LOcal and Cooperative Unified Segmentation (LOCUS)

Abstract.

In most approaches, tissue and subcortical structure segmentations of MR brain scans are handled globally over the entire brain volume through two relatively independent sequential steps. We investigated a fully Bayesian joint model that integrates within a multi-agent framework local tissue and structure segmentations and local intensity distribution modeling.

Selected related publications


Scherrer B, Forbes F, Garbay C, Dojat M,  A joint Bayesian framework for MR brain scan tissue and structure segmentation based on distributed Markovian agents,  In I. Bichindaritz and eds. L. Jain editors, Computational Intelligence in Healtcare,  309,  2010,  81-101
pdf bibtex doi Google Scholar Google Scholar Citation
(EN, Draft version)
Scherrer B, Forbes F, Garbay C, Dojat M,  Distributed Local MRF Models for Tissue and Structure Brain Segmentation,  IEEE Transactions on Medical Imaging,  28(8),  2009,  1278-1295,  PMID19228553
pdf bibtex doi PubMed Google Scholar Google Scholar Citation
(EN, Draft version)
Scherrer B, Dojat M, Forbes F, Garbay C,  Agentification of Markov model-based segmentation: Application to magnetic resonance brain scans,  Artificial Intelligence in Medicine (AIM),  46(1),  2009,  81-95,  PMID18929472
bibtex doi PubMed Google Scholar Google Scholar Citation
Scherrer B, Forbes F, Dojat M,  A Conditional Random Field Approach for Coupling Local Registration with Robust Tissue and Structure Segmentation,  Proc. of the 12th Int Conf Med Image Comput Comput Assist Interv (MICCAI),  12(1),  London, England,  2009,  540-548,  PMID20426154
pdf bibtex doi PubMed
(EN, Draft version)
Scherrer B, Forbes F, Garbay C, Dojat M,  Fully Bayesian Joint Model for MR Brain Scan Tissue and Structure Segmentation,  Proc. of the 11th Int Conf Med Image Comput Comput Assist Interv (MICCAI),  11(2),  New-York, USA,  2008,  1066-1074,  PMID18982710
pdf bibtex doi PubMed Google Scholar Google Scholar Citation
Young Investigator MICCAI Award in the category Segmentation
(EN, Draft version)