Bayesian models for medical image biology using monte carlo markov chains techniques

The objective of Bayesian modelling in pattern analysis is aimed to extract the important characteristics of the pattern using a few parameters so as to represent the pattern effectively. The use of Bayesian methods in medical biology and modelling is an approach, which seeks to provide a unified framework within many different image processes. Markov random fields (M.r.f.) modelling are a very popular pattern analysis methods and it plays an important role in pattern recognition and computer vision. In this work, Bayesian models would be presented to illustrate biological phenomena using the Gibbs sampler technique. Finally, methods for estimating model parameters using likelihood techniques are examined, and a model selection procedure is proposed for classifying the neighbourhood structure of the image. The techniques are investigated using simulated and real data from the area of biology.