文献速递消化道肿瘤放疗放疗物理与技术

基于CT的直肠癌多靶区自动分割用于一体化放疗

CT-based auto-segmentation of multiple target volumes for all-in-one radiotherapy in rectal cancer patients.
PubMed 文献 · Radiat Oncol · 2025-08-19

本研究纳入312例直肠癌患者,用272例训练三个nnU-Net模型分别分割CTV45、CTV50和GTV,40例用于内部、临床AIO及两个外部队列评估。结果显示模型分割精度较高,自动分割使手动勾画时间减少63.3–88.3%(p<0.0001),多中心测试也显示适用性。

要点

  • 内部测试集CTV45、CTV50、GTV的平均DSC分别为0.90、0.86、0.71。
  • 自动分割使手动勾画时间减少63.3–88.3%(p<0.0001)。
  • 临床实践中CTV45、CTV50、GTV平均DSC分别为0.93、0.88、0.78。

核心结论

  • 模型精度高且具临床实用性,可简化靶区勾画并减少常规实践中的手动工作量。

研究设计与样本

  • 纳入312例直肠癌患者,272例训练三个nnU-Net模型分别分割CTV45、CTV50和GTV,40例用于评估。
  • 评估队列包括一个内部测试集(n=10)、一个临床AIO队列(n=10)和两个外部队列(各n=10)。
  • 评估指标包括DSC、HD、HD95、ASSD、ASD及时间效率。

主要发现

  • 内部测试集CTV45、CTV50、GTV平均DSC分别为0.90、0.86、0.71。
  • 内部测试集CTV45、CTV50、GTV的HD分别为17.08、25.48、79.59 mm,HD95分别为4.89、7.33、56.49 mm。
  • 内部测试集CTV45、CTV50、GTV的ASSD分别为1.23、1.90、6.69 mm,ASD分别为1.24、1.58、11.61 mm。
  • 自动分割使手动勾画时间减少63.3–88.3%(p<0.0001)。
  • 临床实践中CTV45、CTV50、GTV平均DSC分别为0.93、0.88、0.78,多中心测试CTV45和GTV平均DSC分别为0.84和0.80。

临床怎么用

  • 可将基于CT的nnU-Net自动分割模型整合至一体化放疗流程,辅助直肠癌CTV45、CTV50和GTV勾画。
  • 自动分割可显著减少手动勾画时间,但GTV精度相对较低,临床需人工审核修正。

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

BACKGROUND: This study aimed to evaluate the clinical feasibility and performance of CT-based auto-segmentation models integrated into an All-in-One radiotherapy workflow for rectal cancer. METHODS: This study included 312 rectal cancer patients, with 272 used to train three nnU-Net models for CTV45, CTV50, and GTV segmentation, and 40 for evaluation across one internal (n = 10), one clinical AIO (n = 10), and two external cohorts (n = 10 each). Segmentation accuracy (DSC, HD, HD95, ASSD, ASD) and time efficiency were assessed. RESULTS: In the internal testing set, mean DSC of CTV45, CTV50, and GTV were 0.90, 0.86, and 0.71; HD were 17.08, 25.48, and 79.59 mm; HD 95 were 4.89, 7.33, and 56.49 mm; ASSD were 1.23, 1.90, and 6.69 mm; and ASD were 1.24, 1.58, and 11.61 mm. Auto-segmentation reduced manual delineation time by 63.3–88.3% (p < 0.0001). In clinical practice, average DSC of CTV45, CTV50 and GTV were 0.93, 0.88, and 0.78; HD were 13.56, 23.84, and 35.38 mm; HD 95 were 3.33, 6.46, and 21.34 mm; ASSD were 0.78, 1.49, and 3.30 mm; and ASD were 0.74, 1.18, and 2.13 mm. The results from the multi-center testing also showed applicability of these models, since the average DSC of CTV45 and GTV were 0.84 and 0.80 respectively. CONCLUSIONS: The models demonstrated high accuracy and clinical utility, effectively streamlining target volume delineation and reducing manual workload in routine practice. TRIAL REGISTRATION: The study protocol was approved by the Institutional Review Board of Peking University Third Hospital (Approval No. (2024) Medical Ethics Review No. 182-01).

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Li X, Wang L, Yang M, et al. CT-based auto-segmentation of multiple target volumes for all-in-one radiotherapy in rectal cancer patients. Radiat Oncol. 2025. PMID: 40830483. doi:10.1186/s13014-025-02694-9

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。