Kaustubh Supekar1, Srikanth Ryali2, Rui Yuan2, Devinder Kumar2, Carlo de Los Angeles2, Vinod Menon3. 1. Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California. Electronic address: ksupekar@stanford.edu. 2. Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California. 3. Department of Psychiatry and Behavioral Sciences, Stanford University School of Medicine, Stanford, California; Department of Neurology & Neurological Sciences, Stanford University School of Medicine, Stanford, California; Stanford Neurosciences Institute, Stanford University School of Medicine, Stanford, California. Electronic address: menon@stanford.edu.
Abstract
BACKGROUND: Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders, yet the neurobiology of ASD is still poorly understood because inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms. METHODS: We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical control subjects and predict clinical symptom severity. RESULTS: stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE (Autism Brain Imaging Data Exchange) cohort (n = 834). Crucially, stDNN also accurately classified data from independent Stanford (n = 202) and GENDAAR (Gender Exploration of Neurogenetics and Development to Advanced Autism Research) (n = 90) cohorts without additional training. stDNN could not distinguish attention-deficit/hyperactivity disorder from neurotypical control subjects, highlighting the model's specificity. Explainable artificial intelligence revealed that brain features associated with the posterior cingulate cortex and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network, cognitive control, and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical control subjects in the three cohorts. Furthermore, features associated with the posterior cingulate cortex and precuneus nodes of the default mode network emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD. CONCLUSIONS: Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.
BACKGROUND: Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders, yet the neurobiology of ASD is still poorly understood because inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms. METHODS: We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical control subjects and predict clinical symptom severity. RESULTS: stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE (Autism Brain Imaging Data Exchange) cohort (n = 834). Crucially, stDNN also accurately classified data from independent Stanford (n = 202) and GENDAAR (Gender Exploration of Neurogenetics and Development to Advanced Autism Research) (n = 90) cohorts without additional training. stDNN could not distinguish attention-deficit/hyperactivity disorder from neurotypical control subjects, highlighting the model's specificity. Explainable artificial intelligence revealed that brain features associated with the posterior cingulate cortex and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network, cognitive control, and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical control subjects in the three cohorts. Furthermore, features associated with the posterior cingulate cortex and precuneus nodes of the default mode network emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD. CONCLUSIONS: Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.
Authors: Angela R Laird; P Mickle Fox; Simon B Eickhoff; Jessica A Turner; Kimberly L Ray; D Reese McKay; David C Glahn; Christian F Beckmann; Stephen M Smith; Peter T Fox Journal: J Cogn Neurosci Date: 2011-06-14 Impact factor: 3.225
Authors: Chun Lun Eric Lai; Zoe Lau; Simon S Y Lui; Eugenia Lok; Venus Tam; Quinney Chan; Koi Man Cheng; Siu Man Lam; Eric F C Cheung Journal: Autism Res Date: 2016-11-22 Impact factor: 5.216
Authors: Archit Rathore; Sourabh Palande; Jeffrey S Anderson; Brandon A Zielinski; P Thomas Fletcher; Bei Wang Journal: Med Image Comput Comput Assist Interv Date: 2019-10-10
Authors: Rogier B Mars; Franz-Xaver Neubert; Maryann P Noonan; Jerome Sallet; Ivan Toni; Matthew F S Rushworth Journal: Front Hum Neurosci Date: 2012-06-21 Impact factor: 3.169