Neural Computation
Bayesian Estimation of Hyperparameters in MRI through the Maximum Evidence Method
SIBGRAPI '08 Proceedings of the 2008 XXI Brazilian Symposium on Computer Graphics and Image Processing
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient and reliable schemes for nonlinear diffusion filtering
IEEE Transactions on Image Processing
Estimation of Markov random field prior parameters using Markov chain Monte Carlo maximum likelihood
IEEE Transactions on Image Processing
| Hi-index | 0.10 |
Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that constitute MR brain volumes. Two models are examined: the Discrete Model (DM), in which every voxel belongs to a single tissue class, and the Partial Volume Model (PVM), where two classes may be present in a single voxel with a certain probability. We make use of the Maximum Evidence (ME) criterion to estimate the most probable parameters describing each model in a separate fashion. Since an exact image inference would be computationally very expensive, we propose an approximate algorithm for model optimization. Such method was tested on a simulated MRI-T1 brain phantom in 3D, as well as on clinical MR images. As a result, we found that the PVM slightly outperforms the DM, both in terms of Evidence and Mean Absolute Error (MAE). We also show that the Evidence is a very useful figure of merit for error prediction as well as a convenient tool to determine the most probable model from measured data.