A radiomics model for predicting the response to methylprednisolone in brain necrosis after radiotherapy for nasopharyngeal carcinoma

• Published in: Radiation oncology (London, England) Vol. 18; no. 1; p. 43
• Main Authors: Zhuo, Xiaohuang, Zhao, Huiying, Chen, Meiwei, Mu, Youqing, Li, Yi, Cai, Jinhua, Li, Honghong, Xu, Yongteng, Tang, Yamei
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 01.03.2023; BioMed Central; BMC
• Subjects: Brain; Brain necrosis; Calibration; Cancer therapies; Care and treatment; Causes of; Decision analysis; Diagnosis; Dosage and administration; Feature extraction; Humans; Magnetic resonance; Magnetic resonance imaging; Medical records; Methylprednisolone; Nasopharyngeal cancer; Nasopharyngeal Carcinoma; Nasopharyngeal Neoplasms; Necrosis; Patient outcomes; Patients; Performance evaluation; Radiation; Radiation effects; Radiation Injuries; Radiation therapy; Radiomics; Radiomics model; Radiotherapy; Regression analysis; Software; Steroids; Throat cancer; Treatment response; China; Nasopharyngeal carcinoma; Treatment response; Methylprednisolone; Radiotherapy; Radiomics model; Brain necrosis
• ISSN: 1748-717X; 1748-717X
• DOI: 10.1186/s13014-023-02235-2

Methylprednisolone is recommended as the front-line therapy for radiation-induced brain necrosis (RN) after radiotherapy for nasopharyngeal carcinoma. However, some patients fail to benefit from methylprednisolone or even progress. This study aimed to develop and validate a radiomic model to predict the response to methylprednisolone in RN. Sixty-six patients receiving methylprednisolone were enrolled. In total, 961 radiomic features were extracted from the pre-treatment magnetic resonance imagings of the brain. Least absolute shrinkage and selection operator regression was then applied to construct the radiomics signature. Combined with independent clinical predictors, a radiomics model was built with multivariate logistic regression analysis. Discrimination, calibration and clinical usefulness of the model were assessed. The model was internally validated using 10-fold cross-validation. The radiomics signature consisted of 16 selected features and achieved favorable discrimination performance. The radiomics model incorporating the radiomics signature and the duration between radiotherapy and RN diagnosis, yielded an AUC of 0.966 and an optimism-corrected AUC of 0.967 via 10-fold cross-validation, which also revealed good discrimination. Calibration curves showed good agreement. Decision curve analysis confirmed the clinical utility of the model. The presented radiomics model can be conveniently used to facilitate individualized prediction of the response to methylprednisolone in patients with RN.