Department of Radiation Oncology, University of Pennsylvania, Philadelphia, Pennsylvania.
Department of Radiation Oncology, University of Pennsylvania, Philadelphia, Pennsylvania.
Int J Radiat Oncol Biol Phys. 2021 Aug 1;110(5):1451-1465. doi: 10.1016/j.ijrobp.2021.02.030. Epub 2021 Mar 1.
The main objective of the present study was to integrate F-FDG-PET/CT radiomics with multiblock discriminant analysis for predicting circulating tumor cells (CTCs) in early-stage non-small cell lung cancer (ES-NSCLC) treated with stereotactic body radiation therapy (SBRT).
Fifty-six patients with stage I NSCLC treated with SBRT underwent F-FDG-PET/CT imaging pre-SBRT and post-SBRT (median, 5 months; range, 3-10 months). CTCs were assessed via a telomerase-based assay before and within 3 months after SBRT and dichotomized at 5 and 1.3 CTCs/mL. Pre-SBRT, post-SBRT, and delta PET/CT radiomics features (n = 1548 × 3/1562 × 3) were extracted from gross tumor volume. Seven feature blocks were constructed including clinical parameters (n = 12). Multiblock data integration was performed using block sparse partial least squares-discriminant analysis (sPLS-DA) referred to as Data Integration Analysis for Biomarker Discovery Using Latent Components (DIABLO) for identifying key signatures by maximizing common information between different feature blocks while discriminating CTC levels. Optimal input blocks were identified using a pairwise combination method. DIABLO performance for predicting pre-SBRT and post-SBRT CTCs was evaluated using combined AUC (area under the curve, averaged across different blocks) analysis with 20 × 5-fold cross-validation (CV) and compared with that of concatenation-based sPLS-DA that consisted of combining all features into 1 block. CV prediction scores between 1 class versus the other were compared using the Wilcoxon rank sum test.
For predicting pre-SBRT CTCs, DIABLO achieved the best performance with combined pre-SBRT PET radiomics and clinical feature blocks, showing CV AUC of 0.875 (P = .009). For predicting post-SBRT CTCs, DIABLO achieved the best performance with combined post-SBRT CT and delta CT radiomics feature blocks, showing CV AUCs of 0.883 (P = .001). In contrast, all single-block sPLS-DA models could not attain CV AUCs higher than 0.7.
Multiblock integration with discriminant analysis of F-FDG-PET/CT radiomics has the potential for predicting pre-SBRT and post-SBRT CTCs. Radiomics and CTC analysis may complement and together help guide the subsequent management of patients with ES-NSCLC.
本研究的主要目的是将 F-FDG-PET/CT 放射组学与多块判别分析相结合，以预测接受立体定向体放射治疗（SBRT）的早期非小细胞肺癌（ES-NSCLC）患者的循环肿瘤细胞（CTC）。
56 例接受 SBRT 治疗的 I 期 NSCLC 患者在 SBRT 前和 SBRT 后（中位数为 5 个月；范围为 3-10 个月）进行 F-FDG-PET/CT 成像。在 SBRT 前、后和 SBRT 后 3 个月内，通过端粒酶检测法评估 CTCs，并将其分为 5 和 1.3 CTCs/mL 两个水平。从大体肿瘤体积中提取了 1548×3/1562×3 个预 SBRT、post-SBRT 和 delta PET/CT 放射组学特征（n=1548×3/1562×3）。构建了包括临床参数（n=12）在内的 7 个特征块。采用块稀疏偏最小二乘判别分析（sPLS-DA）进行多块数据集成，称为使用潜在成分进行生物标志物发现的生物标志物发现的多块数据集成分析（DIABLO），通过最大化不同特征块之间的共同信息，同时区分 CTC 水平，从而识别关键特征。使用成对组合方法确定最佳输入块。使用 20×5 折交叉验证（CV）和结合所有特征的串联 sPLS-DA 进行组合 AUC（曲线下面积，跨不同块平均）分析，评估 DIABLO 对预测 pre-SBRT 和 post-SBRT CTCs 的性能，并与由所有特征组合为 1 个块组成的串联 sPLS-DA 进行比较。使用 Wilcoxon 秩和检验比较 1 类与其他类之间的 CV 预测评分。
对于预测 pre-SBRT CTCs，DIABLO 结合了预 SBRT PET 放射组学和临床特征块，表现出最佳的性能，CV AUC 为 0.875（P=0.009）。对于预测 post-SBRT CTCs，DIABLO 结合 post-SBRT CT 和 delta CT 放射组学特征块表现出最佳性能，CV AUC 为 0.883（P=0.001）。相比之下，所有单块 sPLS-DA 模型都无法达到高于 0.7 的 CV AUC。
基于 F-FDG-PET/CT 放射组学的多块集成与判别分析具有预测 pre-SBRT 和 post-SBRT CTCs 的潜力。放射组学和 CTC 分析可以互补，并共同有助于指导 ES-NSCLC 患者的后续管理。
