Evaluation of Volumetric Medical Images Segmentation Using Hidden Markov Random Field Model

Medical image segmentation is a crucial step in the process of image analysis. An automatic aid in interpretation of huge amount of data can be of great value to specialists that hold final decision. Hidden Markov Random Field (HMRF) Model and Gibbs distributions provide powerful tools for image modeling. In this paper, we use a HMRF model to perform segmentation of volumetric medical images handling inter-image similarity. This modelling leads to the minimization of an energy function. This problem is computationally intractable. Therefore, optimizations techniques are used to compute a solution. We will use and compare promising relatively recent methods based on graph cuts with older well known methods that are Simulated Annealing and ICM.