Gaussian Mixture Models for Brain Activation Detection from fMRI Data

G Garg, G Prasad, L Garg, DH Coyle

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

Abstract

Gaussian Mixture Model (GMM) based clustering has been successfully used in various types of medical and image data analysis, because of its robustness and stability under high noise levels. GMMs are employed in this work to extract the activation patterns from functional Magnetic Resonance Imaging (fMRI) data. The highly correlated time-series obtained with a given stimulus has been used to find the voxels contributing to the Blood Oxygenation Level Dependent (BOLD) activation regions. GMM clustering has been used for modeling of various activation patterns considering the strength, delay and duration of the epochs. A synthetic dataset and a real dataset provided by the Wellcome Trust Centre for Neuroimaging, University College London, UK are used to demonstrate the superiority of this approach in automating the process of identifying activated brain regions.

Conference

ConferenceSymp. on Noninvasive Functional Source Imaging of the Brain & Heart and the 8th Intl. Conference on Bioelectromagnetism (NFSI & ICBEM 2011), Banff, Canada
Period1/01/11 → …

Fingerprint

Brain
Chemical activation
Neuroimaging
Oxygenation
Time series
Blood
Magnetic Resonance Imaging

Cite this

@inproceedings{0f1ed07a88d74f0b887b582113832ce1,
title = "Gaussian Mixture Models for Brain Activation Detection from fMRI Data",
abstract = "Gaussian Mixture Model (GMM) based clustering has been successfully used in various types of medical and image data analysis, because of its robustness and stability under high noise levels. GMMs are employed in this work to extract the activation patterns from functional Magnetic Resonance Imaging (fMRI) data. The highly correlated time-series obtained with a given stimulus has been used to find the voxels contributing to the Blood Oxygenation Level Dependent (BOLD) activation regions. GMM clustering has been used for modeling of various activation patterns considering the strength, delay and duration of the epochs. A synthetic dataset and a real dataset provided by the Wellcome Trust Centre for Neuroimaging, University College London, UK are used to demonstrate the superiority of this approach in automating the process of identifying activated brain regions.",
author = "G Garg and G Prasad and L Garg and DH Coyle",
year = "2011",
language = "English",
booktitle = "Unknown Host Publication",

}

Garg, G, Prasad, G, Garg, L & Coyle, DH 2011, Gaussian Mixture Models for Brain Activation Detection from fMRI Data. in Unknown Host Publication. Symp. on Noninvasive Functional Source Imaging of the Brain & Heart and the 8th Intl. Conference on Bioelectromagnetism (NFSI & ICBEM 2011), Banff, Canada, 1/01/11.

Gaussian Mixture Models for Brain Activation Detection from fMRI Data. / Garg, G; Prasad, G; Garg, L; Coyle, DH.

Unknown Host Publication. 2011.

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

TY - GEN

T1 - Gaussian Mixture Models for Brain Activation Detection from fMRI Data

AU - Garg, G

AU - Prasad, G

AU - Garg, L

AU - Coyle, DH

PY - 2011

Y1 - 2011

N2 - Gaussian Mixture Model (GMM) based clustering has been successfully used in various types of medical and image data analysis, because of its robustness and stability under high noise levels. GMMs are employed in this work to extract the activation patterns from functional Magnetic Resonance Imaging (fMRI) data. The highly correlated time-series obtained with a given stimulus has been used to find the voxels contributing to the Blood Oxygenation Level Dependent (BOLD) activation regions. GMM clustering has been used for modeling of various activation patterns considering the strength, delay and duration of the epochs. A synthetic dataset and a real dataset provided by the Wellcome Trust Centre for Neuroimaging, University College London, UK are used to demonstrate the superiority of this approach in automating the process of identifying activated brain regions.

AB - Gaussian Mixture Model (GMM) based clustering has been successfully used in various types of medical and image data analysis, because of its robustness and stability under high noise levels. GMMs are employed in this work to extract the activation patterns from functional Magnetic Resonance Imaging (fMRI) data. The highly correlated time-series obtained with a given stimulus has been used to find the voxels contributing to the Blood Oxygenation Level Dependent (BOLD) activation regions. GMM clustering has been used for modeling of various activation patterns considering the strength, delay and duration of the epochs. A synthetic dataset and a real dataset provided by the Wellcome Trust Centre for Neuroimaging, University College London, UK are used to demonstrate the superiority of this approach in automating the process of identifying activated brain regions.

M3 - Conference contribution

BT - Unknown Host Publication

ER -