The Nomogram of MRI‐based Radiomics with Complementary Visual Features by Machine Learning Improves Stratification of Glioblastoma Patients: A Multicenter Study. Issue 2 (8th February 2021)

• Record Type: Journal Article
• Authors: Xu, Yuyun; He, Xiaodong; Li, Yumei; Pang, Peipei; Shu, Zhenyu; Gong, Xiangyang
• Is Part Of: Journal of magnetic resonance imaging. Volume 54:Issue 2(2021)
• Page Start: 571
• Page End: 583
• Publication Date: 2021-02-08
• Subjects: glioblastoma -- overall survival -- nomogram -- prediction -- stratification -- machine learning; Magnetic resonance imaging -- Periodicals; 616
• DOI: 10.1002/jmri.27536
• Languages: English
• ISSNs: 1053-1807

Abstract

Abstract : Background: Glioblastomas (GBMs) represent both the most common and the most highly malignant primary brain tumors. The subjective visual imaging features from MRI make it challenging to predict the overall survival (OS) of GBM. Radiomics can quantify image features objectively as an emerging technique. A pragmatic and objective method in the clinic to assess OS is strongly in need. Purpose: To construct a radiomics nomogram to stratify GBM patients into long‐ vs. short‐term survival. Study Type: Retrospective. Population: One‐hundred and fifty‐eight GBM patients from Brain Tumor Segmentation Challenge 2018 (BRATS2018) were for model construction and 32 GBM patients from the local hospital for external validation. Field Strength/Sequence: 1.5 T and 3.0 T MRI Scanners, T1 WI, T2 WI, T2 FLAIR, and contrast‐enhanced T1 WI sequences Assessment: All patients were divided into long‐term or short‐term based on a survival of greater or fewer than 12 months. All BRATS2018 subjects were divided into training and test sets, and images were assessed for ependymal and pia mater involvement (EPI) and multifocality by three experienced neuroradiologists. All tumor tissues from multiparametric MRI were fully automatically segmented into three subregions to calculate the radiomic features. Based on the training set, the most powerful radiomic features were selected to constitute radiomic signature. Statistical Tests: Receiver operating characteristic (ROC) curve, sensitivity, specificity, and the Hosmer–Lemeshow test. Results: The nomogram had a survival prediction accuracy of 0.878 and 0.875, a specificity of 0.875 and 0.583, and a sensitivity of 0.704 and 0.833, respectively, in the training and test set. The ROC curve showed the accuracy of the nomogram, radiomic signature, age, and EPI for external validation set were 0.858, 0.826, 0.664, and 0.66 in the validate set, respectively. Data Conclusion: Radiomics nomogram integrated with radiomic signature, EPI, and age was found to be robust for the stratification of GBM patients into long‐ vs. short‐term survival. Level of Evidence: 3 Technical Efficacy Stage: 2