深度学习引导的剂量学用于减轻接受立体定向体部放疗的非小细胞肺癌患者的局部失败
研究基于535例接受50 Gy/5分次立体定向体部放疗的非小细胞肺癌患者,开发可解释深度学习局部反应模型,识别与局部控制相关的剂量体积指标及其最佳切点。模型交叉验证c-index为0.72(95%CI 0.68-0.75),测试c-index为0.69,空间注意力集中于肿瘤周边区域。结论认为深度学习识别的剂量体积指标具有显著预后价值(log-rank P=0.003),可作为治疗计划的附加可操作标准。
要点
- 模型识别IGTV中BED Dnear-min≥103.8 Gy与局部控制改善相关(HR 0.31,95%CI 0.15-0.63)。
- IGTV中V104≥98%(HR 0.30,95%CI 0.15-0.60)与局部控制改善相关。
- PTV-IGTV中gEUD≥103.8 Gy(HR 0.25,95%CI 0.12-0.50)与Dmean≥104.5 Gy(HR 0.25,95%CI 0.12-0.51)与局部控制改善相关。
核心结论
- 深度学习识别的剂量体积指标显示出显著预后价值(log-rank P=0.003),可作为接受50 Gy/5分次立体定向体部放疗的非小细胞肺癌患者治疗计划的附加可操作标准。
- 尽管数据未证实或反驳处方剂量需要显著更高BED才能实现肿瘤控制,但将名义处方剂量从BED 100 Gy提升至105 Gy可能具有临床效果。
研究设计与样本
- 研究纳入535例接受50 Gy/5分次治疗的非小细胞肺癌患者,用于开发新型深度学习局部反应模型。
- 采用多模态方法整合计算机断层扫描图像、三维剂量分布和患者人口学特征,结合离散时间生存模型预测失败时间和局部控制概率。
- 使用积分梯度加权类激活映射方法识别预测局部失败的最重要剂量体积指标及其最佳切点。
主要发现
- 模型交叉验证表现可接受,c-index为0.72(95%CI 0.68-0.75),测试c-index为0.69。
- 模型空间注意力主要集中在肿瘤周边区域(计划靶区[PTV]减去内大体肿瘤体积[IGTV]区域)。
- IGTV中BED Dnear-min≥103.8 Gy与局部控制改善相关(HR 0.31,95%CI 0.15-0.63)。
- IGTV中V104≥98%与局部控制改善相关(HR 0.30,95%CI 0.15-0.60)。
- PTV-IGTV中gEUD≥103.8 Gy(HR 0.25,95%CI 0.12-0.50)和Dmean≥104.5 Gy(HR 0.25,95%CI 0.12-0.51)与局部控制改善相关。
关键数值与推荐
- IGTV中BED Dnear-min≥103.8 Gy(HR 0.31,95%CI 0.15-0.63)。
- IGTV中V104≥98%(HR 0.30,95%CI 0.15-0.60)。
- PTV-IGTV中gEUD≥103.8 Gy(HR 0.25,95%CI 0.12-0.50)。
- PTV-IGTV中Dmean≥104.5 Gy(HR 0.25,95%CI 0.12-0.51)。
临床怎么用
- 作者认为深度学习识别的剂量体积指标可作为治疗计划的附加可操作标准,帮助计划设计者实现优化治疗计划以获得最大局部控制。
- 作者认为将名义处方剂量从BED 100 Gy提升至105 Gy可能具有临床效果。
局限性
- 原文未报告局限性。
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
PURPOSE: Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control. METHODS AND MATERIALS: A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points. RESULTS: The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51). CONCLUSIONS: Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.
引用
- Dudas D, Saghand PG, Dilling TJ, et al. Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy. Int J Radiat Oncol Biol Phys. 2023. PMID: 38056778. doi:10.1016/j.ijrobp.2023.11.059
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。