AUTHOR=Liu Mingyang , Yu Weibo , Xu Dandan , Wang Miaoyan , Peng Bo , Jiang Haoxiang , Dai Yakang 

TITLE=Diagnosis for autism spectrum disorder children using T1-based gray matter and arterial spin labeling-based cerebral blood flow network metrics

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 18 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1356241

DOI=10.3389/fnins.2024.1356241

ISSN=1662-453X

ABSTRACT=Autism Spectrum Disorder (ASD) is a multifaceted neurodevelopmental condition marked by challenges in motor skills, communication, emotional expression, and social interaction. Nevertheless, diagnosing ASD remains a challenge due to the heavy reliance on subjective behavioral observations and assessment scales, which lack objective indicators. In this study, we propose an innovative approach to diagnosing ASD by utilizing T1-based gray matter and ASLbased cerebral blood flow network metrics. This study involved thirty preschool-aged patients with ASD and twenty-two typically developing (TD) individuals. We extracted brain network features from both T1-weighted magnetic resonance imaging (MRI) images and ASL images, including gray matter network metrics and cerebral blood flow network metrics. The selection of the brain network features was carried out using statistical t-tests and Minimum Redundancy Maximum Relevance (mRMR). To train the diagnostic model, we construct a machine learning model based on random vector functional link network. The proposed approach achieved a commendable classification accuracy of 84.91% in distinguishing ASD and TD. The specific network features that differentiate ASD from TD locate mainly at inferior frontal gyrus and superior occipital gyrus, both of which significantly impact the social and executive function of ASD patients. Our proposed method offers an objective and effective approach to the clinical diagnosis of ASD.