Spatial emission tomography reconstruction using Pitman-Yor process

Journal Article · Tue Dec 08 00:00:00 EST 2009 · AIP Conference Proceedings

DOI:https://doi.org/10.1063/1.3275614· OSTI ID:21335883

Fall, Mame Diarra; Mohammad-Djafari, Ali ^[1]; Barat, Eric ^[2]; Comtat, Claude ^[3]

---

1. L2S, Supelec, 3 rue Joliot-Curie, F-91192 Gif-sur-Yvette cedex (France)
2. CEA-LIST, LPSS, CEA-Saclay, F-91191 Gif-sur-Yvette (France)
3. SHFJ, CEA/DSV/I2BM, F-91401 Orsay (France)

In this paper, we address the problem of emission tomography spatial reconstruction in three dimensions following a Bayesian nonparametric approach. Our model makes use of a generalization of the Dirichlet process called Pitman-Yor process. The problem in this approach is to deal with the infinite representation of the distribution in the inference. So we propose an efficient Markov Chain Monte-Carlo sampling scheme which is able to generate samples from the posterior distribution of the activity distribution. An application to 3D-PET reconstruction is presented.

• OSTI ID: 21335883
• Journal Information: AIP Conference Proceedings, Vol. 1193, Issue 1; Conference: 29. international workshop on Bayesian inference and maximum entropy methods in science and engineering, Oxford, MS (United States), 5-10 Jul 2009; Other Information: DOI: 10.1063/1.3275614; (c) 2009 American Institute of Physics; Country of input: International Atomic Energy Agency (IAEA); ISSN 0094-243X
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
DIRICHLET PROBLEM
FUNCTIONAL ANALYSIS
IMAGE PROCESSING
MARKOV PROCESS
MONTE CARLO METHOD
POSITRON COMPUTED TOMOGRAPHY
PROBABILITY
SAMPLING
THREE-DIMENSIONAL CALCULATIONS