PET image segmentation using a Gaussian mixture model and Markov random fields.

Background: Classification algorithms for positron emission tomography (PET) images support computational treatment planning in radiotherapy. Common clinical practice is based on manual delineation and fixed or iterative threshold methods, the latter of which requires regression curves dependent on many parameters.

Methods: An improved statistical approach using a Gaussian mixture model (GMM) is proposed to obtain initial estimates of a target volume, followed by a correction step based on a Markov random field (MRF) and a Gibbs distribution to account for dependencies among neighboring voxels.

Measurements of occupational and patient exposure as well as image quality for two C-arms.

Two different C-arms, a Philips Veradius and a Ziehm Vision FD were evaluated with regard to occupational and patient radiation exposure as well as image quality. For this, the scatter radiation, the entrance surface dose rate (ESD rate) and the low contrast detectability (LCD) were evaluated with regard to different examination modes, using phantoms with different thicknesses as well as a Leeds Test Object. The results show a large range of variance between the two systems in relation to the topics investigated.