International Meeting for Autism Research (May 7 - 9, 2009): Automatic Classification of Structural MR Scans Using Support Vector Machine: a Diagnostic Tool for Adult Autism?

Automatic Classification of Structural MR Scans Using Support Vector Machine: a Diagnostic Tool for Adult Autism?

Thursday, May 7, 2009
Northwest Hall (Chicago Hilton)
11:00 AM
C. Ecker , Psychological Medicine and Psychiatry, Section of Brain Maturation, King's College London, Institute of Psychiatry, London, United Kingdom
V. Rocha-Rego , Institute of Biophysics Carlos Chagas Filho, University of Rio de Janeiro, Rio de Janeiro, Brazil
P. Johnston , Psychological Medicine and Psychiatry, Section of Brain Maturation, King's College London, Institute of Psychiatry, London, United Kingdom
J. Mourao-Miranda , Brain Image Analysis Unit, Centre for Neuroimaging Sciences, London, United Kingdom
A. Marquand , Brain Image Analysis Unit, Centre for Neuroimaging Sciences, London, United Kingdom
E. Daly , Section of Brain Maturation, Department of Psychological Medicine and Psychiatry, Institute of Psychiatry, King's College London, London, United Kingdom
C. Murphy , Psychological Medicine and Psychiatry, Section of Brain Maturation, King's College London, Institute of Psychiatry, London, United Kingdom
D. G. Murphy , Section of Brain Maturation, Department of Psychological Medicine and Psychiatry, Institute of Psychiatry, King's College London, London, United Kingdom
M. R. C. AIMS Consortium , University of Oxford, University of Cambridge, Institute of Psychiatry, London, United Kingdom
Background: Autistic spectrum disorder (ASD) is a highly genetic neurodevelopmental disorder, which is characterized by impairments in social communication, social reciprocity, and repetitive behaviour. Although autism is accompanied by significant differences in brain anatomy, it continues to be diagnosed on the basis of behavioural criteria. Additional biologically based methods may, however, aid the diagnosis; but this has not previously been tested.

Objectives: The aims of this study was to investigate the diagnostic value of grey matter anatomical images in adults with ASD.

Methods: Support Vector Machine algorithms (SVM) were used to automatically classify structrual MRI scan in a sample of 54 male adults; 27 with a diagnosis of ASD made using gold standard research interviews and 27 healthy matched controls. The performance of the classification was evaluated using the leave-two-out cross validation approach. To identify the degree to which the classification is driven by autistic symptoms, the test marging was correlated the level of symptom severity.

Results: SVM correctly classified individuals with autism based on their grey matter anatomy with 67% specificity and sensitivity. The test margin (i.e. distance from separating hyperplane) was positively correlated with the level of symptom severity as measured by the Autism Spectrum Quotient (AQ) and Autism Diagnostic Observation Schedule (ADOS) The most discriminating regions between groups were the (1) the limbic system, (2) the fronto-striatal system, and (3) fronto-temporal and fronto-parietal networks. In addition, we found increased regional volumes in components of the cerebellar circuitry.

Conclusions: The brain regions identified by SVM are in agreement with many previous studies employing voxel-based analyses, and have been functionally linked to autistic core symptoms in the past. In addition we have shown that the classification was driven by autistic symptoms rather than autism-unrelated effects. Therefore we propose that the application of SVM on grey matter anatomical scans might provide a valid neuropathological screening tool for ASD to guide and complement a traditional behaviourally guided diagnosis in the future.

See more of: Poster I
See more of: Poster Presentations