Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 59 of the 59 references it cites were found in a registry or an index.

Multiparametric MRI Characterization and Prediction in Autism Spectrum Disorder Using Graph Theory and Machine Learning

Open access
Zhou, Yongxia, Yu, Fang, Duong, Timothy · 2014 · PLoS ONE

Abstract

This study employed graph theory and machine learning analysis of multiparametric MRI data to improve characterization and prediction in autism spectrum disorders (ASD). Data from 127 children with ASD (13.5±6.0 years) and 153 age- and gender-matched typically developing children (14.5±5.7 years) were selected from the multi-center Functional Connectome Project. Regional gray matter volume and cortical thickness increased, whereas white matter volume decreased in ASD compared to controls. Small-world network analysis of quantitative MRI data demonstrated decreased global efficiency based on gray matter cortical thickness but not with functional connectivity MRI (fcMRI) or volumetry. An integrative model of 22 quantitative imaging features was used for classification and prediction of phenotypic features that included the autism diagnostic observation schedule, the revised autism diagnostic interview, and intelligence quotient scores. Among the 22 imaging features, four (caudate volume, caudate-cortical functional connectivity and inferior frontal gyrus functional connectivity) were found to be highly informative, markedly improving classification and prediction accuracy when compared with the single imaging features. This approach could potentially serve as a biomarker in prognosis, diagnosis, and monitoring disease progression.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0090405

