Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.
Chinese Academy of Sciences, Institute of Automation, Beijing, China.
Neuroimage Clin. 2018;20:1070-1077. doi: 10.1016/j.nicl.2018.10.014. Epub 2018 Oct 16.
The aim of this study was to develop a radiomics signature for prediction of progression-free survival (PFS) in lower-grade gliomas and to investigate the genetic background behind the radiomics signature.
In this retrospective study, training (n = 216) and validation (n = 84) cohorts were collected from the Chinese Glioma Genome Atlas and the Cancer Genome Atlas, respectively. For each patient, a total of 431 radiomics features were extracted from preoperative T2-weighted magnetic resonance images. A radiomics signature was generated in the training cohort, and its prognostic value was evaluated in both the training and validation cohorts. The genetic characteristics of the group with high-risk scores were identified by radiogenomic analysis, and a nomogram was established for prediction of PFS.
There was a significant association between the radiomics signature (including 9 screened radiomics features) and PFS, which was independent of other clinicopathologic factors in both the training (P < 0.001, multivariable Cox regression) and validation (P = 0.045, multivariable Cox regression) cohorts. Radiogenomic analysis revealed that the radiomics signature was associated with the immune response, programmed cell death, cell proliferation, and vasculature development. A nomogram established using the radiomics signature and clinicopathologic risk factors demonstrated high accuracy and good calibration for prediction of PFS in both the training (C-index, 0.684) and validation (C-index, 0.823) cohorts.
PFS can be predicted non-invasively in patients with LGGs by a group of radiomics features that could reflect the biological processes of these tumors.
本研究旨在建立预测低级别胶质瘤无进展生存期（PFS）的影像组学特征，并探讨该影像组学特征背后的遗传背景。
本回顾性研究分别从中国脑胶质瘤基因组图谱和癌症基因组图谱中收集了训练（n=216）和验证（n=84）队列。对每位患者，从术前 T2 加权磁共振图像中提取了总共 431 个影像组学特征。在训练队列中生成了影像组学特征，在训练和验证队列中评估了其预后价值。通过放射基因组学分析确定了高风险评分组的遗传特征，并建立了预测 PFS 的列线图。
影像组学特征（包括 9 个筛选出的影像组学特征）与 PFS 之间存在显著相关性，在训练（P<0.001，多变量 Cox 回归）和验证（P=0.045，多变量 Cox 回归）队列中均独立于其他临床病理因素。放射基因组学分析表明，影像组学特征与免疫反应、程序性细胞死亡、细胞增殖和血管发育有关。使用影像组学特征和临床病理危险因素建立的列线图在训练（C 指数，0.684）和验证（C 指数，0.823）队列中均表现出了较高的准确性和良好的校准度，可用于预测 PFS。
通过一组可以反映这些肿瘤生物学过程的影像组学特征，可以无创预测 LGG 患者的 PFS。
