Alternating diffusion map based fusion of multimodal brain connectivity networks for iq prediction

Li Xiao, Julia M. Stephen, Tony W Wilson, Vince D. Calhoun, Yuping Wang

Research output: Contribution to journalArticle

Abstract

Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture the nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, the FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal n-back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and n-back task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ.

Original languageEnglish (US)
Article number8552463
Pages (from-to)2140-2151
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
Volume66
Issue number8
DOIs
StatePublished - Aug 1 2019

Fingerprint

Brain
Electric fuses
Data fusion
Fractals
Magnetic Resonance Imaging
Geometry

Keywords

  • Alternating diffusion map
  • Classification
  • Data fusion
  • Dimensionality reduction
  • Fmri
  • Functional connectivity
  • Networks

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Alternating diffusion map based fusion of multimodal brain connectivity networks for iq prediction. / Xiao, Li; Stephen, Julia M.; Wilson, Tony W; Calhoun, Vince D.; Wang, Yuping.

In: IEEE Transactions on Biomedical Engineering, Vol. 66, No. 8, 8552463, 01.08.2019, p. 2140-2151.

Research output: Contribution to journalArticle

Xiao, Li ; Stephen, Julia M. ; Wilson, Tony W ; Calhoun, Vince D. ; Wang, Yuping. / Alternating diffusion map based fusion of multimodal brain connectivity networks for iq prediction. In: IEEE Transactions on Biomedical Engineering. 2019 ; Vol. 66, No. 8. pp. 2140-2151.
@article{595dad9b7de74ba89f2154a9215ba810,
title = "Alternating diffusion map based fusion of multimodal brain connectivity networks for iq prediction",
abstract = "Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture the nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, the FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal n-back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and n-back task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ.",
keywords = "Alternating diffusion map, Classification, Data fusion, Dimensionality reduction, Fmri, Functional connectivity, Networks",
author = "Li Xiao and Stephen, {Julia M.} and Wilson, {Tony W} and Calhoun, {Vince D.} and Yuping Wang",
year = "2019",
month = "8",
day = "1",
doi = "10.1109/TBME.2018.2884129",
language = "English (US)",
volume = "66",
pages = "2140--2151",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "8",

}

TY - JOUR

T1 - Alternating diffusion map based fusion of multimodal brain connectivity networks for iq prediction

AU - Xiao, Li

AU - Stephen, Julia M.

AU - Wilson, Tony W

AU - Calhoun, Vince D.

AU - Wang, Yuping

PY - 2019/8/1

Y1 - 2019/8/1

N2 - Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture the nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, the FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal n-back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and n-back task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ.

AB - Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture the nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, the FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal n-back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and n-back task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ.

KW - Alternating diffusion map

KW - Classification

KW - Data fusion

KW - Dimensionality reduction

KW - Fmri

KW - Functional connectivity

KW - Networks

UR - http://www.scopus.com/inward/record.url?scp=85057779707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057779707&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2884129

DO - 10.1109/TBME.2018.2884129

M3 - Article

VL - 66

SP - 2140

EP - 2151

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 8

M1 - 8552463

ER -