Department of Radiation Oncology, Erasmus MC, University Medical Center Rotterdam, 3015 GD, Rotterdam, The Netherlands.
Med Phys. 2020 Apr;47(4):1499-1508. doi: 10.1002/mp.14073. Epub 2020 Mar 5.
In automated treatment planning, configuration of the underlying algorithm to generate high-quality plans for all patients of a particular tumor type can be a major challenge. Often, a time-consuming trial-and-error tuning procedure is required. The purpose of this paper is to automatically configure an automated treatment planning algorithm for oropharyngeal cancer patients.
Recently, we proposed a new procedure to automatically configure the reference point method (RPM), a fast automatic multi-objective treatment planning algorithm. With a well-tuned configuration, the RPM generates a single Pareto optimal treatment plan with clinically favorable trade-offs for each patient. The automatic configuration of the RPM requires a set of computed tomography (CT) scans with corresponding dose distributions for training. Previously, we demonstrated for prostate cancer planning with 12 objectives that training with only 9 patients resulted in high-quality configurations. This paper further develops and explores the new automatic RPM configuration procedure for head and neck cancer planning with 22 objectives. Investigations were performed with planning CT scans of 105 previously treated unilateral or bilateral oropharyngeal cancer patients together with corresponding Pareto optimal treatment plans. These plans were generated with our clinically applied two-phase ε-constraint method (Erasmus-iCycle) for automated multi-objective treatment planning, ensuring consistent high quality and Pareto optimality of all plans. Clinically relevant, nonconvex criteria, such as dose-volume parameters and NTCPs, were included to steer the RPM configuration.
Training sets with 20-50 patients were investigated. Even with 20 training plans, high-quality configurations of the RPM were feasible. Automated plan generation with the automatically configured RPM resulted in Pareto optimal plans with overall similar or better quality than that of the Pareto optimal database plans.
Automatic configuration of the RPM for automated treatment planning is feasible and drastically reduces the time and workload required when compared to manual tuning of an automated treatment planning algorithm.
在自动化治疗计划中，为特定肿瘤类型的所有患者生成高质量计划的基础算法的配置可能是一个主要挑战。通常需要进行耗时的反复试验调优过程。本文的目的是为口咽癌患者自动配置自动治疗计划算法。
最近，我们提出了一种新的方法来自动配置参考点方法（RPM），这是一种快速的自动多目标治疗计划算法。通过精心调整的配置，RPM 为每个患者生成具有临床有利权衡的单一 Pareto 最优治疗计划。RPM 的自动配置需要一组具有相应剂量分布的计算机断层扫描（CT）扫描进行训练。此前，我们已经证明，对于前列腺癌规划，使用 12 个目标进行训练，仅使用 9 个患者即可获得高质量的配置。本文进一步开发并探索了新的用于头颈部癌症规划的具有 22 个目标的 RPM 自动配置程序。使用 105 例单侧或双侧口咽癌患者的治疗前 CT 扫描以及相应的 Pareto 最优治疗计划进行了研究。这些计划是使用我们临床应用的两阶段ε约束方法（Erasmus-iCycle）为自动化多目标治疗计划生成的，确保所有计划的高质量和 Pareto 最优性一致。纳入了临床相关的非凸标准，如剂量-体积参数和 NTCPs，以指导 RPM 配置。
研究了包含 20-50 个训练病例的训练集。即使使用 20 个训练计划，也可以实现 RPM 的高质量配置。使用自动配置的 RPM 进行自动计划生成可生成 Pareto 最优计划，其整体质量与 Pareto 最优数据库计划相似或更好。
RPM 的自动配置用于自动化治疗计划是可行的，与手动调整自动化治疗计划算法相比，大大减少了所需的时间和工作量。
