The 2016 WHO classification of central nervous system tumors has included four molecular subgroups under medulloblastoma (MB) as sonic hedgehog (SHH), wingless (WNT), Grade 3, and Group 4. We aimed to develop machine learning models for predicting MB molecular subgroups based on multi-parameter magnetic resonance imaging (MRI) radiomics, tumor locations, and clinical factors. A total of 122 MB patients were enrolled retrospectively. After selecting robust, non-redundant, and relevant features from 5,529 extracted radiomics features, a random forest model was constructed based on a training cohort ( n = 92) and evaluated on a testing cohort ( n = 30). By combining radiographic features and clinical parameters, two combined prediction models were also built. The subgroup can be classified using an 11-feature radiomics model with a high area under the curve (AUC) of 0.8264 for WNT and modest AUCs of 0.6683, 0.6004, and 0.6979 for SHH, Group 3, and Group 4 in the testing cohort, respectively. Incorporating location and hydrocephalus into the radiomics model resulted in improved AUCs of 0.8403 and 0.8317 for WNT and SHH, respectively. After adding gender and age, the AUCs for WNT and SHH were further improved to 0.9097 and 0.8654, while the accuracies were 70 and 86.67% for Group 3 and Group 4, respectively. Prediction performance was excellent for WNT and SHH, while that for Group 3 and Group 4 needs further improvements. Machine learning algorithms offer potentials to non-invasively predict the molecular subgroups of MB.

Background/Aims: CDH18 (cadherin 18) is specifically expressed in the central nervous system and associated with various neuropsychiatric disorders. In this study, the role of CDH18 in glioma carcinogenesis and progression was investigated. Methods: The expression of CDH18 and its prognostic value in patients with gliomas were analyzed in public database and validated by real-time PCR/immunohistochemical staining (IHC) in our cohort. CCK-8 assay, transwell migration assay, wound healing assay, clonogenic assay and tumorigenicity assay were used to compare the proliferation, invasion and migration ability of glioma cells with different expressions of CDH18. iTRAQ-based quantitative proteomic analysis were used to reveal the downstream target of CDH18. Rescue experiments were conducted to further validate the relationship between UQCRC2 and CDH18. Results: The expression of CDH18 was depressed in a ladder-like pattern from normal tissues to WHO IV gliomas, and was an independent prognostic factor in TCGA (The Cancer Genome Atlas), CGGA (the Chinese glioma genome-atlas) and our glioma cohorts (n=453). Functional experiments in vitro and in vivo demonstrated that CDH18 inhibited invasion/migration, enhanced chemoresistance and suppressed tumorigenicity of glioma cells. UQCRC2 was identified as the downstream target of CDH18 by proteomic analysis. The expression of UQCRC2 was gradually absent as the WHO grades of gliomas escalated and was positively correlated with the expression of CDH18. Furthermore, in vitro assays demonstrated that down-regulation of UQCRC2 partly reversed the inhibition of invasion/migration ability and chemoresistance in CDH18 overexpressed glioma cell lines. Survival analysis demonstrated that combined CDH18/UQCRC2 biomarkers significantly influenced the prognosis of glioma patients. Conclusions: The present research demonstrated that CDH18 exerted its tumor-suppressor role via UQCRC2 in glioma cells and CDH18 might serve as a therapeutic target for treating gliomas.

Background To develop a radiomics signature for predicting overall survival (OS)/progression-free survival (PFS) in patients with medulloblastoma (MB), and to investigate the incremental prognostic value and biological pathways of the radiomics patterns. Methods A radiomics signature was constructed based on magnetic resonance imaging (MRI) from a training cohort ( n = 83), and evaluated on a testing cohort ( n = 83). Key pathways associated with the signature were identified by RNA-seq (GSE151519). Prognostic value of pathway genes was assessed in a public GSE85218 cohort. Findings The radiomics-clinicomolecular signature predicted OS (C-index 0.762) and PFS (C-index 0.697) better than either the radiomics signature (C-index: OS: 0.649; PFS: 0.593) or the clinicomolecular signature (C-index: OS: 0.725; PFS: 0.691) alone, with a better calibration and classification accuracy (net reclassification improvement: OS: 0.298, P = 0.022; PFS: 0.252, P = 0.026). Nine pathways were significantly correlated with the radiomics signature. Average expression value of pathway genes achieved significant risk stratification in GSE85218 cohort (log-rank P = 0.016). Interpretation This study demonstrated radiomics signature, which associated with dysregulated pathways, was an independent parameter conferring incremental value over clinicomolecular factors in survival predictions for MB patients. Funding A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.

The prediction of clinical outcome for patients with infiltrative gliomas is challenging. Although preoperative hematological markers have been proposed as predictors of survival in glioma and other cancers, systematic investigations that combine these data with other relevant clinical variables are needed to improve prognostic accuracy and patient outcomes. We investigated the prognostic value of preoperative hematological markers, alone and in combination with molecular pathology, for the survival of 592 patients with Grade II-IV diffuse gliomas. On univariate analysis, increased neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and monocyte-to-lymphocyte ratio (MLR), and decreased albumin-to-globulin ratio (AGR), all predicted poor prognosis in Grade II/III gliomas. Multivariate analysis incorporating tumor status based on the presence of IDH mutations, TERT promoter mutations, and 1p/19q codeletion showed that in lower-grade gliomas, high NLR predicted poorer survival for the triple-negative, IDH mutation only, TERT mutation only, and IDH and TERT mutation groups. NLR was an independent prognostic factor in Grade IV glioma. We therefore propose a prognostic model for diffuse gliomas based on the presence of IDH and TERT promoter mutations, 1p/19q codeletion, and NLR. This model classifies lower-grade gliomas into nine subgroups that can be combined into four main risk groups based on survival projections.

Background To develop and validate a deep learning signature (DLS) from diffusion tensor imaging (DTI) for predicting overall survival in patients with infiltrative gliomas, and to investigate the biological pathways underlying the developed DLS. Methods The DLS was developed based on a deep learning cohort (n = 688). The key pathways underlying the DLS were identified on a radiogenomics cohort with paired DTI and RNA-seq data (n=78), where the prognostic value of the pathway genes was validated in public databases (TCGA, n = 663; CGGA, n = 657). Findings The DLS was associated with survival (log-rank P < 0.001) and was an independent predictor ( P < 0.001). Incorporating the DLS into existing risk system resulted in a deep learning nomogram predicting survival better than either the DLS or the clinicomolecular nomogram alone, with a better calibration and classification accuracy (net reclassification improvement 0.646, P < 0.001). Five kinds of pathways (synaptic transmission, calcium signaling, glutamate secretion, axon guidance, and glioma pathways) were significantly correlated with the DLS. Average expression value of pathway genes showed prognostic significance in our radiogenomics cohort and TCGA/CGGA cohorts (log-rank P < 0.05). Interpretation DTI-derived DLS can improve glioma stratification by identifying risk groups with dysregulated biological pathways that contributed to survival outcomes. Therapies inhibiting neuron-to-brain tumor synaptic communication may be more effective in high-risk glioma defined by DTI-derived DLS. Funding A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.