Spect image reconstruction using compound prior models

Antonio López*, Rafael Molina, Javier Mateos, Aggelos K. Katsaggelos

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

We propose a new iterative method for Maximum a Posteriori (MAP) reconstruction of SPECT (Single Photon Emission Computed Tomography) images. The method uses Compound Gauss Markov Random Fields (CGMRF) as prior model and is stochastic for the line process and deterministic for the reconstruction. Synthetic and real images are used to compare the new method with existing ones.

Original languageEnglish (US)
Pages (from-to)317-330
Number of pages14
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume16
Issue number3
DOIs
StatePublished - May 2002

Keywords

  • Bayesian reconstruction
  • Compound Gauss Markov random fields
  • Deterministic image reconstruction
  • SPECT imaging
  • Simulated annealing

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Spect image reconstruction using compound prior models'. Together they form a unique fingerprint.

Cite this