Abstract
Functional brain networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used for Autism Spectrum Disorder (ASD) diagnosis. Typically, these networks are constructed by calculating functional connectivity (FC) between any pair of brain regions of interest (ROIs), i.e., using Pearson's correlation between rs-fMRI time series. However, this can only be called as a low-order representation of the functional interaction, because the relationship is investigated just between two ROIs. Brain disorders might not only affect low-order FC, but also high-order FC, i.e., the higher-level relationship among multiple brain regions, which might be more crucial for diagnosis. To comprehensively characterize such relationship for better diagnosis of ASD, we propose a multi-level, high-order FC network representation that can nicely capture complex interactions among brain regions. Then, we design a feature selection method to identify those discriminative multi-level, high-order FC features for ASD diagnosis. Finally, we design an ensemble classifier with multiple linear SVMs, each trained on a specific level of FC networks, for boosting the final classification accuracy. Experimental results show that the integration of both low-order and first-level high-order FC networks achieves the best ASD diagnostic accuracy (81%). We further investigated those selected discriminative low-order and high-order FC features and found that the high-order FC features can provide complementary information to the low-order FC features in the ASD diagnosis.
Highlights
Autism spectrum disorder (ASD) is a prevalent and highly heterogeneous childhood neurodevelopmental disease
Prevention1, one out of 68 American children was affected by some form of Autism Spectrum Disorder (ASD), an increase of 78% compared with the past decade
Similar to the hypothesis behind Alzheimer’s disease studies using high-order functional connectivity (FC) (Chen et al, 2016; Wee et al, 2016; Zhang et al, 2016, 2017b; Zhou et al, 2018), we propose that the high-order FC could be affected in ASD and can be used as effective biomarkers for ASD diagnosis
Summary
Autism spectrum disorder (ASD) is a prevalent and highly heterogeneous childhood neurodevelopmental disease. The second type of methods is more straightforward (Zhang et al, 2016, 2017a,b; Zhou et al, 2018), by first calculating regional low-order FC topographical profiles (each characterizing the FC between one brain region and all other brain regions) and using them as regional features to further compute another level of Pearson’s correlation between any pair of brain regions (i.e., “correlation of correlations”) This kind of high-order FC networks could carry complementary information to the traditional low-order FC networks, and could be jointly used for improving ASD diagnosis. For each ROI, we computed its mean time series and performed the band-pass filtering (0.01–0.08 Hz) for trading-off between avoiding physiological noise (Cordes et al, 2001), measurement error (Achard et al, 2008), and magnetic field drifts of the scanner (Tomasi and Volkow, 2010)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
