White Matter Perivascular Space Burden in Children With Autism Spectrum Disorder and Typically Developing Controls: An Automated Quantitative MRI Study

ABSTRACT Background Perivascular spaces (PVS) are compartments involved in brain waste clearance. PVS are commonly observed in typically developing (TD) children; however, their burden in autism spectrum disorder (ASD) remains unclear. Purpose To investigate whether quantitative white matter (WM) PVS burden differs between children with ASD and TD controls using automatic segmentation. Study Type Observational. Population Ninety‐eight children with ASD (age range: 2–8 years; mean age 4.8 ± 1.5 years; 78M/20F) and 38 TD children (age range: 2–8 years; mean age 5.5 ± 0.9 years; 23M/15F). Field Strength/Sequence 3T; 3D T1‐weighted ultrafast gradient‐echo and 3D T2‐weighted turbo spin‐echo sequences. Assessment Human Connectome Project pipeline was used to generate enhanced perivascular contrast (EPC) images. The Weakly Supervised Perivascular Spaces Segmentation algorithm was applied to EPC to segment PVS. PVS volume (WM‐PVSv) and count (WM‐PVSc) were quantified in total WM and six subregions (frontal, parietal, temporal, occipital, limbic, and deepWM). Statistical Tests Welch's t ‐test, chi‐square test, and ANCOVA for group differences; Spearman's rank correlation for age, structural brain volumes, and PVS metrics exploratory correlations; multivariable linear regression for global PVS metrics, and linear mixed‐effects models for regional analyses, adjusted for age, sex, WM, and extra‐axial cerebrospinal fluid volumes. Results In the adjusted models, no significant differences between ASD and TD were observed, as the diagnostic group was not independently associated with either WM‐PVSv (ASD: 2.3 ± 1.2 cm 3 ; TD: 2.0 ± 0.9 cm 3 ; p = 0.228 ) or WM‐PVSc (ASD: 832 ± 298; TD: 754 ± 260; p = 0.121), whereas WM volume was significantly associated with both metrics ( β = 0.012 mm 3 for WM‐PVSv; β = 0.004 mm 3 for WM‐PVSc). In both ASD and TD, frontal WM exhibited the highest WM‐PVScn (ASD: 37.0% ± 4.9%; TD: 28.9% ± 6.6%), whereas deep WM showed the highest WM‐PVSvf (ASD: 0.010 ± 0.004; TD: 0.010 ± 0.003). Data Conclusion PVS measures appear to reflect inter‐individual variability associated with WM volume. No evidence was found for WM‐PVS burden as an early‐childhood ASD biomarker. Evidence Level 3. Technical Efficacy Stage 3.