Passer à la navigation principale Passer à la recherche Passer au contenu principal

Sparse model learning for high dimensional diffusion MRI data in traumatic brain injury

  • Northeastern University
  • Brigham and Women’s Hospital

Résultats de recherche: Chapitre dans un livre, rapport, actes de conférence › Participation à un ouvrage collectif lié à un colloque ou une conférence › Revue par des pairs

1 Citation (Scopus)

Résumé

The estimation of multivariate distributions of from high dimensional data with low sample size is at the core of many image analysis applications. Here, we present a method to estimate a multivariate Gaussian distribution of diffusion tensor features in a set of brain regions based on 45 healthy individuals. This distribution is used to identify the imaging abnormalities in subjects with traumatic brain injury (TBI). The model receives apriori knowledge in the form of a neighborhood graph, and maximizes the likelihood of the distribution while putting an additional L1 sparsity constraint on the model parameters. This leads to an interpretable model where the interactions of brain regions are encoded into the estimated model coefficients. The likelihoods of normal and TBI subjects under the estimated distribution are used as features to evaluate discriminatory power of model, using the area under receiver operating characteristic (ROC) curves. Our experiments show that the addition of the neighborhood graph constraint results in significant improvements in classification compared to a model which does not take into account the brain region interactions. In addition, our prior graph leads to a better model than one using a fully connected prior graph as it provides similar classification performance with 10 times fewer parameters (model order), and significantly lower Bayesian information criterion (BIC).

Langue originaleAnglais
titre2015 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2015
rédacteurs en chefDeniz Erdogmus, Serdar Kozat, Jan Larsen, Murat Akcakaya
EditeurIEEE Computer Society
ISBN (Electronique)9781467374545
Les DOIs
ÉtatPublié - 10 nov. 2015
Modification externeOui
Evénement25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015 - Boston, Etats-Unis
Durée: 17 sept. 2015 → 20 sept. 2015

Série de publications

NomIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2015-November
ISSN (imprimé)2161-0363
ISSN (Electronique)2161-0371

Conférence

Conférence25th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2015
Pays/TerritoireEtats-Unis
La villeBoston
Période17/09/15 → 20/09/15

Classification disciplinaire ASJC Scopus

  • Interaction humain-ordinateur
  • Traitement du signal

Empreinte digitale

Voici les principaux termes ou expressions associés à « Sparse model learning for high dimensional diffusion MRI data in traumatic brain injury ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.

Citer cette ressource