Distributed Markovian segmentation: Application to MR brain scans

Authors:
Nathalie Richard;Michel Dojat;Catherine Garbay
Affiliations:
INSERM, U594, Neuroimagerie fonctionnelle et métabolique, Grenoble F-38043, France and CNRS, UMR 5525, Techniques de l'Imagerie, de la Modélisation et de la Cognition, Grenoble F-38706, ...;INSERM, U594, Neuroimagerie fonctionnelle et métabolique, Grenoble F-38043, France and CNRS, UMR 5525, Techniques de l'Imagerie, de la Modélisation et de la Cognition, Grenoble F-38706, ...;CNRS, UMR 5525, Techniques de l'Imagerie, de la Modélisation et de la Cognition, Grenoble F-38706, France and Université Joseph Fourier, Grenoble F-38043, France
Venue:
Pattern Recognition
Year:
2007

Citing 7
Cited 4

Adaptive Image Segmentation With Distributed Behavior-Based Agents

IEEE Transactions on Pattern Analysis and Machine Intelligence
Cooperative agents society organized as an irregular pyramid: a mammography segmentation application

Pattern Recognition Letters
STREM: a robust multidimensional parametric method to segment MS lesions in MRI

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
The mean field theory in EM procedures for Markov random fields

IEEE Transactions on Signal Processing
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bayesian pixel classification using spatially variant finite mixtures and the generalized EM algorithm

IEEE Transactions on Image Processing
Statistical models of partial volume effect

IEEE Transactions on Image Processing

Agentification of Markov model-based segmentation: Application to magnetic resonance brain scans

Artificial Intelligence in Medicine
Segmentation of CT Brain Images Using Unsupervised Clusterings

Journal of Visualization
Automated Segmentation and Retrieval System for CT Head Images

IVIC '09 Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and Practice
Learning image context for segmentation of prostate in CT-guided radiotherapy

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part III

Quantified Score

Hi-index	0.01

Visualization

Abstract

A situated approach to Markovian image segmentation is proposed based on a distributed, decentralized and cooperative strategy for model estimation. According to this approach, the EM-based model estimation is performed locally to cope with spatially varying intensity distributions, as well as non-homogeneities in the appearance of objects. This distributed segmentation is performed under a collaborative and decentralized strategy, to ensure the consistency of segmentation over neighboring zones, and the robustness of model estimation in front of small samples. Specific coordination mechanisms are required to guarantee the proper management of the corresponding processing, which are implemented in the framework of a reactive agent-based architecture. The approach has been experimented on phantoms and real 1.5T MR brain scans. The reported evaluation results demonstrate that this approach is particularly appropriate in front of complex and spatially variable image models.