Identification of MCI individuals using structural and functional connectivity networks

Chong Yaw Wee, Pew Thian Yap, Daoqiang Zhang, Kevin Denny, Jeffrey N. Browndyke, Guy G. Potter, Kathleen A. Welsh-Bohmer, Lihong Wang, Dinggang Shen

Research output: Contribution to journalArticle

207 Citations (Scopus)

Abstract

Different imaging modalities provide essential complementary information that can be used to enhance our understanding of brain disorders. This study focuses on integrating multiple imaging modalities to identify individuals at risk for mild cognitive impairment (MCI). MCI, often an early stage of Alzheimer's disease (AD), is difficult to diagnose due to its very mild or insignificant symptoms of cognitive impairment. Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible, thus providing new avenues for brain diseases classification. Employing multiple-kernel Support Vector Machines (SVMs), we attempt to integrate information from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) for improving classification performance. Our results indicate that the multimodality classification approach yields statistically significant improvement in accuracy over using each modality independently. The classification accuracy obtained by the proposed method is 96.3%, which is an increase of at least 7.4% from the single modality-based methods and the direct data fusion method. A cross-validation estimation of the generalization performance gives an area of 0.953 under the receiver operating characteristic (ROC) curve, indicating excellent diagnostic power. The multimodality classification approach hence allows more accurate early detection of brain abnormalities with greater sensitivity.

Original languageEnglish
Pages (from-to)2045-2056
Number of pages12
JournalNeuroImage
Volume59
Issue number3
DOIs
Publication statusPublished - 2012 Feb 1
Externally publishedYes

Fingerprint

Brain Diseases
Brain
Diffusion Tensor Imaging
Nervous System Diseases
ROC Curve
Alzheimer Disease
Magnetic Resonance Imaging
Cognitive Dysfunction
Support Vector Machine
Power (Psychology)

Keywords

  • Alzheimer's disease (AD)
  • Brain network analysis multiple-kernel Support Vector Machines (SVMs)
  • Diffusion tensor imaging (DTI)
  • Mild cognitive impairment (MCI)
  • Multimodality representation
  • Resting-state functional magnetic resonance imaging (rs-fMRI)

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Wee, C. Y., Yap, P. T., Zhang, D., Denny, K., Browndyke, J. N., Potter, G. G., ... Shen, D. (2012). Identification of MCI individuals using structural and functional connectivity networks. NeuroImage, 59(3), 2045-2056. https://doi.org/10.1016/j.neuroimage.2011.10.015

Identification of MCI individuals using structural and functional connectivity networks. / Wee, Chong Yaw; Yap, Pew Thian; Zhang, Daoqiang; Denny, Kevin; Browndyke, Jeffrey N.; Potter, Guy G.; Welsh-Bohmer, Kathleen A.; Wang, Lihong; Shen, Dinggang.

In: NeuroImage, Vol. 59, No. 3, 01.02.2012, p. 2045-2056.

Research output: Contribution to journalArticle

Wee, CY, Yap, PT, Zhang, D, Denny, K, Browndyke, JN, Potter, GG, Welsh-Bohmer, KA, Wang, L & Shen, D 2012, 'Identification of MCI individuals using structural and functional connectivity networks', NeuroImage, vol. 59, no. 3, pp. 2045-2056. https://doi.org/10.1016/j.neuroimage.2011.10.015
Wee CY, Yap PT, Zhang D, Denny K, Browndyke JN, Potter GG et al. Identification of MCI individuals using structural and functional connectivity networks. NeuroImage. 2012 Feb 1;59(3):2045-2056. https://doi.org/10.1016/j.neuroimage.2011.10.015
Wee, Chong Yaw ; Yap, Pew Thian ; Zhang, Daoqiang ; Denny, Kevin ; Browndyke, Jeffrey N. ; Potter, Guy G. ; Welsh-Bohmer, Kathleen A. ; Wang, Lihong ; Shen, Dinggang. / Identification of MCI individuals using structural and functional connectivity networks. In: NeuroImage. 2012 ; Vol. 59, No. 3. pp. 2045-2056.
@article{5ad425b9b88f4c0a9e22321cfa9e8c20,
title = "Identification of MCI individuals using structural and functional connectivity networks",
abstract = "Different imaging modalities provide essential complementary information that can be used to enhance our understanding of brain disorders. This study focuses on integrating multiple imaging modalities to identify individuals at risk for mild cognitive impairment (MCI). MCI, often an early stage of Alzheimer's disease (AD), is difficult to diagnose due to its very mild or insignificant symptoms of cognitive impairment. Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible, thus providing new avenues for brain diseases classification. Employing multiple-kernel Support Vector Machines (SVMs), we attempt to integrate information from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) for improving classification performance. Our results indicate that the multimodality classification approach yields statistically significant improvement in accuracy over using each modality independently. The classification accuracy obtained by the proposed method is 96.3{\%}, which is an increase of at least 7.4{\%} from the single modality-based methods and the direct data fusion method. A cross-validation estimation of the generalization performance gives an area of 0.953 under the receiver operating characteristic (ROC) curve, indicating excellent diagnostic power. The multimodality classification approach hence allows more accurate early detection of brain abnormalities with greater sensitivity.",
keywords = "Alzheimer's disease (AD), Brain network analysis multiple-kernel Support Vector Machines (SVMs), Diffusion tensor imaging (DTI), Mild cognitive impairment (MCI), Multimodality representation, Resting-state functional magnetic resonance imaging (rs-fMRI)",
author = "Wee, {Chong Yaw} and Yap, {Pew Thian} and Daoqiang Zhang and Kevin Denny and Browndyke, {Jeffrey N.} and Potter, {Guy G.} and Welsh-Bohmer, {Kathleen A.} and Lihong Wang and Dinggang Shen",
year = "2012",
month = "2",
day = "1",
doi = "10.1016/j.neuroimage.2011.10.015",
language = "English",
volume = "59",
pages = "2045--2056",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Identification of MCI individuals using structural and functional connectivity networks

