Harms Joseph, Lei Yang, Wang Tonghe, McDonald Mark, Ghavidel Beth, Stokes William, Curran Walter J, Zhou Jun, Liu Tian, Yang Xiaofeng
Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.
Med Phys. 2020 Sep;47(9):4416-4427. doi: 10.1002/mp.14347. Epub 2020 Jul 27.
In intensity-modulated proton therapy (IMPT), protons are used to deliver highly conformal dose distributions, targeting tumors, and sparing organs-at-risk. However, due to uncertainties in both patient setup and relative stopping power (RSP) calculation, margins are added to the treatment volume during treatment planning, leading to higher doses to normal tissues. Cone-beam computed tomography (CBCT) images are taken daily before treatment; however, the poor image quality of CBCT limits the use of these images for online dose calculation. In this work, we use a deep-learning-based method to predict RSP maps from daily CBCT images, allowing for online dose calculation in a step toward adaptive radiation therapy.
Twenty-three head-and-neck cancer patients were simulated using a Siemens TwinBeam dual-energy CT (DECT) scanner. Mixed-energy scans (equivalent to a 120 kVp single-energy CT scan) were converted to RSP maps for treatment planning. Cone-beam computed tomography images were taken on the first day of treatment, and the planning RSP maps were registered to these images. A deep learning network based on a cycle-GAN architecture, relying on a compound loss function designed for structural and contrast preservation, was then trained to create an RSP map from a CBCT image. Leave-one-out and holdout cross validations were used for evaluation, and mean absolute error (MAE), mean error (ME), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were used to quantify the differences between the CT-based and CBCT-based RSP maps. The proposed method was compared to a deformable image registration-based method which was taken as the ground truth and two other deep learning methods. For one patient who underwent resimulation, the new planning RSP maps and CBCT images were used for further evaluation and validation.
The CBCT-based RSP generation method was evaluated on 23 head-and-neck cancer patients. From leave-one-out testing, the MAE between CT-based and CBCT-based RSP was 0.06 ± 0.01 and the ME was -0.01 ± 0.01. The proposed method statistically outperformed the comparison DL methods in terms of MAE and ME when compared to the planning CT. In terms of dose comparison, the mean gamma passing rate at 3%/3 mm was 94% when three-dimensional (3D) gamma index was calculated per plan and 96% when gamma index was calculated per field.
The proposed method provides sufficiently accurate RSP map generation from CBCT images, allowing for evaluation of daily dose based on CBCT and possibly allowing for CBCT-guided adaptive treatment planning for IMPT.
在调强质子治疗（IMPT）中，质子用于传递高度适形的剂量分布，靶向肿瘤并保护危及器官。然而，由于患者摆位和相对阻止本领（RSP）计算存在不确定性，在治疗计划期间会在治疗体积上添加边界，导致正常组织接受更高剂量。每天在治疗前采集锥束计算机断层扫描（CBCT）图像；然而，CBCT的图像质量较差，限制了这些图像在在线剂量计算中的应用。在这项工作中，我们使用基于深度学习的方法从每日CBCT图像预测RSP图，朝着自适应放射治疗迈出一步，实现在线剂量计算。
使用西门子双束双能CT（DECT）扫描仪对23例头颈癌患者进行模拟。将混合能量扫描（相当于120 kVp单能CT扫描）转换为RSP图用于治疗计划。在治疗的第一天采集CBCT图像，并将计划的RSP图配准到这些图像上。然后训练基于循环生成对抗网络（cycle-GAN）架构的深度学习网络，该网络依赖于为结构和对比度保留设计的复合损失函数，以从CBCT图像创建RSP图。采用留一法和验证集交叉验证进行评估，使用平均绝对误差（MAE）、平均误差（ME）、峰值信噪比（PSNR）和结构相似性（SSIM）来量化基于CT的RSP图和基于CBCT的RSP图之间的差异。将所提出的方法与基于可变形图像配准的方法（作为基准事实）以及其他两种深度学习方法进行比较。对于一名接受重新模拟的患者，使用新的计划RSP图和CBCT图像进行进一步评估和验证。
基于CBCT的RSP生成方法在23例头颈癌患者上进行了评估。从留一法测试来看，基于CT的RSP和基于CBCT的RSP之间的MAE为0.06±0.01，ME为-0.01±0.01。与计划CT相比，所提出的方法在MAE和ME方面在统计学上优于比较的深度学习方法。在剂量比较方面，按每个计划计算三维（3D）伽马指数时，3%/3 mm处的平均伽马通过率为94%，按每个射野计算伽马指数时为96%。
所提出的方法能从CBCT图像生成足够准确的RSP图，允许基于CBCT评估每日剂量，并可能允许对头颈癌调强质子治疗进行CBCT引导的自适应治疗计划。
