Intrinsic radiomic expression patterns after 20 Gy demonstrate early metabolic response of oropharyngeal cancers.
Intrinsic radiomic expression patterns after 20 Gy demonstrate early metabolic response of oropharyngeal cancers.
复制标题
DOI：
10.1002/mp.14926
复制
发表时间：
2021-07
期刊：
影响因子：
3.8
通讯作者：
Yin, Fang-Fang
中科院分区：
文献类型：
--
作者：
Lafata, Kyle J.;Chang, Yushi;Wang, Chunhao;Mowery, Yvonne M.;Vergalasova, Irina;Niedzwiecki, Donna;Yoo, David S.;Liu, Jian-Guo;Brizel, David M.;Yin, Fang-Fang
本研究在一项前瞻性临床试验中调查了接受口咽癌（OPC）确定性（化疗）放射治疗的患者中治疗期间PET放射组学数据的预后潜力。我们假设20戈伊后OPC肿瘤的放射组学表达与无复发生存率（RFS）相关。64例接受确定性（化疗）放疗治疗OPC的患者前瞻性入组IRB批准的研究。在治疗前和7周疗程后2周（20戈伊）采集研究性18 F-FDG-PET/CT图像。从原发性肿瘤中提取了55个定量放射组学特征作为早期代谢反应的潜在生物标志物。一个无监督的数据聚类算法被用来划分成集群的基础上，只有他们的放射组学表达的患者。将聚类结果与残留疾病和/或随后的复发进行简单比较，并用于推导RFS的Kaplan-Meier估计值。为了测试放射组学表达是否提供超出与头颈癌相关的常规临床特征的预后价值，使用多变量考克斯比例风险建模来调整T和N分期、HPV状态和肿瘤体积变化的放射组学簇。虽然治疗前放射组学不具有预后性，但治疗中放射组学表达与残留/复发疾病（P = 0.0256，χ2检验）和RFS（HR = 7.53，95%CI = 2.54-22.3; P = 0.0201）内在相关。在单变量考克斯分析中，放射组学簇与RFS相关（未校正HR = 2.70; 95% CI = 1.26-5.76; P = 0.0104），并在校正T、N分期、HPV状态和20戈伊后肿瘤体积变化后保持显著性（校正HR = 2.69; 95% CI = 1.03-7.04; P = 0.0442）。与结果相关的特定放射组学特征表明，20戈伊后的代谢空间异质性预示着完全和持久的治疗反应。这一发现与头颈癌的基线代谢成像特征和临床特征无关，因此提供了优于现有方法的预后优势。我们的数据说明了治疗中代谢图像询问的预后价值，这可能会指导OPC患者的适应性治疗策略，并作为其他疾病部位的蓝图。我们的研究质量得到了前瞻性图像采集协议、同质患者队列、相对较长的患者随访时间以及无监督聚类形式主义的加强，与监督学习相比，无监督聚类形式主义不太容易进行超参数调整和过度拟合。
This study investigated the prognostic potential of intra-treatment PET radiomics data in patients undergoing definitive (chemo) radiation therapy for oropharyngeal cancer (OPC) on a prospective clinical trial. We hypothesized that the radiomic expression of OPC tumors after 20 Gy is associated with recurrence-free survival (RFS). Sixty-four patients undergoing definitive (chemo)radiation for OPC were prospectively enrolled on an IRB-approved study. Investigational 18F-FDG-PET/CT images were acquired prior to treatment and 2 weeks (20 Gy) into a seven-week course of therapy. Fifty-five quantitative radiomic features were extracted from the primary tumor as potential biomarkers of early metabolic response. An unsupervised data clustering algorithm was used to partition patients into clusters based only on their radiomic expression. Clustering results were naïvely compared to residual disease and/or subsequent recurrence and used to derive Kaplan-Meier estimators of RFS. To test whether radiomic expression provides prognostic value beyond conventional clinical features associated with head and neck cancer, multivariable Cox proportional hazards modeling was used to adjust radiomic clusters for T and N stage, HPV status, and change in tumor volume. While pre-treatment radiomics were not prognostic, intra-treatment radiomic expression was intrinsically associated with both residual/recurrent disease (P = 0.0256, χ2 test) and RFS (HR = 7.53, 95% CI = 2.54–22.3; P = 0.0201). On univariate Cox analysis, radiomic cluster was associated with RFS (unadjusted HR = 2.70; 95% CI = 1.26–5.76; P = 0.0104) and maintained significance after adjustment for T, N staging, HPV status, and change in tumor volume after 20 Gy (adjusted HR = 2.69; 95% CI = 1.03–7.04; P = 0.0442). The particular radiomic characteristics associated with outcomes suggest that metabolic spatial heterogeneity after 20 Gy portends complete and durable therapeutic response. This finding is independent of baseline metabolic imaging characteristics and clinical features of head and neck cancer, thus providing prognostic advantages over existing approaches. Our data illustrate the prognostic value of intra-treatment metabolic image interrogation, which may potentially guide adaptive therapy strategies for OPC patients and serve as a blueprint for other disease sites. The quality of our study was strengthened by its prospective image acquisition protocol, homogenous patient cohort, relatively long patient follow-up times, and unsupervised clustering formalism that is less prone to hyper-parameter tuning and over-fitting compared to supervised learning.
登录
查看更多内容
影响因子：
2.3
作者：
Corradetti, Michael N.;Torok, Jordan A.;Nixon, Andrew B.
通讯作者：
Nixon, Andrew B.
影响因子：
9.3
作者：
Hatt, Mathieu;Majdoub, Mohamed;Visvikis, Dimitris
通讯作者：
Visvikis, Dimitris
影响因子：
3.1
作者：
Bogowicz, Marta;Riesterer, Oliver;Tanadini-Lang, Stephanie
通讯作者：
Tanadini-Lang, Stephanie
DOI：
10.1016/j.ejmp.2017.10.008
发表时间：
2018-01-01
影响因子：
3.4
作者：
Abdollahi, Hamid;Mostafaei, Shayan;Kazemnejad, Anoshirvan
通讯作者：
Kazemnejad, Anoshirvan
影响因子：
45.3
作者：
Chera, Bhishamjit S.;Kumar, Sunil;Gupta, Gaorav P.
通讯作者：
Gupta, Gaorav P.