PET-CT/MR Department, Harbin Medical University Cancer Hospital, Harbin, 150001, People's Republic of China.
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150001, People's Republic of China.
J Cancer Res Clin Oncol. 2024 Oct 10;150(10):453. doi: 10.1007/s00432-024-05971-4.
Presently, the options of concurrent chemo-radiotherapy (CCR) in patients with locally advanced non-small cell lung cancer (LA-NSCLC) are controversial and there is no reliable prediction tool to stratify poor- and good-responders. Although radiomic analysis has provided new opportunities for personalized medicine in oncological practice, the repeatability and reproducibility of radiomic features are critical challenges that hinder their widespread clinical adoption. This study aimed to develop a qualitative radiomic signature based on the within-sample rank of radiomics features, and to use this novel method to predict CCR sensitivity in LA-NSCLC, avoiding the variability of quantitative signatures to multicenter effect.
We retrospectively analyzed 125 patients with stage III NSCLC who received treatment from our hospital. Radiomic features were extracted from pretreatment plain CT scans and constructed as feature pairs based on their within-sample rank. Fisher and univariate Cox analyses were performed to select feature pairs significantly associated with patients' overall survival (OS). NSCLC-Radiomic (R422) cohort including 104 NSCLC patients was used as an independent testing cohort. NSCLC-Radiogenomic (RG211) cohort with matched RNA sequencing profiles, was used for functional enrichment analysis to reveal the underlying biological mechanism reflected by the signature.
A qualitative signature, consisting of 15 radiomic feature pairs (termed as 15-RFPS), was developed based on the Genetic Algorithm, which could optimally distinguish responder from non-responder with significantly improved OS if they received CCR treatment (log-rank P = 0.0009, HR = 13.79, 95% CIs 1.83-104.1). The performance of 15-RFPS was validated in an independent public cohort (log-rank P = 0.0037, HR = 2.40, 95% CIs 1.30-4.40). Furthermore, the transcriptomic analyses provided biological pathways ('glutathione metabolic process', 'cellular oxidant detoxification') underlying the signature.
We developed a CT-derived 15-RFPS, which could potentially help predict individualized therapeutic benefit of CCR in patients with LA-NSCLC. Additionally, we investigated the underlying intra-tumoral biological characteristics behind 15-RFPS which would accelerate its clinical application. This approach could be applied to a wider range of treatments and cancer types.
目前，局部晚期非小细胞肺癌（LA-NSCLC）患者同步放化疗（CCR）的选择存在争议，尚无可靠的预测工具来分层预后不良和预后良好的患者。虽然放射组学分析为肿瘤学实践中的个性化医学提供了新的机会，但放射组学特征的可重复性和再现性是阻碍其广泛临床应用的关键挑战。本研究旨在基于样本内放射组学特征的等级，开发一种定性放射组学特征，并使用这种新方法预测 LA-NSCLC 患者的 CCR 敏感性，避免定量特征的可变性对多中心效应的影响。
我们回顾性分析了 125 例在我院接受治疗的 III 期 NSCLC 患者。从治疗前的平扫 CT 扫描中提取放射组学特征，并根据其样本内等级构建特征对。进行 Fisher 和单变量 Cox 分析，以选择与患者总生存期（OS）显著相关的特征对。使用包括 104 例 NSCLC 患者的 NSCLC-Radiomic（R422）队列作为独立测试队列。使用具有匹配 RNA 测序图谱的 NSCLC-Radiogenomic（RG211）队列进行功能富集分析，以揭示该特征所反映的潜在生物学机制。
基于遗传算法，我们开发了一种定性特征，由 15 个放射组学特征对（称为 15-RFPS）组成，如果接受 CCR 治疗，该特征可以最佳地区分应答者和非应答者，并显著改善 OS（对数秩 P=0.0009，HR=13.79，95%CI 1.83-104.1）。在一个独立的公共队列中验证了 15-RFPS 的性能（对数秩 P=0.0037，HR=2.40，95%CI 1.30-4.40）。此外，转录组学分析提供了特征背后的生物学途径（“谷胱甘肽代谢过程”、“细胞氧化还原解毒”）。
我们开发了一种 CT 衍生的 15-RFPS，它可能有助于预测 LA-NSCLC 患者 CCR 的个体化治疗获益。此外，我们研究了 15-RFPS 背后的肿瘤内内在生物学特征，这将加速其临床应用。这种方法可以应用于更广泛的治疗和癌症类型。
