Development of a robust radiomic biomarker of progression-free survival in advanced non-small cell lung cancer patients treated with first-line immunotherapy.
Development of a robust radiomic biomarker of progression-free survival in advanced non-small cell lung cancer patients treated with first-line immunotherapy.
复制标题
DOI：
10.1038/s41598-022-14160-7
复制
发表时间：
2022-06-15
影响因子：
4.6
通讯作者：
Kontos, Despina
中科院分区：
文献类型：
--
作者：
Singh, Apurva;Horng, Hannah;Roshkovan, Leonid;Weeks, Joanna K.;Hershman, Michelle;Noel, Peter;Luna, Jose Marcio;Cohen, Eric A.;Pantalone, Lauren;Shinohara, Russell T.;Bauml, Joshua M.;Thompson, Jeffrey C.;Aggarwal, Charu;Carpenter, Erica L.;Katz, Sharyn, I;Kontos, Despina
我们的目标是确定一种新型放射组学生物标志物的可行性，该生物标志物可以与其他已确定的临床预后因素相结合，以预测接受一线免疫治疗的非小细胞肺癌（NSCLC）患者的无进展生存期（PFS）。我们的研究包括 107 名接受基于派姆单抗治疗的 4 期 NSCLC 患者（单一疗法：30%，联合化疗：70%）。 ITK-SNAP 软件用于根据治疗前 CT 扫描进行 3D 肿瘤体积分割。使用 CaPTk 软件提取放射组学特征 (n = 102)。通过将图像重采样为最小体素间距参数并通过嵌套 ComBat 技术进行协调，减轻了图像物理尺寸（体素间距参数）和采集参数（对比度增强和 CT 重建内核）引入的异质性影响。该技术以放射组学特征、年龄、性别、种族、PD-L1 表达、ECOG 状态、体重指数 (BMI)、吸烟状况、复发事件和无进展生存期月数等临床因素以及图像采集参数作为批次变量进行初始化。使用协调特征的无监督层次聚类来识别两种表型。预后因素，包括 PDL1 表达、ECOG 状态、BMI 和吸烟状况，与 PFS 的 Cox 回归模型和 Kaplan Meier (KM) 曲线拟合中的放射组学表型相结合。基于临床因素的 Cox 模型的 c 统计量为 0.57，在添加源自协调特征的表型后，该统计量增加至 0.63。通过对数秩检验测量，按临床协变量分层的生存结果存在统计学显着差异（p = 0.034），并且在添加表型后得到改善（p = 0.00022）。我们发现，通过图像重采样和嵌套 ComBat 协调来减轻异质性可以提高表型的预后价值，当添加到其他预后变量时，可以更好地预测 PFS。
We aim to determine the feasibility of a novel radiomic biomarker that can integrate with other established clinical prognostic factors to predict progression-free survival (PFS) in patients with non-small cell lung cancer (NSCLC) undergoing first-line immunotherapy. Our study includes 107 patients with stage 4 NSCLC treated with pembrolizumab-based therapy (monotherapy: 30%, combination chemotherapy: 70%). The ITK-SNAP software was used for 3D tumor volume segmentation from pre-therapy CT scans. Radiomic features (n = 102) were extracted using the CaPTk software. Impact of heterogeneity introduced by image physical dimensions (voxel spacing parameters) and acquisition parameters (contrast enhancement and CT reconstruction kernel) was mitigated by resampling the images to the minimum voxel spacing parameters and harmonization by a nested ComBat technique. This technique was initialized with radiomic features, clinical factors of age, sex, race, PD-L1 expression, ECOG status, body mass index (BMI), smoking status, recurrence event and months of progression-free survival, and image acquisition parameters as batch variables. Two phenotypes were identified using unsupervised hierarchical clustering of harmonized features. Prognostic factors, including PDL1 expression, ECOG status, BMI and smoking status, were combined with radiomic phenotypes in Cox regression models of PFS and Kaplan Meier (KM) curve-fitting. Cox model based on clinical factors had a c-statistic of 0.57, which increased to 0.63 upon addition of phenotypes derived from harmonized features. There were statistically significant differences in survival outcomes stratified by clinical covariates, as measured by the log-rank test (p = 0.034), which improved upon addition of phenotypes (p = 0.00022). We found that mitigation of heterogeneity by image resampling and nested ComBat harmonization improves prognostic value of phenotypes, resulting in better prediction of PFS when added to other prognostic variables.
登录
查看更多内容
影响因子：
45.3
作者：
Rizvi, Naiyer A.;Hellmann, Matthew D.;Antonia, Scott
通讯作者：
Antonia, Scott
影响因子：
5.3
作者：
Chouaid, Christos;Dujon, Cecile;Vergnenegre, Alain
通讯作者：
Vergnenegre, Alain
影响因子：
3.5
作者：
Mahon, R. N.;Ghita, M.;Weiss, E.
通讯作者：
Weiss, E.
癌症的定量成像在后基因组时代：无线电（Geno）麦克风，深度学习和栖息地。
影响因子：
6.2
作者：
Napel S;Mu W;Jardim-Perassi BV;Aerts HJWL;Gillies RJ
通讯作者：
Gillies RJ
影响因子：
19.7
作者：
Orlhac, Fanny;Frouin, Frederique;Buvat, Irene
通讯作者：
Buvat, Irene