• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of applied clinical medical physics / >An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning
【24h】

An interactive plan and model evolution method for knowledge‐based pelvic VMAT planning

机译：基于知识的骨盆VMAT计划的交互式计划和模型演化方法

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Purpose To test if a RapidPlan DVH estimation model and its training plans can be improved interactively through a closed‐loop evolution process. Methods and materials Eighty‐one manual plans (P0) that were used to configure an initial rectal RapidPlan model (M0) were reoptimized using M0 (closed‐loop), yielding 81 P1 plans. The 75 improved P1 (P1+) and the remaining 6 P0 were used to configure model M1. The 81 training plans were reoptimized again using M1, producing 23 P2 plans that were superior to both their P0 and P1 forms (P2+). Hence, the knowledge base of model M2 composed of 6 P0, 52 P1+, and 23 P2+. Models were tested dosimetrically on 30 VMAT validation cases (Pv) that were not used for training, yielding Pv(M0), Pv(M1), and Pv(M2) respectively. The 30 Pv were also optimized by M2_new as trained by the library of M2 and 30 Pv(M0). Results Based on comparable target dose coverage, the first closed‐loop reoptimization significantly ( P 1 (by 0.34 Gy/1.47%, 0.25 Gy/1.13%) and M2 (by 0.36 Gy/1.56%, 0.30 Gy/1.36%) than using M0. However, mean dose to femoral head increased by 0.81 Gy/6.64% (M1) and 0.91 Gy/7.46% (M2) than using M0. The overfitting problem was relieved by applying model M2_new. Conclusions The RapidPlan model and its constituent plans can improve each other interactively through a closed‐loop evolution process. Incorporating new patients into the original training library can improve the RapidPlan model and the upcoming plans interactively.
机译：目的测试是否可以通过闭环演化过程交互地改进RapidPlan DVH估计模型及其训练计划。方法和材料使用M 0 重新优化了用于配置初始直肠RapidPlan模型（M 0 ）的八十一个手动计划（P 0 ）。 sub>（闭环），产生81个P 1 计划。 75个改进的P 1 （P 1 + ）和其余6个P 0 用于配置模型M 1 。使用M 1 重新优化了81个训练计划，产生了23个P 2 计划，这些计划优于其P 0 和P 1 形式（P 2 + ）。因此，模型M 2 的知识库由6 P 0 ，52 P 1 + 和23 P 2+ < / sub>。在30个未用于训练的VMAT验证案例（P v ）上进行了剂量测试，得出P v （M 0 ），P v （M 1 ）和P v （M 2 ）。在M 2 和30 P v 库的训练下，M 2_new 也对30 P v 进行了优化。 （M 0 ）。结果基于可比较的目标剂量范围，首次闭环再优化显着（P 1 （分别为0.34 Gy / 1.47％，0.25 Gy / 1.13％）和M 2 （分别为0.36 Gy） /1.56%，0.30 Gy / 1.36％），而使用M 0 的患者，但股骨头平均剂量分别增加了0.81 Gy / 6.64％（M 1 ）和0.91 Gy /7.46%（M 2 ）比使用M 0 的情况要好。通过应用模型M 2_new 可以缓解过度拟合的问题。组成计划可以通过闭环演化过程相互改善，将新患者纳入原始培训库可以交互地改善RapidPlan模型和即将到来的计划。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号