The capacity for machine learning (ML) to facilitate radiotherapy (RT) planning for primary brain tumors has not been described. We evaluated ML-assisted RT planning with regards to clinical acceptability, dosimetric outcomes and planning efficiency for adults and children with primary brain tumours. In this prospective study, children and adults receiving 54 Gy fractionated radiotherapy for a primary brain tumor were enrolled. For each patient, one ML-assisted RT plan was created and compared with one or two plans created using standard (“manual”) planning procedures. Plans were evaluated by the treating oncologist, who was blinded to the method of plan creation. The primary endpoint was the proportion of ML plans that were clinically acceptable for treatment. Secondary endpoints included the frequency with which ML plans were selected as preferable for treatment, and dosimetric differences between ML and manual plans. A total of 116 manual plans and 61 ML plans were evaluated across 61 patients. Ninety-four percent of ML plans and 93% of manual plans were judged to be clinically acceptable (p = 1.0). Overall, the quality of ML plans were similar to manual plans. ML plans comprised 34.5% of all plans evaluated, and were selected for treatment in 36.1% of cases (p = 0.82). Similar tumor target coverage was achieved between both planning methods. Normal brain (brain minus PTV) received an average of 1 Gy less mean dose with ML plans (as compared to manual plans, p < 0.001). ML plans required an average of 45.8 minutes less time to create, as compared with manual plans (p < 0.001). ML-assisted automated planning creates high-quality plans for patients with brain tumours, including children. Plans created with ML assistance delivered slightly less dose to normal brain tissues, and can be designed in less time.

中文翻译：

---

针对接受 54 Gy 脑部照射的患者的机器学习辅助放射治疗计划的前瞻性研究

机器学习 (ML) 促进原发性脑肿瘤放射治疗 (RT) 规划的能力尚未被描述。我们评估了机器学习辅助 RT 计划对患有原发性脑肿瘤的成人和儿童的临床可接受性、剂量测定结果和计划效率。在这项前瞻性研究中，儿童和成人因原发性脑肿瘤接受 54 Gy 分割放射治疗。对于每位患者，创建一个 ML 辅助 RT 计划，并与使用标准（“手动”）计划程序创建的一两个计划进行比较。计划由治疗肿瘤科医生评估，但他对计划创建方法一无所知。主要终点是临床可接受治疗的 ML 计划的比例。次要终点包括选择 ML 计划作为治疗首选的频率，以及 ML 和手动计划之间的剂量差异。总共对 61 名患者评估了 116 个手动计划和 61 个 ML 计划。94% 的 ML 计划和 93% 的手动计划被认为是临床可接受的 (p = 1.0)。总体而言，机器学习计划的质量与手动计划相似。ML 计划占所有评估计划的 34.5%，并在 36.1% 的病例中被选择进行治疗 (p = 0.82)。两种规划方法之间实现了类似的肿瘤靶点覆盖。正常大脑（大脑减去 PTV）接受 ML 计划的平均剂量平均减少 1 Gy（与手动计划相比，p < 0.001）。与手动计划相比，ML 计划的创建时间平均减少 45.8 分钟 (p < 0.001)。机器学习辅助的自动化规划为脑肿瘤患者（包括儿童）创建高质量的计划。利用机器学习辅助创建的计划向正常脑组织提供的剂量略少，并且可以在更短的时间内设计。