An MRI-based radiomics signature as a pretreatment noninvasive predictor of overall survival and chemotherapeutic benefits in lower-grade gliomas

• Published in: European radiology Vol. 31; no. 4; pp. 1785 - 1794
• Main Authors: Wang, Jingtao, Zheng, Xuejun, Zhang, Jinling, Xue, Hao, Wang, Lijie, Jing, Rui, Chen, Shuo, Che, Fengyuan, Heng, Xueyuan, Li, Gang, Xue, Fuzhong
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2021; Springer Nature B.V
• Subjects: Chemotherapy; Diagnostic Radiology; Feature extraction; Glioma; Glioma - diagnostic imaging; Glioma - drug therapy; Humans; Imaging; Imaging Informatics and Artificial Intelligence; Internal Medicine; Interventional Radiology; Magnetic Resonance Imaging; Medical prognosis; Medicine; Medicine & Public Health; Neuroradiology; Nomograms; Prognosis; Radiology; Radiomics; Regression analysis; Regression models; Retrospective Studies; Signatures; Survival; Ultrasound; Prognosis; Glioma; Magnetic resonance imaging; Nomograms; Radiomics
• ISSN: 0938-7994; 1432-1084; 1432-1084
• DOI: 10.1007/s00330-020-07581-3

Objectives The aim of this study was to develop and validate a radiomics signature for predicting survival and chemotherapeutic benefits of patients with lower-grade gliomas (LGG). Methods Radiomics features were extracted from precontrast axial fluid-attenuated inversion recovery (FLAIR) and contrast-enhanced axial T-1 weighted (CE-T1-w) sequence. Lasso Cox regression model was used for feature selection and radiomics signature building. The radiomics signature was developed in a primary cohort that consisted of 149 LGG patients and was then validated on an entirely new validation cohort that contained 66 LGG patients. A radiomics nomogram for the prediction of OS was established by adding the radiomics to clinicopathologic nomogram which developed with clinical data. Results A radiomics signature derived from joint CE-T1-w and FLAIR images showed better prognostic performance (C-index, 0.798) than signatures derived from CE-T1-w (C-index, 0.744) or FLAIR (C-index, 0.736) sequences alone. Multivariable Cox regression revealed that the radiomics signature was an independent prognostic factor. One radiomics nomogram integrated the radiomics signature from joint CE-T1-w and FLAIR sequences with the clinicopathologic nomogram outperformed the clinicopathologic nomogram based on clinicopathologic data alone in predicting OS of LGG (C-index, 0.821 vs. 0.692; p < 0.001). Further analysis revealed that patients with higher radiomics signature were prone to benefit from chemotherapy. Conclusions The radiomics signature was independent with clinicopathologic data and was a noninvasive pretreatment predictor for LGG patients’ survival. Moreover, it could predict which patients with LGG benefit from chemotherapy. Key Points • A radiomics signature derived from joint CE-T1-w and FLAIR sequences showed better prognostic performance than signatures derived from either single imaging modality. • The radiomics signature is an independent prognostic factor and outperformed clinicopathologic features in predicting overall survival of LGG patients. • The radiomics signature could help preoperatively identify LGG patients who may benefit from chemotherapy.