ANSTO, Lucas Heights, Australia.
Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW, Australia.
Phys Med Biol. 2022 Sep 23;67(19). doi: 10.1088/1361-6560/ac88b2.
. We aim to evaluate a method for estimating 1D physical dose deposition profiles in carbon ion therapy via analysis of dynamic PET images using a deep residual learning convolutional neural network (CNN). The method is validated using Monte Carlo simulations ofC ion spread-out Bragg peak (SOBP) profiles, and demonstrated with an experimental PET image.. A set of dose deposition and positron annihilation profiles for monoenergeticC ion pencil beams in PMMA are first generated using Monte Carlo simulations. From these, a set of random polyenergetic dose and positron annihilation profiles are synthesised and used to train the CNN. Performance is evaluated by generating a second set of simulatedC ion SOBP profiles (one 116 mm SOBP profile and ten 60 mm SOBP profiles), and using the trained neural network to estimate the dose profile deposited by each beam and the position of the distal edge of the SOBP. Next, the same methods are used to evaluate the network using an experimental PET image, obtained after irradiating a PMMA phantom with aC ion beam at QST's Heavy Ion Medical Accelerator in Chiba facility in Chiba, Japan. The performance of the CNN is compared to that of a recently published iterative technique using the same simulated and experimentalC SOBP profiles.. The CNN estimated the simulated dose profiles with a mean relative error (MRE) of 0.7% ± 1.0% and the distal edge position with an accuracy of 0.1 mm ± 0.2 mm, and estimate the dose delivered by the experimentalC ion beam with a MRE of 3.7%, and the distal edge with an accuracy of 1.7 mm.. The CNN was able to produce estimates of the dose distribution with comparable or improved accuracy and computational efficiency compared to the iterative method and other similar PET-based direct dose quantification techniques.
. 我们旨在通过使用深度残差学习卷积神经网络 (CNN) 分析动态 PET 图像，评估一种用于估算碳离子治疗中一维物理剂量沉积分布的方法。该方法通过 Monte Carlo 模拟碳离子扩展布拉格峰 (SOBP) 分布进行验证，并通过实验 PET 图像进行演示。. 首先使用 Monte Carlo 模拟生成一组用于 PMMA 中单能碳离子铅笔束的剂量沉积和正电子湮没分布。由此，合成一组随机的多能剂量和正电子湮没分布，并用于训练 CNN。通过生成第二组模拟碳离子 SOBP 分布（一个 116mm SOBP 分布和十个 60mm SOBP 分布），并使用训练好的神经网络来估算每个束沉积的剂量分布和 SOBP 远端边缘的位置，来评估网络的性能。接下来，使用相同的方法评估使用日本千叶 QST 重离子医疗加速器设施用碳离子束辐照 PMMA 体模后获得的实验 PET 图像的网络。将 CNN 的性能与使用相同模拟和实验碳 SOBP 分布的最近发表的迭代技术进行比较。. CNN 以 0.7%±1.0%的平均相对误差 (MRE) 估计模拟剂量分布，以 0.1mm±0.2mm 的精度估计 SOBP 远端边缘位置，以 3.7%的 MRE 估计实验碳离子束的剂量分布，以 1.7mm 的精度估计 SOBP 远端边缘位置。. CNN 能够生成剂量分布的估计值，与迭代方法和其他类似的基于 PET 的直接剂量定量技术相比，具有可比或更高的精度和计算效率。
