A broad scope knowledge based model for optimization of VMAT in esophageal cancer: validation and assessment of plan quality among different treatment centers.
A broad scope knowledge based model for optimization of VMAT in esophageal cancer: validation and assessment of plan quality among different treatment centers.
复制标题
DOI：
10.1186/s13014-015-0530-5
复制
发表时间：
2015-10-31
期刊：
影响因子：
--
通讯作者：
Cozzi L
中科院分区：
文献类型：
--
作者：
Fogliata A;Nicolini G;Clivio A;Vanetti E;Laksar S;Tozzi A;Scorsetti M;Cozzi L
评估一种基于大范围模型的优化流程在食道癌容量调节弧形治疗中的应用效果。选择了一组来自两个不同机构的70名先前接受治疗的患者，以训练一个用于预测剂量-体积约束的模型。该模型具有广泛的用途，旨在对不同剂量的处方和肿瘤的定位有效。它在来自同一机构和另一家诊所的三组患者身上进行了验证，这些患者没有为培训阶段提供患者。将自动计划与临床接受的计划提供的参考病例进行比较。在基准和测试计划之间观察到了数量上的改进(对大多数分析的剂量-体积参数具有统计学意义)。在为计划评估而评估的624个剂量-体积目标中，21例(3.3%)参考计划未能尊重约束，而基于模型的计划成功。仅有3例(0.5%)参考计划通过标准，而基于模型的失败。在5.3%的情况下，两组计划都不合格，在其余情况下，两组计划都通过了测试。使用基于知识的大范围模型优化计划，以确定剂量-体积约束。结果显示，与基准数据相比，剂量学有所改善。特别是为来自第三中心的患者优化的计划，没有参加培训，导致了卓越的质量。数据表明，新发动机是可靠的，可能会鼓励其在临床实践中的应用。本文的在线版本(doi：10.1186/s13014-0150530-5)包含补充材料，授权用户可以使用。
To evaluate the performance of a broad scope model-based optimisation process for volumetric modulated arc therapy applied to esophageal cancer. A set of 70 previously treated patients in two different institutions, were selected to train a model for the prediction of dose-volume constraints. The model was built with a broad-scope purpose, aiming to be effective for different dose prescriptions and tumour localisations. It was validated on three groups of patients from the same institution and from another clinic not providing patients for the training phase. Comparison of the automated plans was done against reference cases given by the clinically accepted plans. Quantitative improvements (statistically significant for the majority of the analysed dose-volume parameters) were observed between the benchmark and the test plans. Of 624 dose-volume objectives assessed for plan evaluation, in 21 cases (3.3 %) the reference plans failed to respect the constraints while the model-based plans succeeded. Only in 3 cases (<0.5 %) the reference plans passed the criteria while the model-based failed. In 5.3 % of the cases both groups of plans failed and in the remaining cases both passed the tests. Plans were optimised using a broad scope knowledge-based model to determine the dose-volume constraints. The results showed dosimetric improvements when compared to the benchmark data. Particularly the plans optimised for patients from the third centre, not participating to the training, resulted in superior quality. The data suggests that the new engine is reliable and could encourage its application to clinical practice. The online version of this article (doi:10.1186/s13014-015-0530-5) contains supplementary material, which is available to authorized users.