Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Republic of Korea.
Department of Radiation Oncology, Seoul National University College of Medicine, Seoul National University Hospital, Republic of Korea; Institute of Radiation Medicine, Seoul National University Medical Research Center, Republic of Korea; Cancer Research Institute, Seoul National University, Republic of Korea.
Radiother Oncol. 2021 Dec;165:166-173. doi: 10.1016/j.radonc.2021.10.022. Epub 2021 Nov 5.
To validate a computed tomography (CT)-based deep learning prognostication model, originally developed for a surgical cohort, in patients with primary lung cancer undergoing stereotactic ablative radiotherapy (SABR).
This retrospective study identified patients with clinical stage T1-2N0M0 lung cancer treated with SABR between 2013 and 2018. The outcomes were local recurrence-free survival (LRFS), disease-free survival (DFS), and overall survival (OS). The discrimination performance of the model, which extracted a quantitative score of cumulative risk for an adverse event up to 900 days, was evaluated using time-dependent receiver operating characteristic curve analysis. Multivariable Cox regression was performed to investigate the independent prognostic value of the model output adjusting for clinical factors including age, sex, smoking status, and clinical T category.
In total, 135 patients (median age, 78 years; 101 men; 78 [57.8%] adenocarcinomas and 57 [42.2%] squamous cell carcinomas) were evaluated. Most patients (117/135) were treated with 48-60 Gy in four fractions. Median biologically effective dose was 150.0 Gy (interquartile range, 126.9, 150.0 Gy). For LRFS, the area under the curve (AUC) was 0.72 (95% confidence interval [CI]: 0.58, 0.87). The AUCs were 0.70 (95% CI: 0.60, 0.81) for DFS and 0.66 (95% CI: 0.54, 0.77) for OS. Model output was associated with LRFS (adjusted hazard ratio [HR], 1.043; 95% CI: 1.003, 1.085; P = 0.04), DFS (adjusted HR, 1.03; 95% CI: 1.01, 1.05; P = 0.008), and OS (adjusted HR, 1.025; 95% CI: 1.002, 1.047; P = 0.03).
This study showed external validity and transportability of the CT-based deep learning prognostication model for radiotherapy candidates.
为了验证最初为外科队列开发的基于计算机断层扫描（CT）的深度学习预后模型在接受立体定向消融放疗（SABR）的原发性肺癌患者中的适用性。
本回顾性研究纳入了 2013 年至 2018 年间接受 SABR 治疗的临床分期为 T1-2N0M0 肺癌患者。结局包括局部无复发生存率（LRFS）、无疾病生存率（DFS）和总生存率（OS）。使用时间依赖性接受者操作特征曲线分析评估该模型提取 900 天内不良事件累积风险的定量评分的判别性能。采用多变量 Cox 回归分析调整年龄、性别、吸烟状况和临床 T 分期等临床因素后模型输出的独立预后价值。
共评估了 135 例患者（中位年龄 78 岁；101 例男性；78 例（57.8%）腺癌和 57 例（42.2%）鳞癌）。大多数患者（117/135）接受 48-60Gy 分 4 次治疗。中位生物有效剂量为 150.0Gy（四分位间距，126.9，150.0Gy）。对于 LRFS，曲线下面积（AUC）为 0.72（95%置信区间[CI]：0.58，0.87）。DFS 的 AUC 为 0.70（95%CI：0.60，0.81），OS 的 AUC 为 0.66（95%CI：0.54，0.77）。模型输出与 LRFS（调整后的危险比[HR]，1.043；95%CI：1.003，1.085；P=0.04）、DFS（调整后的 HR，1.03；95%CI：1.01，1.05；P=0.008）和 OS（调整后的 HR，1.025；95%CI：1.002，1.047；P=0.03）相关。
本研究表明，基于 CT 的深度学习预后模型对放疗候选者具有外部有效性和可转移性。
