Radiomics features based on MRI predict BRAF V600E mutation in pediatric low-grade gliomas: A non-invasive method for molecular diagnosis

• Published in: Clinical neurology and neurosurgery 2022-11, Vol.222, p.107478-107478, Article 107478
• Main Authors: Xu, Jiali, Lai, Mingyao, Li, Shaoqun, Ye, Kunlin, Li, Linzhen, Hu, Qingjun, Ai, Ruyu, Zhou, Jiangfen, Li, Juan, Zhen, Junjie, Cai, Linbo, Shi, Changzheng
• Format: Article
• Language: English
• Subjects: Age; BRAF V600E; Brain cancer; FLAIR; Glioma; Kinases; Magnetic resonance imaging; MRI; Mutation; Neuroimaging; Pathology; Patients; Pediatrics; PLGG; Prediction models; Principal components analysis; Radiomics; Raf protein; Threonine; Tumors
• ISSN: 0303-8467; 1872-6968
• DOI: 10.1016/j.clineuro.2022.107478

To investigate the clinical application value of radiomics features based on preoperative magnetic resonance imaging for predicting B-Raf proto-oncogene serine/threonine-protein (BRAF) V600E mutation in pediatric low-grade gliomas. The clinical, imaging, and pathological data from 113 pediatric patients with low-grade gliomas patients were retrospectively analyzed. Using open-source software, three-dimensional imaging features were extracted on the basis of FLAIR sequences, and the radiomics process was analyzed to dichotomize BRAFV600E mutant and wild type. All cases were randomly divided into the training and test sets according to a 7:3 training and test group ratio, and a 5-fold cross-validation was performed on the training set. The optimal hyperparameters were selected to build the prediction model, and the test set was used for external validation to assess the diagnostic value of the model using the receiver operating characteristic curve. The training set comprised 79 patients (47 males, 32 females, mean age 9.86 ± 5.20) and the test set comprised 34 patients (20 males, 14 females, mean age 10.97 ± 5.14). Sex, age, and brain side were not significant predictors of BRAF, and tumor location on the supratentorial region was a BRAF predictor (p