Improving survival prediction of high-grade glioma via machine learning techniques based on MRI radiomic, genetic and clinical risk factors

Abstract

ObjectivesTo develop a radiomic signature to predict overall survival (OS) for high-grade glioma (HGG), and construct a nomogram by combining selected radiomic, genetic and clinical risk factors to further improve the performance of the risk model. Materials and Methods147 cases of HGG with MRI images, genetic data, clinical data were studied, wherein 112 patients were used as training cohort, and 35 patients were as independent test cohort. Radiomics features were extracted from tumor area and peritumoral edema area on CE-T1WI and T2FLAIR images. Association between radiomics signature, genetic, clinical risk factors and OS was explored by Kaplan-Meier survival analysis and log rank test. The multivariate Cox regression analysis was trained with radiomic features along with selected genetic and clinical risk factors, which was presented as a nomogram. ResultsThe radiomic signature constructed by 11 radiomics features stratified patients into low- and high-risk groups, and the C-Index for OS prediction was 0.707 and 0.711 in training and test cohorts, respectively. The multivariable Cox regression analysis identified radiomics signature (hazard ratio (HR): 2.18, P = 0.005), IDH (HR: 0.490, P = 0.007) and age (HR: 1.039, P = 0.005) as independent risk factors. A nomogram combining these independent risk factors further improved the performance for OS estimation (C-index = 0.764 and 0.758 in training and test cohorts, respectively). ConclusionThe radiomics signature is a new prognostic biomarker for HGG. A nomogram incorporating radiomics signature, IDH and age improved the performance of OS estimation, which might be a new complement to the treatment guidelines of glioma.