Glioblastoma and primary central nervous system lymphoma: Preoperative differentiation by using MRI-based 3D texture analysis

Abstract

ObjectivesTo investigate the diagnostic value of magnetic resonance imaging (MRI)-based 3D texture and shape features in the differentiation of glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL). Patients and methodsA total of eighty-two patients, including sixty patients with GBM and twenty-two patients with PCNSL were followed up retrospectively from January 2012 to September 2017. MRI-based 3D texture and shape analysis were performed to evaluate the detectable differences between the two malignancies. The performance of machine-learning models was assessed. The Mann-Whitney U test and receiver operating characteristic (ROC) analysis were performed, and the corresponding sensitivity, specificity, accuracy, and area under the curve (AUC) were calculated.Ultimately, 60 GBM patients (33 males, 27 females; mean age 51.55 ± 13.58 years, range 8–74 years) and 22 PCNSL patients (14 males, 8 females; mean age 55.18 ± 12.19 years, range 32–78 years) were included in this study. All the PCNSLs were of the diffuse large B-cell type, and all patients were immunocompetent. ResultsThe variables Firstorder_Skewness, Firstorder_Kurtosis, and Ngtdm_Busyness, representing features extracted from contrast-enhanced T1-weighted images, showed high discriminatory power. Firstorder_ Skewness was the best selected predictor for classification (AUC = 0.86), followed by Ngtdm_Busyness (AUC = 0.83) and Firstorder_Kurtosis (AUC = 0.80). The sensitivities and specificities ranged from 70.0% to 83.3% and from 71.4% to 90.5%, respectively. Among three classification models, the naive Bayes classifier was superior overall, with a high AUC (0.90) and the best specificity (0.91). The support vector machine models provided the best sensitivity and accuracy (0.92 and 0.88, respectively). ConclusionsMRI-based 3D texture analysis has potential utility for preoperative discrimination of GBM and PCNSL.