The supervised machine learning technique Gradient Tree Boosting (GTB) has shown good accuracy for position estimation of gamma interaction in PET crystals for bench-top experiments while its computational requirements can easily be adjusted. Transitioning to preclinical and clinical applications requires near real-time processing in the scale of full PET systems. In this work, a high throughput GTB-based singles positioning C++ implementation is proposed and a series of optimizations are evaluated regarding their effect on the achievable processing throughput. Moreover, the crucial feature and parameter selection for GTB is investigated for the segmented detectors of the Hyperion II^D PET insert with two main models and a range of GTB hyperparameters. The proposed framework achieves singles positioning throughputs of more than 9.5 GB/s for smaller models and of 240 MB/s for more complex models on a recent Intel Skylake server. Detailed throughput analysis reveals the key performance limiting factors, and an empirical throughput model is derived to guide the GTB model selection process and scanner design decisions. The throughput model allows for throughput estimations with a mean absolute error (MAE) of 175.78 MB/s.

监督机器学习技术 Gradient Tree Boosting (GTB) 在台式实验的 PET 晶体中伽马相互作用的位置估计方面表现出良好的准确性，同时其计算要求可以轻松调整。过渡到临床前和临床应用需要在全 PET 系统的规模上进行近乎实时的处理。在这项工作中，提出了一种基于 GTB 的高吞吐量单打定位 C++ 实现，并评估了一系列优化对可实现处理吞吐量的影响。^{此外，针对 Hyperion II D}的分段探测器，研究了 GTB 的关键特征和参数选择。具有两个主要模型和一系列 GTB 超参数的 PET 插入物。所提出的框架在最近的英特尔 Skylake 服务器上实现了较小模型的超过 9.5 GB/s 和更复杂模型的 240 MB/s 的单次定位吞吐量。详细的吞吐量分析揭示了关键的性能限制因素，并得出了一个经验吞吐量模型来指导 GTB 模型选择过程和扫描仪设计决策。吞吐量模型允许以 175.78 MB/s 的平均绝对误差 (MAE) 进行吞吐量估计。