Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification

Renping Yu, Han Zhang, Le An, Xiaobo Chen, Zhihui Wei, Dinggang Shen

Research output: Research - peer-reviewArticle

  • 4 Citations

Abstract

Brain functional network analysis has shown great potential in understanding brain functions and also in identifying biomarkers for brain diseases, such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). In these applications, accurate construction of biologically meaningful brain network is critical. Sparse learning has been widely used for brain network construction; however, its l1-norm penalty simply penalizes each edge of a brain network equally, without considering the original connectivity strength which is one of the most important inherent linkwise characters. Besides, based on the similarity of the linkwise connectivity, brain network shows prominent group structure (i.e., a set of edges sharing similar attributes). In this article, we propose a novel brain functional network modeling framework with a “connectivity strength-weighted sparse group constraint.” In particular, the network modeling can be optimized by considering both raw connectivity strength and its group structure, without losing the merit of sparsity. Our proposed method is applied to MCI classification, a challenging task for early AD diagnosis. Experimental results based on the resting-state functional MRI, from 50 MCI patients and 49 healthy controls, show that our proposed method is more effective (i.e., achieving a significantly higher classification accuracy, 84.8%) than other competing methods (e.g., sparse representation, accuracy = 65.6%). Post hoc inspection of the informative features further shows more biologically meaningful brain functional connectivities obtained by our proposed method. Hum Brain Mapp 38:2370–2383, 2017.

LanguageEnglish (US)
Pages2370-2383
Number of pages14
JournalHuman Brain Mapping
Volume38
Issue number5
DOIs
StatePublished - May 1 2017

Fingerprint

Brain
Cognitive Dysfunction
Group Structure
Alzheimer Disease
Brain Diseases
Biomarkers
Magnetic Resonance Imaging
Learning

Keywords

  • brain network
  • disease classification
  • functional connectivity
  • mild cognitive impairment (MCI)
  • sparse representation

ASJC Scopus subject areas

  • Anatomy
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Neurology
  • Clinical Neurology

Cite this

Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification. / Yu, Renping; Zhang, Han; An, Le; Chen, Xiaobo; Wei, Zhihui; Shen, Dinggang.

In: Human Brain Mapping, Vol. 38, No. 5, 01.05.2017, p. 2370-2383.

Research output: Research - peer-reviewArticle

Yu, Renping ; Zhang, Han ; An, Le ; Chen, Xiaobo ; Wei, Zhihui ; Shen, Dinggang. / Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification. In: Human Brain Mapping. 2017 ; Vol. 38, No. 5. pp. 2370-2383
@article{fb692760fc5e4fecb2053ed631c068b5,
title = "Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification",
abstract = "Brain functional network analysis has shown great potential in understanding brain functions and also in identifying biomarkers for brain diseases, such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). In these applications, accurate construction of biologically meaningful brain network is critical. Sparse learning has been widely used for brain network construction; however, its l1-norm penalty simply penalizes each edge of a brain network equally, without considering the original connectivity strength which is one of the most important inherent linkwise characters. Besides, based on the similarity of the linkwise connectivity, brain network shows prominent group structure (i.e., a set of edges sharing similar attributes). In this article, we propose a novel brain functional network modeling framework with a “connectivity strength-weighted sparse group constraint.” In particular, the network modeling can be optimized by considering both raw connectivity strength and its group structure, without losing the merit of sparsity. Our proposed method is applied to MCI classification, a challenging task for early AD diagnosis. Experimental results based on the resting-state functional MRI, from 50 MCI patients and 49 healthy controls, show that our proposed method is more effective (i.e., achieving a significantly higher classification accuracy, 84.8%) than other competing methods (e.g., sparse representation, accuracy = 65.6%). Post hoc inspection of the informative features further shows more biologically meaningful brain functional connectivities obtained by our proposed method. Hum Brain Mapp 38:2370–2383, 2017.",
keywords = "brain network, disease classification, functional connectivity, mild cognitive impairment (MCI), sparse representation",
author = "Renping Yu and Han Zhang and Le An and Xiaobo Chen and Zhihui Wei and Dinggang Shen",
year = "2017",
month = "5",
doi = "10.1002/hbm.23524",
volume = "38",
pages = "2370--2383",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "5",

}

TY - JOUR

T1 - Connectivity strength-weighted sparse group representation-based brain network construction for MCI classification

AU - Yu,Renping

AU - Zhang,Han

AU - An,Le

AU - Chen,Xiaobo

AU - Wei,Zhihui

AU - Shen,Dinggang

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Brain functional network analysis has shown great potential in understanding brain functions and also in identifying biomarkers for brain diseases, such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). In these applications, accurate construction of biologically meaningful brain network is critical. Sparse learning has been widely used for brain network construction; however, its l1-norm penalty simply penalizes each edge of a brain network equally, without considering the original connectivity strength which is one of the most important inherent linkwise characters. Besides, based on the similarity of the linkwise connectivity, brain network shows prominent group structure (i.e., a set of edges sharing similar attributes). In this article, we propose a novel brain functional network modeling framework with a “connectivity strength-weighted sparse group constraint.” In particular, the network modeling can be optimized by considering both raw connectivity strength and its group structure, without losing the merit of sparsity. Our proposed method is applied to MCI classification, a challenging task for early AD diagnosis. Experimental results based on the resting-state functional MRI, from 50 MCI patients and 49 healthy controls, show that our proposed method is more effective (i.e., achieving a significantly higher classification accuracy, 84.8%) than other competing methods (e.g., sparse representation, accuracy = 65.6%). Post hoc inspection of the informative features further shows more biologically meaningful brain functional connectivities obtained by our proposed method. Hum Brain Mapp 38:2370–2383, 2017.

AB - Brain functional network analysis has shown great potential in understanding brain functions and also in identifying biomarkers for brain diseases, such as Alzheimer's disease (AD) and its early stage, mild cognitive impairment (MCI). In these applications, accurate construction of biologically meaningful brain network is critical. Sparse learning has been widely used for brain network construction; however, its l1-norm penalty simply penalizes each edge of a brain network equally, without considering the original connectivity strength which is one of the most important inherent linkwise characters. Besides, based on the similarity of the linkwise connectivity, brain network shows prominent group structure (i.e., a set of edges sharing similar attributes). In this article, we propose a novel brain functional network modeling framework with a “connectivity strength-weighted sparse group constraint.” In particular, the network modeling can be optimized by considering both raw connectivity strength and its group structure, without losing the merit of sparsity. Our proposed method is applied to MCI classification, a challenging task for early AD diagnosis. Experimental results based on the resting-state functional MRI, from 50 MCI patients and 49 healthy controls, show that our proposed method is more effective (i.e., achieving a significantly higher classification accuracy, 84.8%) than other competing methods (e.g., sparse representation, accuracy = 65.6%). Post hoc inspection of the informative features further shows more biologically meaningful brain functional connectivities obtained by our proposed method. Hum Brain Mapp 38:2370–2383, 2017.

KW - brain network

KW - disease classification

KW - functional connectivity

KW - mild cognitive impairment (MCI)

KW - sparse representation

UR - http://www.scopus.com/inward/record.url?scp=85011708016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011708016&partnerID=8YFLogxK

U2 - 10.1002/hbm.23524

DO - 10.1002/hbm.23524

M3 - Article

VL - 38

SP - 2370

EP - 2383

JO - Human Brain Mapping

T2 - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 5

ER -