Globally convergent algorithms for maximum a posteriori transmission tomography
IEEE Transactions on Image ProcessingPublished 1 January 1995Open access
Kenneth Lange, Jeffrey A. Fessler
Citations311
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
This paper reviews and compares three maximum likelihood algorithms for transmission tomography. One of these algorithms is the EM algorithm, one is based on a convexity argument devised by De Pierro (see IEEE Trans. Med. Imaging, vol.12, p.328-333, 1993) in the context of emission tomography, and one is an ad hoc gradient algorithm. The algorithms enjoy desirable local and global convergence properties and combine gracefully with Bayesian smoothing priors. Preliminary numerical testing of the algorithms on simulated data suggest that the convex algorithm and the ad hoc gradient algorithm are computationally superior to the EM algorithm. This superiority stems from the larger number of exponentiations required by the EM algorithm. The convex and gradient algorithms are well adapted to parallel computing.
Keywords
MedicineEngineering
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
49,657 Citations1977A. P. Dempster, N. M. Laird +1 more
Society for Industrial and Applied Mathematics eBooksIterative Solution of Nonlinear Equations in Several Variables
6,875 Citations2000J. M. Ortega, Werner C. Rheinboldt
Convergence of Minimization Methods An Annotated List of Basic Reference Books Bibliography Author Index Subject Index.
Digital Access to Scholarship at Harvard (DASH) (Harvard University)Maximum Likelihood from Incomplete Data via the EM Algorithm
4,523 Citations1977Dempster, Arthur P., Laird, Nan M. +1 more
IEEE Transactions on Medical ImagingMaximum Likelihood Reconstruction for Emission Tomography
4,341 Citations1982L. A. Shepp, Y. Vardi
PubMedEM reconstruction algorithms for emission and transmission tomography.
1,781 Citations1984Kenneth Lange, Richard E. Carson
The general principles behind all EM algorithms are discussed and in detail the specific algorithms for emission and transmission tomography are derived and the specification of necessary physical features such as source and detector geometries are discussed.
IEEE Transactions on Medical ImagingBayesian reconstructions from emission tomography data using a modified EM algorithm
1,228 Citations1990P.J. Green
This method builds on the expectation-maximization approach to maximum likelihood reconstruction from emission tomography data, but aims instead at maximum posterior probability estimation, which takes account of prior belief about smoothness in the isotope concentration.
Journal of the American Statistical AssociationA Statistical Model for Positron Emission Tomography
806 Citations1985Y. Vardi, L. A. Shepp +1 more
This article tailor a mathematical model to the physics of positron emissions, and it is used to describe the basic image reconstruction problem of PET as a standard problem in statistical estimation from incomplete data.
Mathematics of ComputationNumerical Analysis, A Second Course
564 Citations1973C. W. de Boor, James M. Ortega
IEEE Transactions on Medical ImagingA modified expectation maximization algorithm for penalized likelihood estimation in emission tomography
470 Citations1995A.R. De Pierro
A modification of the EM algorithm for maximizing likelihood with concave priors in emission tomography is presented, which is a natural extension of the EM for maximizing likelihood with concave priors.
Journal of the Royal Statistical Society Series B (Statistical Methodology)On Use of the Em Algorithm for Penalized Likelihood Estimation
416 Citations1990Peter J. Green
Property of the EM algorithm in such contexts are discussed, concentrating on rates of conver- gence, and an alternative that is usually more practical and converges at least as quickly is presented.
IEEE Transactions on Medical ImagingConvergence of EM image reconstruction algorithms with Gibbs smoothing
398 Citations1990Kenneth Lange
An OSL (one-step late) algorithm is defined that retains the E-step of the EM algorithm but provides an approximate solution to the M-step, and modifications of the OSL algorithm guarantee convergence to the unique maximum of the log posterior function.
Journal of the Royal Statistical Society Series B (Statistical Methodology)A Gradient Algorithm Locally Equivalent to the Em Algorithm
383 Citations1995Kenneth Lange
This EM gradient algorithm approximately solves the M-step of the EM algorithm by one iteration of Newton's method, and the proof of global convergence applies and improves existing theory for the EM algorithms.
IEEE Transactions on Medical ImagingA Theoretical Study of Some Maximum Likelihood Algorithms for Emission and Transmission Tomography
324 Citations1987Kenneth Lange, Mark M. Bahn +1 more
The Bayesian versions of the EM algorithms are shown to have superior convergence properties in a vicinity of the maximum and it is anticipated that some of the other algorithms will also converge faster than theEM algorithms.
Journal of the American Statistical AssociationA Statistical Model for Positron Emission Tomography
300 Citations1985Y. Vardi, L. A. Shepp +1 more
IEEE Transactions on Nuclear ScienceNonuniform attenuation correction using simultaneous transmission and emission converging tomography
179 Citations1992Chi‐Hua Tung, G.T. Gullberg +4 more
The quantitative accuracy of cardiac SPECT is significantly improved using simultaneously acquired transmission and emission data which are obtained in clinically acceptable patient scanning times.
IEEE Transactions on Medical ImagingOn the relation between the ISRA and the EM algorithm for positron emission tomography
169 Citations1993A.R. De Pierro
It is shown that both image space reconstruction algorithm and expectation maximization algorithm may be obtained from a common mathematical framework and this fact is used to extend ISRA for penalized likelihood estimates.
Journal of the Operational Research SocietyOptimization Theory: The Finite Dimensional Case
139 Citations1977R. J. Paul
IEEE Transactions on Image ProcessingHybrid Poisson/polynomial objective functions for tomographic image reconstruction from transmission scans
116 Citations1995Jeffrey A. Fessler
IEEE Transactions on Medical ImagingMaximum-likelihood reconstruction of transmission images in emission computed tomography via the EM algorithm
87 Citations1994John Ollinger
Evaluations using both Monte Carlo simulations and phantom studies on the Siemens 953B scanner suggest that the expectation-maximization algorithm yields unbiased images with significantly lower variances than filtered-backprojection when the images are reconstructed to the intrinsic resolution.
PubMedPhantom study of breast tissue attenuation in myocardial imaging.
57 Citations1993S.H. Manglos, F.D. Thomas +2 more
It is expected that attenuation compensation will improve diagnostic accuracy in myocardial imaging in female patients and in males with excessive musculature or soft tissue, because without such compensation, diagnosis may be compromised.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Overview of Bayesian methods in image reconstruction</title>
28 Citations1990Kenneth Lange