文献速递中枢神经肿瘤放疗头颈部肿瘤放疗泌尿生殖与妇科肿瘤放疗

深度学习自动勾画在两家癌症中心放疗计划工作流程中的实施研究

Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers.
PubMed 文献 · Radiat Oncol · 2021-06-08

在两家癌症中心实施深度学习自动勾画(DC)模型,用于中枢神经系统、头颈和前列腺癌放疗的危及器官(OAR)和临床靶区(CTV)生成。收集203份勾画后调查问卷,多数OAR DC仅需少量编辑,主观平均编辑评分≤2,客观平均DSC≥0.90且95%HD≤2.0 mm,用户满意度高,但问卷依从率仅32%。

要点

  • OAR自动勾画多数仅需少量编辑,DSC≥0.90且95%HD≤2.0 mm。
  • OAR平均满意度:CNS 4.1、头颈4.4、前列腺4.6。
  • CTV满意度4.1,但评估数量有限;问卷依从率32%是顾虑。

核心结论

  • 已验证的OAR DC模型用于CNS、头颈和前列腺放疗计划时,主观和客观编辑需求均较小,用户体验积极。
  • CTV DC模型评估有限,但高用户满意度提示其可作为患者特异性编辑的合适起点。

研究设计与样本

  • 在两家癌症中心实施DC模型,为所有接受CNS、头颈或前列腺癌放疗的患者生成OAR和CTV。
  • 放疗技师/剂量师和放疗肿瘤医生完成勾画后问卷,评价编辑程度(1=最小,5=显著)和总体满意度(1=差,5=高)。
  • 未编辑DC与编辑后治疗批准轮廓比较,使用Dice相似系数(DSC)和95% Hausdorff距离(HD)。

主要发现

  • 2019年9月19日至2020年3月6日,约551例合格病例生成DC。
  • 收集203份问卷,涉及27例CNS、54例头颈和93例前列腺放疗计划,总体问卷依从率32%。
  • 多数OAR DC主观需最小编辑(平均编辑评分≤2),客观平均DSC≥0.90且95%HD≤2.0 mm。
  • OAR平均满意度评分:CNS 4.1,头颈4.4,前列腺4.6。
  • 总体CTV满意度评分(n=25,包括前列腺、精囊和颈部淋巴结体积)为4.1。

关键数值与推荐

  • OAR DC主观编辑评分均值≤2(1=最小,5=显著)。
  • OAR DC客观平均DSC≥0.90且95%HD≤2.0 mm。
  • OAR平均满意度:CNS 4.1、头颈4.4、前列腺4.6(1=差,5=高)。
  • 总体CTV满意度(n=25)为4.1。
  • 问卷总体依从率32%。

临床怎么用

  • OAR自动勾画可用于CNS、头颈和前列腺癌放疗计划,多数仅需少量编辑。
  • CTV自动勾画可作为患者特异性编辑的起点,但需注意评估病例有限。
  • 低问卷依从率提示需改进用户反馈收集机制。

局限性

  • 问卷依从率仅32%,可能影响用户经验评价的代表性。
  • CTV DC模型评估更有限(满意度问卷n=25),结论需谨慎解读。

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

PURPOSE: We recently described the validation of deep learning-based auto-segmented contour (DC) models for organs at risk (OAR) and clinical target volumes (CTV). In this study, we evaluate the performance of implemented DC models in the clinical radiotherapy (RT) planning workflow and report on user experience. METHODS AND MATERIALS: DC models were implemented at two cancer centers and used to generate OAR and CTVs for all patients undergoing RT for a central nervous system (CNS), head and neck (H&N), or prostate cancer. Radiation Therapists/Dosimetrists and Radiation Oncologists completed post-contouring surveys rating the degree of edits required for DCs (1 = minimal, 5 = significant) and overall DC satisfaction (1 = poor, 5 = high). Unedited DCs were compared to the edited treatment approved contours using Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD). RESULTS: Between September 19, 2019 and March 6, 2020, DCs were generated on approximately 551 eligible cases. 203 surveys were collected on 27 CNS, 54 H&N, and 93 prostate RT plans, resulting in an overall survey compliance rate of 32%. The majority of OAR DCs required minimal edits subjectively (mean editing score ≤ 2) and objectively (mean DSC and 95% HD was ≥ 0.90 and ≤ 2.0 mm). Mean OAR satisfaction score was 4.1 for CNS, 4.4 for H&N, and 4.6 for prostate structures. Overall CTV satisfaction score (n = 25), which encompassed the prostate, seminal vesicles, and neck lymph node volumes, was 4.1. CONCLUSIONS: Previously validated OAR DC models for CNS, H&N, and prostate RT planning required minimal subjective and objective edits and resulted in a positive user experience, although low survey compliance was a concern. CTV DC model evaluation was even more limited, but high user satisfaction suggests that they may have served as appropriate starting points for patient specific edits.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Wong J, Huang V, Wells D, et al. Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers. Radiat Oncol. 2021. PMID: 34103062. doi:10.1186/s13014-021-01831-4

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。