Probabilistic M/EEG source imaging from sparse spatio-temporal event structure

Carsten Stahlhut; Hagai T. Attias; David Wipf; Lars Kai Hansen; Srikantan S. Nagarajan

Probabilistic M/EEG source imaging from sparse spatio-temporal event structure

Carsten Stahlhut
, Hagai T. Attias
, David Wipf
, Lars Kai Hansen
, Srikantan S. Nagarajan

Convex Imaging
Microsoft Research Asia
University of California at San Francisco

Research output: Contribution to conference › Paper › Research › peer-review

255 Downloads (Orbit)

Abstract

While MEG and EEG source imaging methods have to tackle a severely ill-posed problem their success can be stated as their ability to constrain the solutions using appropriate priors. In this paper we propose a hierarchical Bayesian model facilitating spatio-temporal patterns through the use of both spatial and temporal basis functions. We demonstrate the efficacy of the model on both artificial data and real EEG data.

Original language	English
Publication date	2012
Number of pages	7
Publication status	Published - 2012
Event	2nd NIPS Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI 2012) - Lake Tahoe, Nevada, United States Duration: 7 Dec 2012 → 8 Dec 2012 https://sites.google.com/site/nipsmlini2012/

Conference

Conference	2nd NIPS Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI 2012)
Country/Territory	United States
City	Lake Tahoe, Nevada
Period	07/12/2012 → 08/12/2012
Internet address	https://sites.google.com/site/nipsmlini2012/

Keywords

M/EEG
Spatio-temporal patterns
Variational Bayes

Access to Document

StahlhutEtAl2012 - Probabilistic MEEG source imaging from sparse spatio-temporal event structure

OpenUrl availability

Check availability in DTU Findit

Cite this

@conference{abae5ea35c934cde9baec7e82297dc04,

title = "Probabilistic M/EEG source imaging from sparse spatio-temporal event structure",

abstract = "While MEG and EEG source imaging methods have to tackle a severely ill-posed problem their success can be stated as their ability to constrain the solutions using appropriate priors. In this paper we propose a hierarchical Bayesian model facilitating spatio-temporal patterns through the use of both spatial and temporal basis functions. We demonstrate the efficacy of the model on both artificial data and real EEG data.",

keywords = "M/EEG, Spatio-temporal patterns, Variational Bayes",

author = "Carsten Stahlhut and Attias, \{Hagai T.\} and David Wipf and Hansen, \{Lars Kai\} and Nagarajan, \{Srikantan S.\}",

year = "2012",

language = "English",

note = "2nd NIPS Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI 2012) ; Conference date: 07-12-2012 Through 08-12-2012",

url = "https://sites.google.com/site/nipsmlini2012/",

}

TY - CONF

T1 - Probabilistic M/EEG source imaging from sparse spatio-temporal event structure

AU - Stahlhut, Carsten

AU - Attias, Hagai T.

AU - Wipf, David

AU - Hansen, Lars Kai

AU - Nagarajan, Srikantan S.

PY - 2012

Y1 - 2012

N2 - While MEG and EEG source imaging methods have to tackle a severely ill-posed problem their success can be stated as their ability to constrain the solutions using appropriate priors. In this paper we propose a hierarchical Bayesian model facilitating spatio-temporal patterns through the use of both spatial and temporal basis functions. We demonstrate the efficacy of the model on both artificial data and real EEG data.

AB - While MEG and EEG source imaging methods have to tackle a severely ill-posed problem their success can be stated as their ability to constrain the solutions using appropriate priors. In this paper we propose a hierarchical Bayesian model facilitating spatio-temporal patterns through the use of both spatial and temporal basis functions. We demonstrate the efficacy of the model on both artificial data and real EEG data.

KW - M/EEG

KW - Spatio-temporal patterns

KW - Variational Bayes

M3 - Paper

T2 - 2nd NIPS Workshop on Machine Learning and Interpretation in NeuroImaging (MLINI 2012)

Y2 - 7 December 2012 through 8 December 2012

ER -

Probabilistic M/EEG source imaging from sparse spatio-temporal event structure

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this