version française rss feed
Fiche concise
Fast joint detection-estimation of evoked brain activity in event-related fMRI using a variational approach
Chaari L., Vincent T., Forbes F., Dojat M., CIUCIU P.
IEEE Transactions on Medical Imaging 32, 5 (2013) 821-837 - http://www.hal.inserm.fr/inserm-00753873
Fast joint detection-estimation of evoked brain activity in event-related fMRI using a variational approach
Lotfi Chaari () 1, 2, Thomas Vincent () 1, 2, Florence Forbes () 2, Michel Dojat () 3, Philippe CIUCIU1
1 :  LNAO - Laboratoire de Neuroimagerie Assistée par Ordinateur
2 :  INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann - MISTIS
INRIA – Laboratoire Jean Kuntzmann – CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Institut polytechnique de Grenoble (Grenoble INP)
Inria Grenoble - Rhône-Alpes 655 avenue de l'Europe - Montbonnot 38334 Saint Ismier Cedex
3 :  GIN - U836 - Grenoble Institut des Neurosciences
INSERM : U836 – Université Joseph Fourier - Grenoble I – CHU Grenoble – CEA : DSV/IRTSV
UJF - Site Santé La Tronche - BP 170 - 38042 Grenoble Cedex 9
INSERM U836, équipe 5, Neuroimagerie fonctionnelle et perfusion cérébrale
In standard within-subject analyses of event-related fMRI data, two steps are usually performed separately: detection of brain activity and estimation of the hemodynamic response. Because these two steps are inherently linked, we adopt the socalled region-based Joint Detection-Estimation (JDE) framework that addresses this joint issue using a multivariate inference for detection and estimation. JDE is built by making use of a regional bilinear generative model of the BOLD response and constraining the parameter estimation by physiological priors using temporal and spatial information in a Markovian model. In contrast to previous works that use Markov Chain Monte Carlo (MCMC) techniques to sample the resulting intractable posterior distribution, we recast the JDE into a missing data framework and derive a Variational Expectation-Maximization (VEM) algorithm for its inference. A variational approximation is used to approximate the Markovian model in the unsupervised spatially adaptive JDE inference, which allows automatic fine-tuning of spatial regularization parameters. It provides a new algorithm that exhibits interesting properties in terms of estimation error and computational cost compared to the previously used MCMC-based approach. Experiments on artificial and real data show that VEM-JDE is robust to model misspecification and provides computational gain while maintaining good performance in terms of activation detection and hemodynamic shape recovery.
Informatique/Imagerie médicale
Informatique/Traitement du signal et de l'image
Sciences de l'ingénieur/Traitement du signal et de l'image
Sciences du Vivant/Neurosciences

Articles dans des revues avec comité de lecture
IEEE Transactions on Medical Imaging (IEEE Trans Med Imaging)
Publisher Institute of Electrical and Electronics Engineers (IEEE)
ISSN 0278-0062 

Biomedical signal detection-estimation – functional MRI – brain imaging – Joint Detection-Estimation – Markov random field – EM algorithm – Variational approximation – fMRI – VEM – Mean-field
Liste des fichiers attachés à ce document : 
Chaari_2012_Fast_joint_MA.pdf(2.4 MB)