REGULARIZED EMISSION IMAGE-RECONSTRUCTION USING IMPERFECT SIDE INFORMATION

The inadequacy of the maximum-likelihood criterion for emission image reconstruction has spurred the development of several regularization methods. Despite the spatial variance of medical images, most of the proposed methods are spatially invariant. This paper reports an investigation of a spatially-variant penalized-likelihood method for tomographic image reconstruction based on a weighted Gibbs penalty. The penalty weights are determined from structural side information, such as the locations of anatomical boundaries in high-resolution magnetic resonance images. Such side information will be imperfect in practice, and a simple simulation demonstrates the importance of accounting for the errors in boundary locations. We discuss methods for prescribing the penalty weights when the side information is noisy. Simulation results suggest that even imperfect side information is useful for guiding spatially-variant regularization.