Integration of network topological and connectivity properties for neuroimaging classification

Biao Jie, Daoqiang Zhang, Wei Gao, Qian Wang, Chong Yaw Wee, Dinggang Shen

Research output: Contribution to journalArticle

69 Citations (Scopus)

Abstract

Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results.

Original languageEnglish
Article number6617721
Pages (from-to)576-589
Number of pages14
JournalIEEE Transactions on Biomedical Engineering
Volume61
Issue number2
DOIs
Publication statusPublished - 2014 Feb 1

Fingerprint

Neuroimaging
Brain
Alzheimer Disease
Neurodegenerative diseases
Electric fuses
Learning systems
Neurodegenerative Diseases
Healthy Volunteers
Learning
Parturition
Cognitive Dysfunction

Keywords

  • Connectivity network
  • connectivity property
  • mild cognitive impairment (MCI)
  • multikernel learning (MKL)
  • topological property

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Integration of network topological and connectivity properties for neuroimaging classification. / Jie, Biao; Zhang, Daoqiang; Gao, Wei; Wang, Qian; Wee, Chong Yaw; Shen, Dinggang.

In: IEEE Transactions on Biomedical Engineering, Vol. 61, No. 2, 6617721, 01.02.2014, p. 576-589.

Research output: Contribution to journalArticle

Jie, Biao ; Zhang, Daoqiang ; Gao, Wei ; Wang, Qian ; Wee, Chong Yaw ; Shen, Dinggang. / Integration of network topological and connectivity properties for neuroimaging classification. In: IEEE Transactions on Biomedical Engineering. 2014 ; Vol. 61, No. 2. pp. 576-589.
@article{e9e745f9562d40d188a4ae562e80e62a,
title = "Integration of network topological and connectivity properties for neuroimaging classification",
abstract = "Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9{\%}, which is 10.8{\%} better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results.",
keywords = "Connectivity network, connectivity property, mild cognitive impairment (MCI), multikernel learning (MKL), topological property",
author = "Biao Jie and Daoqiang Zhang and Wei Gao and Qian Wang and Wee, {Chong Yaw} and Dinggang Shen",
year = "2014",
month = "2",
day = "1",
doi = "10.1109/TBME.2013.2284195",
language = "English",
volume = "61",
pages = "576--589",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "2",

}

TY - JOUR

T1 - Integration of network topological and connectivity properties for neuroimaging classification

AU - Jie, Biao

AU - Zhang, Daoqiang

AU - Gao, Wei

AU - Wang, Qian

AU - Wee, Chong Yaw

AU - Shen, Dinggang

PY - 2014/2/1

Y1 - 2014/2/1

N2 - Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results.

AB - Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer's disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results.

KW - Connectivity network

KW - connectivity property

KW - mild cognitive impairment (MCI)

KW - multikernel learning (MKL)

KW - topological property

UR - http://www.scopus.com/inward/record.url?scp=84893330870&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893330870&partnerID=8YFLogxK

U2 - 10.1109/TBME.2013.2284195

DO - 10.1109/TBME.2013.2284195

M3 - Article

C2 - 24108708

AN - SCOPUS:84893330870

VL - 61

SP - 576

EP - 589

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 2

M1 - 6617721

ER -