Title :
On the convergence of an EM-type algorithm for penalized likelihood estimation in emission tomography
Author :
De Pierro, Alvaro R.
Author_Institution :
Dept. of Appl. Math., State Univ. of Campinas, Brazil
fDate :
12/1/1995 12:00:00 AM
Abstract :
Recently, we proposed an extension of the expectation maximization (EM) algorithm that was able to handle regularization terms in a natural way. Although very general, convergence proofs were not valid for many possibly useful regularizations. We present here a simple convergence result that is valid assuming only continuous differentiability of the penalty term and can be also extended to other methods for penalized likelihood estimation in tomography
Keywords :
convergence of numerical methods; emission tomography; maximum likelihood estimation; positron emission tomography; EM-type algorithm; continuous differentiability; convergence; convergence proofs; emission tomography; expectation maximization algorithm; penalized likelihood estimation; penalty term; regularization terms; regularizations; simple convergence result; Convergence; Detectors; Image reconstruction; Mathematics; Maximum likelihood detection; Maximum likelihood estimation; Positron emission tomography;
Journal_Title :
Medical Imaging, IEEE Transactions on
