Department of Physics and Astronomy, University of Calgary, Calgary, Alberta, Canada; Department of Medical Physics, Tom Baker Cancer Centre, Calgary, Alberta, Canada.
Department of Physics and Astronomy, University of Calgary, Calgary, Alberta, Canada; Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MD.
Brachytherapy. 2024 May-Jun;23(3):368-376. doi: 10.1016/j.brachy.2024.02.008. Epub 2024 Mar 26.
To Demonstrate the clinical validation of a machine learning (ML) model for applicator and interstitial needle prediction in gynecologic brachytherapy through a prospective clinical study in a single institution.
The study included cervical cancer patients receiving high-dose-rate brachytherapy using intracavitary (IC) or hybrid interstitial (IC/IS) applicators. For each patient, the primary radiation oncologist contoured the high-risk clinical target volume on a pre-brachytherapy MRI, indicated the approximate applicator location, and made a clinical determination of the first fraction applicator. A pre-trained ML model predicted the applicator and IC/IS needle arrangement using tumor geometry. Following the first fraction, ML and radiation oncologist predictions were compared and a replanning study determined the applicator providing optimal organ-at-risk (OAR) dosimetry. The ML-predicted applicator and needle arrangement and the clinical determination were compared to this dosimetric ground truth.
Ten patients were accrued from December 2020 to October 2022. Compared to the dosimetrically optimal applicator, both the radiation oncologist and ML had an accuracy of 70%. ML demonstrated better identification of patients requiring IC/IS applicators and provided balanced IC and IC/IS predictions. The needle selection model achieved an average accuracy of 82.5%. ML-predicted needle arrangements matched or improved plan quality when compared to clinically selected arrangements. Overall, ML predictions led to an average total improvement of 2.0 Gy to OAR doses over three treatment fractions when compared to clinical predictions.
In the context of a single institution study, the presented ML model demonstrates valuable decision-support for the applicator and needle selection process with the potential to provide improved dosimetry. Future work will include a multi-center study to assess generalizability.
通过单机构前瞻性临床研究，展示机器学习（ML）模型在妇科近距离放疗中预测施源器和间质针的临床验证。
该研究纳入了接受高剂量率腔内（IC）或混合间质（IC/IS）施源器近距离放疗的宫颈癌患者。对于每位患者，主要放射肿瘤学家在近距离放疗前 MRI 上勾画高危临床靶区（CTV），指示大致施源器位置，并对第一分割施源器进行临床判断。一个预先训练的 ML 模型使用肿瘤几何形状预测施源器和 IC/IS 针布局。在第一分割后，比较 ML 和放射肿瘤学家的预测，并进行再计划研究以确定提供最佳器官危及器官（OAR）剂量学的施源器。将 ML 预测的施源器和针布局与临床判断与该剂量学基准进行比较。
2020 年 12 月至 2022 年 10 月期间共纳入了 10 名患者。与最佳剂量学的施源器相比，放射肿瘤学家和 ML 的准确性均为 70%。ML 能更好地识别需要 IC/IS 施源器的患者，并提供平衡的 IC 和 IC/IS 预测。针选择模型的平均准确率为 82.5%。与临床选择的布局相比，ML 预测的针布局匹配或改善了计划质量。总体而言，与临床预测相比，ML 预测在三个治疗分期间平均使 OAR 剂量提高了 2.0Gy。
在单机构研究的背景下，所提出的 ML 模型为施源器和针选择过程提供了有价值的决策支持，有可能提供更好的剂量学。未来的工作将包括一项多中心研究，以评估其普遍性。
