Medical University of Vienna, Department of Radiation Oncology, Währinger Gürtel 18-20, 1090 Wien, Austria; MedAustron Ion Therapy Center, Marie-Curie-Straße 5, 2700 Wiener Neustadt, Austria.
Medical University of Vienna, Department of Radiation Oncology, Währinger Gürtel 18-20, 1090 Wien, Austria; Faculty of Health, University of Applied Sciences Wiener Neustadt, Johannes-Gutenberg-Straße 3, Wiener Neustadt, Austria; Competence Center for Preclinical Imaging and Biomedical Engineering, University of Applied Sciences Wiener Neustadt, Johannes-Gutenberg-Straße 3, 2700 Wiener Neustadt, Austria.
Z Med Phys. 2023 May;33(2):135-145. doi: 10.1016/j.zemedi.2022.04.006. Epub 2022 Jun 7.
Monte Carlo (MC) simulations of X-ray image devices require splitting the simulation into two parts (i.e. the generation of x-rays and the actual imaging). The X-ray production remains unchanged for repeated imaging and can thus be stored in phase space (PhS) files and used for subsequent MC simulations. Especially for medical images these dedicated PhS files require a large amount of data storage, which is partly why Generative Adversarial Networks (GANs) were recently introduced. We enhanced the approach by a conditional GAN to model multiple energies using one network. This study compares the use of PhSs, GANs, and conditional GANs as photon source with measurements. An X-ray -based imaging system (i.e. ImagingRing) was modelled in this study. half-value layers (HVLs), focal spot, and Heel effect were measured for subsequent comparison. MC simulations were performed with GATE-RTion v1.0 considering the geometry and materials of the imaging system with vendor specific schematics. A traditional GAN model as well as the favourable conditional GAN was implemented for PhS generation. Results of the MC simulation were in agreement with the measurements regarding HVL, focal spot, and Heel effect. The conditional GAN performed best with a non-saturated loss function with R1 regularisation and gave similarly results as the traditional GAN approach. GANs proved to be superior to the PhS approach in terms of data storage and calculation overhead. Moreover, a conditional GAN enabled an energy interpolation to separate the network training process from the final required X-ray energies.
蒙特卡罗 (MC) 射线成像设备模拟需要将模拟过程分为两部分（即 X 射线的产生和实际成像）。重复成像时 X 射线的产生保持不变，因此可以存储在相空间 (PhS) 文件中，并用于后续的 MC 模拟。特别是对于医学图像，这些专用的 PhS 文件需要大量的数据存储，这也是最近引入生成对抗网络 (GAN) 的部分原因。我们通过条件 GAN 对该方法进行了增强，以使用一个网络来模拟多个能量。本研究将 PhS、GAN 和条件 GAN 作为光子源与测量结果进行了比较。本研究中使用了基于 X 射线的成像系统（即 ImagingRing）进行建模。对半值层 (HVL)、焦点和 Heel 效应进行了测量，以便随后进行比较。使用 GATE-RTion v1.0 进行了 MC 模拟，考虑了成像系统的几何形状和材料以及供应商特定的原理图。实现了传统的 GAN 模型和有利的条件 GAN 以生成 PhS。MC 模拟的结果与 HVL、焦点和 Heel 效应的测量结果一致。条件 GAN 在具有 R1 正则化的非饱和损失函数下表现最佳，并给出了与传统 GAN 方法类似的结果。在数据存储和计算开销方面，GAN 优于 PhS 方法。此外，条件 GAN 可以进行能量插值，从而将网络训练过程与最终所需的 X 射线能量分开。
