Exploring White Matter Abnormalities in Young Children with Autism Spectrum Disorder: Integrating Multi-shell Diffusion Data and Machine Learning Analysis.

RATIONALE AND OBJECTIVES: This study employed tract-based spatial statistics (TBSS) to investigate abnormalities in the white matter microstructure among children with autism spectrum disorder (ASD). Additionally, an eXtreme Gradient Boosting (XGBoost) model was developed to effectively classify individuals with ASD and typical developing children (TDC). METHODS AND MATERIALS: Multi-shell diffusion weighted images were acquired from 62 children with ASD and 44 TDC. Using the Pydesigner procedure, diffusion tensor (DT), diffusion kurtosis (DK), and white matter tract integrity (WMTI) metrics were computed. Subsequently, TBSS analysis was applied to discern differences in these diffusion parameters between ASD and TDC groups. The XGBoost model was then trained using metrics showing significant differences, and Shapley Additive explanations (SHAP) values were computed to assess the feature importance in the model's predictions. RESULTS: TBSS analysis revealed a significant reduction in axonal diffusivity (AD) in the left posterior corona radiata and the right superior corona radiata. Among the DK indicators, mean kurtosis, axial kurtosis, and kurtosis fractional anisotropy were notably increased in children with ASD, with no significant difference in radial kurtosis. WMTI metrics such as axonal water fraction, axonal diffusivity of the extra-axonal space (EAS_AD), tortuosity of the extra-axonal space (EAS_TORT), and diffusivity of intra-axonal space (IAS_Da) were significantly increased, primarily in the corpus callosum and fornix. Notably, there was no significant difference in radial diffusivity of the extra-axial space (EAS_RD). The XGBoost model demonstrated excellent classification ability, and the SHAP analysis identified EAS_TORT as the feature with the highest importance in the model's predictions. CONCLUSION: This study utilized TBSS analyses with multi-shell diffusion data to examine white matter abnormalities in pediatric autism. Additionally, the developed XGBoost model showed outstanding performance in classifying ASD and TDC. The ranking of SHAP values based on the XGBoost model underscored the significance of features in influencing model predictions.

Cortical gray-white matter contrast abnormalities in male children with attention deficit hyperactivity disorder.

Purpose: Presently, research concerning alterations in brain structure among individuals with attention deficit hyperactivity disorder (ADHD) predominantly focuses on entire brain volume and cortical thickness. In this study, we extend our examination to the cortical microstructure of male children with ADHD. To achieve this, we employ the gray-white matter tissue contrast (GWC) metric, allowing for an assessment of modifications in gray matter density and white matter microstructure. Furthermore, we explore the potential connection between GWC and the severity of disorder in male children by ADHD. Methods: We acquired 3DT1 sequences from the public ADHD-200 database. In this study, we conducted a comparative analysis between 43 male children diagnosed with ADHD and 50 age-matched male controls exhibiting typical development trajectories. Our investigation entailed assessing differences in GWC and cortical thickness. Additionally, we explored the potential correlation between GWC and the severity of ADHD. To delineate the cerebral landscape, each hemisphere was subdivided into 34 cortical regions using freesurfer 7.2.0. For quantification, GWC was computed by evaluating the intensity contrast of non-normalized T1 images above and below the gray-white matter interface. Results: Our findings unveiled elevated GWC within the bilateral lingual, bilateral insular, left transverse temporal, right parahippocampal and right pericalcarine regions in male children with ADHD when contrasted with their healthy counterparts. Moreover, the cortical thickness in the ADHD group no notable distinctions that of control group in all areas. Intriguingly, the GWC of left transverse temporal demonstrated a negative correlation with the extent of inattention experienced by male children with ADHD. Conclusion: Utilizing GWC as a metric facilitates a more comprehensive assessment of microstructural brain changes in children with ADHD. The fluctuations in GWC observed in specific brain regions might serve as a neural biomarker, illuminating structural modifications in male children grappling with ADHD. This perspective enriches our comprehension of white matter microstructure and cortical density in these children. Notably, the inverse correlation between the GWC of the left transverse temporal and inattention severity underscores the potential role of structural and functional anomalies within this region in ADHD progression. Enhancing our insight into ADHD-related brain changes holds significant promise in deciphering potential neuropathological mechanisms.