Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction.

Background: There is growing interest in utilizing artificial intelligence, and particularly deep learning, for computer vision in histopathology. While accumulating studies highlight expert-level performance of convolutional neural networks (CNNs) on focused classification tasks, most studies rely on probability distribution scores with empirically defined cutoff values based on post-hoc analysis. More generalizable tools that allow humans to visualize histology-based deep learning inferences and decision making are scarce.

5-Hydroxymethylcytosine preferentially targets genes upregulated in isocitrate dehydrogenase 1 mutant high-grade glioma.

Gliomas demonstrate epigenetic dysregulation exemplified by the Glioma CpG Island Methylator Phenotype (G-CIMP) seen in IDH1 mutant tumors. 5-Hydroxymethylcytosine (5hmC) is implicated in glioma pathogenesis; however, its role in IDH1 mutant gliomas is incompletely understood. To characterize 5hmC in IDH1 mutant gliomas further, we examine 5hmC in a cohort of IDH1 mutant and wild-type high-grade gliomas (HGG) using a quantitative locus-specific approach.

Molecular Signatures for Tumor Classification: An Analysis of The Cancer Genome Atlas Data.

Cancer classification in the clinic is primarily based on histological analysis in the proper clinical context, often supplemented by immunohistochemical and molecular studies. Recent genomic studies have shown the potential of integrated multiomics platforms for molecular classification. We performed unsupervised analyses of molecular platforms in The Cancer Genome Atlas data (n = 6,216 samples) in comparison with tumor type.

Therapeutic radiation for childhood cancer drives structural aberrations of NF2 in meningiomas.

Cranial radiotherapy improves survival of the most common childhood cancers, including brain tumors and leukemia. Unfortunately, long-term survivors are faced with consequences of secondary neoplasia, including radiation-induced meningiomas (RIMs). We characterized 31 RIMs with exome/NF2 intronic sequencing, RNA sequencing and methylation profiling, and found NF2 gene rearrangements in 12/31 of RIMs, an observation previously unreported in sporadic meningioma (SM).

Gli1-induced deubiquitinase USP48 aids glioblastoma tumorigenesis by stabilizing Gli1.

Aberrant activation of the Hedgehog (Hh) signaling pathway drives the tumorigenesis of multiple cancers. In this study, we screened a panel of deubiquitinases that may regulate the Hh pathway. We find that deubiquitinase USP48 activates Gli-dependent transcription by stabilizing Gli1 protein.

Prognostic significance of preoperative neutrophilia on recurrence-free survival in meningioma.

Background: Meningioma is the most common primary intracranial tumor and recurrence is one of the important challenges in patient management. Prognostic factors for tumor recurrences in these patients especially before surgical resection are not fully characterized. Several studies have indicated an association between changes in hematologic laboratory parameters with patient outcomes in solid malignancies.

The genomic landscape of schwannoma.

Schwannomas are common peripheral nerve sheath tumors that can cause debilitating morbidities. We performed an integrative analysis to determine genomic aberrations common to sporadic schwannomas. Exome sequence analysis with validation by targeted DNA sequencing of 125 samples uncovered, in addition to expected NF2 disruption, recurrent mutations in ARID1A, ARID1B and DDR1.

DICER governs characteristics of glioma stem cells and the resulting tumors in xenograft mouse models of glioblastoma.

The RNAse III endonuclease DICER is a key regulator of microRNA (miRNA) biogenesis and is frequently decreased in a variety of malignancies. We characterized the role of DICER in glioblastoma (GB), specifically demonstrating its effects on the ability of glioma stem-like cells (GSCs) to form tumors in a mouse model of GB. DICER silencing in GSCs reduced their stem cell characteristics, while tumors arising from these cells were more aggressive, larger in volume, and displayed a higher proliferation index and lineage differentiation.

Glioblastoma: pathology, molecular mechanisms and markers.

Recent advances in genomic technology have led to a better understanding of key molecular alterations that underlie glioblastoma (GBM). The current WHO-based classification of GBM is mainly based on histologic features of the tumor, which frequently do not reflect the molecular differences that describe the diversity in the biology of these lesions. The current WHO definition of GBM relies on the presence of high-grade astrocytic neoplasm with the presence of either microvascular proliferation and/or tumor necrosis.