Purpose: Isocitrate dehydrogenase 1 (IDH1) has been proven as a prognostic and predictive marker in glioblastoma (GBM) patients. The purpose was to preoperatively predict IDH mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI).Methods: In this retrospective multicenter study, 225 patients were included. A total of 1614 multiregional features were extracted from enhancement area, non‐enhancement area, necrosis, edema, tumor core, and whole tumor in multiparametric MRI. Three multiregional radiomics models were built from tumor core, whole tumor, and all regions using an all‐relevant feature selection and a random forest classification for predicting IDH1. Four single‐region models and a model combining all‐region features with clinical factors (age, sex, and Karnofsky performance status) were also built. All models were built from a training cohort (118 patients) and tested on an independent validation cohort (107 patients).Results: Among the four single‐region radiomics models, the edema model achieved the best accuracy of 96% and the best F1‐score of 0.75 while the non‐enhancement model achieved the best area under the receiver operating characteristic curve (AUC) of 0.88 in the validation cohort. The overall performance of the tumor‐core model (accuracy 0.96, AUC 0.86 and F1‐score 0.75) and the whole‐tumor model (accuracy 0.96, AUC 0.88 and F1‐score 0.75) was slightly better than the single‐regional models. The 8‐feature all‐region radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90, and an F1‐score 0.78. Among all models, the model combining all‐region imaging features with age achieved the best performance of an accuracy 97%, an AUC 0.96, and an F1‐score 0.84.Conclusions: The radiomics model built with multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The multiregional model built with all‐region features performed better than the single‐region models, while combining age with all‐region features achieved the best performance.

Although the incidence of glioma is relatively low, it is the most malignant tumor of the central nervous system. The prognosis of high-grade glioma patient is very poor due to the difficulties in complete resection and resistance to radio-/chemotherapy. Therefore, it is worth investigating the molecular mechanisms involved in glioma drug resistance. MicroRNAs have been found to play important roles in tumor progression and drug resistance. Our previous work showed that miR-181b is involved in the regulation of temozolomide resistance. In the current study, we investigated whether miR-181b also plays a role in antagonizing the effect of teniposide. MiR-181b expression was measured in 90 glioma patient tissues and its relationship to prognosis of these patients was analyzed. Cell sensitivity to teniposide was tested in 48 primary cultured glioma samples. Then miR-181b stably overexpressed U87 cells were generated. The candidate genes of miR-181b from our previous study were reanalyzed, and the interaction between miR-181b and target gene MDM2 was confirmed by dual luciferase assay. Cell sensitivity to teniposide was detected on miR-181b over expressed and MDM2 down regulated cells. Our data confirmed the low expression levels of miR-181b in high-grade glioma tissues, which is related to teniposide resistance in primary cultured glioma cells. Overexpression of miR-181b increased glioma cell sensitivity to teniposide. Through target gene prediction, we found that MDM2 is a candidate target of miR-181b. MDM2 knockdown mimicked the sensitization effect of miR-181b. Further study revealed that miR-181b binds to the 3’-UTR region of MDM2 leading to the decrease in MDM2 levels and subsequent increase in teniposide sensitivity. Partial restoration of MDM2 attenuated the sensitivity enhancement by miR-181b. MiR-181b is an important positive regulator on glioma cell sensitivity to teniposide. It confers glioma cell sensitivity to teniposide through binding to the 3’-UTR region of MDM2 leading to its reduced expression. Our findings not only reveal the novel mechanism involved in teniposide resistance, but also shed light on the optimization of glioma treatment in the future.

Background: The progression and metastasis of cancers are associated with systematic immune inflammation and nutritional dysfunction. The systemic immune-inflammation index and prognostic nutritional index (PNI) have shown a prognostic impact in several malignancies. Therefore, our study aimed to evaluate immune inflammation and nutritional index prognostic significance in patients with medulloblastoma (MB).Methods: We retrospectively analyzed 111 patients with MB between 2001 and 2021 at our institution. The optimal cutoff values for systemic immune-inflammation index (SII), neutrophil/lymphocyte ratio (NLR), monocyte/lymphocyte counts ration (MLR), and PNI were evaluated with receiver operating characteristic (ROC) curve analysis. Clinical characteristics and SII, NLR, MLR, and PNI were tested with the Pearson's chi-squared test. The Kaplan–Meier survival curves and the Cox proportional hazards model were used to evaluate the effects of immune inflammation and nutritional index on overall survival (OS).Results: Receiver operating characteristic curve analysis determined the optimal SII, NLR, MLR, and PNI cutoff values of 2,278, 14.83, 0.219, and 56.5 that significantly interacts with OS and divided the patients into two groups. Comparative survival analysis exhibited that the high-SII cohort had significantly shorter OS (p = 0.0048) than the low-SII cohort. For the univariate analysis, the results revealed that preoperative hydrocephalus (p = 0.01), SII (p = 0.006), albumin–bilirubin score (ALBI) (p = 0.04), and coSII–PNI were predictors of OS. In the multivariate analysis, preoperative hydrocephalus (p < 0.001), ALBI (p = 0.010), SII (p < 0.001), and coSII–PNI as independent prognostic factors were significantly correlated with OS.Conclusion: The preoperative SII, ALBI, and coSII–PNI serve as robust prognostic biomarkers for patients with MB undergoing surgical resection.

Objectives: Phosphatase and tensin homolog (PTEN) mutation is an indicator of poor prognosis of low-grade and high-grade glioma. This study built a reliable model from multi-parametric magnetic resonance imaging (MRI) for predicting the PTEN mutation status in patients with glioma.Methods: In this study, a total of 244 patients with glioma were retrospectively collected from our center (n = 77) and The Cancer Imaging Archive (n = 167). All patients were randomly divided into a training set (n = 170) and a validation set (n = 74). Three models were built from preoperative MRI for predicting PTEN status, including a radiomics model, a convolutional neural network (CNN) model, and an integrated model based on both radiomics and CNN features. The performance of each model was evaluated by accuracy and the area under the receiver operating characteristic curve (AUC).Results: The CNN model achieved an AUC of 0.84 and an accuracy of 0.81, which performed better than did the radiomics model, with an AUC of 0.83 and an accuracy of 0.66. Combining radiomics with CNN will further benefit the predictive performance (accuracy = 0.86, AUC = 0.91).Conclusions: The combination of both the CNN and radiomics features achieved significantly higher performance in predicting the mutation status of PTEN in patients with glioma than did the radiomics or the CNN model alone.