Sparse multivariate autoregressive modeling for mild cognitive impairment classification

Yang Li, Chong Yaw Wee, Biao Jie, Ziwen Peng, Dinggang Shen

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Brain connectivity network derived from functional magnetic resonance imaging (fMRI) is becoming increasingly prevalent in the researches related to cognitive and perceptual processes. The capability to detect causal or effective connectivity is highly desirable for understanding the cooperative nature of brain network, particularly when the ultimate goal is to obtain good performance of control-patient classification with biological meaningful interpretations. Understanding directed functional interactions between brain regions via brain connectivity network is a challenging task. Since many genetic and biomedical networks are intrinsically sparse, incorporating sparsity property into connectivity modeling can make the derived models more biologically plausible. Accordingly, we propose an effective connectivity modeling of resting-state fMRI data based on the multivariate autoregressive (MAR) modeling technique, which is widely used to characterize temporal information of dynamic systems. This MAR modeling technique allows for the identification of effective connectivity using the Granger causality concept and reducing the spurious causality connectivity in assessment of directed functional interaction from fMRI data. A forward orthogonal least squares (OLS) regression algorithm is further used to construct a sparse MAR model. By applying the proposed modeling to mild cognitive impairment (MCI) classification, we identify several most discriminative regions, including middle cingulate gyrus, posterior cingulate gyrus, lingual gyrus and caudate regions, in line with results reported in previous findings. A relatively high classification accuracy of 91.89 % is also achieved, with an increment of 5.4 % compared to the fully-connected, non-directional Pearson-correlation-based functional connectivity approach.

Original languageEnglish
Pages (from-to)455-469
Number of pages15
JournalNeuroinformatics
Volume12
Issue number3
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Brain
Gyrus Cinguli
Magnetic Resonance Imaging
Causality
Occipital Lobe
Least-Squares Analysis
Information Systems
Dynamical systems
Cognitive Dysfunction
Research

ASJC Scopus subject areas

  • Neuroscience(all)
  • Information Systems
  • Software

Cite this

Sparse multivariate autoregressive modeling for mild cognitive impairment classification. / Li, Yang; Wee, Chong Yaw; Jie, Biao; Peng, Ziwen; Shen, Dinggang.

In: Neuroinformatics, Vol. 12, No. 3, 01.01.2014, p. 455-469.

Research output: Contribution to journalArticle

Li, Yang ; Wee, Chong Yaw ; Jie, Biao ; Peng, Ziwen ; Shen, Dinggang. / Sparse multivariate autoregressive modeling for mild cognitive impairment classification. In: Neuroinformatics. 2014 ; Vol. 12, No. 3. pp. 455-469.
@article{1dd85e13a199450ab534892da6c9f62e,
title = "Sparse multivariate autoregressive modeling for mild cognitive impairment classification",
abstract = "Brain connectivity network derived from functional magnetic resonance imaging (fMRI) is becoming increasingly prevalent in the researches related to cognitive and perceptual processes. The capability to detect causal or effective connectivity is highly desirable for understanding the cooperative nature of brain network, particularly when the ultimate goal is to obtain good performance of control-patient classification with biological meaningful interpretations. Understanding directed functional interactions between brain regions via brain connectivity network is a challenging task. Since many genetic and biomedical networks are intrinsically sparse, incorporating sparsity property into connectivity modeling can make the derived models more biologically plausible. Accordingly, we propose an effective connectivity modeling of resting-state fMRI data based on the multivariate autoregressive (MAR) modeling technique, which is widely used to characterize temporal information of dynamic systems. This MAR modeling technique allows for the identification of effective connectivity using the Granger causality concept and reducing the spurious causality connectivity in assessment of directed functional interaction from fMRI data. A forward orthogonal least squares (OLS) regression algorithm is further used to construct a sparse MAR model. By applying the proposed modeling to mild cognitive impairment (MCI) classification, we identify several most discriminative regions, including middle cingulate gyrus, posterior cingulate gyrus, lingual gyrus and caudate regions, in line with results reported in previous findings. A relatively high classification accuracy of 91.89 {\%} is also achieved, with an increment of 5.4 {\%} compared to the fully-connected, non-directional Pearson-correlation-based functional connectivity approach.",
keywords = "Effective connectivity, Functional magnetic resonance imaging (fMRI), Mild cognitive impairment (MCI), Orthogonal least squares (OLS), Sparse multivariate autoregressive (MAR) model, Support vector machines (SVMs)",
author = "Yang Li and Wee, {Chong Yaw} and Biao Jie and Ziwen Peng and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s12021-014-9221-x",
language = "English",
volume = "12",
pages = "455--469",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Humana Press",
number = "3",

