School of Biomedical Engineering, Faculty of Engineering, The University of Sydney, Sydney, NSW 2006, Australia.
Brain and Mind Centre, The University of Sydney, Sydney, NSW 2050, Australia.
Phys Med Biol. 2024 Aug 5;69(16). doi: 10.1088/1361-6560/ad682e.
High-resolution positron emission tomography (PET) relies on the accurate positioning of annihilation photons impinging the crystal array. However, conventional positioning algorithms in light-sharing PET detectors are often limited due to edge effects and/or the absence of additional information for identifying and correcting scattering within the crystal array (known as inter-crystal scattering). This study explores the feasibility of deep neural network (DNN) techniques for more precise event positioning in finely segmented and highly multiplexed PET detectors with light-sharing.Initially, a Geant4 Application for Tomographic Emission (GATE) simulation was used to study the spatial and statistical properties of inter-crystal scatter (ICS) events in finely segmented LYSO PET detectors. Next, a DNN for crystal localisation was designed, trained and tested with light distributions of photoelectric (P) and Compton + photoelectric (CP) events simulated using optical GATE and an analytical method to speed up data generation. Using the statistical properties of ICS events, an energy-guided positioning algorithm was then built into the DNN. The positioning algorithm enables selection of the unique or first crystal of interaction in P and CP events, respectively. Performance of the DNN was compared with Anger logic using light distributions from simulated 511 keV point sources placed at different locations around a single PET detector module.. The fraction of events forward and backward scattered in the LYSO detector was 0.54 and 0.46, respectively, whereas naïve application of the Klein-Nishina formulation predicts 70% forward scatter. Despite coarse photodetector data due to signal multiplexing, the DNN demonstrated a crystal classification accuracy of 90% for P events and 82% for CP events. For crystal positioning, the DNN outperformed Anger logic by at least 34% and 14% for P and CP events, respectively. Further improvement is somewhat constrained by the physics-specifically, the ratio of backward to forward scattering of gamma rays within the crystal array being close to 1. This prevents selecting the first crystal of interaction in CP events with a high degree of certainty.Light sharing and multiplexed PET detectors are common in high-resolution PET, yet their traditional positioning algorithms often underperform due to edge effects and/or the difficulty in correcting ICS events. Our study indicates that DNN-based event positioning has the potential to enhance 2D coincidence event positioning accuracy by nearly a factor of 3 compared to Anger logic. However, further improvements are difficult to foresee without additional information such as event timing.
高分辨率正电子发射断层扫描（PET）依赖于准确定位撞击晶体阵列的湮没光子。然而，传统的光共享 PET 探测器中的定位算法由于边缘效应和/或缺乏用于识别和校正晶体阵列内散射（称为晶间散射）的附加信息，通常受到限制。本研究探讨了深度学习神经网络（DNN）技术在具有光共享的精细分段和高度多路复用 PET 探测器中更精确事件定位的可行性。
首先，使用 Geant4 断层发射应用程序（GATE）模拟研究了精细分段 LYSO PET 探测器中晶间散射（ICS）事件的空间和统计特性。接下来，设计、训练和测试了用于晶体定位的 DNN，使用光学 GATE 和分析方法模拟光电（P）和康普顿+光电（CP）事件的光分布来加速数据生成。然后，使用 ICS 事件的统计特性，在 DNN 中构建了一个能量引导的定位算法。该定位算法能够分别选择 P 和 CP 事件中相互作用的唯一或第一个晶体。使用放置在单个 PET 探测器模块周围不同位置的 511keV 点源的模拟光分布比较了 DNN 的性能与 Anger 逻辑。LYSO 探测器中向前和向后散射的事件分数分别为 0.54 和 0.46，而 Klein-Nishina 公式的盲目应用预测向前散射为 70%。尽管由于信号多路复用导致粗光电探测器数据，DNN 仍对 P 事件的晶体分类准确率为 90%，对 CP 事件的晶体分类准确率为 82%。对于晶体定位，DNN 在 P 和 CP 事件上的性能分别优于 Anger 逻辑至少 34%和 14%。进一步的改进受到物理的限制-具体来说，晶体阵列内伽马射线的向后散射与向前散射的比例接近 1。这阻止了在 CP 事件中以高度确定性选择相互作用的第一个晶体。
光共享和多路复用 PET 探测器在高分辨率 PET 中很常见，但由于边缘效应和/或校正 ICS 事件的困难，它们的传统定位算法通常表现不佳。我们的研究表明，与 Anger 逻辑相比，基于 DNN 的事件定位有可能将 2D 符合事件定位精度提高近 3 倍。然而，如果没有额外的信息，例如事件时间，很难预见进一步的改进。
