An accelerated convergent ordered subsets algorithm for emission tomography
Authors:
- Ing-Tsung HsiaoIHIng-Tsung Hsiao
- Anand RangarajanARAnand Rangarajan
- Parmeshwar KhurdPKParmeshwar Khurd
- Gene GindiGGGene Gindi
- 20 May 2004
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 49 (11) , 2145-2156
Abstract
We propose an algorithm, E-COSEM (enhanced complete-data ordered subsets expectation-maximization), for fast maximum likelihood (ML) reconstruction in emission tomography. E-COSEM is founded on an incremental EM approach. Unlike the familiar OSEM (ordered subsets EM) algorithm which is not convergent, we show that E-COSEM converges to the ML solution. Alternatives to the OSEM include RAMLA, and for the related maximum a posteriori (MAP) problem, the BSREM and OS-SPS algorithms. These are fast and convergent, but require ajudicious choice of a user-specified relaxation schedule. E-COSEM itself uses a sequence of iteration-dependent parameters (very roughly akin to relaxation parameters) to control a tradeoff between a greedy, fast but non-convergent update and a slower but convergent update. These parameters are computed automatically at each iteration and require no user specification. For the ML case, our simulations show that E-COSEM is nearly as fast as RAMLA.Keywords
This publication has 9 references indexed in Scilit:
- A new convergent MAP reconstruction algorithm for emission tomography using ordered subsets and separable surrogates2003
- Globally convergent image reconstruction for emission tomography using relaxed ordered subsets algorithmsIEEE Transactions on Medical Imaging, 2003
- Provably convergent OSEM-like reconstruction algorithm for emission tomography2002
- Fast EM-like methods for maximum "a posteriori" estimates in emission tomographyIEEE Transactions on Medical Imaging, 2001
- A Bayesian Joint Mixture Framework for the Integration of Anatomical Information in Functional Image ReconstructionJournal of Mathematical Imaging and Vision, 2000
- A row-action alternative to the EM algorithm for maximizing likelihood in emission tomographyIEEE Transactions on Medical Imaging, 1996
- Mechanical Models as Priors in Bayesian Tomographic Reconstruction1996
- Accelerated image reconstruction using ordered subsets of projection dataIEEE Transactions on Medical Imaging, 1994
- Another interpretation of the EM algorithm for mixture distributionsStatistics & Probability Letters, 1986