Ni Yimin, Chen Shufei, Hibbard Lyndon, Voet Peter
Elekta (Shanghai) Technology Co. Ltd, Shanghai, People's Republic of China.
Elekta Inc., St. Charles, MO, United States of America.
Phys Med Biol. 2022 Jul 27;67(15). doi: 10.1088/1361-6560/ac80e5.
. To develop and evaluate a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method for prostate radiotherapy.. A customized 3D U-Net was trained and validated to predict initial segments at 90 evenly distributed control points of an arc, linked to our research treatment planning system (TPS) for segment shape optimization (SSO) and segment weight optimization (SWO). For 27 test patients, the VMAT plans generated based on the deep learning prediction (VMAT) were compared with VMAT plans generated with a previously validated automated treatment planning method (VMAT). For all test cases, the deep learning prediction accuracy, plan dosimetric quality, and the planning efficiency were quantified and analyzed.. For all 27 test cases, the resulting plans were clinically acceptable. Thefor the PTV2 was greater than 99%, and thewas below 0.2%. Statistically significant difference in target coverage was not observed between the VMATand VMATplans ( = 0.3243 > 0.05). The dose sparing effect to the OARs between the two groups of plans was similar. Small differences were only observed for the Dmean of rectum and anus. Compared to the VMAT, the VMATreduced 29.3% of the optimization time on average.. A fully automated VMAT plan generation method may result in significant improvement in prostate treatment planning efficiency. Due to the clinically acceptable dosimetric quality and high efficiency, it could potentially be used for clinical planning application and real-time adaptive therapy application after further validation.
开发并评估一种基于深度学习的前列腺癌放射治疗快速容积调强弧形治疗（VMAT）计划生成方法。定制了一个3D U-Net并进行训练和验证，以预测弧形的90个均匀分布控制点处的初始射野分段，这些分段与我们的研究治疗计划系统（TPS）相连，用于射野形状优化（SSO）和射野权重优化（SWO）。对于27例测试患者，将基于深度学习预测生成的VMAT计划（VMAT）与使用先前验证的自动治疗计划方法生成的VMAT计划进行比较。对所有测试病例，量化并分析深度学习预测准确性、计划剂量学质量和计划效率。对于所有27例测试病例，生成的计划在临床上是可接受的。PTV2的覆盖率大于99%，而[此处原文缺失相关指标名称]低于0.2%。VMAT和VMAT计划之间在靶区覆盖方面未观察到统计学显著差异（P = 0.3243 > 0.05）。两组计划对危及器官的剂量 sparing效应相似。仅在直肠和肛门的平均剂量（Dmean）方面观察到小的差异。与VMAT相比，VMAT平均减少了29.3%的优化时间。一种全自动VMAT计划生成方法可能会显著提高前列腺癌治疗计划效率。由于其在临床上可接受的剂量学质量和高效率，经过进一步验证后，它有可能用于临床计划应用和实时自适应治疗应用。
