This study explored the clinical, radiological, and pathological characteristics of cerebellopontine angle (CPA) meningiomas with internal auditory canal (IAC) involvement. The pre- and postoperative MR images of 193 consecutive patients with pathologically diagnosed meningioma centered around the IAC were analyzed, focusing on changes in the IAC, maximal axial tumor volume, peritumoral brain edema, and postoperative residual tumor. Patient age, sex, tumor volume, postoperative residual tumor, and pathological subtype were compared in patients with and without IAC involvement by the tumor and among the different types of IAC involvement. The results showed that the 71 patients (36.8%) with IAC involvement had a higher ratio of peritumoral edema (χ²=5.922, P=0.015), postoperative residual tumor (χ²=22.183, P< 0.001), and a predominance of the meningothelial subtype (χ²=5.89, P=0 .015). Peritumoral edema was a risk factor for IAC involvement (P=0.016, OR=2.186). Radiologically, IAC involvement could be distinguished as intruding (31%, 22/71), filled (29.6%, 21/71), and dilated (39.4%, 28/71). Patients with intruding IAC were significantly older (54.5±9.54 years, P=0.021) and had the lowest postoperative residual tumor values (42%, χ²=7.865, P= 0.005), while those with filled IAC were more likely to be female (95%, χ²=9.404, P=0.009).Our observations provide the basis for a morphological classification of IAC involvement by CPA meningiomas and further insight into the clinical features of these tumors.

Objective: To identify optimal machine-learning methods for the radiomics-based differentiation of gliosarcoma (GSM) from glioblastoma (GBM).Materials and Methods: This retrospective study analyzed cerebral magnetic resonance imaging (MRI) data of 83 patients with pathologically diagnosed GSM (58 men, 25 women; mean age, 50.5 ± 12.9 years; range, 16-77 years) and 100 patients with GBM (58 men, 42 women; mean age, 53.4 ± 14.1 years; range, 12-77 years) and divided them into a training and validation set randomly. Radiomics features were extracted from the tumor mass and peritumoral edema. Three feature selection and classification methods were evaluated in terms of their performance in distinguishing GSM and GBM: the least absolute shrinkage and selection operator (LASSO), Relief, and Random Forest (RF); and adaboost classifier (Ada), support vector machine (SVM), and RF; respectively. The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) of each method were analyzed.Results: Based on tumor mass features, the selection method LASSO + classifier SVM was found to feature the highest AUC (0.85) and ACC (0.77) in the validation set, followed by Relief + RF (AUC = 0.84, ACC = 0.72) and LASSO + RF (AUC = 0.82, ACC = 0.75). Based on peritumoral edema features, Relief + SVM was found to have the highest AUC (0.78) and ACC (0.73) in the validation set. Regardless of the method, tumor mass features significantly outperformed peritumoral edema features in the differentiation of GSM from GBM (P < 0.05). Furthermore, the sensitivity, specificity, and accuracy of the best radiomics model were superior to those obtained by the neuroradiologists.Conclusion: Our radiomics study identified the selection method LASSO combined with the classifier SVM as the optimal method for differentiating GSM from GBM based on tumor mass features.