Shen Hesong, Wang Yu, Liu Daihong, Lv Rongfei, Huang Yuanying, Peng Chao, Jiang Shixi, Wang Ying, He Yongpeng, Lan Xiaosong, Huang Hong, Sun Jianqing, Zhang Jiuquan
Department of Radiology, Chongqing University Cancer Hospital and Chongqing Cancer Institute and Chongqing Cancer Hospital, Chongqing, China.
Key Laboratory for Biorheological Science and Technology of Ministry of Education (Chongqing University), Chongqing University Cancer Hospital and Chongqing Cancer Institute and Chongqing Cancer Hospital, Chongqing, China.
Front Oncol. 2020 May 12;10:618. doi: 10.3389/fonc.2020.00618. eCollection 2020.
This study aimed to explore the predictive value of MRI-based radiomic model for progression-free survival (PFS) in nonmetastatic nasopharyngeal carcinoma (NPC). A total of 327 nonmetastatic NPC patients [training cohort ( = 230) and validation cohort ( = 97)] were enrolled. The clinical and MRI data were collected. The least absolute shrinkage selection operator (LASSO) and recursive feature elimination (RFE) were used to select radiomic features. Five models [Model 1: clinical data, Model 2: overall stage, Model 3: radiomics, Model 4: radiomics + overall stage, Model 5: radiomics + overall stage + Epstein-Barr virus (EBV) DNA] were constructed. The prognostic performances of these models were evaluated by Harrell's concordance index (C-index). The Kaplan-Meier method was applied for the survival analysis. : Model 5 incorporating radiomics, overall stage, and EBV DNA yielded the highest C-indices for predicting PFS in comparison with Model 1, Model 2, Model 3, and Model 4 (training cohorts: 0.805 vs. 0.766 vs. 0.749 vs. 0.641 vs. 0.563, validation cohorts: 0.874 vs. 0.839 vs. 836 vs. 0.689 vs. 0.456). The survival curve showed that the high-risk group yielded a lower PFS than the low-risk group. The model incorporating radiomics, overall stage, and EBV DNA showed better performance for predicting PFS in nonmetastatic NPC patients.
本研究旨在探讨基于MRI的影像组学模型对非转移性鼻咽癌（NPC）无进展生存期（PFS）的预测价值。共纳入327例非转移性NPC患者[训练队列（n = 230）和验证队列（n = 97）]。收集临床和MRI数据。采用最小绝对收缩选择算子（LASSO）和递归特征消除（RFE）来选择影像组学特征。构建了五个模型[模型1：临床数据，模型2：总体分期，模型3：影像组学，模型4：影像组学+总体分期，模型5：影像组学+总体分期+爱泼斯坦-巴尔病毒（EBV）DNA]。通过Harrell一致性指数（C指数）评估这些模型的预后性能。采用Kaplan-Meier法进行生存分析。结果：与模型1、模型2、模型3和模型4相比，纳入影像组学、总体分期和EBV DNA的模型5在预测PFS方面产生了最高的C指数（训练队列：0.805 vs. 0.766 vs. 0.749 vs. 0.641 vs. 0.563，验证队列：0.874 vs. 0.839 vs. 0.836 vs. 0.689 vs. 0.456）。生存曲线显示，高危组的PFS低于低危组。纳入影像组学、总体分期和EBV DNA的模型在预测非转移性NPC患者的PFS方面表现更好。
