We introduce and evaluate a block-iterative Fisher scoring (BFS) algorithm for emission tomography. Regularization is achieved by penalized likelihood with a general quadratic penalty. When the algorithm converges, it converges to the unconstrained maximum penalized likelihood (MPL) solution. In a simulated data set, constrained BFS achieves a higher penalized likelihood in fewer iterations than other block-iterative algorithms which are designed for non-negatively constrained penalized reconstruction.
Copyright 2007 IEEE. Reprinted from Proceedings of the 4th IEEE International Symposium on Biomedical Imaging : From Nano to Macro. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Macquarie University’s products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to firstname.lastname@example.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.