文献速递头颈MR

基于MRI的影像组学特征作为头颈部鳞状细胞癌患者的预测标志物

MRI-based radiomic signature as predictive marker for patients with head and neck squamous cell carcinoma.
PubMed 文献 · Eur J Radiol · 2019-06-25

本研究为回顾性研究,纳入训练队列85例和验证队列85例头颈部鳞状细胞癌患者,采用LASSO Cox回归筛选MRI影像组学特征并构建影像组学特征及列线图。影像组学特征与总生存显著相关(训练队列P<0.0001,验证队列P=0.0013),列线图预后能力优于单独TNM分期(训练队列P=0.005,验证队列P=0.01),校准曲线与实测观察一致性良好。

要点

  • MRI影像组学特征由7个MR图像特征组成,与HNSCC患者总生存显著相关。
  • 影像组学特征和TNM分期均为总生存的独立相关因素,联合构建列线图。
  • 列线图预后能力优于单独TNM分期,校准曲线显示与实测观察一致性良好。

核心结论

  • 基于MRI的影像组学特征是HNSCC患者的独立预后因素。
  • 基于影像组学特征和TNM分期的列线图在临床实践中无创且术前预测HNSCC患者预后方面显示出前景。

研究设计与样本

  • 回顾性研究,包括训练队列(n=85)和验证队列(n=85)的头颈部鳞状细胞癌患者。
  • 采用LASSO Cox回归模型选择最有用的预后特征及其系数,并生成影像组学特征。
  • 在两组队列中评估影像组学特征与总生存的关联,并构建结合影像组学特征和独立临床预测因素的列线图。

诊断标准与关键数值

  • 影像组学特征由7个选定的MR图像特征组成,与HNSCC患者总生存显著相关(训练队列P<0.0001,验证队列P=0.0013)。
  • 影像组学特征和TNM分期被证明与HNSCC患者总生存独立相关,并纳入构建影像组学列线图。
  • 在训练队列中,列线图预后能力优于单独TNM分期(P=0.005),并在验证队列中得到确认(P=0.01)。
  • 列线图的校准曲线显示与实际观察良好一致。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To develop magnetic resonance imaging (MRI)-based radiomic signature and nomogram for preoperatively predicting prognosis in head and neck squamous cell carcinoma (HNSCC) patients.

METHOD: This retrospective study consisted of a training cohort (n = 85) and a validation cohort (n = 85) of patients with HNSCC. LASSO Cox regression model was used to select the most useful prognostic features with their coefficients, upon which a radiomic signature was generated. The receiver operator characteristics (ROC) analysis and association of the radiomic signature with overall survival (OS) of patients was assessed in both cohorts. A nomogram incorporating the radiomic signature and independent clinical predictors was then constructed. The incremental prognostic value of the radiomic signature was evaluated.

RESULTS: The radiomic signature, consisted of 7 selected features from MR images, was significantly associated with OS of patients with HNSCC (P < 0.0001 for training cohort, P = 0.0013 for validation cohort). The radiomic signature and TNM stage were proved to be independently associated with OS of HNSCC patients, which therefore were incorporated to generate the radiomic nomogram. In the training cohort, the nomogram showed a better prognostic capability than TNM stage only (P = 0.005), which was confirmed in the validation cohort (P = 0.01). Furthermore, the calibration curves of the nomogram demonstrated good agreement with actual observation.

CONCLUSIONS: MRI-based radiomic signature is an independent prognostic factor for HNSCC patients. Nomogram based on radiomic signature and TNM stage shows promising in non-invasively and preoperatively predicting prognosis of HNSCC patient in clinical practice.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Yuan Y, Ren J, Shi Y, et al. MRI-based radiomic signature as predictive marker for patients with head and neck squamous cell carcinoma. Eur J Radiol. 2019. PMID: 31307647. doi:10.1016/j.ejrad.2019.06.019

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。