Event-by-Event Random and Scatter Estimator Based on Support Vector Machine using Multi-anode Outputs

In PET, an incident angle of gamma ray is estimated from a coincidence information, but coincidence events are contaminated with random and scatter components. The mean contribution to the image from these components can be measured or estimated, but the noise resulting from the statistical variations in the detected events still remains and decreases noise equivalent count rates (NECR). Theoretically, incident angle to detectors or other related information can be used to discriminate random and scatter events from true events for increasing the NECR. These information can be delineated from spatial distributions of deposit energies on multi-anode PMTs, which arise from inter-crystal scattering and vary with the coincidence event type (true or random/scatter). In this work, a novel method for random and scatter subtraction has been developed using a recently developed and widely used statistical pattern recognition scheme of the support vector machine (SVM). Input data of the SVM is a pair of spatial distributions of 256 outputs of multi-anode PMTs from coincidence detectors. SVM was trained by coincidence events generated from a detector simulator using Monte Carlo calculation. The simulation study showed the proposed method was applicable for event-by-event estimation of scatter and random coincidence.Medical Image Conferenc