Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning

Research output: Contribution to journalArticleAcademicpeer-review

69 Citations (Scopus)

Abstract

Machine learning and Pattern recognition techniques are being increasingly employed in Functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. Ill typical fMRI applications, pattern recognition algorithms "learn" a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ("brain reading"). In this article, we describe the mathematical foundations of machine learning applications in fMRI We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges Of Using machine learning algorithms in the context of fMRI data analysis.
Original languageEnglish
Pages (from-to)921-934
JournalMagnetic Resonance Imaging
Volume26
Issue number7
DOIs
Publication statusPublished - 1 Jan 2008

Cite this

@article{cb5203b22cd84e13877120ae68056e3c,
title = "Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning",
abstract = "Machine learning and Pattern recognition techniques are being increasingly employed in Functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. Ill typical fMRI applications, pattern recognition algorithms {"}learn{"} a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ({"}brain reading{"}). In this article, we describe the mathematical foundations of machine learning applications in fMRI We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges Of Using machine learning algorithms in the context of fMRI data analysis.",
author = "E. Formisano and {de Martino}, F. and G. Valente",
year = "2008",
month = "1",
day = "1",
doi = "10.1016/j.mri.2008.01.052",
language = "English",
volume = "26",
pages = "921--934",
journal = "Magnetic Resonance Imaging",
issn = "0730-725X",
publisher = "Elsevier Inc.",
number = "7",

}

Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning. / Formisano, E.; de Martino, F.; Valente, G.

In: Magnetic Resonance Imaging, Vol. 26, No. 7, 01.01.2008, p. 921-934.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning

AU - Formisano, E.

AU - de Martino, F.

AU - Valente, G.

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Machine learning and Pattern recognition techniques are being increasingly employed in Functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. Ill typical fMRI applications, pattern recognition algorithms "learn" a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ("brain reading"). In this article, we describe the mathematical foundations of machine learning applications in fMRI We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges Of Using machine learning algorithms in the context of fMRI data analysis.

AB - Machine learning and Pattern recognition techniques are being increasingly employed in Functional magnetic resonance imaging (fMRI) data analysis. By taking into account the full spatial pattern of brain activity measured simultaneously at many locations, these methods allow detecting subtle, non-strictly localized effects that may remain invisible to the conventional analysis with univariate statistical methods. Ill typical fMRI applications, pattern recognition algorithms "learn" a functional relationship between brain response patterns and a perceptual, cognitive or behavioral state of a subject expressed in terms of a label, which may assume discrete (classification) or continuous (regression) values. This learned functional relationship is then used to predict the unseen labels from a new data set ("brain reading"). In this article, we describe the mathematical foundations of machine learning applications in fMRI We focus on two methods, support vector machines and relevance vector machines, which are respectively suited for the classification and regression of fMRI patterns. Furthermore, by means of several examples and applications, we illustrate and discuss the methodological challenges Of Using machine learning algorithms in the context of fMRI data analysis.

U2 - 10.1016/j.mri.2008.01.052

DO - 10.1016/j.mri.2008.01.052

M3 - Article

VL - 26

SP - 921

EP - 934

JO - Magnetic Resonance Imaging

JF - Magnetic Resonance Imaging

SN - 0730-725X

IS - 7

ER -