A supervised singular value decomposition for independent component analysis of fMRI

Ping Bai, Haipeng Shen, Xuemei Huang, Young Truong

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Functional Magnetic Resonance Imaging (fMRI) is a non-invasive technique for studying the brain activity. The data acquisition process results a temporal sequence of 3D brain images. Due to the high sensitivity of MR scanners, spikes are commonly observed in the data. Along with the temporal and spatial features of fMRI data, this artifact raises a challenging problem in the statistical analysis. In this paper, we introduce a supervised singular value decomposition technique as a data reduction step of independent component analysis (ICA), which is an effective tool for exploring spatio-temporal features in fMRI data. Two major advantages are discussed: first, the proposed method improves the robustness of ICA against spikes; second, the method uses the fMRI experimental designs to guide the fully data-driven ICA, yielding a more computationally efficient procedure and highly interpretable results. The advantages are demonstrated using spatio-temporal simulation studies as well as a data analysis.

Original languageEnglish (US)
Pages (from-to)1233-1252
Number of pages20
JournalStatistica Sinica
Volume18
Issue number4
StatePublished - Oct 1 2008

Fingerprint

Functional Magnetic Resonance Imaging
Independent Component Analysis
Singular value decomposition
Spike
Data Reduction
Decomposition Techniques
Scanner
Experimental design
Data Acquisition
Data-driven
Statistical Analysis
Data analysis
Simulation Study
Robustness
Independent component analysis
Functional magnetic resonance imaging
Brain

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Bai, Ping ; Shen, Haipeng ; Huang, Xuemei ; Truong, Young. / A supervised singular value decomposition for independent component analysis of fMRI. In: Statistica Sinica. 2008 ; Vol. 18, No. 4. pp. 1233-1252.
@article{2a60cf9c6061454eb511e2d2a4fcabc1,
title = "A supervised singular value decomposition for independent component analysis of fMRI",
abstract = "Functional Magnetic Resonance Imaging (fMRI) is a non-invasive technique for studying the brain activity. The data acquisition process results a temporal sequence of 3D brain images. Due to the high sensitivity of MR scanners, spikes are commonly observed in the data. Along with the temporal and spatial features of fMRI data, this artifact raises a challenging problem in the statistical analysis. In this paper, we introduce a supervised singular value decomposition technique as a data reduction step of independent component analysis (ICA), which is an effective tool for exploring spatio-temporal features in fMRI data. Two major advantages are discussed: first, the proposed method improves the robustness of ICA against spikes; second, the method uses the fMRI experimental designs to guide the fully data-driven ICA, yielding a more computationally efficient procedure and highly interpretable results. The advantages are demonstrated using spatio-temporal simulation studies as well as a data analysis.",
author = "Ping Bai and Haipeng Shen and Xuemei Huang and Young Truong",
year = "2008",
month = "10",
day = "1",
language = "English (US)",
volume = "18",
pages = "1233--1252",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "4",

}

A supervised singular value decomposition for independent component analysis of fMRI. / Bai, Ping; Shen, Haipeng; Huang, Xuemei; Truong, Young.

In: Statistica Sinica, Vol. 18, No. 4, 01.10.2008, p. 1233-1252.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A supervised singular value decomposition for independent component analysis of fMRI

AU - Bai, Ping

AU - Shen, Haipeng

AU - Huang, Xuemei

AU - Truong, Young

PY - 2008/10/1

Y1 - 2008/10/1

N2 - Functional Magnetic Resonance Imaging (fMRI) is a non-invasive technique for studying the brain activity. The data acquisition process results a temporal sequence of 3D brain images. Due to the high sensitivity of MR scanners, spikes are commonly observed in the data. Along with the temporal and spatial features of fMRI data, this artifact raises a challenging problem in the statistical analysis. In this paper, we introduce a supervised singular value decomposition technique as a data reduction step of independent component analysis (ICA), which is an effective tool for exploring spatio-temporal features in fMRI data. Two major advantages are discussed: first, the proposed method improves the robustness of ICA against spikes; second, the method uses the fMRI experimental designs to guide the fully data-driven ICA, yielding a more computationally efficient procedure and highly interpretable results. The advantages are demonstrated using spatio-temporal simulation studies as well as a data analysis.

AB - Functional Magnetic Resonance Imaging (fMRI) is a non-invasive technique for studying the brain activity. The data acquisition process results a temporal sequence of 3D brain images. Due to the high sensitivity of MR scanners, spikes are commonly observed in the data. Along with the temporal and spatial features of fMRI data, this artifact raises a challenging problem in the statistical analysis. In this paper, we introduce a supervised singular value decomposition technique as a data reduction step of independent component analysis (ICA), which is an effective tool for exploring spatio-temporal features in fMRI data. Two major advantages are discussed: first, the proposed method improves the robustness of ICA against spikes; second, the method uses the fMRI experimental designs to guide the fully data-driven ICA, yielding a more computationally efficient procedure and highly interpretable results. The advantages are demonstrated using spatio-temporal simulation studies as well as a data analysis.

UR - http://www.scopus.com/inward/record.url?scp=60149104077&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60149104077&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:60149104077

VL - 18

SP - 1233

EP - 1252

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 4

ER -