Jožef Stefan Institute, Ljubljana, Slovenia.
Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia.
Radiol Oncol. 2020 Jul 29;54(3):285-294. doi: 10.2478/raon-2020-0042.
Background Immune checkpoint inhibitors have changed the paradigm of cancer treatment; however, non-invasive biomarkers of response are still needed to identify candidates for non-responders. We aimed to investigate whether immunotherapy [18F]FDG PET radiomics signature (iRADIOMICS) predicts response of metastatic non-small-cell lung cancer (NSCLC) patients to pembrolizumab better than the current clinical standards. Patients and methods Thirty patients receiving pembrolizumab were scanned with [18F]FDG PET/CT at baseline, month 1 and 4. Associations of six robust primary tumour radiomics features with overall survival were analysed with Mann-Whitney U-test (MWU), Cox proportional hazards regression analysis, and ROC curve analysis. iRADIOMICS was constructed using univariate and multivariate logistic models of the most promising feature(s). Its predictive power was compared to PD-L1 tumour proportion score (TPS) and iRECIST using ROC curve analysis. Prediction accuracies were assessed with 5-fold cross validation. Results The most predictive were baseline radiomics features, e.g. Small Run Emphasis (MWU, p = 0.001; hazard ratio = 0.46, p = 0.007; AUC = 0.85 (95% CI 0.69-1.00)). Multivariate iRADIOMICS was found superior to the current standards in terms of predictive power and timewise with the following AUC (95% CI) and accuracy (standard deviation): iRADIOMICS (baseline), 0.90 (0.78-1.00), 78% (18%); PD-L1 TPS (baseline), 0.60 (0.37-0.83), 53% (18%); iRECIST (month 1), 0.79 (0.62-0.95), 76% (16%); iRECIST (month 4), 0.86 (0.72-1.00), 76% (17%). Conclusions Multivariate iRADIOMICS was identified as a promising imaging biomarker, which could improve management of metastatic NSCLC patients treated with pembrolizumab. The predicted non-responders could be offered other treatment options to improve their overall survival.
免疫检查点抑制剂改变了癌症治疗的模式；然而，仍然需要非侵入性的反应生物标志物来识别无应答者的候选者。我们旨在研究免疫疗法[18F]FDG PET 放射组学特征（iRADIOMICS）是否比当前的临床标准更能预测转移性非小细胞肺癌（NSCLC）患者对 pembrolizumab 的反应。
30 名接受 pembrolizumab 治疗的患者在基线、第 1 个月和第 4 个月接受[18F]FDG PET/CT 扫描。使用 Mann-Whitney U 检验（MWU）、Cox 比例风险回归分析和 ROC 曲线分析，分析了 6 个稳健的原发肿瘤放射组学特征与总生存期的相关性。使用单变量和多变量逻辑模型构建 iRADIOMICS，选择最有前途的特征。使用 ROC 曲线分析比较 iRADIOMICS 与 PD-L1 肿瘤比例评分（TPS）和 iRECIST 的预测能力。使用 5 倍交叉验证评估预测准确性。
最具预测性的是基线放射组学特征，例如小运行强调（MWU，p = 0.001；风险比 = 0.46，p = 0.007；AUC = 0.85（95%CI 0.69-1.00））。多变量 iRADIOMICS 在预测能力和时间方面均优于当前标准，其 AUC（95%CI）和准确性（标准差）如下：iRADIOMICS（基线），0.90（0.78-1.00），78%（18%）；PD-L1 TPS（基线），0.60（0.37-0.83），53%（18%）；iRECIST（第 1 个月），0.79（0.62-0.95），76%（16%）；iRECIST（第 4 个月），0.86（0.72-1.00），76%（17%）。
多变量 iRADIOMICS 被确定为一种有前途的成像生物标志物，可改善接受 pembrolizumab 治疗的转移性 NSCLC 患者的管理。预测的无应答者可以提供其他治疗选择，以提高其总生存期。
