Multicriteria maximum likelihood neural network approach to positron emission tomography

The emerging technology of positron emission image reconstruction is introd uced in this paper as a multicriteria optimization problem. We show how sel ected families of objective functions may be used to reconstruct positron e mission images. We develop a novel neural network approach to positron emis sion imaging problems. We also studied the most frequently used Image recon struction methods, namely, maximum likelihood under the framework of single performance criterion optimization. Finally, we Introduced some of the res ults obtained by various reconstruction algorithms using computer-generated noisy projection data from a chest phantom and real positron emission tomo graphy (PET) scanner data. Comparison of the reconstructed images indicated that the multicriteria optimization method gave the best in error, smoothn ess (suppression of noise), gray value resolution, and ghost-free images. ( C) 2001 John Wiley & Sons, Inc.