Université de Lyon, CREATIS; CNRS UMR5220; Inserm U1044; INSA-Lyon; Université Lyon 1; Centre Léon Bérard, France.
Phys Med Biol. 2023 Jul 3;68(13). doi: 10.1088/1361-6560/acdfb1.
Following previous works on virtual sources model with Generative Adversarial Network (GAN), we extend the proof of concept for generating back-to-back pairs of gammas with timing information, typically for Monte Carlo simulation of Positron Emission Tomography(PET) imaging.A conditional GAN is trained once from a low statistic simulation in a given attenuation phantom and enables the generation of various activity source distributions. GAN training input is a set of gammas exiting a phantom, tracked from a source of positron emitters, described by position, direction and energy. A new parameterization that improves the training is also proposed. An ideal PET reconstruction algorithm is used to evaluate the quality of the GAN.The proposed method is evaluated on National Electrical Manufacturers Association (NEMA) International Electrotechnical Commission (IEC) phantoms and with CT patient image showing good agreement with reference simulations. The proportions of 2-gammas, 1-gammas and absorbed-gammas are respected to within one percent, image profiles matched and recovery coefficients were close with less than 5% difference. GAN tends to blur gamma energy peak, e.g. 511 keV.Once trained, the GAN generator can be used as input source for Monte Carlo simulations of PET imaging systems, decreasing the computational time with speedups up to ×400 according to the configurations.
在前人关于具有生成对抗网络（GAN）的虚拟源模型的工作基础上，我们扩展了生成具有时间信息的伽马对的概念验证，通常用于正电子发射断层扫描（PET）成像的蒙特卡罗模拟。条件 GAN 从给定衰减体模中的低统计模拟中进行一次训练，并能够生成各种活性源分布。GAN 训练输入是从正电子发射器源跟踪的、通过位置、方向和能量描述的一组离开体模的伽马射线。还提出了一种改进训练的新参数化方法。使用理想的 PET 重建算法来评估 GAN 的质量。该方法在国家电器制造商协会（NEMA）国际电工委员会（IEC）体模和 CT 患者图像上进行了评估，与参考模拟结果吻合良好。2-伽马射线、1-伽马射线和吸收-伽马射线的比例相差不到 1%，图像轮廓匹配，恢复系数相差不到 5%。GAN 倾向于使伽马射线能量峰值模糊，例如 511keV。一旦训练完成，GAN 发生器就可以用作 PET 成像系统的蒙特卡罗模拟的输入源，根据配置可将计算时间缩短 400 倍。
