Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification

Chong Yaw Wee, Sen Yang, Pew Thian Yap, Dinggang Shen, The Alzheimer’S Disease Neuroimaging Initiative For The Alzheimer’S Disease Neuroimaging Initiative

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

In conventional resting-state functional MRI (R-fMRI) analysis, functional connectivity is assumed to be temporally stationary, overlooking neural activities or interactions that may happen within the scan duration. Dynamic changes of neural interactions can be reflected by variations of topology and correlation strength in temporally correlated functional connectivity networks. These connectivity networks may potentially capture subtle yet short neural connectivity disruptions induced by disease pathologies. Accordingly, we are motivated to utilize disrupted temporal network properties for improving control-patient classification performance. Specifically, a sliding window approach is firstly employed to generate a sequence of overlapping R-fMRI sub-series. Based on these sub-series, sliding window correlations, which characterize the neural interactions between brain regions, are then computed to construct a series of temporal networks. Individual estimation of these temporal networks using conventional network construction approaches fails to take into consideration intrinsic temporal smoothness among successive overlapping R-fMRI sub-series. To preserve temporal smoothness of R-fMRI sub-series, we suggest to jointly estimate the temporal networks by maximizing a penalized log likelihood using a fused sparse learning algorithm. This sparse learning algorithm encourages temporally correlated networks to have similar network topology and correlation strengths. We design a disease identification framework based on the estimated temporal networks, and group level network property differences and classification results demonstrate the importance of including temporally dynamic R-fMRI scan information to improve diagnosis accuracy of mild cognitive impairment patients.

Original languageEnglish
JournalBrain Imaging and Behavior
DOIs
Publication statusAccepted/In press - 2015 Jun 28

Fingerprint

Magnetic Resonance Imaging
Learning
Pathology
Brain

Keywords

  • Mild Cognitive Impairment (MCI)
  • Resting-state functional MRI (R-fMRI)
  • Sliding window correlation
  • Sparse temporal networks
  • Temporal dynamics
  • Temporal smoothness

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Behavioral Neuroscience
  • Cellular and Molecular Neuroscience
  • Cognitive Neuroscience
  • Neurology
  • Psychiatry and Mental health
  • Clinical Neurology

Cite this

Wee, C. Y., Yang, S., Yap, P. T., Shen, D., & For The Alzheimer’S Disease Neuroimaging Initiative, T. AS. D. N. I. (Accepted/In press). Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification. Brain Imaging and Behavior. https://doi.org/10.1007/s11682-015-9408-2

Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification. / Wee, Chong Yaw; Yang, Sen; Yap, Pew Thian; Shen, Dinggang; For The Alzheimer’S Disease Neuroimaging Initiative, The Alzheimer’S Disease Neuroimaging Initiative.

In: Brain Imaging and Behavior, 28.06.2015.

Research output: Contribution to journalArticle

Wee, Chong Yaw ; Yang, Sen ; Yap, Pew Thian ; Shen, Dinggang ; For The Alzheimer’S Disease Neuroimaging Initiative, The Alzheimer’S Disease Neuroimaging Initiative. / Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification. In: Brain Imaging and Behavior. 2015.
@article{82716c98d3b34d1ca35188aaa0beef83,
title = "Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification",
abstract = "In conventional resting-state functional MRI (R-fMRI) analysis, functional connectivity is assumed to be temporally stationary, overlooking neural activities or interactions that may happen within the scan duration. Dynamic changes of neural interactions can be reflected by variations of topology and correlation strength in temporally correlated functional connectivity networks. These connectivity networks may potentially capture subtle yet short neural connectivity disruptions induced by disease pathologies. Accordingly, we are motivated to utilize disrupted temporal network properties for improving control-patient classification performance. Specifically, a sliding window approach is firstly employed to generate a sequence of overlapping R-fMRI sub-series. Based on these sub-series, sliding window correlations, which characterize the neural interactions between brain regions, are then computed to construct a series of temporal networks. Individual estimation of these temporal networks using conventional network construction approaches fails to take into consideration intrinsic temporal smoothness among successive overlapping R-fMRI sub-series. To preserve temporal smoothness of R-fMRI sub-series, we suggest to jointly estimate the temporal networks by maximizing a penalized log likelihood using a fused sparse learning algorithm. This sparse learning algorithm encourages temporally correlated networks to have similar network topology and correlation strengths. We design a disease identification framework based on the estimated temporal networks, and group level network property differences and classification results demonstrate the importance of including temporally dynamic R-fMRI scan information to improve diagnosis accuracy of mild cognitive impairment patients.",
keywords = "Mild Cognitive Impairment (MCI), Resting-state functional MRI (R-fMRI), Sliding window correlation, Sparse temporal networks, Temporal dynamics, Temporal smoothness",
author = "Wee, {Chong Yaw} and Sen Yang and Yap, {Pew Thian} and Dinggang Shen and {For The Alzheimer’S Disease Neuroimaging Initiative}, {The Alzheimer’S Disease Neuroimaging Initiative}",
year = "2015",
month = "6",
day = "28",
doi = "10.1007/s11682-015-9408-2",
language = "English",
journal = "Brain Imaging and Behavior",
issn = "1931-7557",
publisher = "Springer New York",

