Gross Tumour Volume CT Radiomics for Prognostication of Recurrence & Death following Curative-Intent Radiotherapy for Non-Small Cell Lung Cancer

Recurrence occurs in up to 36% of patients treated with curative-intent radiotherapy for NSCLC. Identifying patients at higher risk of recurrence for more intensive surveillance may facilitate earlier introduction of the next line of treatment. We aimed to use radiotherapy planning CT scans to develop radiomic classification models that predict overall survival (OS), recurrence-free survival (RFS) and recurrence two years post-treatment for risk-stratification. A retrospective multi-centre study of >900 patients receiving curative-intent radiotherapy for stage I-III NSCLC was undertaken. Models using radiomic and/or clinical features were developed, compared with ten-fold cross-validation and an external test set, and benchmarked against TNM-stage. Such models could be integrated into the routine radiotherapy workflow, thus informing a personalised surveillance strategy at the point of treatment. Our work lays the foundations for future prospective clinical trials for quantitative personalised risk-stratification for surveillance following curative-intent radiotherapy for NSCLC.
The radiomic feature data are provided here. Due to confidentiality, clinical data collected for the study are not publicly available for download, however the corresponding authors can be contacted for academic inquiries.

接受根治性放疗的非小细胞肺癌（NSCLC）患者中，复发率最高可达36%。识别复发风险较高的患者并实施强化随访监测，有助于更早启动后续治疗方案。本研究旨在利用放疗规划CT影像构建放射组学分类模型，以预测患者的总生存期（OS）、无复发生存期（RFS）以及治疗后两年的复发情况，从而实现风险分层。本研究开展了一项纳入900余例接受根治性放疗的I-III期非小细胞肺癌患者的多中心回顾性研究，并构建了融合放射组学特征与/或临床特征的预测模型，采用十折交叉验证及外部测试集开展性能验证，并以TNM分期（TNM-stage）作为基准对照。此类模型可嵌入常规放疗工作流程，从而在治疗实施阶段即可为个性化随访策略提供决策支持。本研究为后续开展针对非小细胞肺癌根治性放疗后随访的量化个性化风险分层前瞻性临床试验奠定了坚实基础。
本研究的放射组学特征数据已在此处提供。鉴于保密要求，研究中收集的临床数据暂不对外开放下载，若有学术咨询需求，可联系通讯作者。