Diagnosis of Autism Spectrum Disorders Using Temporally Distinct Resting-State Functional Connectivity Networks

Chong Yaw Wee, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Introduction: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. Aims: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. Results: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. Conclusions: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.

Original languageEnglish
Pages (from-to)212-219
Number of pages8
JournalCNS Neuroscience and Therapeutics
Volume22
Issue number3
DOIs
Publication statusPublished - 2016 Mar 1

Fingerprint

Brain
Autistic Disorder
Magnetic Resonance Imaging
Cluster Analysis
Autism Spectrum Disorder
Weights and Measures
Datasets

Keywords

  • Brain Activation Patterns
  • Resting-State Functional Connectivity
  • Sparse Representation
  • Spatiotemporal Dynamics
  • Temporal Decomposition

ASJC Scopus subject areas

  • Pharmacology (medical)
  • Physiology (medical)
  • Psychiatry and Mental health
  • Pharmacology

Cite this

Diagnosis of Autism Spectrum Disorders Using Temporally Distinct Resting-State Functional Connectivity Networks. / Wee, Chong Yaw; Yap, Pew Thian; Shen, Dinggang.

In: CNS Neuroscience and Therapeutics, Vol. 22, No. 3, 01.03.2016, p. 212-219.

Research output: Contribution to journalArticle

@article{4f622ab61e8f4bf5b16c261cdd2abee0,
title = "Diagnosis of Autism Spectrum Disorders Using Temporally Distinct Resting-State Functional Connectivity Networks",
abstract = "Introduction: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. Aims: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. Results: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7{\%} on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. Conclusions: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.",
keywords = "Brain Activation Patterns, Resting-State Functional Connectivity, Sparse Representation, Spatiotemporal Dynamics, Temporal Decomposition",
author = "Wee, {Chong Yaw} and Yap, {Pew Thian} and Dinggang Shen",
year = "2016",
month = "3",
day = "1",
doi = "10.1111/cns.12499",
language = "English",
volume = "22",
pages = "212--219",
journal = "CNS Neuroscience and Therapeutics",
issn = "1755-5930",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Diagnosis of Autism Spectrum Disorders Using Temporally Distinct Resting-State Functional Connectivity Networks

AU - Wee, Chong Yaw

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2016/3/1

Y1 - 2016/3/1

N2 - Introduction: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. Aims: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. Results: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. Conclusions: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.

AB - Introduction: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. Aims: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. Results: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. Conclusions: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.

KW - Brain Activation Patterns

KW - Resting-State Functional Connectivity

KW - Sparse Representation

KW - Spatiotemporal Dynamics

KW - Temporal Decomposition

UR - http://www.scopus.com/inward/record.url?scp=84958639079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958639079&partnerID=8YFLogxK

U2 - 10.1111/cns.12499

DO - 10.1111/cns.12499

M3 - Article

C2 - 26821773

AN - SCOPUS:84958639079

VL - 22

SP - 212

EP - 219

JO - CNS Neuroscience and Therapeutics

JF - CNS Neuroscience and Therapeutics

SN - 1755-5930

IS - 3

ER -