Title :
Image segmentation in Bayesian reconstructions for emission computed tomography
Author :
Bowsher, J.E. ; Johnson, V.E. ; Floyd, C.E., Jr.
Author_Institution :
Dept. of Radiol., Duke Univ. Med. Center, Durham, NC, USA
Abstract :
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.<>
Keywords :
Bayes methods; computerised tomography; image reconstruction; image segmentation; medical image processing; radioisotope scanning and imaging; Bayesian reconstructions; PET; SPECT; conditional probability; emission computed tomography; image segmentation; medical diagnostic imaging; nuclear medicine; pixel; positron emission tomography; radiopharmaceutical concentration; single photon emission computed tomography; Bayesian methods; Biomedical imaging; Computed tomography; Detectors; Image reconstruction; Image segmentation; Maximum likelihood estimation; Probability distribution; Radiology; Statistics;
Conference_Titel :
Nuclear Science Symposium and Medical Imaging Conference, 1991., Conference Record of the 1991 IEEE
Conference_Location :
Santa Fe, NM, USA
Print_ISBN :
0-7803-0513-2
DOI :
10.1109/NSSMIC.1991.259268
