Multidimensional Neuroanatomical Subtyping of Autism Spectrum Disorder

• Published in: Cerebral cortex (New York, N.Y. 1991) Vol. 28; no. 10; pp. 3578 - 3588
• Main Authors: Hong, Seok-Jun, Valk, Sofie L, Di Martino, Adriana, Milham, Michael P, Bernhardt, Boris C
• Format: Journal Article
• Language: English
• Published: United States Oxford University Press 01.10.2018
• Subjects: Adolescent; Artificial Intelligence; Autism Spectrum Disorder - classification; Autism Spectrum Disorder - diagnostic imaging; Autism Spectrum Disorder - psychology; Cerebral Cortex - diagnostic imaging; Cohort Studies; Female; Humans; Magnetic Resonance Imaging; Male; Nerve Net - diagnostic imaging; Neuropsychological Tests; Original; Predictive Value of Tests; Social Perception; Young Adult; biotype; computational neuroanatomy; magnetic resonance imaging; biomarker; subtype; autism
• ISSN: 1047-3211; 1460-2199; 1460-2199
• DOI: 10.1093/cercor/bhx229

Abstract Autism spectrum disorder (ASD) is a group of neurodevelopmental disorders with multiple biological etiologies and highly variable symptoms. Using a novel analytical framework that integrates cortex-wide MRI markers of vertical (i.e., thickness, tissue contrast) and horizontal (i.e., surface area, geodesic distance) cortical organization, we could show that a large multi-centric cohort of individuals with ASD falls into 3 distinctive anatomical subtypes (ASD-I: cortical thickening, increased surface area, tissue blurring; ASD-II: cortical thinning, decreased distance; ASD-III: increased distance). Bootstrap analysis indicated a high consistency of these biotypes across thousands of simulations, while analysis of behavioral phenotypes and resting-state fMRI showed differential symptom load (i.e., Autism Diagnostic Observation Schedule; ADOS) and instrinsic connectivity anomalies in communication and social-cognition networks. Notably, subtyping improved supervised learning approaches predicting ADOS score in single subjects, with significantly increased performance compared to a subtype-blind approach. The existence of different subtypes may reconcile previous results so far not converging on a consistent pattern of anatomical anomalies in autism, and possibly relate the presence of diverging corticogenic and maturational anomalies. The high accuracy for symptom severity prediction indicates benefits of MRI biotyping for personalized diagnostics and may guide the development of targeted therapeutic strategies.