Parallax recovery using neural networks in PET detectors based on continuous scintillators

Abstract

The photon incidence position onto a continuous scintillator can be obtained from the light distribution measured by a pixilated photon detector such as APD arrays. This information is extracted using a series of neural networks trained for events with a particular incidence angle. Using a 20x10x10 mm block of LSO mounted onto a S8550 Hamamatsu APD matrix we achieved an intrinsic resolution of 1.9 mm FWHM for perpendicular incident photons and 2.6 mm FWHM at a 40 o incidence angle 0-7803-8257