Search

Objectives: To develop and validate a deep learning model for predicting overall survival from whole-brain MRI without tumor segmentation in patients with diffuse gliomas., Methods: In this multicenter retrospective study, two deep learning models were built for survival prediction from MRI, including a DeepRisk model built from whole-brain MRI, and an original ResNet model built from expert-segmented tumor images. Both models were developed using a training dataset (n = 935) and an internal tuning dataset (n = 156) and tested on two external test datasets (n = 194 and 150) and a TCIA dataset (n = 121). C-index, integrated Brier score (IBS), prediction error curves, and calibration curves were used to assess the model performance., Results: In total, 1556 patients were enrolled (age, 49.0 ± 13.1 years; 830 male). The DeepRisk score was an independent predictor and can stratify patients in each test dataset into three risk subgroups. The IBS and C-index for DeepRisk were 0.14 and 0.83 in external test dataset 1, 0.15 and 0.80 in external dataset 2, and 0.16 and 0.77 in TCIA dataset, respectively, which were comparable with those for original ResNet. The AUCs at 6, 12, 24, 26, and 48 months for DeepRisk ranged between 0.77 and 0.94. Combining DeepRisk score with clinicomolecular factors resulted in a nomogram with a better calibration and classification accuracy (net reclassification improvement 0.69, p < 0.001) than the clinical nomogram., Conclusions: DeepRisk that obviated the need of tumor segmentation can predict glioma survival from whole-brain MRI and offers incremental prognostic value., Key Points: • DeepRisk can predict overall survival directly from whole-brain MRI without tumor segmentation. • DeepRisk achieves comparable accuracy in survival prediction with deep learning model built using expert-segmented tumor images. • DeepRisk has independent and incremental prognostic value over existing clinical parameters and IDH mutation status., (© 2022. The Author(s), under exclusive licence to European Society of Radiology.)

Background: Glioma is the most lethal nervous system cancer. Recent studies have made great efforts to study the occurrence and development of glioma, but the molecular mechanisms are still unclear. This study was designed to reveal the molecular mechanisms of glioma based on protein-protein interaction network combined with machine learning methods. Key differentially expressed genes (DEGs) were screened and selected by using the protein-protein interaction (PPI) networks., Results: As a result, 19 genes between grade I and grade II, 21 genes between grade II and grade III, and 20 genes between grade III and grade IV. Then, five machine learning methods were employed to predict the gliomas stages based on the selected key genes. After comparison, Complement Naive Bayes classifier was employed to build the prediction model for grade II-III with accuracy 72.8%. And Random forest was employed to build the prediction model for grade I-II and grade III-VI with accuracy 97.1% and 83.2%, respectively. Finally, the selected genes were analyzed by PPI networks, Gene Ontology (GO) terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways, and the results improve our understanding of the biological functions of select DEGs involved in glioma growth. We expect that the key genes expressed have a guiding significance for the occurrence of gliomas or, at the very least, that they are useful for tumor researchers., Conclusion: Machine learning combined with PPI networks, GO and KEGG analyses of selected DEGs improve our understanding of the biological functions involved in glioma growth., (Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved.)

