A Joint Bayesian Framework for MR Brain Scan Tissue and Structure Segmentation Based on Distributed Markovian Agents - Computational Intelligence in Healthcare: Advanced Methodologies - page 78

formulation and simplifies into alternating and cooperative estimation proce-
dures for standard Hidden MRF models that can be implemented eciently via
a two agent-layer architecture.
The chapter is organized as follows. In Section 2, we explain the motivation in
coupling agent-based and Markov-centered designs. In Section 3, we introduce
the probabilistic setting and inference framework. The joint tissue and structure
model is described in more details in Section 4. An appropriate estimation pro-
cedure is proposed in Section 5. Experimental results are reported in Section 6
and a discussion ends the chapter.
2 Distributed Cooperative Markovian Agents
While Markov modeling has largely been used in the domain of MRI segmen-
tation, agent-based approaches have seldom been considered. Agents are au-
tonomous entities sharing a common environment and working in a cooperative
way to achieve a common goal. They are usually provided with limited percep-
tion abilities and local knowledge. Some advantages of multi-agent systems are
among others [7] their ability to handle knowledge from different domains, to
Fig. 1. Symbolic multi-level design of our approach