• Wei Xia, Bin Hu, Haiqing Li, Chen Geng, Qiuwen Wu, Liqin Yang, Bo Yin, Xin Gao, Yuxin Li, and Daoying Geng.
• Academy for Engineering and Technology, Fudan University, Shanghai, China.
• J Magn Reson Imaging. 2021 Jan 1; 53 (1): 242-250.

BackgroundPreoperative differentiation of primary central nervous system lymphoma (PCNSL) from glioblastoma (GBM) is important to guide neurosurgical decision-making.PurposeTo validate the generalization ability of radiomics models based on multiparametric-MRI (MP-MRI) for differentiating PCNSL from GBM.Study TypeRetrospective.PopulationIn all, 240 patients with GBM (n = 129) or PCNSL (n = 111).Field Strength/Sequence3.0T scanners (two vendors). Sequences: fluid-attenuation inversion recovery, diffusion-weighted imaging (DWI), and contrast-enhanced T1 -weighted imaging (CE-T1 WI). Apparent diffusion coefficients (ADCs) were derived from DWI.AssessmentCross-vendor and mixed-vendor validation were conducted. In cross-vendor validation, the training set was 149 patients' data from vendor 1, and test set was 91 patients' data from vendor 2. In mixed-vendor validation, a training set was 80% of data from both vendors, and the test set remained at 20% of data. Single and multisequence radiomics models were built. The diagnoses by radiologists with 5, 10, and 20 years' experience were obtained. The integrated models were built combining the diagnoses by the best-performing radiomics model and each radiologist. Model performance was validated in the test set using area under the ROC curve (AUC). Histological results were used as the reference standard.Statistical TestsDeLong test: differences between AUCs. U-test: differences of numerical variables. Fisher's exact test: differences of categorical variables.ResultsIn cross-vendor and mixed-vendor validation, the combination of CE-T1 WI and ADC produced the best-performing radiomics model, with AUC of 0.943 vs. 0.935, P = 0.854. The integrated models had higher AUCs than radiologists, with 5 (0.975 vs. 0.891, P = 0.002 and 0.995 vs. 0.885, P = 0.007), 10 (0.975 vs. 0.913, P = 0.029 and 0.995 vs. 0.900, P = 0.030), and 20 (0.975 vs. 0.945, P = 0.179 and 0.995 vs. 0.923, P = 0.046) years' experiences.Data ConclusionRadiomics for differentiating PCNSL from GBM was generalizable. The model combining MP-MRI and radiologists' diagnoses had superior performance compared to the radiologists alone.Level Of Evidence4 TECHNICAL EFFICACY STAGE: 2.© 2020 International Society for Magnetic Resonance in Medicine.

14 keywords...

hide…