Martin Styner, PhD​​
Professor, Departments of Psychiatry and Computer Science, University of North Carolina at Chapel Hill
When: Friday, January 16, 2026,11am-12pm Eastern Time​​
​​​​​​
Title: Phenotype Representation and Analysis via Discriminative Atypicality (PRADA)  for Neurodevelopmental Disorders

Abstract: Neurodevelopmental disorders are a diverse group of conditions characterized by atypical brain development, leading to cognitive, social, and emotional impairment, and are inherently heterogeneous in presentation and neurobiology. For instance, over 30% of individuals with Autism Spectrum Disorder (ASD) also receive an Attention Deficit Hyperactivity Disorder diagnosis, underscoring the significant overlap and complexity of NDDs. Understanding this variability is crucial for advancing diagnostic methods and insights into the shared and unique neural mechanisms underlying these conditions. 
In this talk, we present a novel approach called PRADA (Prototype Representation and Analysis via Discriminative Atypicality) that embraces the heterogeneity of both typical and atypical brain morphometry. This approach employs our Multiscale Score Matching Analysis (MSMA),  a global and local multiscale out-of-distribution analysis via the gradients of the log density (scores). Combining MSMA and manifold-mapping, we compute a morphospace of brain prototypes representing deviations from a population of typical subjects.  Using these brain prototypes, disorder-related subtyping can be performed.  Furthermore, subject-specific profiles of atypicality can be extracted and summarized per subtype. We show the application of PRADA to the study structural MRI data in Autism Spectrum Disorder (ASD) as well as  Down Syndrome (DS) at school age.  The resulting analysis detects disorder-related subtypes and reveals that subtype-specific structural atypicality correlates with cognitive and behavioral outcomes. These results shed much-needed light on the understanding ASD and DS, and paving the way for subject-centered treatment plans.

Bio: Dr. Styner is a leading expert in medical image computing with specific research on novel neuroimaging methods and software tools for structural and diffusion MRI. His research is focused on studies of early postnatal brain development, encompassing a broad range of studies in human and non-human primate neuroimaging such as normal development, autism spectrum disorder, fragile-X, Angelman Syndrome, Down Syndrome, and intra-uterine exposure studies. Dr. Styner has co-authored over 500 papers in peer-reviewed journals and conferences. He is the director of the UNC Neuro Image Research and Analysis Laboratory (NIRAL).