Abstract Background To systematically evaluate and compare the diagnostic efficacy of radiomics models derived from noncontrast CT (NCCT) versus multiparametric MRI in differentiating glioblastoma (GBM) from primary central nervous system lymphoma (PCNSL). Methods In this retrospective, bicentric study, 490 patients with pathologically confirmed GBM (n = 365) or PCNSL (n = 125) were divided into 3 cohorts. 1084 quantitative features were extracted from contrast-enhancing (CE) and non-enhancing (NE) regions across NCCT and five MRI sequences (T2WI, T1WI, ADC, FLAIR, and CE-T1WI). Feature selection employed ANOVA, Kruskal-Wallis test, and recursive feature elimination, followed by nested cross-validation (5-fold outer, 3-fold inner) to construct four machine learning classifiers: support vector machine, linear discriminant analysis, logistic regression, and decision tree. Model performance was rigorously assessed through AUC, accuracy, sensitivity, specificity with bootstrap-derived 95% confidence intervals. Results The CE-T1WI radiomics model demonstrated superior diagnostic capability, with its AUCs of train/internal test/external test in CE regions and NE regions were 0.962/0.963/0.822 and 0.966/0.892/0.905, respectively. Notably, the CT-based model was not significantly different from other MRI models except for CE-T1WI model. The AUCs of train/internal test/external test for CT model in CE and NE regions were 0.941/0.906/0.828 and 0.902/0.891 /0.766, respectively. Conclusions Both NCCT and multiparametric MRI are valuable in identifying GBM and PCNSL. The CE-T1WI radiomics model has the best diagnostic efficacy.
Yu et al. (Sun,) studied this question.