Wang Tonghe, Lei Yang, Harms Joseph, Ghavidel Beth, Lin Liyong, Beitler Jonathan J, McDonald Mark, Curran Walter J, Liu Tian, Zhou Jun, Yang Xiaofeng
Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, USA.
Int J Part Ther. 2021 Feb 12;7(3):46-60. doi: 10.14338/IJPT-D-20-00020.1. eCollection 2021 Winter.
Dual-energy computed tomography (DECT) has been used to derive relative stopping power (RSP) maps by obtaining the energy dependence of photon interactions. The DECT-derived RSP maps could potentially be compromised by image noise levels and the severity of artifacts when using physics-based mapping techniques. This work presents a noise-robust learning-based method to predict RSP maps from DECT for proton radiation therapy.
The proposed method uses a residual attention cycle-consistent generative adversarial network to bring DECT-to-RSP mapping close to a 1-to-1 mapping by introducing an inverse RSP-to-DECT mapping. To evaluate the proposed method, we retrospectively investigated 20 head-and-neck cancer patients with DECT scans in proton radiation therapy simulation. Ground truth RSP values were assigned by calculation based on chemical compositions and acted as learning targets in the training process for DECT datasets; they were evaluated against results from the proposed method using a leave-one-out cross-validation strategy.
The predicted RSP maps showed an average normalized mean square error of 2.83% across the whole body volume and an average mean error less than 3% in all volumes of interest. With additional simulated noise added in DECT datasets, the proposed method still maintained a comparable performance, while the physics-based stoichiometric method suffered degraded inaccuracy from increased noise level. The average differences from ground truth in dose volume histogram metrics for clinical target volumes were less than 0.2 Gy for D and D with no statistical significance. Maximum difference in dose volume histogram metrics of organs at risk was around 1 Gy on average.
These results strongly indicate the high accuracy of RSP maps predicted by our machine-learning-based method and show its potential feasibility for proton treatment planning and dose calculation.
双能计算机断层扫描（DECT）已被用于通过获取光子相互作用的能量依赖性来推导相对阻止本领（RSP）图。在使用基于物理的映射技术时，DECT衍生的RSP图可能会受到图像噪声水平和伪影严重程度的影响。这项工作提出了一种基于噪声鲁棒学习的方法，用于从DECT预测质子放射治疗的RSP图。
所提出的方法使用残差注意力循环一致生成对抗网络，通过引入反向的RSP到DECT映射，使DECT到RSP的映射接近1对1映射。为了评估所提出的方法，我们回顾性研究了20例在质子放射治疗模拟中进行了DECT扫描的头颈癌患者。基于化学成分通过计算分配真实的RSP值，并在DECT数据集的训练过程中作为学习目标；使用留一法交叉验证策略将其与所提出方法的结果进行评估。
预测的RSP图在全身体积上的平均归一化均方误差为2.83%，在所有感兴趣体积中的平均平均误差小于3%。在DECT数据集中添加额外的模拟噪声后，所提出的方法仍保持了可比的性能，而基于物理的化学计量方法因噪声水平增加而准确性下降。临床靶体积的剂量体积直方图指标与真实值的平均差异在D和D时小于0.2 Gy，无统计学意义。危及器官的剂量体积直方图指标的最大差异平均约为1 Gy。
这些结果有力地表明了我们基于机器学习的方法预测的RSP图具有很高的准确性，并显示了其在质子治疗计划和剂量计算中的潜在可行性。
