Gray Matter Alterations in Young Children with Autism Spectrum Disorders: Comparing Morphometry at the Voxel and Regional Level

Ilaria Gori, Alessia Giuliano, Filippo Muratori, Irene Saviozzi, Piernicola Oliva, Raffaella Tancredi, Angela Cosenza, Michela Tosetti, Sara Calderoni, Alessandra Retico

Research output: Contribution to journalArticle

Abstract

Sophisticated algorithms to infer disease diagnosis, pathology progression and patient outcome are increasingly being developed to analyze brain MRI data. They have been successfully implemented in a variety of diseases and are currently investigated in the field of neuropsychiatric disorders, including autism spectrum disorder (ASD). We aim to test the ability to predict ASD from subtle morphological changes in structural magnetic resonance imaging (sMRI). The analysis of sMRI of a cohort of male ASD children and controls matched for age and nonverbal intelligence quotient (NVIQ) has been carried out with two widely used preprocessing software packages (SPM and Freesurfer) to extract brain morphometric information at different spatial scales. Then, support vector machines have been implemented to classify the brain features and to localize which brain regions contribute most to the ASD-control separation. RESULTS: The features extracted from the gray matter subregions provide the best classification performance, reaching an area under the receiver operating characteristic curve (AUC) of 74%. This value is enhanced to 80% when considering only subjects with NVIQ over 70. Despite the subtle impact of ASD on brain morphology and a limited cohort size, results from sMRI-based classifiers suggest a consistent network of altered brain regions.

Original languageEnglish
Pages (from-to)866-874
Number of pages9
JournalJournal of Neuroimaging
Volume25
Issue number6
DOIs
Publication statusPublished - Nov 1 2015

Fingerprint

Brain
Magnetic Resonance Imaging
Intelligence
Aptitude
ROC Curve
Area Under Curve
Gray Matter
Autism Spectrum Disorder
Software
Pathology

Keywords

  • Autism spectrum disorders
  • Classification
  • Feature extraction
  • Machine learning
  • Magnetic resonance imaging
  • Support vector machines

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology

Cite this

Gray Matter Alterations in Young Children with Autism Spectrum Disorders : Comparing Morphometry at the Voxel and Regional Level. / Gori, Ilaria; Giuliano, Alessia; Muratori, Filippo; Saviozzi, Irene; Oliva, Piernicola; Tancredi, Raffaella; Cosenza, Angela; Tosetti, Michela; Calderoni, Sara; Retico, Alessandra.

In: Journal of Neuroimaging, Vol. 25, No. 6, 01.11.2015, p. 866-874.

Research output: Contribution to journalArticle

@article{eee751c0c0114ab2a381eea6d028b2e8,
title = "Gray Matter Alterations in Young Children with Autism Spectrum Disorders: Comparing Morphometry at the Voxel and Regional Level",
abstract = "Sophisticated algorithms to infer disease diagnosis, pathology progression and patient outcome are increasingly being developed to analyze brain MRI data. They have been successfully implemented in a variety of diseases and are currently investigated in the field of neuropsychiatric disorders, including autism spectrum disorder (ASD). We aim to test the ability to predict ASD from subtle morphological changes in structural magnetic resonance imaging (sMRI). The analysis of sMRI of a cohort of male ASD children and controls matched for age and nonverbal intelligence quotient (NVIQ) has been carried out with two widely used preprocessing software packages (SPM and Freesurfer) to extract brain morphometric information at different spatial scales. Then, support vector machines have been implemented to classify the brain features and to localize which brain regions contribute most to the ASD-control separation. RESULTS: The features extracted from the gray matter subregions provide the best classification performance, reaching an area under the receiver operating characteristic curve (AUC) of 74{\%}. This value is enhanced to 80{\%} when considering only subjects with NVIQ over 70. Despite the subtle impact of ASD on brain morphology and a limited cohort size, results from sMRI-based classifiers suggest a consistent network of altered brain regions.",
keywords = "Autism spectrum disorders, Classification, Feature extraction, Machine learning, Magnetic resonance imaging, Support vector machines",
author = "Ilaria Gori and Alessia Giuliano and Filippo Muratori and Irene Saviozzi and Piernicola Oliva and Raffaella Tancredi and Angela Cosenza and Michela Tosetti and Sara Calderoni and Alessandra Retico",
year = "2015",
month = "11",
day = "1",
doi = "10.1111/jon.12280",
language = "English",
volume = "25",
pages = "866--874",
journal = "Journal of Neuroimaging",
issn = "1051-2284",
publisher = "Wiley-Blackwell",
number = "6",

