An exploration of structural brain differences in Autism Spectrum Disorders: A multi-parcellation and multi-age analysis.

Autism Spectrum Disorders (ASD) assessment relies on clinical rating scales to measure related social and behavioral changes, a subjective process which is prone to misdiagnosis. ASD heterogeneity of social and cognitive functioning has been associated with underlying neuro-anatomical alterations. Automatic medical imaging analyses have made possible quantification of these anatomical changes, yet these complex morphological patterns have been partially characterized by simple absolute scalar values. This paper presents a much more complete exploration of the global–local differences between ASD and control subjects using a multiscale descriptor that captures sub-visual spatial patterns. This analysis consists in three main steps: a pre-processing for segmenting the brain into a particular anatomical parcellation, a region-based characterization for capturing global–local folding/shape patterns, and a statistical analysis for quantifying differences between ASD and control individuals. A large data cohort (n = 1245) consisting in three different age groups, was used to perform this exploration. The analysis was carried out in the entire set of cortical and subcortical brain regions: (i) using two different brain parcellations, and (ii) separately for each age group. This characterization revealed statistically significant differences (p ¡ 0.05) in the ASD group compared to control individuals using two brain parcellations. These results demonstrate the representation is able to identify folding and shape differences for a particular age range in both parcellations, supporting the generalizability of these findings. • Quantification of brain folding/shape differences at different orientation, depths and circumvolution patterns in every cortical and subcortical brain region. • A statistical analysis for establishing brain differences between ASD and control individuals. • A more complete evaluation by assessing the representation with a larger population (n = 1245, three groups of age), and two different brain parcellations. • An anatomical–functional correlation, crucial for developing an unbiased quantification of the disease and a more accurate categorization. [ABSTRACT FROM AUTHOR]