Zhang Nannan, Zhang Xinxin, Li Junheng, Ren Jie, Li Luyang, Dong Wenlei, Liu Yixin
Modern Educational Technology and Experiment Center, Harbin Normal University, Harbin, China.
College of Life Science and Technology, Harbin Normal University, Harbin, China.
Phys Med. 2023 Mar;107:102546. doi: 10.1016/j.ejmp.2023.102546. Epub 2023 Feb 14.
Radiomics provides an opportunity to minimize adverse effects and optimize the efficacy of treatments noninvasively. This study aims to develop a computed tomography (CT) derived radiomic signature to predict radiological response for the patients with non-small cell lung cancer (NSCLC) receiving radiotherapy.
Total 815 NSCLC patients receiving radiotherapy were sourced from public datasets. Using CT images of 281 NSCLC patients, we adopted genetic algorithm to establish a predictive radiomic signature for radiotherapy that had optimal C-index value by Cox model. Survival analysis and receiver operating characteristic curve were performed to estimate the predictive performance of the radiomic signature. Furthermore, radiogenomics analysis was performed in a dataset with matched images and transcriptome data.
Radiomic signature consisting of three features was established and then validated in the validation dataset (log-rank P = 0.0047) including 140 patient, and showed a significant predictive power in two independent datasets totaling 395 NSCLC patients with binary 2-year survival endpoint. Furthermore, the novel proposed radiomic nomogram significantly improved the prognostic performance (concordance index) of clinicopathological factors. Radiogenomics analysis linked our signature with important tumor biological processes (e.g. Mismatch repair, Cell adhesion molecules and DNA replication) associated with clinical outcomes.
The radiomic signature, reflecting tumor biological processes, could noninvasively predict therapeutic efficacy of NSCLC patients receiving radiotherapy and demonstrate unique advantage for clinical application.
放射组学提供了一个机会，以无创方式将不良反应降至最低并优化治疗效果。本研究旨在开发一种基于计算机断层扫描（CT）的放射组学特征，以预测接受放疗的非小细胞肺癌（NSCLC）患者的放射学反应。
总共815例接受放疗的NSCLC患者来自公共数据集。使用281例NSCLC患者的CT图像，我们采用遗传算法建立了一个用于放疗的预测性放射组学特征，该特征通过Cox模型具有最佳的C指数值。进行生存分析和受试者工作特征曲线分析以评估放射组学特征的预测性能。此外，在具有匹配图像和转录组数据的数据集中进行了放射基因组学分析。
建立了由三个特征组成的放射组学特征，然后在包括140例患者的验证数据集中进行验证（对数秩P = 0.0047），并在总共395例具有两年生存二元终点的NSCLC患者的两个独立数据集中显示出显著的预测能力。此外，新提出的放射组学列线图显著提高了临床病理因素的预后性能（一致性指数）。放射基因组学分析将我们的特征与与临床结果相关的重要肿瘤生物学过程（例如错配修复、细胞粘附分子和DNA复制）联系起来。
反映肿瘤生物学过程的放射组学特征可以无创地预测接受放疗的NSCLC患者的治疗效果，并在临床应用中显示出独特的优势。
