Purpose: The aim of this study was to test whether radiomics-based machine learning can enable the better differentiation between glioblastoma (GBM) and anaplastic oligodendroglioma (AO).Methods: This retrospective study involved 126 patients histologically diagnosed as GBM (n = 76) or AO (n = 50) in our institution from January 2015 to December 2018. A total number of 40 three-dimensional texture features were extracted from contrast-enhanced T1-weighted images using LIFEx package. Six diagnostic models were established with selection methods and classifiers. The optimal radiomics features were separately selected into three datasets with three feature selection methods [distance correlation, least absolute shrinkage and selection operator (LASSO), and gradient boosting decision tree (GBDT)]. Then datasets were separately adopted into linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Specificity, sensitivity, accuracy, and area under curve (AUC) of each model were calculated to evaluate their diagnostic performances.Results: The diagnostic performance of machine learning models was superior to human readers. Both classifiers showed promising ability in discrimination with AUC more than 0.900 when combined with suitable feature selection method. For LDA-based models, the AUC of models were 0.986, 0.994, and 0.970 in the testing group, respectively. For the SVM-based models, the AUC of models were 0.923, 0.817, and 0.500 in the testing group, respectively. The over-fitting model was GBDT + SVM, suggesting that this model was too volatile that unsuitable for classification.Conclusion: This study indicates radiomics-based machine learning has the potential to be utilized in clinically discriminating GBM from AO.

BackgroundCraniopharyngioma (CP) is a common refractory tumor of the central nervous system. However, little is known about the expression and clinical significance of B7 family ligands/receptors in CP patients. Thus, we conducted the present study to address this issue in a cohort of 132 CP cases.MethodsWe mapped and quantified the expression of B7 family ligands/receptors molecules programmed cell death ligand 1 (PD-L1), B7-H3, B7-H4 and V-domain Ig-containing suppressor of T cell activation (VISTA) in 89 adamantinomatous-type CP and 43 papillary-type CP samples using immunohistochemistry and immunofluorescence. Associations between the marker levels, clinicopathological variables and survival were evaluated.ResultsThe positive rates of PD-L1, B7-H3, B7-H4 and VISTA in the cohort of 132 CP cases were 76.5%, 100%, 40.2% and 80.3%, respectively. The cut-off values of PD-L1, B7-H3, B7-H4 and PD-L1 expression were determined by survival receiver operating characteristic (ROC) package, which was 70, 182, 0 and 20, respectively. Elevated expressions of PD-L1, B7-H3, B7-H4 and VISTA were significantly associated with some clinicopathological characteristics. Kaplan-Meier analysis indicated that higher VISTA expressions correlated with better overall survival (OS) and progression-free survival (PFS) (p=0.0053 and p=0.0066, respectively). Multivariate Cox regression analysis indicated that VISTA was an independent prognostic factor for OS (p=0.018) but not for PFS (p=0.898).ConclusionsWe found variable expression of PD-L1, B7-H3, B7-H4 and VISTA proteins in CPs. The results suggest that the expression level of VISTA may be used as an important indicator to predict the OS and PFS of CPs. B7 family ligands/receptors could be potential immunotherapeutic targets when treating CPs.

ObjectivesTo investigate the diagnostic value of MRI-based texture analysis in discriminating common posterior fossa tumors, including medulloblastoma, brain metastatic tumor, and hemangioblastoma.MethodsA total number of 185 patients were enrolled in the current study: 63 of them were diagnosed with medulloblastoma, 56 were diagnosed with brain metastatic tumor, and 66 were diagnosed with hemangioblastoma. Texture features were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images within two matrixes. Mann–Whitney U test was conducted to identify whether texture features were significantly different among subtypes of tumors. Logistic regression analysis was performed to assess if they could be taken as independent predictors and to establish the integrated models. Receiver operating characteristic analysis was conducted to evaluate their performances in discrimination.ResultsThere were texture features from both T1C images and FLAIR images found to be significantly different among the three types of tumors. The integrated model represented that the promising diagnostic performance of texture analysis depended on a series of features rather than a single feature. Moreover, the predictive model that combined texture features and clinical feature implied feasible performance in prediction with an accuracy of 0.80.ConclusionMRI-based texture analysis could potentially be served as a radiological method in discrimination of common tumors located in posterior fossa.

Introduction: Glioblastoma and anaplastic astrocytoma (ANA) are two of the most common primary brain tumors in adults. The differential diagnosis is important for treatment recommendations and prognosis assessment. This study aimed to assess the discriminative ability of texture analysis using machine learning to distinguish glioblastoma from ANA.Methods: A total of 123 patients with glioblastoma (n = 76) or ANA (n = 47) were enrolled in this study. Texture features were extracted from contrast-enhanced Magnetic Resonance (MR) images using LifeX package. Three independent feature-selection methods were performed to select the most discriminating parameters:Distance Correlation, least absolute shrinkage and selection operator (LASSO), and gradient correlation decision tree (GBDT). These selected features (datasets) were then randomly split into the training and the validation group at the ratio of 4:1 and were fed into linear discriminant analysis (LDA), respectively, and independently. The standard sensitivity, specificity, the areas under receiver operating characteristic curve (AUC) and accuracy were calculated for both training and validation group.Results: All three models (Distance Correlation + LDA, LASSO + LDA and GBDT + LDA) showed promising ability to discriminate glioblastoma from ANA, with AUCs ≥0.95 for both the training and the validation group using LDA algorithm and no overfitting was observed. LASSO + LDA showed the best discriminative ability in horizontal comparison among three models.Conclusion: Our study shows that MRI texture analysis using LDA algorithm had promising ability to discriminate glioblastoma from ANA. Multi-center studies with greater number of patients are warranted in future studies to confirm the preliminary result.