Modeling regional dynamics in low-frequency fluctuation and its application to Autism spectrum disorder diagnosis

Eunji Jun, Eunsong Kang, Jaehun Choi, Heung-Il Suk

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

With the advent of neuroimaging techniques, many studies in the literature have validated the use of resting-state fMRI (rs-fMRI) for understanding functional mechanisms of the brain, as well as for identifying brain disorders or diseases. One of the main streams in recent studies of modeling and analyzing rs-fMRI data is to account for the dynamic characteristics of a brain. In this study, we propose a novel method that directly models the regional temporal BOLD fluctuations in a stochastic manner and estimates the dynamic characteristics in the form of likelihoods. Specifically, we modeled temporal BOLD fluctuation of individual Regions Of Interest (ROIs) by means of Hidden Markov Models (HMMs), and then estimated the ‘goodness-of-fit’ of each ROI's BOLD signals to the corresponding trained HMM in terms of a likelihood. Using estimated likelihoods of the ROIs over the whole brain as features, we built a classifier that can discriminate subjects with Autism Spectrum Disorder (ASD) from Typically Developing (TD) controls at an individual level. In order to interpret the trained HMMs and a classifier from a neuroscience perspective, we also conducted model analysis. First, we investigated the learned weight coefficients of a classifier by transforming them into activation patterns, from which we could identify the ROIs that are highly associated with ASD and TD groups. Second, we explored the characteristics of temporal BOLD signals in terms of functional networks by clustering them based on sequences of the hidden states decoded with the trained HMMs. We validated the effectiveness of the proposed method by achieving the state-of-the-art performance on the ABIDE dataset and observed insightful patterns related to ASD.

Original languageEnglish
Pages (from-to)669-686
Number of pages18
JournalNeuroImage
Volume184
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Brain Diseases
Brain
Magnetic Resonance Imaging
Neurosciences
Neuroimaging
Cluster Analysis
Weights and Measures
Autism Spectrum Disorder
Datasets

Keywords

  • Autism spectrum disorder
  • Hidden markov models
  • Representing regional BOLD fluctuations
  • Resting-state fMRI
  • Temporal dynamics

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Modeling regional dynamics in low-frequency fluctuation and its application to Autism spectrum disorder diagnosis. / Jun, Eunji; Kang, Eunsong; Choi, Jaehun; Suk, Heung-Il.

In: NeuroImage, Vol. 184, 01.01.2019, p. 669-686.

Research output: Contribution to journalArticle

@article{2e6201e12d6e4b87a892308384ff387a,
title = "Modeling regional dynamics in low-frequency fluctuation and its application to Autism spectrum disorder diagnosis",
abstract = "With the advent of neuroimaging techniques, many studies in the literature have validated the use of resting-state fMRI (rs-fMRI) for understanding functional mechanisms of the brain, as well as for identifying brain disorders or diseases. One of the main streams in recent studies of modeling and analyzing rs-fMRI data is to account for the dynamic characteristics of a brain. In this study, we propose a novel method that directly models the regional temporal BOLD fluctuations in a stochastic manner and estimates the dynamic characteristics in the form of likelihoods. Specifically, we modeled temporal BOLD fluctuation of individual Regions Of Interest (ROIs) by means of Hidden Markov Models (HMMs), and then estimated the ‘goodness-of-fit’ of each ROI's BOLD signals to the corresponding trained HMM in terms of a likelihood. Using estimated likelihoods of the ROIs over the whole brain as features, we built a classifier that can discriminate subjects with Autism Spectrum Disorder (ASD) from Typically Developing (TD) controls at an individual level. In order to interpret the trained HMMs and a classifier from a neuroscience perspective, we also conducted model analysis. First, we investigated the learned weight coefficients of a classifier by transforming them into activation patterns, from which we could identify the ROIs that are highly associated with ASD and TD groups. Second, we explored the characteristics of temporal BOLD signals in terms of functional networks by clustering them based on sequences of the hidden states decoded with the trained HMMs. We validated the effectiveness of the proposed method by achieving the state-of-the-art performance on the ABIDE dataset and observed insightful patterns related to ASD.",
keywords = "Autism spectrum disorder, Hidden markov models, Representing regional BOLD fluctuations, Resting-state fMRI, Temporal dynamics",
author = "Eunji Jun and Eunsong Kang and Jaehun Choi and Heung-Il Suk",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.neuroimage.2018.09.043",
language = "English",
volume = "184",
pages = "669--686",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Modeling regional dynamics in low-frequency fluctuation and its application to Autism spectrum disorder diagnosis