}

TY - JOUR

T1 - Sparse multivariate autoregressive modeling for mild cognitive impairment classification

AU - Li, Yang

AU - Wee, Chong Yaw

AU - Jie, Biao

AU - Peng, Ziwen

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Brain connectivity network derived from functional magnetic resonance imaging (fMRI) is becoming increasingly prevalent in the researches related to cognitive and perceptual processes. The capability to detect causal or effective connectivity is highly desirable for understanding the cooperative nature of brain network, particularly when the ultimate goal is to obtain good performance of control-patient classification with biological meaningful interpretations. Understanding directed functional interactions between brain regions via brain connectivity network is a challenging task. Since many genetic and biomedical networks are intrinsically sparse, incorporating sparsity property into connectivity modeling can make the derived models more biologically plausible. Accordingly, we propose an effective connectivity modeling of resting-state fMRI data based on the multivariate autoregressive (MAR) modeling technique, which is widely used to characterize temporal information of dynamic systems. This MAR modeling technique allows for the identification of effective connectivity using the Granger causality concept and reducing the spurious causality connectivity in assessment of directed functional interaction from fMRI data. A forward orthogonal least squares (OLS) regression algorithm is further used to construct a sparse MAR model. By applying the proposed modeling to mild cognitive impairment (MCI) classification, we identify several most discriminative regions, including middle cingulate gyrus, posterior cingulate gyrus, lingual gyrus and caudate regions, in line with results reported in previous findings. A relatively high classification accuracy of 91.89 % is also achieved, with an increment of 5.4 % compared to the fully-connected, non-directional Pearson-correlation-based functional connectivity approach.

AB - Brain connectivity network derived from functional magnetic resonance imaging (fMRI) is becoming increasingly prevalent in the researches related to cognitive and perceptual processes. The capability to detect causal or effective connectivity is highly desirable for understanding the cooperative nature of brain network, particularly when the ultimate goal is to obtain good performance of control-patient classification with biological meaningful interpretations. Understanding directed functional interactions between brain regions via brain connectivity network is a challenging task. Since many genetic and biomedical networks are intrinsically sparse, incorporating sparsity property into connectivity modeling can make the derived models more biologically plausible. Accordingly, we propose an effective connectivity modeling of resting-state fMRI data based on the multivariate autoregressive (MAR) modeling technique, which is widely used to characterize temporal information of dynamic systems. This MAR modeling technique allows for the identification of effective connectivity using the Granger causality concept and reducing the spurious causality connectivity in assessment of directed functional interaction from fMRI data. A forward orthogonal least squares (OLS) regression algorithm is further used to construct a sparse MAR model. By applying the proposed modeling to mild cognitive impairment (MCI) classification, we identify several most discriminative regions, including middle cingulate gyrus, posterior cingulate gyrus, lingual gyrus and caudate regions, in line with results reported in previous findings. A relatively high classification accuracy of 91.89 % is also achieved, with an increment of 5.4 % compared to the fully-connected, non-directional Pearson-correlation-based functional connectivity approach.

KW - Effective connectivity

KW - Functional magnetic resonance imaging (fMRI)

KW - Mild cognitive impairment (MCI)

KW - Orthogonal least squares (OLS)

KW - Sparse multivariate autoregressive (MAR) model

KW - Support vector machines (SVMs)

UR - http://www.scopus.com/inward/record.url?scp=84904720191&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904720191&partnerID=8YFLogxK

U2 - 10.1007/s12021-014-9221-x

DO - 10.1007/s12021-014-9221-x

M3 - Article

C2 - 24595922

AN - SCOPUS:84904720191

VL - 12

SP - 455

EP - 469

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

IS - 3

ER -