Cites

59 of 59 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Regions with significant volume percentage increment (A, red color) in gray matter, and volume decrement in gray matter (A, blue color) as well as white matter volume reduction (B, blue color) in autism compared to controls (P<0.01). Significant cortical thickness increment in percentage change in autism compared to controls is shown in C with red color (P<0.01). Both medial and lateral views on sagittal surface in the left and right hemispheres of an individual control subject are shown for gray matter volume (A), white matter volume (B) and cortical thickness (C) comparison between autistic children and controls. The percentage change of volume in autism was calculated as the mean difference between volumes of two groups normalized with individual supratentorial volume and scaled by the mean normalized volume of control group.
Figure 1 Regions with significant volume percentage increment (A, red color) in gray matter, and volume decrement in gray matter (A, blue color) as well as white matter volume reduction (B, blue color) in autism compared to controls (P<0.01). Significant cortical thickness increment in percentage change in autism compared to controls is shown in C with red color (P<0.01). Both medial and lateral views on sagittal surface in the left and right hemispheres of an individual control subject are shown for gray matter volume (A), white matter volume (B) and cortical thickness (C) comparison between autistic children and controls. The percentage change of volume in autism was calculated as the mean difference between volumes of two groups normalized with individual supratentorial volume and scaled by the mean normalized volume of control group.CC BY · PubMed Central
Figure 2 The functional connectivity network seeding from caudate and IFG region are demonstrated. In controls, the caudate-cortical network showed positive connections with the frontal and subcortical regions, and negative connections with the posterior visual and parietal areas (A1). The caudate-cortical network in children with ASD showed a primary reduction of cingulum and middle temporal connectivity (red color), but increased connectivity in several regions including the inferior and dorso-latero frontal areas (blue color, A2-A3). The functional connectivity network seeding from the IFG pars trianglaris in controls (B1) showed positive connections with the frontal and temporal regions and negative connections with the posterior visual and superior parietal areas. Difference of connectivity pattern comparing autism to controls seeded from pars trianglaris are shown in B2 and B3, with some reductions of visual and temporal connectivity in autism (red) and increments in the regions including medial temporal areas (blue). Functional connectivity seeding from IFG pars opercularis is shown in C1–C3, with primarily decreased connectivity in autism in the superior frontal regions. Seed regions are shown in the upper left images, and all statistical results were obtained with the threshold of minimal Z>2.3; cluster significance, P<0.05, corrected.
Figure 2 The functional connectivity network seeding from caudate and IFG region are demonstrated. In controls, the caudate-cortical network showed positive connections with the frontal and subcortical regions, and negative connections with the posterior visual and parietal areas (A1). The caudate-cortical network in children with ASD showed a primary reduction of cingulum and middle temporal connectivity (red color), but increased connectivity in several regions including the inferior and dorso-latero frontal areas (blue color, A2-A3). The functional connectivity network seeding from the IFG pars trianglaris in controls (B1) showed positive connections with the frontal and temporal regions and negative connections with the posterior visual and superior parietal areas. Difference of connectivity pattern comparing autism to controls seeded from pars trianglaris are shown in B2 and B3, with some reductions of visual and temporal connectivity in autism (red) and increments in the regions including medial temporal areas (blue). Functional connectivity seeding from IFG pars opercularis is shown in C1–C3, with primarily decreased connectivity in autism in the superior frontal regions. Seed regions are shown in the upper left images, and all statistical results were obtained with the threshold of minimal Z>2.3; cluster significance, P<0.05, corrected.CC BY · PubMed Central
Figure 3 A: Small-world network analysis based on fMRI data showed similar efficiency (including both local and global) between children with ASD and TD controls. Small-worldness analysis based on regional volume (red and blue colors) showed no significant differences of total efficiency (B) and global efficiency (C) between children with ASD and controls neither. However, small-worldness analysis based on structural cortical thickness measure showed reduced total efficiency (B), specifically decreased global efficiency (i.e. shortest path length) (C) in ASD group (magenta color) compared to TD group (cyan color). Error bar denotes standard deviation at each sparsity level after scaling to a random network with the same number of degree.
Figure 3 A: Small-world network analysis based on fMRI data showed similar efficiency (including both local and global) between children with ASD and TD controls. Small-worldness analysis based on regional volume (red and blue colors) showed no significant differences of total efficiency (B) and global efficiency (C) between children with ASD and controls neither. However, small-worldness analysis based on structural cortical thickness measure showed reduced total efficiency (B), specifically decreased global efficiency (i.e. shortest path length) (C) in ASD group (magenta color) compared to TD group (cyan color). Error bar denotes standard deviation at each sparsity level after scaling to a random network with the same number of degree.CC BY · PubMed Central
Figure 4 A: Co-variance matrix of 22 quantitative imaging features showed highly-correlated structural metrics (i.e. volumetry) of 9 regions, and strong association between average Z-value and voxel number N-value of fcMRI for each region (or global metric). B: principal component analysis decomposition of the covariance matrix showing most (>95%) data variation (information) was contained with 4 primary components (pink color) and 99% data information was contained in 6 primary components (red color). C: The four imaging features selected via mRMR criteria were right caudate volume (1), the fcMRI average Z values seeded from bilateral caudate (2), bilateral IFG pars opercularis (3) and IFG pars triangularis (4). Together with the four imaging features selected, the DMN average Z (5) and the VMHC average Z (6) were the other two imaging features selected for 99% criteria.
Figure 4 A: Co-variance matrix of 22 quantitative imaging features showed highly-correlated structural metrics (i.e. volumetry) of 9 regions, and strong association between average Z-value and voxel number N-value of fcMRI for each region (or global metric). B: principal component analysis decomposition of the covariance matrix showing most (>95%) data variation (information) was contained with 4 primary components (pink color) and 99% data information was contained in 6 primary components (red color). C: The four imaging features selected via mRMR criteria were right caudate volume (1), the fcMRI average Z values seeded from bilateral caudate (2), bilateral IFG pars opercularis (3) and IFG pars triangularis (4). Together with the four imaging features selected, the DMN average Z (5) and the VMHC average Z (6) were the other two imaging features selected for 99% criteria.CC BY · PubMed Central
Figure 5 Margin curves showing the cumulative probability of difference between true positive (sensitivity) and false positive (1-specificity) as a function of instance number (i.e. subject number) for 4-feature classification (A) and 6-feature classification (B) based on full dataset. As expected, the 6-feature classifier performed slightly better than 4-feature classifier with faster convergence and more margins maintained.
Figure 5 Margin curves showing the cumulative probability of difference between true positive (sensitivity) and false positive (1-specificity) as a function of instance number (i.e. subject number) for 4-feature classification (A) and 6-feature classification (B) based on full dataset. As expected, the 6-feature classifier performed slightly better than 4-feature classifier with faster convergence and more margins maintained.CC BY · PubMed Central
Figure 6 Kstar, an instance (similarity) based classifier for regression analysis had the greatest prediction power for ADOS module score for ASD children among all the regressors combining 4 selected imaging features. A1–A4: standardized histogram distribution showing x-axis as the z-scores of each feature and y-axis being the frequency. A1-right caudate volume, A2-average Z of caudate fcMRI, A3-average Z of IFG opercularis fcMRI, A4-average Z of IFG triangularis fcMRI. A5: phenotypic ADOS module score histogram distribution with x-axis as the original score and y-axis being the frequency. B: The correlation coefficient between integrated imaging features and ADOS module score improved largely from −0.64 based on single best imaging feature to 0.95 combining 4 imaging features. The fitted score using Kstar classifier with 4 selected imaging features showed a tight coupling (linear slope = 1; r = 0.95, P<0.0001) with the original ADOS module score with only a few outliers.
Figure 6 Kstar, an instance (similarity) based classifier for regression analysis had the greatest prediction power for ADOS module score for ASD children among all the regressors combining 4 selected imaging features. A1–A4: standardized histogram distribution showing x-axis as the z-scores of each feature and y-axis being the frequency. A1-right caudate volume, A2-average Z of caudate fcMRI, A3-average Z of IFG opercularis fcMRI, A4-average Z of IFG triangularis fcMRI. A5: phenotypic ADOS module score histogram distribution with x-axis as the original score and y-axis being the frequency. B: The correlation coefficient between integrated imaging features and ADOS module score improved largely from −0.64 based on single best imaging feature to 0.95 combining 4 imaging features. The fitted score using Kstar classifier with 4 selected imaging features showed a tight coupling (linear slope = 1; r = 0.95, P<0.0001) with the original ADOS module score with only a few outliers.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 59 references

