Yefet, Leeor

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 DNA methylation profiling can be used to robustly predict postsurgical outcomes and response to radiotherapy (RT) for meningioma patients. To allow for seamless integration of these complementary models into clinical practice, a practical framework is needed. Methods We leveraged a cohort of nearly 2000 surgically-treated meningiomas with DNA methylation profiling and clinical outcomes data. Existing methylation-based prediction models were dichotomized to yield four risk groups: low and high recurrent risk, each with RT sensitive and resistant subgroups. Risk groups were correlated with progression-free survival in the context of existing biomarkers including extent of resection and WHO grade. Results We first demonstrated that all risk groups benefit from gross total resection. All “high-risk, RT sensitive” tumors (n = 306, 15.7%) also benefited from adjuvant RT: after GTR, median PFS increased from 4.68 (4.13-9.48) years to not reached (P = .003); after subtotal resection (STR), from 2.12 (1.59-3.02) to 4.09 (3.41-not reached) years (P = .004). “Low-risk, RT sensitive cases” (n = 1207, 61.8%) also benefited from RT after STR (median PFS 7.39 (6.66-12.8) vs. 16.53 (10.35-not reached) years, P = .03), suggesting that RT be considered in these patients. Neither “low-risk RT resistant” (n = 84, 4.3%) nor “high-risk RT resistant” (n = 356, 18.2%) cases benefited from RT, and the latter group was associated with universally poor outcomes. Conclusions We identify methylation-defined risk groups of meningioma for which additional benefit is gained from adjuvant RT, leading to a clinical decision-making framework for straightforward integration of molecular models into clinical practice.

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 Background Adolescent and young adult (AYA) patients remain underrepresented in neuro-oncology research. Despite being the second most common primary brain tumor in this population, meningiomas have not been studied using age-specific molecular analyses. DNA methylation-based classification and prognostic tools have transformed meningioma care. This study aimed to evaluate the performance of these tools across age groups. Methods We analyzed 1,568 meningiomas with DNA methylation and clinical data, including 18 pediatric patients (<15 years), 195 AYA patients (15-39 years), and 1,355 adult patients (>39 years). Pediatric and AYA (P/AYA) tumors were combined and compared with adult tumors. The performance of established molecular classifiers and recurrence predictors, as well as differences in chromosomal copy number alterations were compared across age groups. Results While histologic grading was comparable between cohorts, P/AYA tumors displayed significantly fewer aggressive molecular groups and lower frequencies of chromosomal arm losses, including 1p, 6q, and 14q. The adult-trained recurrence predictor failed in the P/AYA population (AUC 0.57), despite similar score distributions. Retraining the model on an age-specific cohort using an identical analytic framework improved performance (AUC 0.79) and enabled effective stratification of progression-free survival (P = 0.00054). Importantly, 1p loss retained prognostic significance within the P/AYA group, supporting its clinical utility. Conclusions Molecular tools developed in adult-dominant cohorts do not generalize to younger patients due to both biological divergence and exclusion from model development. These findings underscore the need for age-specific molecular frameworks and highlight the imperative of including P/AYA populations in precision neuro-oncology research to ensure lifespan-equitable care.