Background: Posterior fossa tumors (PFTs) are a morbid group of central nervous system tumors that most often present in childhood. While early diagnosis is critical to drive appropriate treatment, definitive diagnosis is currently only achievable through invasive tissue collection and histopathological analyses. Machine learning has been investigated as an alternative means of diagnosis. In this systematic review and meta-analysis, we evaluated the primary literature to identify all machine learning algorithms developed to classify and diagnose pediatric PFTs using imaging or molecular data. Methods: Of the 433 primary papers identified in PubMed, EMBASE, and Web of Science, 25 ultimately met the inclusion criteria. The included papers were extracted for algorithm architecture, study parameters, performance, strengths, and limitations. Results: The algorithms exhibited variable performance based on sample size, classifier(s) used, and individual tumor types being investigated. Ependymoma, medulloblastoma, and pilocytic astrocytoma were the most studied tumors with algorithm accuracies ranging from 37.5% to 94.5%. A minority of studies compared the developed algorithm to a trained neuroradiologist, with three imaging-based algorithms yielding superior performance. Common algorithm and study limitations included small sample sizes, uneven representation of individual tumor types, inconsistent performance reporting, and a lack of application in the clinical environment. Conclusions: Artificial intelligence has the potential to improve the speed and accuracy of diagnosis in this field if the right algorithm is applied to the right scenario. Work is needed to standardize outcome reporting and facilitate additional trials to allow for clinical uptake.

Embryonal tumor with multilayered rosettes (ETMR) is a pediatric brain tumor with dismal prognosis. Characteristic alterations of the chromosome 19 microRNA cluster (C19MC) are observed in most ETMR; however, the ramifications of C19MC activation and the complex cellular architecture of ETMR remain understudied. Here we analyze 11 ETMR samples from patients using single-cell transcriptomics and multiplexed spatial imaging. We reveal a spatially distinct cellular hierarchy that spans highly proliferative neural stem-like cells and more differentiated neuron-like cells. C19MC is predominantly expressed in stem-like cells and controls a transcriptional network governing stemness and lineage commitment, as resolved by genome-wide analysis of microRNA-mRNA binding. Systematic analysis of receptor–ligand interactions between malignant cell types reveals fibroblast growth factor receptor and Notch signaling as oncogenic pathways that can be successfully targeted in preclinical models and in one patient with ETMR. Our study provides fundamental insights into ETMR pathobiology and a powerful rationale for more effective targeted therapies.

Pediatric high grade gliomas (pHGG) are a highly lethal subgroup of brain tumors that often recur despite lack of measurable disease on imaging, indicating persistent undetected treatment-resistant disease. Measures of disease in the central nervous system tumors are hampered by their sensitive neuroanatomical location, the risk of serial biopsy and limitations in imaging techniques. The development of liquid biomarkers for pHGG holds promise as a clinically relevant tool in diagnosis, prognosis, therapeutic predication, and disease surveillance. This review discusses the current state of liquid biopsy for pHGGs and its potential applications for biomarker development in pHGG.

Supratentorial ependymomas are aggressive childhood brain cancers that retain features of neurodevelopmental cell types¹ and segregate into molecularly and clinically distinct subgroups^2,3, suggesting different developmental roots. The developmental signatures, as well as microenvironmental factors, underlying aberrant cellular transformation and behaviour across each supratentorial ependymoma subgroup are unclear. Here we integrated single-cell and spatial transcriptomics, as well as in vitro and in vivo live-cell imaging, to define supratentorial ependymoma cell states, spatial organization and dynamic behaviour within the neural microenvironment. We find that individual tumour subgroups have two distinct progenitor-like cell states—neuroepithelial-like and embryonic-like—that are reminiscent of early human brain development and diverge in the extent of their neuronal or ependymal differentiation. We further identify several modes of spatial organization of these tumours, including a high-order architecture that is influenced by mesenchymal and hypoxia signatures, and local neighbourhood structures. Finally, we identify a role for brain-resident cells in shifting supratentorial ependymoma cellular heterogeneity towards neuronal-like cells that co-opt immature neuronal morphology and migratory mechanisms, and a subset of neuroepithelial-like cells that are both proliferative and highly migratory. Collectively, these findings provide a multidimensional framework to integrate transcriptional and phenotypic characterization of tumour heterogeneity in supratentorial ependymoma and its potential clinical implications.

Diffuse intrinsic pontine glioma (DIPG) carries an extremely poor prognosis, with 2-year survival rates of <10% despite the maximal radiation therapy. DIPG cells have previously been shown to be sensitive to low-intensity electric fields in vitro. Accordingly, we sought to determine if the endoscopic endonasal (EE) implantation of an electrode array in the clivus would be feasible for the application of tumor-treating fields (TTF) in DIPG. Anatomic constraints are the main limitation in pediatric EE approaches. In our Boston Children’s Hospital’s DIPG cohort, we measured the average intercarotid distance (1.68 ± 0.36 cm), clival width (1.62 ± 0.19 cm), and clival length from the base of the sella (1.43 ± 0.69 cm). Using a linear regression model, we found that only clival length and sphenoid pneumatization were significantly associated with age (R² = 0.568, p = 0.005 *; R² = 0.605, p = 0.0002 *). Critically, neither of these parameters represent limitations to the implantation of a device within the dimensions of those currently available. Our findings confirm that the anatomy present within this age group is amenable to the placement of a 2 × 1 cm electrode array in 94% of patients examined. Our work serves to demonstrate the feasibility of implantable transclival devices for the provision of TTFs as a novel adjunctive therapy for DIPG.