Knowledge-based dose prediction models for head and neck cancer are strongly affected by interorgan dependency and dataset inconsistency
Knowledge-based dose prediction models for head and neck cancer are strongly affected by interorgan dependency and dataset inconsistency
复制标题
DOI：
10.1002/mp.13316
复制
发表时间：
2019-02-01
期刊：
影响因子：
3.8
通讯作者：
Petit, Steven F.
中科院分区：
文献类型：
--
作者：
Wang, Yibing;Heijmen, Ben J. M.;Petit, Steven F.
目的本研究的目标是为头颈部（H&N）癌症患者生成一个大型治疗计划数据库，该数据库可以被视为训练和验证基于知识（KB）的治疗计划和QA模型的金标准。有了这个数据集，内在的预测性能，器官间的依赖性的影响，和数据集不一致的影响进行了调查，为现有的治疗规划QA model.MethodsThe CT扫描的108个先前治疗的口咽部患者被用来建立计划数据库。对于每名患者，使用全自动多标准治疗计划生成15个具有腮腺不同计划优先级的帕累托最优治疗计划（共1620个计划）。对于数据库中的15组计划中的每一组，使用54名患者训练KB模型，并通过将预测与实现的剂量进行比较来验证其他54名患者。评估KB模型的剂量预测准确性（预测达到），并在不同模型之间进行比较，以表征器官间依赖性的内在性能和影响。此外，通过混合具有不同优先级的计划，对于训练，验证数据集以及对于两者的组合，调查了关于规划优先级的数据集不一致性的影响。ResultsIn高规划优先级的情况下，腮腺的平均剂量的预测误差的均值SD仅为0.2 +/- 2.2Gy，但在腮腺具有低计划优先级的情况下，这增加到1.0 ± 5.0Gy。数据集不一致（在计划优先级）导致腮腺的预测误差大幅增加（平均值+/- SD）从0.2 +/- 2.2戈伊至2.8 +/-3.3戈伊、-3.2 +/-5.0戈伊或-0.6 +/-5.4戈伊，根据数据集混合的方式。结论生成的计划数据库可用于验证和表征H&癌症，并将根据要求提供。研究的KB模型在腮腺具有高计划优先级（对较低优先级OAR的依赖性很小）的情况下表现良好，但对于剂量强烈依赖于其他较高优先级OAR的器官表现不佳。为了提高H&N癌症的KB预测模型的性能，应该对器官间依赖性进行建模和说明。数据集不一致性对KB模型的预测误差有很大的负面影响，应尽可能避免。
PurposeThe goal of this study was to generate a large treatment plan database for head and neck (H&N) cancer patients that can be considered as the gold standard to train and validate models for knowledge-based (KB) treatment planning and QA. With this dataset, the intrinsic prediction performance, the effect of interorgan dependency, and the impact of dataset inconsistency was investigated for an existing treatment planning QA model.MethodsThe CT scans of 108 previously treated oropharyngeal patients were used to establish the plan database. For each patient, 15 Pareto optimal treatment plans with different planning priorities for the parotid glands were generated with fully automatic multicriterial treatment planning (1620 plans in total). For each of the 15 sets of plans in the database, a KB model was trained with 54 patients and validated on the other 54 by comparing the predictions with the achieved doses. The dose prediction accuracy (predictedachieved) of the KB models was assessed and compared among the different models to characterize the intrinsic performance and effect of interorgan dependency. In addition, the effect of dataset inconsistency with respect to planning prioritizations was investigated by mixing plans with different prioritizations, for the training, the validation dataset, and for both combined.ResultsIn the case of a high planning priority, the meanSD of the prediction error for the mean dose of the parotid glands was only 0.2 +/- 2.2Gy, but this increased to 1.0 +/- 5.0Gy in the case that the parotid glands had a low planning priority. Dataset inconsistency (in planning priority) led to a large increase in prediction error for the parotid glands (mean +/- SD) from 0.2 +/- 2.2 Gy to 2.8 +/- 3.3Gy, -3.2 +/- 5.0Gy or -0.6 +/- 5.4Gy, depending on the way the datasets were mixed.ConclusionsThe generated plan database can be used to validate and characterize KB prediction models for H&N cancer and will be made available upon request. The investigated KB model performed well in case the parotid glands had a high planning priority (little dependence on lower priority OARs), but poorly for organs for which the dose strongly depends on other higher priority OARs. To improve the performance of KB prediction models for H&N cancer, interorgan dependency should be modeled and accounted for. Dataset inconsistency has a large negative impact on the prediction errors of KB models and should be avoided as much as possible.