Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, 1211, Geneva, Switzerland.
School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
Radiol Med. 2023 Dec;128(12):1521-1534. doi: 10.1007/s11547-023-01725-3. Epub 2023 Sep 26.
Glioblastoma Multiforme (GBM) represents the predominant aggressive primary tumor of the brain with short overall survival (OS) time. We aim to assess the potential of radiomic features in predicting the time-to-event OS of patients with GBM using machine learning (ML) algorithms.
One hundred nineteen patients with GBM, who had T1-weighted contrast-enhanced and T2-FLAIR MRI sequences, along with clinical data and survival time, were enrolled. Image preprocessing methods included 64 bin discretization, Laplacian of Gaussian (LOG) filters with three Sigma values and eight variations of Wavelet Transform. Images were then segmented, followed by the extraction of 1212 radiomic features. Seven feature selection (FS) methods and six time-to-event ML algorithms were utilized. The combination of preprocessing, FS, and ML algorithms (12 × 7 × 6 = 504 models) was evaluated by multivariate analysis.
Our multivariate analysis showed that the best prognostic FS/ML combinations are the Mutual Information (MI)/Cox Boost, MI/Generalized Linear Model Boosting (GLMB) and MI/Generalized Linear Model Network (GLMN), all of which were done via the LOG (Sigma = 1 mm) preprocessing method (C-index = 0.77). The LOG filter with Sigma = 1 mm preprocessing method, MI, GLMB and GLMN achieved significantly higher C-indices than other preprocessing, FS, and ML methods (all p values < 0.05, mean C-indices of 0.65, 0.70, and 0.64, respectively).
ML algorithms are capable of predicting the time-to-event OS of patients using MRI-based radiomic and clinical features. MRI-based radiomics analysis in combination with clinical variables might appear promising in assisting clinicians in the survival prediction of patients with GBM. Further research is needed to establish the applicability of radiomics in the management of GBM in the clinic.
多形性胶质母细胞瘤（GBM）是大脑中主要的侵袭性原发性肿瘤，总生存期（OS）较短。我们旨在使用机器学习（ML）算法评估放射组学特征在预测 GBM 患者时间事件 OS 中的潜力。
共纳入 119 名 GBM 患者，他们均具有 T1 加权对比增强和 T2-FLAIR MRI 序列，以及临床数据和生存时间。图像预处理方法包括 64 个 bin 离散化、三个 Sigma 值的拉普拉斯高斯（LOG）滤波器和八种小波变换变体。然后对图像进行分割，接着提取 1212 个放射组学特征。使用七种特征选择（FS）方法和六种时间事件 ML 算法。通过多元分析评估预处理、FS 和 ML 算法的组合（12×7×6=504 个模型）。
我们的多元分析表明，最佳预后的 FS/ML 组合是互信息（MI）/Cox 提升、MI/广义线性模型提升（GLMB）和 MI/广义线性模型网络（GLMN），均通过 LOG（Sigma=1mm）预处理方法（C 指数=0.77）实现。Sigma=1mm 的 LOG 滤波器预处理方法、MI、GLMB 和 GLMN 的 C 指数显著高于其他预处理、FS 和 ML 方法（所有 p 值均<0.05，平均 C 指数分别为 0.65、0.70 和 0.64）。
ML 算法能够使用基于 MRI 的放射组学和临床特征预测患者的时间事件 OS。基于 MRI 的放射组学分析结合临床变量，在帮助临床医生预测 GBM 患者的生存方面可能具有很大的前景。需要进一步的研究来确定放射组学在 GBM 临床管理中的适用性。
