PET image segmentation using a Gaussian mixture model and Markov random fields
The main contribution of this paper is the proposal of volume modeling of parathyroid gland. Multivariate generalized Gaussian distribution (Multivariate GGD) mixture is assumed. Random walk optimization algorithm is applied for the estimation of parameters. There are 800 synthetic test cases applied for the evaluation of algorithm properties. Example result for real SPECT data are also shown. The essential is the computation time, so GPGPU implementation is proposed for reduction of processing time. Obtained parameters of mixture are required for further analysis of relation to patient data.