基于DAHANCA真实世界数据验证头颈放疗深度学习剂量预测的多中心泛化性
该研究将单中心388例头颈癌计划训练的深度学习剂量预测模型,在内部42例和六个机构560例DAHANCA全国队列上验证。模型预测与临床计划剂量分布接近,PTV中位Dmean差-0.1 Gy,OAR为1.1 Gy,优于中位数模型;预测与临床计划的预期毒性存在差异,提示可用于质控。
要点
- 单中心训练模型在多中心头颈癌队列中剂量预测误差较小,支持泛化性。
- 模型预测与临床计划PTV中位Dmean差-0.1 Gy,OAR为1.1 Gy。
- 模型预测与临床计划的预期毒性差异或反映临床计划次优,可用于质控。
核心结论
- 深度学习剂量预测模型优于中位数模型,跨队列预测-计划差异在四分位范围内,支持泛化性。
- 模型预测与临床计划的毒性差异可能提示临床计划次优,并可用于质量保证。
研究设计与样本
- 深度神经网络在丹麦单中心388例头颈癌治疗计划上训练。
- 内部测试集42例,外部验证为六个机构560例DAHANCA全国队列。
- 采用剂量指标评价,并与中位数模型(各OAR取训练数据中位Dmean)比较。
- 用NTCP和归一化毒性指数(NTI)探索预期毒性。
主要发现
- 跨队列PTV中位Dmean差-0.1 Gy(四分位距-0.5, 0.3),OAR为1.1 Gy(-0.6, 3.7)。
- 中位数模型PTV中位Dmean差0.7 Gy(0.0, 2.1),OAR为-4.6 Gy(-14.6, 3.9),四分位距更大。
- 模型预测与临床计划比较,中位NTI差4.4%(0.4, 9.4)。
- 2级及以上口干和吞咽困难的中位NTCP差约1-3%。
临床怎么用
- 该模型可用于头颈癌自动计划与质量保证的跨机构剂量预测参考。
- 预测与临床计划的毒性差异可辅助识别次优临床计划。
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: Deep learning dose prediction shows promise for automated radiotherapy planning and quality assurance in head and neck cancer (HNC). Clinical adoption requires validation of model generalisability using clinically relevant metrics. The study evaluated generalisability of a dose prediction model trained on single-centre data in a large multi-centre cohort. MATERIALS AND METHODS: A deep neural network was trained on 388 HNC treatment plans from one Danish centre and evaluated on an internal test dataset of 42 patients and on a national DAHANCA cohort of 560 plans from six institutions. Performance was evaluated using dose metrics and compared with a median model assigning each OAR the median Dmean from the training data. Expected toxicity was explored using NTCP and the normalised toxicity index (NTI). RESULTS: Predictions closely matched clinically applied dose distributions with median Dmean differences of -0.1 Gy [interquartile range -0.5, 0.3] for PTVs and 1.1 Gy [-0.6, 3.7] for OARs across cohorts. The median-based model showed larger interquartile ranges, with Dmean differences of 0.7 Gy [0.0, 2.1] for PTVs and -4.6 Gy [-14.6, 3.9] for OARs. Comparison of expected toxicity between model-predicted and clinically applied dose distributions showed median NTI differences of 4.4% [ 0.4, 9.4] and median NTCP differences of about 1-3% for xerostomia and dysphagia grade 2+. CONCLUSIONS: The dose prediction model outperformed the median-based model, with prediction-plan differences within interquartile ranges observed across cohorts, supporting generalisability. Discrepancies between model-predicted and clinically planned toxicity may indicate suboptimality in clinical plans and could inform quality assurance.
引用
- Nielsen CP, Huet-Dastarac M, Jensen K, et al. Multi-centre generalisability of deep learning-based dose prediction for head and neck radiotherapy using DAHANCA real-world data. Radiother Oncol. 2026. PMID: 42468605. doi:10.1016/j.radonc.2026.111702
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。