Please use this identifier to cite or link to this item: https://doi.org/10.1371/journal.pone.0117295
Title: MRI-based intelligence quotient (IQ) estimation with sparse learning
Authors: Wang L.
Wee C.-Y. 
Suk H.-I.
Tang X.
Shen D.
Keywords: adolescent
age
amygdaloid nucleus
analytic method
angular gyrus
anterior cingulate
Article
brain region
caudate nucleus
child
conceptual framework
controlled study
data analysis
dirty model method
elastic net method
feature selection method
female
group lasso method
hippocampus
human
image analysis
inferior frontal gyrus
inferior parietal lobule
intelligence quotient
intermethod comparison
lingual gyrus
male
multi kernel support vector regression
nuclear magnetic resonance imaging
paracentral lobule
parahippocampal gyrus
single kernel support vector regression
superior parietal lobule
support vector machine
temporal gyrus
thalamus
validation study
algorithm
clinical trial
image processing
intelligence
intelligence test
learning
multicenter study
procedures
reproducibility
theoretical model
Adolescent
Algorithms
Child
Female
Humans
Image Processing, Computer-Assisted
Intelligence
Intelligence Tests
Learning
Magnetic Resonance Imaging
Male
Models, Theoretical
Reproducibility of Results
Issue Date: 2015
Citation: Wang 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
Abstract: In 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.
Source Title: PLoS ONE
URI: https://scholarbank.nus.edu.sg/handle/10635/161736
ISSN: 19326203
DOI: 10.1371/journal.pone.0117295
Appears in Collections:Elements
Staff Publications

Show full 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


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.