基于机器学习的治疗床参数预测以支持表面引导放射治疗。
Machine learning-based treatment couch parameter prediction in support of surface guided radiation therapy.
作者信息
De Kerf Geert, Claessens Michaël, Mollaert Isabelle, Vingerhoed Wim, Verellen Dirk
机构信息
Iridium Netwerk, Antwerp, Belgium.
Department of Radiation Oncology, Faculty of Medicine and Health Sciences, University of Antwerp, Antwerp, Belgium.
出版信息
Tech Innov Patient Support Radiat Oncol. 2022 Aug 12;23:15-20. doi: 10.1016/j.tipsro.2022.08.001. eCollection 2022 Sep.
PURPOSE
A fully independent, machine learning-based automatic treatment couch parameters prediction was developed to support surface guided radiation therapy (SGRT)-based patient positioning protocols. Additionally, this approach also acts as a quality assurance tool for patient positioning.
MATERIALS/METHODS: Setup data of 183 patients, divided into four different groups based on used setup devices, was used to calculate the difference between the predicted and the acquired treatment couch value.
RESULTS
Couch parameters can be predicted with high precision . A significant difference (p < 0.01) between the variances of Lung and Brain patients was found. Outliers were not related to the prediction accuracy, but are due to inconsistencies during initial patient setup.
CONCLUSION
Couch parameters can be predicted with high accuracy and can be used as starting point for SGRT-based patient positioning. In case of large deviations (>1.5 cm), patient setup has to be verified to optimally use the surface scanning system.
目的
开发一种完全独立的、基于机器学习的自动治疗床参数预测方法，以支持基于表面引导放射治疗（SGRT）的患者定位方案。此外，该方法还可作为患者定位的质量保证工具。
材料/方法：根据所使用的定位设备将183例患者的设置数据分为四个不同的组，用于计算预测的治疗床值与获取的治疗床值之间的差异。
结果
治疗床参数能够高精度预测。发现肺部和脑部患者的方差之间存在显著差异（p < 0.01）。异常值与预测准确性无关，而是由于患者初始设置期间的不一致性导致的。
结论
治疗床参数能够高精度预测，可作为基于SGRT的患者定位的起点。在偏差较大（>1.5厘米）的情况下，必须对患者设置进行验证，以便最佳地使用表面扫描系统。
Zotero 插件