BAYESIAN MODELS FOR MEDICAL IMAGE BIOLOGY USING MONTE CARLO MARKOV CHAINS TECHNIQUES

Abstract

The use of Bayesian methods in medical biology and modeling is an approach, which seeks to provide a unified framework within many different image processes. In this work, bayesian models would be presented to illustrate biological phenomena using the Gibbs sampler technique. Finally methods for the estimation of model parameters would be proposed based on the likelihood ration tests.In recent years stochastic models and statistical methods have been successfully applied in medical biology using image analysis techniques. Of particular interest are Bayesian methods based on local characteristics. Key components of any statistical analysis, using such methods, are the choice of an appropriate model as the prior and the estimation of the prior model parameters.