Maximum likelihood expectation-maximization (MLEM) is a popular algorithm to reconstruct the activity image in positron emission tomography. This paper introduces a "fundamental equality" for the MLEM complete data from which two key properties easily follow that allows us to: 1) prove in an elegant and compact way the convergence of MLEM for a forward model with fixed background (i.e., counts such as random and scatter coincidences) and 2) generalize this proof for the MLEM-3 algorithm. Moreover, we give necessary and sufficient conditions for the solution to be unique.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TMI.2018.2870968 | DOI Listing |
Publication Analysis
Top Keywords
fixed background
8
convergence proof
4
mlem
4
proof mlem
4
mlem mlem-3
4
mlem-3 fixed
4
background maximum
4
maximum likelihood
4
likelihood expectation-maximization
4
expectation-maximization mlem
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!