 and an average root mean square error of 9.166. All these results show the effectiveness of using imaging data for IQ prediction, which is rarely done in the field according to our knowledge. © 2015, Public Library of Science. All rights reserved.
dc.rightsCC0 1.0 Universal
dc.rights.urihttp://creativecommons.org/publicdomain/zero/1.0/
dc.sourceUnpaywall 20191101
dc.subjectadolescent
dc.subjectage
dc.subjectamygdaloid nucleus
dc.subjectanalytic method
dc.subjectangular gyrus
dc.subjectanterior cingulate
dc.subjectArticle
dc.subjectbrain region
dc.subjectcaudate nucleus
dc.subjectchild
dc.subjectconceptual framework
dc.subjectcontrolled study
dc.subjectdata analysis
dc.subjectdirty model method
dc.subjectelastic net method
dc.subjectfeature selection method
dc.subjectfemale
dc.subjectgroup lasso method
dc.subjecthippocampus
dc.subjecthuman
dc.subjectimage analysis
dc.subjectinferior frontal gyrus
dc.subjectinferior parietal lobule
dc.subjectintelligence quotient
dc.subjectintermethod comparison
dc.subjectlingual gyrus
dc.subjectmale
dc.subjectmulti kernel support vector regression
dc.subjectnuclear magnetic resonance imaging
dc.subjectparacentral lobule
dc.subjectparahippocampal gyrus
dc.subjectsingle kernel support vector regression
dc.subjectsuperior parietal lobule
dc.subjectsupport vector machine
dc.subjecttemporal gyrus
dc.subjectthalamus
dc.subjectvalidation study
dc.subjectalgorithm
dc.subjectclinical trial
dc.subjectimage processing
dc.subjectintelligence
dc.subjectintelligence test
dc.subjectlearning
dc.subjectmulticenter study
dc.subjectprocedures
dc.subjectreproducibility
dc.subjecttheoretical model
dc.subjectAdolescent
dc.subjectAlgorithms
dc.subjectChild
dc.subjectFemale
dc.subjectHumans
dc.subjectImage Processing, Computer-Assisted
dc.subjectIntelligence
dc.subjectIntelligence Tests
dc.subjectLearning
dc.subjectMagnetic Resonance Imaging
dc.subjectMale
dc.subjectModels, Theoretical
dc.subjectReproducibility of Results
dc.typeArticle
dc.contributor.departmentDEPT OF BIOMEDICAL ENGINEERING
dc.description.doi10.1371/journal.pone.0117295
dc.description.sourcetitlePLoS ONE
dc.description.volume10
dc.description.issue3
dc.description.pagee0117295
dc.published.statePublished
Appears in Collections:Elements
Staff Publications

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1371_journal_pone_0117295.pdf2.14 MBAdobe PDF

OPEN

PublishedView/Download

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons