Nasrallah, MacLean P.

Abstract A working group of cIMPACT-NOW evaluated the literature on IDH-mutant gliomas for opportunities to improve pathology-based risk stratification and grading, especially at the interface of CNS WHO grades 2 and 3, since therapeutic decisions depend on risk assessment for clinical management. The group also evaluated newly described IDH-mutant glioma subgroups and considered multidisciplinary aspects of therapeutic decision-making. PDGFRA amplification was associated with highly aggressive clinical behavior of IDH-mutant astrocytomas, consistent with CNS WHO grade 4. Other genetic alterations associated with intermediate risk and most consistent with CNS WHO grade 3 included PIK3 mutations; EGFR alteration; MYCN amplification; and specific retinoblastoma pathway alterations, including CDK4, CDK6, and CCND2 amplification, RB1 homozygous deletion or mutation, and mutation of CDKN2A. DNA methylation signatures of G-CIMP-low or A_IDH_HG were consistent with CNS WHO grade 3 or 4, depending upon other grading criteria. We suggest a mitotic count of ≥3 per 2.4 mm2 could be considered as a CNS WHO grade 3 criterion. Our review did not uncover features to improve the grading of oligodendroglioma, IDH-mutant and 1p/19q-codeleted, although CNS WHO grade 3 tumors with elevated mitotic rates, yet lacking necrosis, microvascular proliferation, CDKN2A/B homozygous deletion, and MRI contrast enhancement, may be associated with extended survival. Implementing evidence-based criteria for risk stratification and grading will improve guidance for clinical decision-making.

Abstract Background Approximately 12 000 adolescents and young adults (ages 15-39, AYAs) are diagnosed with a primary central nervous system (CNS) tumor each year. DNA methylation profiling has transformed CNS tumor classification by refining diagnostic accuracy and identifying biologically distinct subtypes, but its application has not been systematically evaluated in the AYA population. In this study, we examined the spectrum of CNS tumor types across age groups, with a focus on the AYA population. Methods We assembled a large dataset of CNS tumor samples with age annotations and methylation profiles matching with high confidence to a CNS tumor type using the NCI/Bethesda classifier. Prevalence of tumor type, methylation class and DNA copy number aberrations were compared across age strata (pediatric, AYA, and adult). Results The cohort of 21 712 CNS tumors included 5351 tumors from AYAs (25%), which showed a mixed pattern, with tumors typical of childhood (eg, medulloblastoma) as well as those common in older adults (eg, glioblastoma). Several tumor types were specifically enriched in the AYA, including IDH-mutant astrocytoma, pleomorphic xanthoastrocytoma, posterior fossa group B ependymoma, and diffuse hemispheric glioma, H3 G34-mutant, among others. Distinct methylation subclasses of multiple tumor types were observed in the AYA, and patterns of genomic aberrations showed age-specific distributions. Conclusion Large-scale methylation profiling revealed unique classification patterns of CNS tumors in AYAs, with specific tumor types, subclasses, and genomic alterations enriched in this population. These data may serve as a valuable reference resource for better understanding the spectrum of CNS tumors affecting AYA patients.

Abstract Background Intracranial mesenchymal tumors, FET::CREB fusion-positive (ICMT), show fusions involving FET RNA-binding protein family genes (EWSR1 or FUS) and CREB family of transcription factors (ATF1, CREB1, or CREM). The methylation signature(s), gene expression characteristics, and clinical behavior of this important tumor type require further characterization. Methods We study the methylation profiles of 81 ICMT cases (61 newly profiled cases and 20 cases from publicly available sources). Clinicopathologic and genomic data were recorded for each case when available. Results ICMT showed a relatively distinct methylation signature compared to related tumors. Among the 65 cases where fusion types were documented, the identified fusions included EWSR1::ATF1 (25 cases), EWSR1::CREB1 (12 cases), EWSR1::CREM (21 cases), FUS::CREM (3 cases), and SMARCA2::CREM (4 cases). We confirmed the prior description of 2 distinct subgroups of ICMT (subclasses A and B). The majority of the cases belonged to subclass A (n = 69; 85%), which showed a higher median age compared to subclass B patients (26 years vs. 15 years). Subclass B cases (n = 12; 15%) showed shorter progression-free survival (P < 0.01). Gene expression analysis of ICMT showed key overexpressed markers in ICMT, with significant CREM overexpression regardless of fusion type, when compared to either meningioma alone or a larger group of CNS tumors. Conclusions This work provides further characterization of ICMT as an important CNS mesenchymal neoplasm that is prone to tumor recurrence, showing 2 prognostically relevant methylation subclasses and warranting diagnostic distinction from other epigenetically and histologically related tumors. ICMTs show substantial overexpression of the CREM gene, independent of fusion type.

Abstract INTRODUCTION Glioblastoma is the most common malignant adult brain tumor with poor prognosis, largely due to its heterogeneous landscape. The AI-RANO and RANO-RGP groups organized the BraTS-Pathology 2024 challenge, providing a publicly-available dataset and a benchmarking environment for AI models to automatically identify six clinically-relevant histopathologic sub-regions in H&E-stained whole slide images (WSIs). METHODS We reclassified the TCGA-GBM and TCGA-LGG data according to the WHO 2021 criteria and identified diagnostic WSIs of 188 glioblastoma (IDH-wt, CNS WHO Gr.4) patients. A well-defined annotation protocol was communicated to eight neuropathologists, across eight institutions, who created “ground truth” annotations for Cellular Tumor (CT), Geographic Necrosis, Cortical Infiltration, Pseudopalisading Necrosis (PN), Microvascular Proliferation, and Penetration into White Matter (PWM). Comprehensive WSI curation for elimination of artifactual content and follow up partitioning resulted in approximately 300,000 data samples/patches. FINDINGS Inter-observer variability assessment highlighted difficulties in establishing a “gold standard”. The least annotated sub-regions (PWM and PN) were the most challenging to the participating methods, whereas all methods achieved their highest accuracy in the most annotated sub-region (CT). The highest average performance across sub-regions was obtained by a foundation model-based method. However, this top-ranked solution achieved an F1 score of 0.51 (Accuracy=0.65, Sensitivity=0.56, Specificity=0.93). CONCLUSIONS Our findings suggest that achieving state-of-the-art performance, in automatically identifying clinically-relevant glioblastoma sub-regions, remains an unsolved research problem. Analysis of the ground-truth annotations underscores the critical need for more precisely defined and neuropathologically standardized annotation protocol. Current AI algorithms are facing difficulties in addressing glioblastoma’s heterogeneous histologic landscape in the absence of large, comprehensively, and consistently annotated data. Building upon these findings, and towards developing more accurate AI algorithms, the 2025 iteration of the BraTS-Path challenge is currently on-going by leveraging two million data samples, aiming to enhance our disease understanding and improve diagnostic accuracy, ultimately contributing to improved patient outcomes.

Abstract Computer vision now enables deep learning models to link histopathologic features to molecular features in a quantitative manner not previously achievable by human pathologists. However, human interpretability is often limited. We trained a deep neural network to predict gene expression from digital whole slide images (WSIs) using 848 central nervous system (CNS) tumors with paired WSI and RNA-sequencing data. We used inferred RNA expression levels as a surrogate for protein expression of the CNS tumor lineage markers GFAP, OLIG2, and SSTR2, as well as the proliferation marker MKI67 (Ki67). We established thresholds for categorizing the inferred expression levels as positive or negative based on levels observed in cross-validation testing in select tumor types to approximate routine clinical interpretation of immunohistochemical (IHC) staining. We tested the sensitivity and specificity of our ‘virtual’ IHC on an independent, multi-institutional cohort of over 2,000 CNS tumors with objective diagnostic labels derived from DNA methylation-based tumor classification. As a dichotomous variable, inferred GFAP expression showed a sensitivity of 74% and a specificity of 99% as a glial marker in a cohort of gliomas and meningiomas. In the same cohort, OLIG2 showed a sensitivity of 75% and a specificity of 97% as a glial marker, while SSTR2 showed a sensitivity of 83% and a specificity of 97% as a marker of meningioma. In a cohort of ependymomas and gliomas, virtual IHC for OLIG2 showed a sensitivity of 75% and a specificity of 82% in distinguishing ependymomas from gliomas. Finally, in a cohort of gliomas, inferred expression of MKI67 demonstrated a trend consistent with what would be expected by actual IHC, with increasing MKI67 expression with increasing tumor grade. Our model provides the basis for a human interpretable and clinically applicable deep neural network to aid human pathologists in the diagnosis and grading of CNS tumors.

Abstract Molecular testing has become critical components in the diagnostic classification of the central nervous system (CNS) tumors. However, these methods require substantial resources, limiting accessibility for many patients. Recent advances in artificial intelligence (AI) and computer vision empower deep learning models to infer molecular features from histopathology images, which may often be more readily available than molecular testing, to classify CNS tumors. We trained pan-CNS tumor models to predict DNA methylation and gene expression from whole-slide images (WSIs). These molecular predictions were then used in a hierarchical machine learning framework, termed Neuropath-AI, to predict nine broad tumor families and 52 tumor types using a large diverse cohort of 5,715 histopathology samples, of which 2,988 had paired DNA methylation profiling and 848 had paired RNA-sequencing. We evaluated Neuropath-AI on another large independent multi-institutional cohort of 5,516 CNS tumors, for which Neuropath-AI predicted tumor class with an associated confidence score. Neuropath-AI designated 46% of test samples as predictable with high-confidence, which it then accuracy classified in 97% of samples. It made moderate-confidence (and above) predictions for 87% of test samples, for which it achieved a diagnostic accuracy of 80% for the top-1 prediction and 86% accuracy for a top-2 predictions. A comparison with human neuropathologists showed that Neuropath-AI is comparable at classifying tumors. A second test showed that human neuropathologists were more accurate when the Neuropath-AI classifier results were provided to them, testifying to the potential translational benefit of integrating AI classification tools into the pathologist’s workflow. Our model provides the basis for a clinically applicable deep learning assistant to improve human efficiency and accuracy of CNS tumor diagnosis. The model will be made publicly available and can be readily implemented to assist human pathologists in clinical workflows, in further expanded prospective studies.

Abstract 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. Here, we provide recommendations for the use of DNA methylation-based classification in CNS tumor diagnostics, emphasizing the attributes and limitations of the modality. We emphasize that the methylation classifier is one diagnostic tool to be used alongside previously established diagnostic tools in a fully integrated fashion. In addition, we provide examples of the inclusion of DNA methylation data within the layered diagnostic reporting format endorsed by the World Health Organization (WHO) and the International Collaboration on Cancer Reporting. We emphasize the need for backward compatibility of future platforms to enable accumulated data to be compatible with new versions of the array. Finally, we outline the specific connections between methylation classes and CNS WHO tumor types to aid in the interpretation of classifier results. It is hoped that this update will assist the neuro-oncology community in the interpretation of DNA methylation classifier results to facilitate the accurate diagnosis of CNS tumors and thereby help guide patient management.

Abstract Glioblastoma, the most common malignant primary adult brain tumor, poses significant diagnostic and treatment challenges due to its heterogeneous molecular and micro-environmental profiles. To this end, we organize the BraTS-Path challenge to provide a public benchmarking environment and a comprehensive dataset to develop and validate AI models for identifying distinct histopathologic glioblastoma sub-regions in H&E-stained digitized tissue sections. We identified 188 multi-institutional diagnostic slides of glioblastoma (IDH-wt, Gr.4) cases, from the TCGA-GBM and TCGA-LGG data collections, following their reclassification according to the 2021 WHO classification criteria. Sub-regions were selected according to distinctive morphology of histopathologic features and included aggressive tumor biology and areas consistent with potential treatment effect. Selected sub-region annotations included cellular tumor, geographic necrosis, cortical infiltration, pseudopalisading necrosis, microvascular proliferation, white matter penetration, regions dense with macrophages, leptomeningeal infiltration, and presence of lymphocytes. We obtained 107,340 patches of size 512x512 from the 9 sub-regions. A global network of board-certified expert neuropathologists defined and followed a systematic annotation protocol based on clinical definitions and only delineated sub-regions with high confidence, thus ensuring high-quality standardized data. Each tissue section was assigned to an annotator-approver pair, with the annotator delineating sub-regions and the approver ensuring the consistency of the annotations. By crowdsourcing annotations, the BraTS-Path challenge harnesses the collective expertise of clinical neuropathologists and fosters a collaborative environment to advance the neuro-oncology field. The anticipated developed algorithms are expected to integrate state-of-the-art computational methods, achieving high accuracy in identifying diverse histopathologic features and advancing clinical decision-making processes. The BraTS-Path challenge aims to bridge the gap between research and clinical practice by promoting the development of AI-driven tools for precise tumor characterization. This collaborative effort can significantly enhance our understanding of glioblastoma, improve diagnostic accuracy, and inform treatment strategies, thereby contributing to better patient outcomes.

Abstract Methylation profiling of brain tumors has revealed novel clusters whose biological and clinical significance is unknown. These include three entities termed by the 12.5 version of the Heidelberg methylation classifier as adult-type diffuse high grade glioma, IDH-wildtype, subtype B (HGG_B), subtype E (HGG_E), and subtype F (HGG_F). We have identified 75 cases belonging to these groups: HGG_B (25 cases, 32% female), HGG_E (40 cases, 42% female), and HGG_F (18 cases, 33% female). Although originally characterized as “adult-type,” we find that 70% of HGG_E cases are pediatric, with a median age at diagnosis of 11 years. HGG_B cases are predominantly seen in young adults, and HGG_F in older adults. The histology varies among methylation classes, with HGG_B cases demonstrating high-grade, predominantly astrocytic, morphology, while HGG_E cases demonstrate high-grade glial histology with distinct nuclear features, and HGG_F cases show highly infiltrative but lower grade glial morphology. Patient outcome data obtained to date shows a collective median survival exceeding 5 years, suggesting re-consideration of the proposed grading for these tumors. MGMT promoter methylation differs across the HGG_B (0%), HGG_E (12%), and HGG_F (0%) subtypes. Mutational analyses show enrichment of TERT promoter mutations in the HGG_F group, while HGG_E samples are enriched for tumors with POLE mutations and elevated tumor mutation burden. HGG_E tumors show epigenetic similarity to pediatric high-grade diffuse gliomas (pedHGG_RTK1A); we therefore propose that HGG_E be considered a pediatric-type HGG. HGG_B tumors show demographic and genomic similarities to high-grade astrocytomas with piloid features, including a subset of cases with CDKN2A/2B loss and ATRX mutation. HGG_F separate into two groups dictated by brain location, and despite the presence of TERT promoter mutations, appear distinct from GBMs. Overall, our work represents an initial effort to understand the morphologic, genomic and clinical characteristics of these previously uncharacterized subtypes of gliomas.