}

TY - JOUR

T1 - Gray Matter Alterations in Young Children with Autism Spectrum Disorders

T2 - Comparing Morphometry at the Voxel and Regional Level

AU - Gori, Ilaria

AU - Giuliano, Alessia

AU - Muratori, Filippo

AU - Saviozzi, Irene

AU - Oliva, Piernicola

AU - Tancredi, Raffaella

AU - Cosenza, Angela

AU - Tosetti, Michela

AU - Calderoni, Sara

AU - Retico, Alessandra

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Sophisticated algorithms to infer disease diagnosis, pathology progression and patient outcome are increasingly being developed to analyze brain MRI data. They have been successfully implemented in a variety of diseases and are currently investigated in the field of neuropsychiatric disorders, including autism spectrum disorder (ASD). We aim to test the ability to predict ASD from subtle morphological changes in structural magnetic resonance imaging (sMRI). The analysis of sMRI of a cohort of male ASD children and controls matched for age and nonverbal intelligence quotient (NVIQ) has been carried out with two widely used preprocessing software packages (SPM and Freesurfer) to extract brain morphometric information at different spatial scales. Then, support vector machines have been implemented to classify the brain features and to localize which brain regions contribute most to the ASD-control separation. RESULTS: The features extracted from the gray matter subregions provide the best classification performance, reaching an area under the receiver operating characteristic curve (AUC) of 74%. This value is enhanced to 80% when considering only subjects with NVIQ over 70. Despite the subtle impact of ASD on brain morphology and a limited cohort size, results from sMRI-based classifiers suggest a consistent network of altered brain regions.

AB - Sophisticated algorithms to infer disease diagnosis, pathology progression and patient outcome are increasingly being developed to analyze brain MRI data. They have been successfully implemented in a variety of diseases and are currently investigated in the field of neuropsychiatric disorders, including autism spectrum disorder (ASD). We aim to test the ability to predict ASD from subtle morphological changes in structural magnetic resonance imaging (sMRI). The analysis of sMRI of a cohort of male ASD children and controls matched for age and nonverbal intelligence quotient (NVIQ) has been carried out with two widely used preprocessing software packages (SPM and Freesurfer) to extract brain morphometric information at different spatial scales. Then, support vector machines have been implemented to classify the brain features and to localize which brain regions contribute most to the ASD-control separation. RESULTS: The features extracted from the gray matter subregions provide the best classification performance, reaching an area under the receiver operating characteristic curve (AUC) of 74%. This value is enhanced to 80% when considering only subjects with NVIQ over 70. Despite the subtle impact of ASD on brain morphology and a limited cohort size, results from sMRI-based classifiers suggest a consistent network of altered brain regions.

KW - Autism spectrum disorders

KW - Classification

KW - Feature extraction

KW - Machine learning

KW - Magnetic resonance imaging

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84944512339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944512339&partnerID=8YFLogxK

U2 - 10.1111/jon.12280

DO - 10.1111/jon.12280

M3 - Article

AN - SCOPUS:84944512339

VL - 25

SP - 866

EP - 874

JO - Journal of Neuroimaging

JF - Journal of Neuroimaging

SN - 1051-2284

IS - 6

ER -