文献速递头颈部肿瘤放疗放疗物理与技术

多毒性深度学习模型用于头颈癌放疗正常组织并发症概率建模

A multi-toxicity deep learning approach for normal tissue complication probability modelling in head and neck cancer patients receiving radiotherapy.
PubMed 文献 · Radiother Oncol · 2026-03-17

本研究利用1418例头颈癌患者的多中心队列,开发并验证了可同时预测五种放疗后6个月毒性的多毒性深度学习NTCP模型。结果显示该模型在吞咽困难和口干预测上优于传统及单毒性模型,但部分终点获益不显著或被单毒性模型超越,外部队列中各模型性能相近。

要点

  • 多毒性模型在吞咽困难(AUC 0.83 vs 0.81/0.82)和口干(0.80 vs 0.75/0.78)预测上优于传统及单毒性模型。
  • 多毒性模型在黏唾液和味觉改变上未优于单毒性模型,提示获益因终点而异。
  • 外部队列中多毒性模型平均AUC(0.64)仅略高于传统及单毒性模型(均0.63)。

核心结论

  • 多毒性深度学习NTCP模型性能与传统单终点方法相当,部分终点有所提升,但获益不统一。

研究设计与样本

  • 多中心队列纳入1418例头颈癌患者,开发并验证可同时预测五种毒性的多毒性深度学习模型。
  • 模型输入包括3D剂量分布、CT扫描、危及器官分割和患者相关特征。
  • 对比传统NTCP模型及一组单毒性3D深度学习模型,在独立验证队列和外部验证队列中评估。

主要发现

  • 独立验证队列中,多毒性模型预测吞咽困难AUC为0.83,传统模型0.81,单毒性模型0.82。
  • 独立验证队列中,多毒性模型预测口干AUC为0.80,传统模型0.75,单毒性模型0.78。
  • 独立验证队列中,单毒性模型预测黏唾液AUC为0.72和0.71,多毒性模型0.69;预测味觉改变AUC均为0.67,多毒性模型0.71。
  • 独立验证队列中,多毒性模型预测误吸AUC为0.71,高于单毒性模型0.71?原文为多毒性模型误吸AUC高于单毒性模型(0.71),但与参考模型相当(均0.74)。
  • 外部验证队列中,所有模型性能相近,多毒性模型所有终点平均AUC为0.64,传统和单毒性模型均为0.63。

关键数值与推荐

  • 五种毒性终点为误吸、吞咽困难、黏唾液、味觉改变和口干,均在治疗后6个月评估。

临床怎么用

  • 多毒性建模可用于头颈癌放疗后多终点NTCP预测,但需注意不同毒性终点获益不一致。
  • 设计多毒性模型时应考虑毒性特异性特征,而非假设所有终点均能从中获益。

局限性

  • 多毒性建模的获益因终点而异,并非所有终点均优于单终点方法。
  • 外部验证队列中各模型性能相近,多毒性模型的优势有限。

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: Toxicities after radiotherapy for head and neck cancer (HNC) often co-occur and share underlying mechanisms, yet most conventional and deep learning (DL) NTCP models predict only a single endpoint. By developing DL NTCP models which can predict multiple toxicities simultaneously, this study aimed to capture inter-toxicity relationships to improve prediction performance. METHODS AND MATERIALS: A multi-institutional cohort of 1,418 HNC patients was used to develop and validate a multi-toxicity (MT) DL model, incorporating 3D dose distributions, CT scans, organ-at-risk segmentations and patient-related features, that simultaneously predicts five toxicities; aspiration, dysphagia, sticky saliva, taste alteration and xerostomia, all evaluated six months after treatment. Results are compared to conventional NTCP models, as well as a set of single-toxicity (ST) 3D DL models. RESULTS: The MT model outperformed both the conventional and ST models for dysphagia (AUC = 0.83 versus 0.81 and 0.82) and xerostomia (0.80 versus 0.75 and 0.78) prediction on the independent validation cohort. The latter models achieved better performance for sticky saliva (0.72 and 0.71 versus 0.69) and taste alteration (both 0.67 versus 0.71). The MT model achieved a higher AUC on aspiration than the ST model (0.71), but performed as well as the reference model (both 0.74). Within the external validation cohort, all models performed comparably to each other, with the MT model achieving a slightly higher average AUC (0.64) across all endpoints than the conventional and ST models (both 0.63). Sub-analyses revealed that the benefit of the proposed multi-toxicity modelling varied by endpoint. CONCLUSION: MT models offer comparable-and in some cases improved-performance over conventional single-endpoint approaches, indicating their promise for NTCP modelling. However, benefits are not uniform across all endpoints, highlighting the importance of considering toxicity-specific features when designing multi-toxicity models.

来源:Radiother Oncol,查看原文。版权归原作者所有。

引用

  1. MacRae DC, van der Hoek L, de Vette SPM, et al. A multi-toxicity deep learning approach for normal tissue complication probability modelling in head and neck cancer patients receiving radiotherapy. Radiother Oncol. 2026. PMID: 41856253. doi:10.1016/j.radonc.2026.111486

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。