Image segmentation in Bayesian reconstructions for emission computed tomography

Two methods for segmenting SPECT (single photon emission computed tomography) and PET (positron emission tomography) images are introduced and evaluated. These region classification schemes are intended primarily for use within Bayesian reconstruction procedures that estimate the number of regions, the region means, and the region membership and radiopharmaceutical concentration for each pixel. One segmentation method utilizes the probability of the unobserved number of photons emitted from a pixel given that pixel's region membership. The second technique considers directly the conditional probability of the detector data. This second method is more robust and leads to better estimates of radiopharmaceutical concentration.<<ETX>>