Liang Yongguang, Yang Jingru, Wei Shuoyang, Liu Yanfei, He Shumeng, Zhang Kang, Qiu Jie, Yang Bo
Department of Radiation Oncology, Chinese Academy of Medical Sciences, Peking Union Medical College Hospital, Beijing, 100730, China.
United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, 518045, China.
Radiat Oncol. 2025 Aug 20;20(1):131. doi: 10.1186/s13014-025-02684-x.
Knowledge-Based Planning (KBP) pipelines, which integrate machine learning-based models to predict dose distribution, have gained popularity in clinical radiation therapy. However, for patients with specific requirements, the trained models may struggle to rapidly adjust to guide the automatic planning process. Therefore, the aim of this study was to calibrate the dose prediction model to improve the quality and accuracy of automatic planning for cervical cancer radiation therapy.
We retrospectively collected a routine cervical cancer dataset (200 cases) to conduct the KBP pipelines for automatically generating radiation planning, and a small number of ovarian-protection and myelosuppressive datasets (21 cases) to calibrate and evaluate the dose prediction model. A total of three criteria-calibration approaches to solve the data imbalance problem in dose prediction were introduced and compared, including Prediction Tolerance function on uTPS (United Imaging Healthcare Co., Ltd., Shanghai), transfer learning, and mixture density network.
The Prediction Tolerance function allowed for rapid optimization adjustments without model modification, which is suitable for patients with strong desires for ovary protection. The transfer learning approach required minimal training time and data to generate acceptable automatic planning results. The Mixture Density Network (MDN) approach, although the most time-consuming to train, achieved robust prediction results and facilitated dataset analysis. The MDN method showed the greatest consistency between predicted dose distribution and actual optimization outcomes, highlighting its potential as a reliable calibration method for dose prediction.
This study demonstrated an automatic KBP workflow and compared three criteria-calibration approaches to address the data imbalance problem in dose prediction. These approaches can partially calibrate pre-existing models to accommodate newly added criteria and could be implemented according to specific requirements in different scenarios. Although there are trade-offs in various aspects, they all can generate feasible radiation treatment plans.
基于知识的计划（KBP）流程通过集成基于机器学习的模型来预测剂量分布，在临床放射治疗中已变得越来越流行。然而，对于有特定要求的患者，经过训练的模型可能难以迅速调整以指导自动计划过程。因此，本研究的目的是校准剂量预测模型，以提高宫颈癌放射治疗自动计划的质量和准确性。
我们回顾性收集了一个常规宫颈癌数据集（200例）以进行用于自动生成放射计划的KBP流程，并收集了少量卵巢保护和骨髓抑制数据集（21例）以校准和评估剂量预测模型。共引入并比较了三种解决剂量预测中数据不平衡问题的标准校准方法，包括联影医疗科技股份有限公司（上海）的uTPS上的预测容忍函数、迁移学习和混合密度网络。
预测容忍函数无需修改模型即可进行快速优化调整，适用于对卵巢保护有强烈需求的患者。迁移学习方法生成可接受的自动计划结果所需的训练时间和数据最少。混合密度网络（MDN）方法虽然训练耗时最长，但取得了稳健的预测结果并便于进行数据集分析。MDN方法在预测剂量分布与实际优化结果之间显示出最大的一致性，突出了其作为剂量预测可靠校准方法的潜力。
本研究展示了一种自动KBP工作流程，并比较了三种标准校准方法以解决剂量预测中的数据不平衡问题。这些方法可以部分校准现有模型以适应新添加的标准，并可根据不同场景的特定要求来实施。尽管在各个方面存在权衡，但它们都可以生成可行的放射治疗计划。
