Multi-kernel based nonlinear models for connectivity identification of brain networks

G. V. Karanikolas; Georgios B Giannakis; K. Slavakis; R. M. Leahy

doi:10.1109/ICASSP.2016.7472892

Multi-kernel based nonlinear models for connectivity identification of brain networks

G. V. Karanikolas
, Georgios B Giannakis
, K. Slavakis
, R. M. Leahy

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

47 Scopus citations

Abstract

Partial correlations (PCs) of functional magnetic resonance imaging (fMRI) time series play a principal role in revealing connectivity of brain networks. To explore nonlinear behavior of the blood-oxygen-level dependent signal, the present work postulates a kernel-based nonlinear connectivity model based on which it obtains topology revealing PCs. Instead of relying on a single predefined kernel, a data-driven approach is advocated to learn the combination of multiple kernel functions that optimizes the data fit. Synthetically generated data based on both a dynamic causal and a linear model are used to validate the proposed approach in resting-state fMRI scenarios, highlighting the gains in edge detection performance when compared with the popular linear PC method. Tests on real fMRI data demonstrate that connectivity patterns revealed by linear and nonlinear models are different.

Original language	English (US)
Title of host publication	2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6315-6319
Number of pages	5
ISBN (Electronic)	9781479999880
DOIs	https://doi.org/10.1109/ICASSP.2016.7472892
State	Published - May 18 2016
Event	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China Duration: Mar 20 2016 → Mar 25 2016

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2016-May
ISSN (Print)	1520-6149

Other

Other	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/Territory	China
City	Shanghai
Period	3/20/16 → 3/25/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

fMRI
kernel-based regression
multiple kernel learning
partial correlation

Publisher link

10.1109/ICASSP.2016.7472892

Find It

Find It at U of M Libraries

Cite this

Karanikolas, G. V., Giannakis, G. B., Slavakis, K., & Leahy, R. M. (2016). Multi-kernel based nonlinear models for connectivity identification of brain networks. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (pp. 6315-6319). Article 7472892 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2016-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472892

Multi-kernel based nonlinear models for connectivity identification of brain networks. / Karanikolas, G. V.; Giannakis, Georgios B; Slavakis, K. et al.
2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 6315-6319 7472892 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2016-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Karanikolas, GV, Giannakis, GB, Slavakis, K & Leahy, RM 2016, Multi-kernel based nonlinear models for connectivity identification of brain networks. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings., 7472892, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2016-May, Institute of Electrical and Electronics Engineers Inc., pp. 6315-6319, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 3/20/16. https://doi.org/10.1109/ICASSP.2016.7472892

Karanikolas GV, Giannakis GB, Slavakis K, Leahy RM. Multi-kernel based nonlinear models for connectivity identification of brain networks. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 6315-6319. 7472892. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2016.7472892

Karanikolas, G. V. ; Giannakis, Georgios B ; Slavakis, K. et al. / Multi-kernel based nonlinear models for connectivity identification of brain networks. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 6315-6319 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{10cfdf168e6744ed80f61b546c8934c9,

title = "Multi-kernel based nonlinear models for connectivity identification of brain networks",

abstract = "Partial correlations (PCs) of functional magnetic resonance imaging (fMRI) time series play a principal role in revealing connectivity of brain networks. To explore nonlinear behavior of the blood-oxygen-level dependent signal, the present work postulates a kernel-based nonlinear connectivity model based on which it obtains topology revealing PCs. Instead of relying on a single predefined kernel, a data-driven approach is advocated to learn the combination of multiple kernel functions that optimizes the data fit. Synthetically generated data based on both a dynamic causal and a linear model are used to validate the proposed approach in resting-state fMRI scenarios, highlighting the gains in edge detection performance when compared with the popular linear PC method. Tests on real fMRI data demonstrate that connectivity patterns revealed by linear and nonlinear models are different.",

keywords = "fMRI, kernel-based regression, multiple kernel learning, partial correlation",

author = "Karanikolas, \{G. V.\} and Giannakis, \{Georgios B\} and K. Slavakis and Leahy, \{R. M.\}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

year = "2016",

month = may,

day = "18",

doi = "10.1109/ICASSP.2016.7472892",

language = "English (US)",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6315--6319",

booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",

}

TY - GEN

T1 - Multi-kernel based nonlinear models for connectivity identification of brain networks

AU - Karanikolas, G. V.

AU - Giannakis, Georgios B

AU - Slavakis, K.

AU - Leahy, R. M.

PY - 2016/5/18

Y1 - 2016/5/18

N2 - Partial correlations (PCs) of functional magnetic resonance imaging (fMRI) time series play a principal role in revealing connectivity of brain networks. To explore nonlinear behavior of the blood-oxygen-level dependent signal, the present work postulates a kernel-based nonlinear connectivity model based on which it obtains topology revealing PCs. Instead of relying on a single predefined kernel, a data-driven approach is advocated to learn the combination of multiple kernel functions that optimizes the data fit. Synthetically generated data based on both a dynamic causal and a linear model are used to validate the proposed approach in resting-state fMRI scenarios, highlighting the gains in edge detection performance when compared with the popular linear PC method. Tests on real fMRI data demonstrate that connectivity patterns revealed by linear and nonlinear models are different.

AB - Partial correlations (PCs) of functional magnetic resonance imaging (fMRI) time series play a principal role in revealing connectivity of brain networks. To explore nonlinear behavior of the blood-oxygen-level dependent signal, the present work postulates a kernel-based nonlinear connectivity model based on which it obtains topology revealing PCs. Instead of relying on a single predefined kernel, a data-driven approach is advocated to learn the combination of multiple kernel functions that optimizes the data fit. Synthetically generated data based on both a dynamic causal and a linear model are used to validate the proposed approach in resting-state fMRI scenarios, highlighting the gains in edge detection performance when compared with the popular linear PC method. Tests on real fMRI data demonstrate that connectivity patterns revealed by linear and nonlinear models are different.

KW - fMRI

KW - kernel-based regression

KW - multiple kernel learning

KW - partial correlation

UR - https://www.scopus.com/pages/publications/84973367069

UR - https://www.scopus.com/pages/publications/84973367069#tab=citedBy

U2 - 10.1109/ICASSP.2016.7472892

DO - 10.1109/ICASSP.2016.7472892

M3 - Conference contribution

AN - SCOPUS:84973367069

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 6315

EP - 6319

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

Y2 - 20 March 2016 through 25 March 2016

ER -

Multi-kernel based nonlinear models for connectivity identification of brain networks

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this