Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique

Bhaskar Sen, Keshab K Parhi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Blind source separation (BSS) using independent component based analysis (e.g., probabilistic ICA and infomax ICA) have been studied in-depth to extract common hemodynamic sources for a group of functional magnetic resonance images (fMRI). The inherent assumption here is that the sources must be non-Gaussian. For most of the real world data, the decomposition is non-unique. Furthermore, there is no quantitative way to determine the component(s) of interest common for the group. This paper shows that using a novel constrained Parallel Factor Analysis (PARAFAC)-based tensor decomposition, one can extract the common task signals and spatial maps from a group of noisy fMRI as rank-1 tensors. The extracted hemodynamic signals have very high correlation with ideal hemodynamic response. A quantitative algorithm to extract common components for a group of subjects is also presented. The modified decomposition preserves the uniqueness under mild conditions which is the most attractive feature for any PARAFAC-based tensor decomposition approach.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1113-1117
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Factor analysis
Magnetic resonance
Functional groups
Tensors
Hemodynamics
Decomposition
Independent component analysis
Blind source separation

Keywords

  • PARAFAC
  • fMRI
  • spatial map
  • task signal
  • tensor decomposition

Cite this

Sen, B., & Parhi, K. K. (2017). Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 1113-1117). [7952329] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952329

Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique. / Sen, Bhaskar; Parhi, Keshab K.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1113-1117 7952329 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sen, B & Parhi, KK 2017, Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952329, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1113-1117, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. https://doi.org/10.1109/ICASSP.2017.7952329
Sen B, Parhi KK. Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1113-1117. 7952329. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2017.7952329
Sen, Bhaskar ; Parhi, Keshab K. / Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1113-1117 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{8f1b46e59e5343caa3d7668cbcbbd104,
title = "Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique",
abstract = "Blind source separation (BSS) using independent component based analysis (e.g., probabilistic ICA and infomax ICA) have been studied in-depth to extract common hemodynamic sources for a group of functional magnetic resonance images (fMRI). The inherent assumption here is that the sources must be non-Gaussian. For most of the real world data, the decomposition is non-unique. Furthermore, there is no quantitative way to determine the component(s) of interest common for the group. This paper shows that using a novel constrained Parallel Factor Analysis (PARAFAC)-based tensor decomposition, one can extract the common task signals and spatial maps from a group of noisy fMRI as rank-1 tensors. The extracted hemodynamic signals have very high correlation with ideal hemodynamic response. A quantitative algorithm to extract common components for a group of subjects is also presented. The modified decomposition preserves the uniqueness under mild conditions which is the most attractive feature for any PARAFAC-based tensor decomposition approach.",
keywords = "PARAFAC, fMRI, spatial map, task signal, tensor decomposition",
author = "Bhaskar Sen and Parhi, {Keshab K}",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952329",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1113--1117",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",

}

TY - GEN

T1 - Extraction of common task signals and spatial maps from group fMRI using a PARAFAC-based tensor decomposition technique

AU - Sen, Bhaskar

AU - Parhi, Keshab K

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Blind source separation (BSS) using independent component based analysis (e.g., probabilistic ICA and infomax ICA) have been studied in-depth to extract common hemodynamic sources for a group of functional magnetic resonance images (fMRI). The inherent assumption here is that the sources must be non-Gaussian. For most of the real world data, the decomposition is non-unique. Furthermore, there is no quantitative way to determine the component(s) of interest common for the group. This paper shows that using a novel constrained Parallel Factor Analysis (PARAFAC)-based tensor decomposition, one can extract the common task signals and spatial maps from a group of noisy fMRI as rank-1 tensors. The extracted hemodynamic signals have very high correlation with ideal hemodynamic response. A quantitative algorithm to extract common components for a group of subjects is also presented. The modified decomposition preserves the uniqueness under mild conditions which is the most attractive feature for any PARAFAC-based tensor decomposition approach.

AB - Blind source separation (BSS) using independent component based analysis (e.g., probabilistic ICA and infomax ICA) have been studied in-depth to extract common hemodynamic sources for a group of functional magnetic resonance images (fMRI). The inherent assumption here is that the sources must be non-Gaussian. For most of the real world data, the decomposition is non-unique. Furthermore, there is no quantitative way to determine the component(s) of interest common for the group. This paper shows that using a novel constrained Parallel Factor Analysis (PARAFAC)-based tensor decomposition, one can extract the common task signals and spatial maps from a group of noisy fMRI as rank-1 tensors. The extracted hemodynamic signals have very high correlation with ideal hemodynamic response. A quantitative algorithm to extract common components for a group of subjects is also presented. The modified decomposition preserves the uniqueness under mild conditions which is the most attractive feature for any PARAFAC-based tensor decomposition approach.

KW - PARAFAC

KW - fMRI

KW - spatial map

KW - task signal

KW - tensor decomposition

UR - http://www.scopus.com/inward/record.url?scp=85023765776&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85023765776&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952329

DO - 10.1109/ICASSP.2017.7952329

M3 - Conference contribution

AN - SCOPUS:85023765776

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

SP - 1113

EP - 1117

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -