AI-driven WHO 2021 classification of gliomas based only on H&E-stained slides.

Background: The WHO 2021 classification criteria for adult diffuse glioma integrate histology with molecular profiling for conclusive diagnosis. Since molecular profiling can be expensive and time-consuming, often necessitating outsourcing or leading to the 'not otherwise specified (NOS) label', this study develops an AI-driven WHO 2021 classification of gliomas solely from H&E whole-slide images (WSIs).

Methods: Our pipeline is based on a multi-institutional dataset reclassified per WHO 2021 guidelines.

Tumor-initiating genetics and therapy drive divergent molecular evolution in IDH-mutant gliomas.

Astrocytomas and oligodendrogliomas are slow-growing and treatment-sensitive IDH-mutant gliomas diagnosed at ages 30-50. Local tumor regrowth and treatment resistance is inevitable resulting in 3-10 year astrocytoma and up to >20 years oligodendroglioma survival. We sought to identify genetic changes associated with tumor evolution in response to therapy through multi-timepoint whole-genome/whole-exome sequencing of 206 IDH-mutant glioma patient samples collected through the Glioma Longitudinal Analysis (GLASS) Consortium.

Intra-tumoral Preservation of the Stem-like Malignant Cell Proportion in Glioblastoma, Prognostic Impact, and its Radiomethylomic Signatures.

Background: Glioblastoma (GBM) exhibits significant intra-tumoral heterogeneity. However, the presence and extent of intra-tumoral heterogeneity of stem-like and differentiated cell components based on methylation profiles remain poorly understood. Furthermore, the utility of integrating methylation profiles with radiomic features (radiomethylomics) for predicting these cellular states has not been explored.

Interpretable artificial intelligence based determination of glioma IDH mutation status directly from histology slides.

Background: Isocitrate dehydrogenase (IDH) mutation status is a diagnostic requirement for glioma with associated prognostic and therapeutic implications. Clinical routine visual assessment of tissue is insufficient to determine IDH status conclusively, mandating molecular workup that is unavailable everywhere.

Methods: We developed an interpretable Artificial Intelligence (AI)-based approach for determining IDH status directly from H&E-stained glioma slides.

Path2Omics: Enhanced transcriptomic and methylation prediction accuracy from tumor histopathology.

Precision oncology is becoming increasingly integral to clinical practice, demonstrating notable improvements in treatment outcomes. While molecular data provide comprehensive insights, obtaining such data remains costly and time-consuming. To address this challenge, we developed Path2Omics, a deep learning model that predicts gene expression and methylation from histopathology for 23 cancer types.

Cholinergic neuron-to-glioblastoma synapses in a human iPSC-derived co-culture model.

Glioblastoma (GBM) integrates extensively into brain-wide neuronal circuits; however, neuron-tumor interactions have largely been studied with glutamatergic neurons in animal models. The role of neuromodulatory circuits for GBM biology in all-human cell systems remains unclear. Here, we report a co-culture system employing patient-derived GBM organoids and human induced pluripotent stem cell (hiPSC)-derived cholinergic neurons.

Intracerebroventricular bivalent CAR T cells targeting EGFR and IL-13Rα2 in recurrent glioblastoma: a phase 1 trial.

Glioblastoma (GBM) is the most common primary brain cancer in adults and carries a median overall survival (OS) of 12-15 months. Effective therapy for recurrent GBM (rGBM) following frontline chemoradiation is a major unmet medical need. Here we report the dose escalation and exploration phases of a phase 1 trial investigating intracerebroventricular delivery of bivalent chimeric antigen receptor (CAR) T cells targeting epidermal growth factor receptor (EGFR) epitope 806 and interleukin-13 receptor alpha 2 (IL-13Rα2), or CART-EGFR-IL13Rα2 cells, in patients with EGFR-amplified rGBM.

Multimodal Explainable Artificial Intelligence for Prognostic Stratification of Patients With Glioblastoma.

Glioblastoma (GBM) is the most common and aggressive malignant adult tumor of the central nervous system, with a grim prognosis and heterogeneous morphologic and molecular profiles. Since the adoption of the current standard-of-care treatment in 2005, no substantial prognostic improvement has been noticed. In this study, we seek the identification of prognostically relevant GBM characteristics from routinely acquired hematoxylin and eosin-stained whole slide images (WSIs) and clinical data, which when integrated via advanced computational methods could yield improved patient prognostic stratification and hence optimize clinical decision making and patient management.

Diffuse astrocytoma, AYA-type, frequently MAPK-altered: report of 45 patients.