AU - Jun, Eunji

AU - Kang, Eunsong

AU - Choi, Jaehun

AU - Suk, Heung-Il

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With the advent of neuroimaging techniques, many studies in the literature have validated the use of resting-state fMRI (rs-fMRI) for understanding functional mechanisms of the brain, as well as for identifying brain disorders or diseases. One of the main streams in recent studies of modeling and analyzing rs-fMRI data is to account for the dynamic characteristics of a brain. In this study, we propose a novel method that directly models the regional temporal BOLD fluctuations in a stochastic manner and estimates the dynamic characteristics in the form of likelihoods. Specifically, we modeled temporal BOLD fluctuation of individual Regions Of Interest (ROIs) by means of Hidden Markov Models (HMMs), and then estimated the ‘goodness-of-fit’ of each ROI's BOLD signals to the corresponding trained HMM in terms of a likelihood. Using estimated likelihoods of the ROIs over the whole brain as features, we built a classifier that can discriminate subjects with Autism Spectrum Disorder (ASD) from Typically Developing (TD) controls at an individual level. In order to interpret the trained HMMs and a classifier from a neuroscience perspective, we also conducted model analysis. First, we investigated the learned weight coefficients of a classifier by transforming them into activation patterns, from which we could identify the ROIs that are highly associated with ASD and TD groups. Second, we explored the characteristics of temporal BOLD signals in terms of functional networks by clustering them based on sequences of the hidden states decoded with the trained HMMs. We validated the effectiveness of the proposed method by achieving the state-of-the-art performance on the ABIDE dataset and observed insightful patterns related to ASD.

AB - With the advent of neuroimaging techniques, many studies in the literature have validated the use of resting-state fMRI (rs-fMRI) for understanding functional mechanisms of the brain, as well as for identifying brain disorders or diseases. One of the main streams in recent studies of modeling and analyzing rs-fMRI data is to account for the dynamic characteristics of a brain. In this study, we propose a novel method that directly models the regional temporal BOLD fluctuations in a stochastic manner and estimates the dynamic characteristics in the form of likelihoods. Specifically, we modeled temporal BOLD fluctuation of individual Regions Of Interest (ROIs) by means of Hidden Markov Models (HMMs), and then estimated the ‘goodness-of-fit’ of each ROI's BOLD signals to the corresponding trained HMM in terms of a likelihood. Using estimated likelihoods of the ROIs over the whole brain as features, we built a classifier that can discriminate subjects with Autism Spectrum Disorder (ASD) from Typically Developing (TD) controls at an individual level. In order to interpret the trained HMMs and a classifier from a neuroscience perspective, we also conducted model analysis. First, we investigated the learned weight coefficients of a classifier by transforming them into activation patterns, from which we could identify the ROIs that are highly associated with ASD and TD groups. Second, we explored the characteristics of temporal BOLD signals in terms of functional networks by clustering them based on sequences of the hidden states decoded with the trained HMMs. We validated the effectiveness of the proposed method by achieving the state-of-the-art performance on the ABIDE dataset and observed insightful patterns related to ASD.

KW - Autism spectrum disorder

KW - Hidden markov models

KW - Representing regional BOLD fluctuations

KW - Resting-state fMRI

KW - Temporal dynamics

UR - http://www.scopus.com/inward/record.url?scp=85054371296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054371296&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.09.043

DO - 10.1016/j.neuroimage.2018.09.043

M3 - Article

C2 - 30248456

AN - SCOPUS:85054371296

VL - 184

SP - 669

EP - 686

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -