Aldape, Kenneth

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 INTRODUCTION Brain metastases (BM) are the most common intracranial tumor, with a poor prognosis of 10-16 months, and lung adenocarcinoma (LUAD) is the most common source. Currently, we cannot reliably predict which patients will develop BMs clinically, so most are detected after they develop and growing to cause deficits. Here, we use tumor DNA methylomes to predict which patients are likely to develop BM through the course of disease and we use both cerebrospinal fluid (CSF) and plasma methylomes for BM liquid biopsy, enabling their early detection and treatment. METHODS DNA methylomes were acquired from 419 tumor and plasma samples from 363 LUAD and BM patients. We built DNA methylation-based models that predict BM development and that also identify BMs non-invasively from CSF and plasma in discovery data subsets. A nomogram was built that predicts BM risk using methylation scores and clinical stage together. Models were evaluated in independent validation sets. RESULTS Our model predicting BM development was accurate (Univariable Cox: HR=5.7, 95% CI=1.9-17.2), p=0.0023), independent of clinical factors (Multivariable Cox: HR=8.9, 95% CI=2.0-40.5, p=0.0046), and more predictive than cancer staging used currently clinically (AUC=0.81 versus 0.65). Our combinatorial nomogram using methylation and staging data together showed enhanced BM prediction (Univariable Cox: HR=17.2, 95% CI=4.1-71.3, p<0.0001; AUROC=0.82). Our models identifying BM through biofluid methylomes accurately distinguished BM from differential diagnoses of gliomas and lymphomas in plasma (AUROC=0.80, 95% CI=0.68-0.93) and with greater accuracy in CSF (AUROC=0.93, 95% CI=0.71-1.0). CONCLUSION Overall, we show the first approaches for robust molecular prediction of BM development and for reliable liquid biopsy of BM. This work is expected to transform cancer management by identifying high-risk lung cancer patients after initial treatment for inclusion in screening protocols using neuroimaging and liquid biopsy, to identify BM development early with less advanced disease and more optimal therapeutic outcomes.

Abstract Meningiomas are the most common primary intracranial tumors and exhibit clinical heterogeneity. Radiotherapy (RT) remains the only adjuvant therapy, but response is variable and biomarkers are limited. RTOG-0539 is the first prospective phase 2 trial to stratify meningioma patients for adjuvant RT based on clinical risk. Here, we apply modern molecular tools to this cohort and uncover correlates of RT response. To do so, tumor tissue from 100 RTOG-0539 patients was profiled using DNA methylation arrays, RNA sequencing, and whole-exome sequencing. Recurrence scores, Molecular Groups, gene expression, and copy number alterations were compared across clinical groups and between RT responders and non-responders. Using this approach, modern grading criteria, including brain invasion, TERT mutation, CDKN2A/B deletion and 1p/1q status, would reclassify 10% of tumors and alter treatment group assignment in 7%. Notably, non-responders to RT had more frequent 1p and 14q loss, and greater copy number burden. In addition, transcriptomic and epigenetic profiling revealed immune-related signatures in RT responders and upregulation of cell cycle–related pathways in RT non-responders, several of which overlapped with targets of vorinostat, a histone deacetylase inhibitor validated in aggressive meningioma models. Of particular importance, the Proliferative Molecular Group was an independent predictor of post-RT recurrence in multivariable analysis, outperforming WHO grade. In conclusion, multi-omic analysis of the RTOG-0539 cohort shows that updated WHO grading criteria, incorporating molecular and cytogenetic features, improve risk stratification. However, molecular classification, particularly the Proliferative group, remains an independent and stronger predictor of RT response. These findings support integrating molecular biomarkers alongside modern grading frameworks to guide treatment and trial design in meningioma.

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.

Unlike medulloblastoma (MB) in children, robust prospective trials have not taken place for older patients due to the low incidence of MB in adults and adolescent and young adults (AYA). Current MB treatment paradigms for older patients have been extrapolated from the pediatric experience even though questions exist about the applicability of these approaches. Clinical and molecular classification of MB now provides better prognostication and is being incorporated in pediatric therapeutic trials. It has been established that genomic alterations leading to activation of the sonic hedgehog (SHH) pathway occur in approximately 60% of MB in patients over the age of 16 years. Within this cohort, protein patched homolog (PTCH) and smoothened (SMO) mutations are commonly found. Among patients whose tumors harbor the SHH molecular signature, it is estimated that over 80% of patients could respond to SHH pathway inhibitors. Given the advances in the understanding of molecular subgroups and the lack of robust clinical data for adult/AYA MB, the Alliance for Clinical Trial in Oncology group developed the AMBUSH trial: Comprehensive Management of AYA and Adult Patients with Medulloblastoma or Pineal Embryonal Tumors with a Randomized Placebo Controlled Phase II Focusing on Sonic Hedgehog Pathway Inhibition in SHH Subgroup Patients (Adult & Adolescent MedulloBlastoma Using Sonic Hedgehog Trial). This trial will enroll patients 18 years of age or older with MB (any molecular subgroup and risk stratification) or pineal embryonal tumor. Patients will be assigned to one of three cohorts: (1) average risk non-SHH-MB, (2) average risk SHH-MB, and (3) high risk MB or pineal embryonal tumors. All patients will receive protocol-directed comprehensive treatment with radiation therapy and chemotherapy. Patients with SHH-MB in cohort 1 will be randomized to a smoothened inhibitor or placebo as maintenance therapy for one year.

Abstract BACKGROUND With increasing studies reporting on the molecular profiling of meningiomas, there is a need to harmonize language used to capture clinical data across centers to ensure that molecular alterations are appropriately linked to clinical variables of interest. Here the International Consortium on Meningiomas presents a final set of core and supplemental meningioma-specific Common Data Elements (CDEs) to facilitate comparative and pooled analyses. METHODS The generation of CDEs followed the four-phase process similar to other National Institute of Neurological Disorders and Stroke (NINDS) CDE projects: development/discovery based on data from published and ongoing meningioma trials, internal validation, external validation including presentation of our data form at the Society for Neuro-Oncology previously, and distribution. RESULTS We developed a set of CDEs organized into patient- and tumor-level modules. In total, the Consortium identified 16 core CDEs (9 patient-level and 7-tumour-level) e.g. age at index surgery, diagnosis of neurofibromatosis, prior chemotherapy or radiation, tumor location, extent of resection, recurrence, etc. An additional 15 supplemental CDEs were defined and described (8 patient-level and 7 tumour-level) e.g. race, cause of death, multiple tumors, tumor size, Simpson grade, second intervention, etc. These CDES are now made publicly available for dissemination and adoption. We also present a narrative review and analysis of recent and ongoing meningioma trials. CONCLUSIONS These CDEs provide a framework for discussion in the neuro-oncology community that will facilitating data sharing for collaborative research projects and aid in developing a common language for comparative and pooled analyses. The CDEs are intended to be dynamic parameters that evolve with time and The Consortium welcomes international feedback for further refinement and implementation of these CDEs.