Scale hyperparameter estimation for GGMRF prior models with application to SPECT images

Author

López, A. ; Molina, R. ; Katsaggelos, Aggelos K.

Author_Institution

Departamento de Lenguajes y Sistemas Informaticos, Granada Univ., Spain

Volume

2

fYear

2002

fDate

2002

Firstpage

521

Abstract

In this work we develop a Bayesian reconstruction method for SPECT (single photon emission computed tomography) images, using as prior GGMRF (generalized Gaussian Markov random fields) distributions and estimating the scale hyperparameter following the evidence analysis. Preconditioning methods are used to estimate this hyperparameter and the approximations used are compared on synthetic images.

Keywords

Bayes methods; Gaussian distribution; Markov processes; image reconstruction; image resolution; medical image processing; parameter estimation; single photon emission computed tomography; Bayesian reconstruction method; GGMRF prior models; SPECT images; evidence analysis; generalized Gaussian Markov random fields; preconditioning methods; scale hyperparameter estimation; single photon emission computed tomography; Application software; Bayesian methods; Degradation; Distributed computing; Image analysis; Image reconstruction; Markov random fields; Optical computing; Reconstruction algorithms; Single photon emission computed tomography;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on

Print_ISBN

0-7803-7503-3

Type

conf

DOI

10.1109/ICDSP.2002.1028142

Filename

1028142