Identifying and Predicting Autism Spectrum Disorder Based on Multi-Site Structural MRI With Machine Learning

Abstract

Although emerging evidence has implicated structural/functional abnormalities of patients with Autism Spectrum Disorder(ASD), definitive neuroimaging markers remain obscured due to inconsistent or incompatible findings, especially for structural imaging. Furthermore, brain differences defined by statistical analysis are difficult to implement individual prediction. The present study has employed the machine learning techniques under the unified framework in neuroimaging to identify the neuroimaging markers of patients with ASD and distinguish them from typically developing controls(TDC). To enhance the interpretability of the machine learning model, the study has processed three levels of assessments including model-level assessment, feature-level assessment, and biology-level assessment. According to these three levels assessment, the study has identified neuroimaging markers of ASD including the opercular part of bilateral inferior frontal gyrus, the orbital part of right inferior frontal gyrus, right rolandic operculum, right olfactory cortex, right gyrus rectus, right insula, left inferior parietal gyrus, bilateral supramarginal gyrus, bilateral angular gyrus, bilateral superior temporal gyrus, bilateral middle temporal gyrus, and left inferior temporal gyrus. In addition, negative correlations between the communication skill score in the Autism Diagnostic Observation Schedule (ADOS_G) and regional gray matter (GM) volume in the gyrus rectus, left middle temporal gyrus, and inferior temporal gyrus have been detected. A significant negative correlation has been found between the communication skill score in ADOS_G and the orbital part of the left inferior frontal gyrus. A negative correlation between verbal skill score and right angular gyrus and a significant negative correlation between non-verbal communication skill and right angular gyrus have been found. These findings in the study have suggested the GM alteration of ASD and correlated with the clinical severity of ASD disease symptoms. The interpretable machine learning framework gives sight to the pathophysiological mechanism of ASD but can also be extended to other diseases.

Individual brain regulation as learned via neurofeedback is related to affective changes in adolescents with autism spectrum disorder

“…Smaller gray matter volume of the right ITG was previously related to a higher probability of an ASD diagnosis [93]. Reduced gray matter volume of the left ITG was also detected in children with low-functioning ASD [94] and related to communication skills [95]. Similar to the ACC, smaller gray matter volume in the ITG might be related to less activity after structural normalization, relating our finding of an increase after NF training to compensatory processes.…”

Individual brain regulation as learned via neurofeedback is related to affective changes in adolescents with autism spectrum disorder

“…In a classification tree approach using white and gray matter volumes of various temporal regions, smaller gray matter volume of the right ITG was related to a higher probability of an ASD diagnosis (Neeley et al, 2007). Reduced gray matter volume of the left ITG was also detected in children with low-functioning ASD (Riva et al, 2013) and related to communication skills (Duan et al, 2022). As for the ACC, smaller gray matter volume in the ITG might be related to less activity after structural normalization, relating our finding of an increase after NF training to compensatory processes.…”

“…In a classification tree approach using white and gray matter volumes of various temporal regions, smaller gray matter volume of the right ITG was related to a higher probability of an ASD diagnosis (Neeley et al, 2007). Reduced gray matter volume of the left ITG was also detected in children with low-functioning ASD (Riva et al, 2013) and related to communication skills (Duan et al, 2022).…”

Generalizable neuromarker for autism spectrum disorder across imaging sites and developmental stages: A multi-site study

“…Various methods have been proposed to correct inter-site differences (18,19); prior multi-site, case-control studies have confirmed the effectiveness of these methods (20,21). Some classification studies have employed an inter-site cross-validation scheme to evaluate the generalizability of their classifiers to other imaging sites within a dataset (22)(23)(24). However, this approach may not be enough as an index for generalizability, as it only repeats the analyses on the same dataset.…”