Abstract #0513

The Cerebellum and Brainstem Together Increase Classification Accuracy for Autism Spectrum Disorder over the Whole Brain

Muriel M. K. Bruchhage¹, Leon M. Aksman¹, Andre F. Marquand², MRC AIMS Consortium³, EU TACTICS Consortium⁴, Jan Buitelaar², Declan Murphy⁵, and Steven C. R. Williams¹

¹Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom, ²Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, Netherlands, ³Centre for Neuroimaging Sciences, Institute of Psychiatry, Psychology and Neuroscience, King's College London; Cambridge University; Oxford University, London; Cambridge; Oxford, United Kingdom, ⁴Radboud University Medical Center; King's College London; University Medical Center Utrecht; Central Institute of Mental Health Mannheim, Nijmegen; London; Utrecht; Mannheim, Netherlands, ⁵Sackler Institute of Translational Neuroimaging, Department of Forensics and Neurodevelopmental Sciences, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom

Autism spectrum disorder (ASD) has been linked to cerebellar and brainstem dysfunction and abnormal development, but it remains unclear whether these regional abnormalities can help classify the disorder. Performing machine learning based classification using Jacobian determinant based features on two independent male ASD cohorts (adult and paediatric) of different sizes and age range, we demonstrated a consistently higher classification accuracy by up to 15% using the cerebellum and brainstem as regions of interest classifiers over the whole brain. In both cohorts, classification was driven by regional differences in the posterior lateral cerebellum.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.