A putative molecular subtype of IDH-wildtype diffuse glioma with recurrent MAPK pathway alterations has recently been reported. By dimensionality reduction analysis of genome-wide methylation profiling, these tumors form a distinct methylation cluster of gliomas. Characterization of 47 tumors from 45 patients reveals that these gliomas are predominantly supratentorial in young adults, are highly infiltrative, and harbor mitogen-activated protein kinase (MAPK) pathway alterations with high rates of CDKN2A/2B deletion, PDGFRA amplification, MYCN amplification, NF1 variants, and BRAF alterations.

The radiogenomic and spatiogenomic landscapes of glioblastoma and their relationship to oncogenic drivers.

Background: Glioblastoma is a highly heterogeneous brain tumor, posing challenges for precision therapies and patient stratification in clinical trials. Understanding how genetic mutations influence tumor imaging may improve patient management and treatment outcomes. This study investigates the relationship between imaging features, spatial patterns of tumor location, and genetic alterations in IDH-wildtype glioblastoma, as well as the likely sequence of mutational events.

cIMPACT-NOW update 9: Recommendations on utilization of genome-wide DNA methylation profiling for central nervous system tumor diagnostics.

Genome-wide DNA methylation signatures correlate with and distinguish central nervous system (CNS) tumor types. Since the publication of the initial CNS tumor DNA methylation classifier in 2018, this platform has been increasingly used as a diagnostic tool for CNS tumors, with multiple studies showing the value and utility of DNA methylation-based classification of CNS tumors. A Consortium to Inform Molecular and Practical Approaches to CNS Tumor Taxonomy (cIMPACT-NOW) Working Group was therefore convened to describe the current state of the field and to provide advice based on lessons learned to date.

Brain-wide neuronal circuit connectome of human glioblastoma.

Glioblastoma (GBM) infiltrates the brain and can be synaptically innervated by neurons, which drives tumour progression. Synaptic inputs onto GBM cells identified so far are largely short range and glutamatergic. The extent of GBM integration into the brain-wide neuronal circuitry remains unclear.

Machine learning-based prognostic subgrouping of glioblastoma: A multicenter study.

Background: Glioblastoma (GBM) is the most aggressive adult primary brain cancer, characterized by significant heterogeneity, posing challenges for patient management, treatment planning, and clinical trial stratification.

Methods: We developed a highly reproducible, personalized prognostication, and clinical subgrouping system using machine learning (ML) on routine clinical data, magnetic resonance imaging (MRI), and molecular measures from 2838 demographically diverse patients across 22 institutions and 3 continents. Patients were stratified into favorable, intermediate, and poor prognostic subgroups (I, II, and III) using Kaplan-Meier analysis (Cox proportional model and hazard ratios [HR]).

Patient-derived glioblastoma organoids as real-time avatars for assessing responses to clinical CAR-T cell therapy.

Patient-derived tumor organoids have been leveraged for disease modeling and preclinical studies but rarely applied in real time to aid with interpretation of patient treatment responses in clinics. We recently demonstrated early efficacy signals in a first-in-human, phase 1 study of dual-targeting chimeric antigen receptor (CAR)-T cells (EGFR-IL13Rα2 CAR-T cells) in patients with recurrent glioblastoma. Here, we analyzed six sets of patient-derived glioblastoma organoids (GBOs) treated concurrently with the same autologous CAR-T cell products as patients in our phase 1 study.

Optimized Whole-Slide-Image H&E Stain Normalization: A Step Towards Big Data Integration in Digital Pathology.

In the medical diagnostics domain, pathology and histology are pivotal for the precise identification of diseases. Digital histopathology, enhanced by automation, facilitates the efficient analysis of massive amount of biopsy images produced on a daily basis, streamlining the evaluation process. This study focuses in Stain Color Normalization (SCN) within a Whole-Slide Image (WSI) cohort, aiming to reduce batch biases.

Distinction of pseudoprogression from true progression in glioblastomas using machine learning based on multiparametric magnetic resonance imaging and O-methylguanine-methyltransferase promoter methylation status.

Background: It is imperative to differentiate true progression (TP) from pseudoprogression (PsP) in glioblastomas (GBMs). We sought to investigate the potential of physiologically sensitive quantitative parameters derived from diffusion and perfusion magnetic resonance imaging (MRI), and molecular signature combined with machine learning in distinguishing TP from PsP in GBMs in the present study.

Methods: GBM patients ( = 93) exhibiting contrast-enhancing lesions within 6 months after completion of standard treatment underwent 3T MRI.

Prognostic stratification of glioblastoma patients by unsupervised clustering of morphology patterns on whole slide images furthering our disease understanding.

Introduction: Glioblastoma (GBM) is a highly aggressive malignant tumor of the central nervous system that displays varying molecular and morphological profiles, leading to challenging prognostic assessments. Stratifying GBM patients according to overall survival (OS) from H&E-stained whole slide images (WSI) using advanced computational methods is challenging, but with direct clinical implications.

Methods: This work is focusing on GBM (IDH-wildtype, CNS WHO Gr.