Research works printed but not linked: 1

  1. MA Elliott, 1999, Spectral quantitation by principal component analysis using complex singular value decomposition, Magn Reson Med, 41, 450, 10.1002/(SICI)1522-2594(199903)41:3<450::AID-MRM4>3.0.CO;2-9 · doi:10.1002/(sici)1522-2594(199903)41:3<450::aid-mrm4>3.0.co;2-9

Cited by

See all 105

Metadata

Authors
Zhou, Y., Yu, F., & Duong, T.
Affiliations
  • University of Pennsylvania (US)
  • The University of Texas at San Antonio Health Science Center (US)
Corresponding author
Duong, Timothy
Venue
PLoS ONE
Published
2014-06-12
Volume
9
Issue
6
Pages
e90405
ISSN
1932-6203 (ISSN-L)
OpenAlex
W2051306708
Cited by
105
References
59
Citations by year
2025: 7 · 2024: 6 · 2023: 3 · 2022: 18 · 2021: 21 · 2020: 8 · 2019: 8 · 2018: 9 · 2017: 3 · 2016: 9 · 2015: 11 · 2014: 2
FWCI
4.65
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Institute of Neurological Disorders and Stroke (R01NS039135)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Autism Spectrum Disorder Research
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetics and Neurodevelopmental Disorders
Keywords
autism spectrum disorder, multiparametric MRI, graph theory, global efficiency, cortical thickness, gray matter volume, white matter volume, caudate volume, functional connectivity MRI, biomarkers, children
MeSH terms
Adolescent, Artificial Intelligence, Child, Child Development Disorders, Pervasive, Female, Humans, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Male, Case-Control Studies, Connectome

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Multiparametric MRI Characterization and Prediction in Autism Spectrum Disorder Using Graph Theory and Machine Learning. https://app.cochat.ai/papers/10.1371/journal.pone.0090405
The paper
Zhou, Y., Yu, F., & Duong, T. (2014). Multiparametric MRI Characterization and Prediction in Autism Spectrum Disorder Using Graph Theory and Machine Learning. PLoS ONE. https://doi.org/10.1371/journal.pone.0090405

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.