Modelling with independent components

Christian Beckmann

Research output: Contribution to journalArticleAcademicpeer-review

124 Citations (Scopus)

Abstract

Independent Component Analysis (ICA) is a computational technique for identifying hidden statistically independent sources from multivariate data. In its basic form, ICA decomposes a 2D data matrix (e.g. time × voxels) into separate components that have distinct characteristics. In FMRI it is used to identify hidden FMRI signals (such as activations). Since the first application of ICA to Functional Magnetic Resonance Imaging (FMRI) in 1998, this technique has developed into a powerful tool for data exploration in cognitive and clinical neurosciences. In this contribution to the commemorative issue 20 years of FMRI I will briefly describe the basic principles behind ICA, discuss the probabilistic extension to ICA and touch on what I think are some of the most notorious loose ends. Further, I will describe some of the most powerful ‘killer’ applications and finally share some thoughts on where I believe the most promising future developments will lie
Original languageUndefined
Pages (from-to)891-901
JournalNeuroImage
Volume62
Issue number2
DOIs
Publication statusPublished - 2012

Keywords

  • METIS-292310
  • IR-82992

Cite this

Beckmann, Christian. / Modelling with independent components. In: NeuroImage. 2012 ; Vol. 62, No. 2. pp. 891-901.
@article{ca1911d169ac4908a2009d20ce3c1146,
title = "Modelling with independent components",
abstract = "Independent Component Analysis (ICA) is a computational technique for identifying hidden statistically independent sources from multivariate data. In its basic form, ICA decomposes a 2D data matrix (e.g. time × voxels) into separate components that have distinct characteristics. In FMRI it is used to identify hidden FMRI signals (such as activations). Since the first application of ICA to Functional Magnetic Resonance Imaging (FMRI) in 1998, this technique has developed into a powerful tool for data exploration in cognitive and clinical neurosciences. In this contribution to the commemorative issue 20 years of FMRI I will briefly describe the basic principles behind ICA, discuss the probabilistic extension to ICA and touch on what I think are some of the most notorious loose ends. Further, I will describe some of the most powerful ‘killer’ applications and finally share some thoughts on where I believe the most promising future developments will lie",
keywords = "METIS-292310, IR-82992",
author = "Christian Beckmann",
year = "2012",
doi = "10.1016/j.neuroimage.2012.02.020",
language = "Undefined",
volume = "62",
pages = "891--901",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

Modelling with independent components. / Beckmann, Christian.

In: NeuroImage, Vol. 62, No. 2, 2012, p. 891-901.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Modelling with independent components

AU - Beckmann, Christian

PY - 2012

Y1 - 2012

N2 - Independent Component Analysis (ICA) is a computational technique for identifying hidden statistically independent sources from multivariate data. In its basic form, ICA decomposes a 2D data matrix (e.g. time × voxels) into separate components that have distinct characteristics. In FMRI it is used to identify hidden FMRI signals (such as activations). Since the first application of ICA to Functional Magnetic Resonance Imaging (FMRI) in 1998, this technique has developed into a powerful tool for data exploration in cognitive and clinical neurosciences. In this contribution to the commemorative issue 20 years of FMRI I will briefly describe the basic principles behind ICA, discuss the probabilistic extension to ICA and touch on what I think are some of the most notorious loose ends. Further, I will describe some of the most powerful ‘killer’ applications and finally share some thoughts on where I believe the most promising future developments will lie

AB - Independent Component Analysis (ICA) is a computational technique for identifying hidden statistically independent sources from multivariate data. In its basic form, ICA decomposes a 2D data matrix (e.g. time × voxels) into separate components that have distinct characteristics. In FMRI it is used to identify hidden FMRI signals (such as activations). Since the first application of ICA to Functional Magnetic Resonance Imaging (FMRI) in 1998, this technique has developed into a powerful tool for data exploration in cognitive and clinical neurosciences. In this contribution to the commemorative issue 20 years of FMRI I will briefly describe the basic principles behind ICA, discuss the probabilistic extension to ICA and touch on what I think are some of the most notorious loose ends. Further, I will describe some of the most powerful ‘killer’ applications and finally share some thoughts on where I believe the most promising future developments will lie

KW - METIS-292310

KW - IR-82992

U2 - 10.1016/j.neuroimage.2012.02.020

DO - 10.1016/j.neuroimage.2012.02.020

M3 - Article

VL - 62

SP - 891

EP - 901

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -