[Analysis of the convergence relation of reconstructed algorithms disregarding local and global visual evaluations]

Tomographic reconstruction methods used in positron emission tomography are classified in two major groups: the traditionally and still widely applied filtered backprojection, and the iterative methods based on statistical models. This study focused on the objective comparison of different reconstruction algorithms, excluding criteria based on pure visual evaluation. The evaluation criteria were mathematically defined parameters, i.e., mean square error, standard deviation, signal-to-noise ratio and contrast recovery. The methods used for comparison were the classical filtered backprojection, the maximum likelihood expectation maximization algorithm, the maximum a-posteriori reconstruction model based on the Bayes Theorem, as well as the acceleration algorithms based on ordered subsets and high over-relaxation. These algorithms were evaluated by means of a mathematical brain phantom and of a physical spherical phantom. In terms of the applied parameters, the majority of the experiments showed a quantifiable superiority of the iterative methods compared the filtered backprojection.