文献速递泌尿生殖与妇科肿瘤放疗放疗物理与技术

基于机器学习的全自动前列腺癌放疗计划工作流

A fully automated machine-learning-based workflow for radiation treatment planning in prostate cancer.
PubMed 文献 · Clin Transl Radiat Oncol · 2025-02-11

本研究在5例低危前列腺癌外照射患者中评估结合机器学习分割与计划的全自动「一键」工作流的临床可行性,并与6位有经验放射肿瘤科医生勾画轮廓基础上的常规优化与逆向计划比较。自动深度学习靶区分割与专家轮廓总体接近,但深度学习CTV体积显著小于专家CTV(47.1 cm3 vs 62.6 cm3),基于专家轮廓的CTV与PTV剂量覆盖显著低于手工计划;作者认为该工作流临床可行、结果与常规计划相当,同时指出需改进分割模型并开展前瞻性验证。

要点

  • 全自动机器学习工作流在5例低危前列腺癌患者中产生临床可接受的计划,处于手工计划观察者间变异范围内。
  • 自动深度学习CTV体积显著小于专家CTV(47.1 cm3 vs 62.6 cm3)。
  • 因CTV分割较小,基于专家轮廓的CTV与PTV剂量覆盖显著低于手工计划。

核心结论

  • 所测试的全自动机器学习工作流临床可行,结果与常规放疗计划相当。
  • 在本评估队列中,自动分割较手工轮廓靶区体积更小,提示需改进分割模型并开展放疗自动化的前瞻性测试。

研究设计与样本

  • 在5例接受外照射放疗的低危前列腺癌患者上评估全自动机器学习「一键」工作流,结合机器学习分割与治疗计划。
  • 与基于6位有经验放射肿瘤科医生轮廓的常规优化计划和逆向计划进行比较,行定性与定量指标分析。
  • 评估机器学习计划与常规计划在不同分割(手工 vs 手工、手工 vs 自动)上的剂量分布。

主要发现

  • 自动深度学习靶区分割与专家轮廓在Dice相似度和Hausdorff指数上接近一致。
  • 深度学习CTV体积显著小于专家CTV(47.1 cm3 vs 62.6 cm3)。
  • 全自动机器学习计划提供的剂量覆盖在手工计划观察者间变异范围内,属临床可接受。
  • 因CTV分割较小,基于专家轮廓的CTV和PTV剂量覆盖显著低于手工计划。

临床怎么用

  • 该全自动机器学习「一键」工作流在前列腺癌外照射放疗计划中显示临床可行性,结果与常规计划相当。
  • 自动分割靶区体积偏小可影响基于专家轮廓的剂量覆盖,提示需改进分割模型并前瞻性测试自动化。

局限性

  • 原文未述局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

INTRODUCTION: The integration of artificial intelligence into radiotherapy planning for prostate cancer has demonstrated promise in enhancing efficiency and consistency. In this study, we assess the clinical feasibility of a fully automated machine learning (ML)-based "one-click" workflow that combines ML-based segmentation and treatment planning. The proposed workflow was designed to create a clinically acceptable radiotherapy plan within the inter-observer variation of conventional plans. METHODS: We evaluated the fully-automated workflow on five low-risk prostate cancer patients treated with external beam radiotherapy and compared the results with conventional optimized and inverse planned radiotherapy plans based on the contours of six different experienced radiation oncologists. Both qualitative and quantitative metrics were analyzed. Additionally, we evaluated the dose distribution of the ML-based and conventional radiation treatment plans on the different segmentations (manual vs. manual and manual vs. automation). RESULTS: The automatic deep-learning segmentation of the target volume revealed a close agreement between the deep-learning based and expert contours referring to Dice Similarity- and Hausdorff index. However, the deep-learning based CTVs had a significantly smaller volume than the expert CTVs (47.1 cm3 vs. 62.6 cm3). The fully automated ML-based plans provide clinically acceptable dose coverage within the range of inter-observer variability observed in the manual plans. Due to the smaller segmentation of the CTV the dose coverage of the CTV and PTV (expert contours) were significantly lower than that of the manual plans. CONCLUSION: Our study indicates that the tested fully automated ML-based workflow is clinically feasible and leads to comparable results to conventional radiation treatment plans. This represents a promising step towards efficient and standardized prostate cancer treatment. Nevertheless, in the evaluated cohort, auto segmentation was associated with smaller target volumes compared to manual contours, highlighting the necessity of improving segmentation models and prospective testing of automation in radiation therapy.

来源:Clin Transl Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Bolten JH, Neugebauer D, Grott C, et al. A fully automated machine-learning-based workflow for radiation treatment planning in prostate cancer. Clin Transl Radiat Oncol. 2025. PMID: 40028424. doi:10.1016/j.ctro.2025.100933

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。