Evaluation of Machine Learning Algorithms for Localization of photons in undivided scintillator blocks for PET detectors Vrije Universiteit Brussel
Neural Networks trained with error back propagation Levenberg-Marquardt training (LM), Neural Networks trained with an algebraic method and Support Vector Machines (SVM) were evaluated to extract the position information from measured light distributions generated by the interactions of 511 keV photons in monolithic scintillator blocks. All three algorithms can achieve a similar average resolution (similar to 1.6 mm FWHM in a 20 x 10 x 10 mm LSO ...