Introduction: MiR-135a is found to selectively induce apoptosis in glioma cell but not in normal neurons and glial cells. However, low transfection efficacy limits its application in vivo as other miRNAs. We prepared a new kind of nano-vector based on polyethylene glycol methyl ether (mPEG) and hyper-branched polyethylenimine (hy-PEI) in order to improve the miRNA delivery system into the glioma cells., Methods: The mPEG-g-PEI/miR-135a was constructed and detected by 1H NMR and FTIR analyses. Transmission electron microscope was utilized for its characteristics. Stability and release efficiency was assessed by electrophoresis. Biocompatibility was observed and analyzed through co-culture with astrocytes and malignant glioma cells (C6). Transfection rate was monitored by laser confocal microscopy and flow cytometry. The antitumor effect of mPEG-g-PEI/miR-135a to C6 was confirmed in vivo by MR scanning, pathology and survival curve. RT-PCR was used to assay transfection efficiency of mPEG-g-PEI/miR-135a in vitro and in vivo. And Western blotting was used to assess the expressions of the targeted proteins of miR-135a., Results: In this experiment, we found the optimal N/P ratio of mPEG-g-PEI/miR-135a was about 6 judged by Zeta potential, particle size and encapsulation ability. The stability of mPEG-g-PEI/miR-135a in serum and the release efficiency in acid(pH=5.0) of mPEG-g-PEI/miR-135a were simulated the environment in vivo and in tumor. The mPEG-g-PEI nano-vector was co-cultured with malignant glioma cell C6 and normal astrocytes in vitro and showed good biocompatibility evaluated by CCK8 assay. The cell experiments in vitro indicated that mPEG-g-PEI could significantly improve miR-135a transfection by enhancing uptake effect of both normal glial and glioma cells. Given the C6 implanted in situ model, we discovered that the mPEG-g-PEI/miR-135a could obviously increase the survival period and inhibit the growth of glioma confirmed by MRI and histochemistry. In addition, the transfection efficiency of mPEG-g-PEI was better than that of other transfection agents either in vitro or in vivo confirmed by RT-PCR. Moreover, the expressions of the targeted proteins of miR-135a were consistent with the in vitro results., Conclusion: These results suggest that mPEG-g-PEI is expected to provide a new effective intracellular miRNA delivery system with low toxicity for glioma therapy., Competing Interests: Disclosure The authors report no conflicts of interest in this work.

Background: Malignant glioma is the most lethal primary tumor of the central nervous system, with notable cell invasion causing significant recurrence. Suppression of glioma invasion is very important for improving clinical outcomes. Drugs that directly disrupt the cytoskeleton have been developed for this purpose; however, drug resistance and unsatisfactory selectivity have limited their clinical use. Previously, we reported that protein kinase A (PKA, also known as cyclic-AMP dependent protein kinase) activation induced the differentiation of glioma cells., Methods: We used several small molecular inhibitors and RNA interference, combined with wound healing assays, Matrigel transwell assay, and microscopic observation, to determine whether activation of the PKA pathway could inhibit the invasion of human glioma cells., Results: Activation of PKA decreased the invasion of glioma cells. The mechanism operated via transcriptional upregulation of microtubule-associated protein 2 (MAP2), which was activated by the PKA pathway and led to ossification of microtubule dynamics via polymerization of tubulin. This resulted in morphological changes and a reduction in glioma cell invasion. Furthermore, chromosome immunoprecipitation and quantitative real-time polymerase chain reaction showed that signal transducer and activator of transcription 3 (STAT3) is involved in the transcriptional upregulation of MAP2., Conclusion: Our findings suggested that PKA may represent a potential target for anti-invasion glioma therapy and that the downstream modulators (eg, STAT3/MAP2) partially mediate the effects of PKA., (© The Author(s) 2015. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Necroptosis is a recently discovered form of cell death that plays a vital role in the progression of cancer, the spread of metastases, and the immunologic response to tumors. Due to the dual role of necrotic apoptotic processes in tumor pathogenesis and the heterogeneity of gliomas, the function of necroptosis in the glioma microenvironment is still poorly understood. We characterized the expression of necroptosis-related genes (NRGs) within glioma samples at both the genetic and transcriptional levels, identifying three distinct subtypes. Additionally, we constructed a risk score, which is capable of accurately predicting patient prognosis, correlates with tumor mutation burden (TMB), tumor stem cell index (CSC), immune checkpoints, and predicts tumor drug sensitivity. To facilitate its application in the clinic, we developed a nomogram and demonstrated that it predicts the prognosis of glioma patients with good accuracy and reliability using multiple datasets. We examined the function of necroptosis in the tumor microenvironment (TME) and the prognosis of gliomas, which may be useful for guiding individualized treatment plans for gliomas targeting necroptosis. [ABSTRACT FROM AUTHOR]