Improving the Timing Resolution of Positron Emission Tomography Detectors using Boosted Learning -- A Residual Physics Approach

Abstract

Artificial intelligence is finding its way into medical imaging, usually focusing on image reconstruction or enhancing analytical reconstructed images. However, optimizations along the complete processing chain, from detecting signals to computing data, enable significant improvements. Adaptions of the data acquisition and signal processing are potentially easier to translate into clinical applications, as no patient data are involved in the training. At the same time, the robustness of the involved algorithms and their influence on the final image might be easier to demonstrate. Thus, we present an approach toward detector optimization using boosted learning by exploiting the concept of residual physics. In our work, we improve the coincidence time resolution (CTR) of positron emission tomography (PET) detectors. PET enables imaging of metabolic processes by detecting γ-photons with scintillation detectors. Current research exploits light-sharing detectors, where the scintillation light is distributed over and digitized by an array of readout channels. While these detectors demonstrate excellent performance parameters, e.g., regarding spatial resolution, extracting precise timing information for time-of-flight (TOF) becomes more challenging due to deteriorating effects called time skews. Conventional correction methods mainly rely on analytical formulations, theoretically capable of covering all time skew effects, e.g., caused by signal runtimes or physical effects. However, additional effects are involved for lightsharing detectors, so finding suitable analytical formulations can become arbitrarily complicated. The residual physicsbased strategy uses gradient tree boosting (GTB) and a