}

TY - JOUR

T1 - Sparse temporally dynamic resting-state functional connectivity networks for early MCI identification

AU - Wee, Chong Yaw

AU - Yang, Sen

AU - Yap, Pew Thian

AU - Shen, Dinggang

AU - For The Alzheimer’S Disease Neuroimaging Initiative, The Alzheimer’S Disease Neuroimaging Initiative

PY - 2015/6/28

Y1 - 2015/6/28

N2 - In conventional resting-state functional MRI (R-fMRI) analysis, functional connectivity is assumed to be temporally stationary, overlooking neural activities or interactions that may happen within the scan duration. Dynamic changes of neural interactions can be reflected by variations of topology and correlation strength in temporally correlated functional connectivity networks. These connectivity networks may potentially capture subtle yet short neural connectivity disruptions induced by disease pathologies. Accordingly, we are motivated to utilize disrupted temporal network properties for improving control-patient classification performance. Specifically, a sliding window approach is firstly employed to generate a sequence of overlapping R-fMRI sub-series. Based on these sub-series, sliding window correlations, which characterize the neural interactions between brain regions, are then computed to construct a series of temporal networks. Individual estimation of these temporal networks using conventional network construction approaches fails to take into consideration intrinsic temporal smoothness among successive overlapping R-fMRI sub-series. To preserve temporal smoothness of R-fMRI sub-series, we suggest to jointly estimate the temporal networks by maximizing a penalized log likelihood using a fused sparse learning algorithm. This sparse learning algorithm encourages temporally correlated networks to have similar network topology and correlation strengths. We design a disease identification framework based on the estimated temporal networks, and group level network property differences and classification results demonstrate the importance of including temporally dynamic R-fMRI scan information to improve diagnosis accuracy of mild cognitive impairment patients.

AB - In conventional resting-state functional MRI (R-fMRI) analysis, functional connectivity is assumed to be temporally stationary, overlooking neural activities or interactions that may happen within the scan duration. Dynamic changes of neural interactions can be reflected by variations of topology and correlation strength in temporally correlated functional connectivity networks. These connectivity networks may potentially capture subtle yet short neural connectivity disruptions induced by disease pathologies. Accordingly, we are motivated to utilize disrupted temporal network properties for improving control-patient classification performance. Specifically, a sliding window approach is firstly employed to generate a sequence of overlapping R-fMRI sub-series. Based on these sub-series, sliding window correlations, which characterize the neural interactions between brain regions, are then computed to construct a series of temporal networks. Individual estimation of these temporal networks using conventional network construction approaches fails to take into consideration intrinsic temporal smoothness among successive overlapping R-fMRI sub-series. To preserve temporal smoothness of R-fMRI sub-series, we suggest to jointly estimate the temporal networks by maximizing a penalized log likelihood using a fused sparse learning algorithm. This sparse learning algorithm encourages temporally correlated networks to have similar network topology and correlation strengths. We design a disease identification framework based on the estimated temporal networks, and group level network property differences and classification results demonstrate the importance of including temporally dynamic R-fMRI scan information to improve diagnosis accuracy of mild cognitive impairment patients.

KW - Mild Cognitive Impairment (MCI)

KW - Resting-state functional MRI (R-fMRI)

KW - Sliding window correlation

KW - Sparse temporal networks

KW - Temporal dynamics

KW - Temporal smoothness

UR - http://www.scopus.com/inward/record.url?scp=84933566531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84933566531&partnerID=8YFLogxK

U2 - 10.1007/s11682-015-9408-2

DO - 10.1007/s11682-015-9408-2

M3 - Article

C2 - 26123390

AN - SCOPUS:84933566531

JO - Brain Imaging and Behavior

JF - Brain Imaging and Behavior

SN - 1931-7557

ER -