AU - Wee, Chong Yaw

AU - Yap, Pew Thian

AU - Zhang, Daoqiang

AU - Denny, Kevin

AU - Browndyke, Jeffrey N.

AU - Potter, Guy G.

AU - Welsh-Bohmer, Kathleen A.

AU - Wang, Lihong

AU - Shen, Dinggang

PY - 2012/2/1

Y1 - 2012/2/1

N2 - Different imaging modalities provide essential complementary information that can be used to enhance our understanding of brain disorders. This study focuses on integrating multiple imaging modalities to identify individuals at risk for mild cognitive impairment (MCI). MCI, often an early stage of Alzheimer's disease (AD), is difficult to diagnose due to its very mild or insignificant symptoms of cognitive impairment. Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible, thus providing new avenues for brain diseases classification. Employing multiple-kernel Support Vector Machines (SVMs), we attempt to integrate information from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) for improving classification performance. Our results indicate that the multimodality classification approach yields statistically significant improvement in accuracy over using each modality independently. The classification accuracy obtained by the proposed method is 96.3%, which is an increase of at least 7.4% from the single modality-based methods and the direct data fusion method. A cross-validation estimation of the generalization performance gives an area of 0.953 under the receiver operating characteristic (ROC) curve, indicating excellent diagnostic power. The multimodality classification approach hence allows more accurate early detection of brain abnormalities with greater sensitivity.

AB - Different imaging modalities provide essential complementary information that can be used to enhance our understanding of brain disorders. This study focuses on integrating multiple imaging modalities to identify individuals at risk for mild cognitive impairment (MCI). MCI, often an early stage of Alzheimer's disease (AD), is difficult to diagnose due to its very mild or insignificant symptoms of cognitive impairment. Recent emergence of brain network analysis has made characterization of neurological disorders at a whole-brain connectivity level possible, thus providing new avenues for brain diseases classification. Employing multiple-kernel Support Vector Machines (SVMs), we attempt to integrate information from diffusion tensor imaging (DTI) and resting-state functional magnetic resonance imaging (rs-fMRI) for improving classification performance. Our results indicate that the multimodality classification approach yields statistically significant improvement in accuracy over using each modality independently. The classification accuracy obtained by the proposed method is 96.3%, which is an increase of at least 7.4% from the single modality-based methods and the direct data fusion method. A cross-validation estimation of the generalization performance gives an area of 0.953 under the receiver operating characteristic (ROC) curve, indicating excellent diagnostic power. The multimodality classification approach hence allows more accurate early detection of brain abnormalities with greater sensitivity.

KW - Alzheimer's disease (AD)

KW - Brain network analysis multiple-kernel Support Vector Machines (SVMs)

KW - Diffusion tensor imaging (DTI)

KW - Mild cognitive impairment (MCI)

KW - Multimodality representation

KW - Resting-state functional magnetic resonance imaging (rs-fMRI)

UR - http://www.scopus.com/inward/record.url?scp=84855453290&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855453290&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2011.10.015

DO - 10.1016/j.neuroimage.2011.10.015

M3 - Article

C2 - 22019883

AN - SCOPUS:84855453290

VL - 59

SP - 2045

EP - 2056

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -