TY - JOUR
T1 - Multivariate searchlight classification of structural magnetic resonance imaging in children and adolescents with autism
AU - Uddin, Lucina Q.
AU - Menon, Vinod
AU - Young, Christina B.
AU - Ryali, Srikanth
AU - Chen, Tianwen
AU - Khouzam, Amirah
AU - Minshew, Nancy J.
AU - Hardan, Antonio Y.
N1 - Funding Information:
Dr. Hardan has received grants from Bristol-Myers Squibb . He also has received honoraria for speaking fees from Forest, Pfizer, and AstraZeneca. The other authors reported no biomedical financial interests or potential conflicts of interest.
Funding Information:
This work was supported by grants from the Singer Foundation , Stanford Institute for Neuro-Innovation & Translational Neurosciences , National Institute of Child Health & Human Development (Grant Nos. HD047520 and HD059205 ), National Institute of Deafness & Other Communication Disorders (Grant No. DC0111095 ), National Institute of Mental Health (Grant No. MH084164 ), and National Science Foundation (Grant No. BCS/DRL 0750340 ) to VM; a Mosbacher Postdoctoral Fellowship and National Institute of Mental Health (Grant No. K01MH092288 ) to LQU; National Institute of Mental Health (Grant No. MH64027 ) to AH; and National Institute of Child Health & Human Development (Grant Nos. HD 35469 and HD055748 ), and National Institute of Neurological Disorders and Stroke (Grant No. NS33355 ) to NM.
PY - 2011/11/1
Y1 - 2011/11/1
N2 - Background: Autism spectrum disorders (ASD) are neurodevelopmental disorders with a prevalence of nearly 1:100. Structural imaging studies point to disruptions in multiple brain areas, yet the precise neuroanatomical nature of these disruptions remains unclear. Characterization of brain structural differences in children with ASD is critical for development of biomarkers that may eventually be used to improve diagnosis and monitor response to treatment. Methods: We use voxel-based morphometry along with a novel multivariate pattern analysis approach and searchlight algorithm to classify structural magnetic resonance imaging data acquired from 24 children and adolescents with autism and 24 age-, gender-, and IQ-matched neurotypical participants. Results: Despite modest voxel-based morphometry differences, multivariate pattern analysis revealed that the groups could be distinguished with accuracies of approximately 90% based on gray matter in the posterior cingulate cortex, medial prefrontal cortex, and bilateral medial temporal lobesregions within the default mode network. Abnormalities in the posterior cingulate cortex were associated with impaired Autism Diagnostic Interview communication scores. Gray matter in additional prefrontal, lateral temporal, and subcortical structures also discriminated between groups with accuracies between 81% and 90%. White matter in the inferior fronto-occipital and superior longitudinal fasciculi, and the genu and splenium of the corpus callosum, achieved up to 85% classification accuracy. Conclusions: Multiple brain regions, including those belonging to the default mode network, exhibit aberrant structural organization in children with autism. Brain-based biomarkers derived from structural magnetic resonance imaging data may contribute to identification of the neuroanatomical basis of symptom heterogeneity and to the development of targeted early interventions.
AB - Background: Autism spectrum disorders (ASD) are neurodevelopmental disorders with a prevalence of nearly 1:100. Structural imaging studies point to disruptions in multiple brain areas, yet the precise neuroanatomical nature of these disruptions remains unclear. Characterization of brain structural differences in children with ASD is critical for development of biomarkers that may eventually be used to improve diagnosis and monitor response to treatment. Methods: We use voxel-based morphometry along with a novel multivariate pattern analysis approach and searchlight algorithm to classify structural magnetic resonance imaging data acquired from 24 children and adolescents with autism and 24 age-, gender-, and IQ-matched neurotypical participants. Results: Despite modest voxel-based morphometry differences, multivariate pattern analysis revealed that the groups could be distinguished with accuracies of approximately 90% based on gray matter in the posterior cingulate cortex, medial prefrontal cortex, and bilateral medial temporal lobesregions within the default mode network. Abnormalities in the posterior cingulate cortex were associated with impaired Autism Diagnostic Interview communication scores. Gray matter in additional prefrontal, lateral temporal, and subcortical structures also discriminated between groups with accuracies between 81% and 90%. White matter in the inferior fronto-occipital and superior longitudinal fasciculi, and the genu and splenium of the corpus callosum, achieved up to 85% classification accuracy. Conclusions: Multiple brain regions, including those belonging to the default mode network, exhibit aberrant structural organization in children with autism. Brain-based biomarkers derived from structural magnetic resonance imaging data may contribute to identification of the neuroanatomical basis of symptom heterogeneity and to the development of targeted early interventions.
KW - Autism
KW - autism spectrum disorders
KW - biomarker
KW - default mode network
KW - multivariate pattern analysis
KW - support vector machine
KW - voxel-based morphometry
UR - http://www.scopus.com/inward/record.url?scp=80053952154&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80053952154&partnerID=8YFLogxK
U2 - 10.1016/j.biopsych.2011.07.014
DO - 10.1016/j.biopsych.2011.07.014
M3 - Article
C2 - 21890111
AN - SCOPUS:80053952154
VL - 70
SP - 833
EP - 841
JO - Biological Psychiatry
JF - Biological Psychiatry
SN - 0006-3223
IS - 9
ER -