The Effect of Regularization on the MAP-OSEM Algorithm for PET Reconstruction

In this paper, we study the algorithm of MAP-
OSEM for PET reconstruction which is a well known iterative
algorithm. It is desired to use a spatial regularization technique
can improve the quality of reconstructed images and help to
provide accurate diagnosis. The MAP-OSEM algorithm is a
powerful image reconstruction algorithm that has been used
in a variety of medical imaging applications, including PET
reconstruction. In this work, we use the regularized MAP-
OSEM algorithm that incorporates a regularization term into the
objective function. The regularization term is used to promote
smoothness in the reconstructed image, and it is typically chosen
based on prior knowledge about the image. The MAP-OSEM
algorithm is a gradient ascent optimization method which seeks
to maximize the posterior distribution of an image by taking
into account a Poisson-Gaussian noise model for the likelihood
and a uniform prior to reduce bias. The objective function is
maximized by the gradient ascent optimization method.