Diagnosis of Autism Spectrum Disorders Using Multi-Level High-Order Functional Networks Derived From Resting-State Functional MRI

Feng Zhao, Han Zhang, Islem Rekik, Zhiyong An, Dinggang Shen

Research output: Contribution to journalArticle

10 Citations (Scopus)

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.

Original languageEnglish
Article number184
JournalFrontiers in Human Neuroscience
Volume12
DOIs
Publication statusPublished - 2018 May 14

Fingerprint

Magnetic Resonance Imaging
Brain
Brain Diseases
Autism Spectrum Disorder

Keywords

  • Autism spectrum disorder
  • Brain network
  • High-order functional connectivity
  • Learning-based classification
  • Resting-state fMRI

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology
  • Neurology
  • Psychiatry and Mental health
  • Biological Psychiatry
  • Behavioral Neuroscience

Cite this

Diagnosis of Autism Spectrum Disorders Using Multi-Level High-Order Functional Networks Derived From Resting-State Functional MRI. / Zhao, Feng; Zhang, Han; Rekik, Islem; An, Zhiyong; Shen, Dinggang.

In: Frontiers in Human Neuroscience, Vol. 12, 184, 14.05.2018.

Research output: Contribution to journalArticle

@article{71b26b4110644acd83ed99907bbad6a5,
title = "Diagnosis of Autism Spectrum Disorders Using Multi-Level High-Order Functional Networks Derived From Resting-State Functional MRI",
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.",
keywords = "Autism spectrum disorder, Brain network, High-order functional connectivity, Learning-based classification, Resting-state fMRI",
author = "Feng Zhao and Han Zhang and Islem Rekik and Zhiyong An and Dinggang Shen",
year = "2018",
month = "5",
day = "14",
doi = "10.3389/fnhum.2018.00184",
language = "English",
volume = "12",
journal = "Frontiers in Human Neuroscience",
issn = "1662-5161",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Diagnosis of Autism Spectrum Disorders Using Multi-Level High-Order Functional Networks Derived From Resting-State Functional MRI

AU - Zhao, Feng

AU - Zhang, Han

AU - Rekik, Islem

AU - An, Zhiyong

AU - Shen, Dinggang

PY - 2018/5/14

Y1 - 2018/5/14

N2 - 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.

AB - 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.

KW - Autism spectrum disorder

KW - Brain network

KW - High-order functional connectivity

KW - Learning-based classification

KW - Resting-state fMRI

UR - http://www.scopus.com/inward/record.url?scp=85054356385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054356385&partnerID=8YFLogxK

U2 - 10.3389/fnhum.2018.00184

DO - 10.3389/fnhum.2018.00184

M3 - Article

AN - SCOPUS:85054356385

VL - 12

JO - Frontiers in Human Neuroscience

JF - Frontiers in Human Neuroscience

SN - 1662-5161

M1 - 184

ER -