Uddin LQ, Menon V, Young CB, Ryali S, Chen T, Khouzam A et al. Multivariate searchlight classification of structural magnetic resonance imaging in children and adolescents with autism. Biol Psychiatry 70: 833-841

Department of Psychiatry, Western Psychiatric Institute and Clinic, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA.
Biological psychiatry (Impact Factor: 10.26). 09/2011; 70(9):833-41. DOI: 10.1016/j.biopsych.2011.07.014
Source: PubMed


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.
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.
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 lobes-regions 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.
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.

Download full-text


Available from: Lucina Q Uddin,
  • Source
    • "These studies can be broadly categorized into two groups based on the data used: 1) data matched for demographics and behavioral (DB) measures such as age, sex and IQs [2]–[5] and 2) large heterogeneous data [6], [7]. The following classification methods and accuracies have been reported by the first group of studies: Support Vector Machine (SVM) on gray matter scans (81%) [2], Logistic Model Trees (LMT) on regional cortical thickness (87%) [3], SVM on gray matter in default mode network regions (90%) [4], and SVM on regional and inter-regional cortical and subcortical features (96%) [5]. The second group of studies uses the large heterogeneous ABIDE dataset and reports classification accuracies less than 60% [6], [7]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Diagnosis of Autism Spectrum Disorder (ASD) using structural magnetic resonance imaging (sMRI) of the brain has been a topic of significant research interest. Previous studies using small datasets with well-matched Typically Developing Controls (TDC) report high classification accuracies (80-96%) but studies using the large heterogeneous ABIDE dataset report accuracies less than 60%. In this study we investigate the predictive power of sMRI in ASD using 373 ASD and 361 TDC male subjects from the ABIDE. Brain morphometric features were derived using FreeSurfer and classification was performed using three different techniques: Random Forest (RF), Support Vector Machine (SVM) and Gradient Boosting Machine (GBM). Although high classification accuracies were possible in individual sites (with a maximum of 97% in Caltech), the highest classification accuracy across all sites was only 60% (sensitivity = 57%, specificity = 64%). However, the accuracy across all sites improved to 67% when IQ and age information were added to morphometric features. Across all three classifiers, volume and surface area had more discriminative power. In general, important features for classification were present in the frontal and temporal regions and these regions have been implicated in ASD. This study also explores the effect of demographics and behavioral measures on the predictive power of sMRI. Results show that classification accuracy increases with autism severity and that ASD detection with sMRI is easier before the age of 10 years.
    Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE; 08/2015
  • Source
    • "We used the calibrated severity score rather than raw ADOS scores, which is a superior metric of symptom severity because of its independence from chronological age and verbal IQ (Gotham et al., 2009). Our DMN midline functional connectivity findings converge with prior evidence of altered midline functional connectivity in ASD youth and adults (Cherkassky et al., 2006; Doyle-Thomas et al., 2015; Eilam- Stock et al., 2014; Jung et al., 2014; Monk et al., 2009; Weng et al., 2010), as well as atypical structural findings (Ameis et al., 2013; Cauda et al., 2011; Duerden et al., 2012; Ikuta et al., 2014; Jiao et al., 2010; Oblak et al., 2010, 2011; Rojas et al., 2006; Shukla et al., 2011; Uddin et al., 2011; Waiter et al., 2004) and task-evoked functional connectivity findings (Bolling et al., 2011; Kleinhans et al., 2008; Mason et al., 2008). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Functional pathology of the default mode network is posited to be central to social-cognitive impairment in autism spectrum disorders (ASD). Altered functional connectivity of the default mode network's midline core may be a potential endophenotype for social deficits in ASD. Generalizability from prior studies is limited by inclusion of medicated participants and by methods favoring restricted examination of network function. This study measured resting-state functional connectivity in 22 8–13 year-old non-medicated children with ASD and 22 typically developing controls using seed-based and network segregation functional connectivity methods. Relative to controls the ASD group showed both under- and over-functional connectivity within default mode and non-default mode regions, respectively. ASD symptoms correlated negatively with the connection strength of the default mode midline core—medial prefrontal cortex–posterior cingulate cortex. Network segregation analysis with the participation coefficient showed a higher area under the curve for the ASD group. Our findings demonstrate that the default mode network in ASD shows a pattern of poor segregation with both functional connectivity metrics. This study confirms the potential for the functional connection of the midline core as an endophenotype for social deficits. Poor segregation of the default mode network is consistent with an excitation/inhibition imbalance model of ASD.
    Clinical neuroimaging 08/2015; 9:223-232. DOI:10.1016/j.nicl.2015.07.018 · 2.53 Impact Factor
  • Source
    • "Multivariate classification techniques offer a method for decoding the group identity of ASD and control subjects based on patterns of anatomical features, rather than single anatomical measures. Several recent studies have reported exceptional decoding accuracies (over 85%) of group identity when using measures of cortical thickness, geometry, curvature, and/or surface area in small samples of 20–30 subjects from each group (Ecker, Marquand et al. 2010; Jiao et al. 2010; Uddin et al. 2011). These studies have suggested that distributed anatomical abnormalities can consistently be used to identify adults with ASD. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Substantial controversy exists regarding the presence and significance of anatomical abnormalities in autism spectrum disorders (ASD). The release of the Autism Brain Imaging Data Exchange (∼1000 participants, age 6-65 years) offers an unprecedented opportunity to conduct large-scale comparisons of anatomical MRI scans across groups and to resolve many of the outstanding questions. Comprehensive univariate analyses using volumetric, thickness, and surface area measures of over 180 anatomically defined brain areas, revealed significantly larger ventricular volumes, smaller corpus callosum volume (central segment only), and several cortical areas with increased thickness in the ASD group. Previously reported anatomical abnormalities in ASD including larger intracranial volumes, smaller cerebellar volumes, and larger amygdala volumes were not substantiated by the current study. In addition, multivariate classification analyses yielded modest decoding accuracies of individuals' group identity (<60%), suggesting that the examined anatomical measures are of limited diagnostic utility for ASD. While anatomical abnormalities may be present in distinct subgroups of ASD individuals, the current findings show that many previously reported anatomical measures are likely to be of low clinical and scientific significance for understanding ASD neuropathology as a whole in individuals 6-35 years old.
    Cerebral Cortex 10/2014; DOI:10.1093/cercor/bhu242 · 8.67 Impact Factor
Show more