利用深度学习预测I-IIIA期非小细胞肺癌生存
本研究基于治疗前CT影像特征与临床变量构建深度学习混合模型,用于预测接受根治性放疗的I-IIIA期非小细胞肺癌患者2年总生存。模型在UMCG测试集(81例)中位AUC为0.76(95%CI 0.65-0.86),在Maastro外部验证集(228例)为0.64(95%CI 0.58-0.70),两测试集高低死亡风险组Kaplan-Meier曲线均显著分离(log-rank P<0.001和P=0.012)。
要点
- 多变量分析显示年龄和临床分期是2年总生存的显著预后临床因素。
- 混合模型在UMCG测试集中位AUC为0.76(95%CI 0.65-0.86)。
- 混合模型在Maastro外部验证集中位AUC为0.64(95%CI 0.58-0.70)。
核心结论
- 混合模型联合临床与影像特征可对2年总生存预测达到合理性能,有潜力识别高死亡风险患者并指导临床决策。
研究设计与样本
- 前瞻性收集UMCG接受立体定向放疗的NSCLC患者,分为训练集189例和留出测试集81例。
- 在Maastro诊所接受放疗或同步放化疗的228例NSCLC患者(Lung1数据集)上进行外部验证。
- 采用深度学习实现整合影像与临床特征的混合模型,影像特征从治疗前CT扫描提取的含肿瘤立方块块中学习。
主要发现
- 多变量分析显示年龄和临床分期是2年总生存的显著预后临床因素。
- 混合模型在完整UMCG测试集中位AUC为0.76(95%CI 0.65-0.86)。
- 混合模型在Maastro测试集中位AUC为0.64(95%CI 0.58-0.70)。
- UMCG测试集低与高死亡风险组Kaplan-Meier曲线显著分离(log-rank检验P<0.001)。
- Maastro测试集低与高死亡风险组Kaplan-Meier曲线显著分离(log-rank检验P=0.012)。
临床怎么用
- 原文未据此给出推荐。
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
BACKGROUND AND PURPOSE: The aim of this study was to develop and evaluate a prediction model for 2-year overall survival (OS) in stage I-IIIA non-small cell lung cancer (NSCLC) patients who received definitive radiotherapy by considering clinical variables and image features from pre-treatment CT-scans. MATERIALS AND METHODS: NSCLC patients who received stereotactic radiotherapy were prospectively collected at the UMCG and split into a training and a hold out test set including 189 and 81 patients, respectively. External validation was performed on 228 NSCLC patients who were treated with radiation or concurrent chemoradiation at the Maastro clinic (Lung1 dataset). A hybrid model that integrated both image and clinical features was implemented using deep learning. Image features were learned from cubic patches containing lung tumours extracted from pre-treatment CT scans. Relevant clinical variables were selected by univariable and multivariable analyses. RESULTS: Multivariable analysis showed that age and clinical stage were significant prognostic clinical factors for 2-year OS. Using these two clinical variables in combination with image features from pre-treatment CT scans, the hybrid model achieved a median AUC of 0.76 [95 % CI: 0.65-0.86] and 0.64 [95 % CI: 0.58-0.70] on the complete UMCG and Maastro test sets, respectively. The Kaplan-Meier survival curves showed significant separation between low and high mortality risk groups on these two test sets (log-rank test: p-value < 0.001, p-value = 0.012, respectively) CONCLUSION: We demonstrated that a hybrid model could achieve reasonable performance by utilizing both clinical and image features for 2-year OS prediction. Such a model has the potential to identify patients with high mortality risk and guide clinical decision making.
引用
- Zheng S, Guo J, Langendijk JA, et al. Survival prediction for stage I-IIIA non-small cell lung cancer using deep learning. Radiother Oncol. 2023. PMID: 36690302. doi:10.1016/j.radonc.2023.109483
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。