Skip to main content
Neuro-Oncology Advances logoLink to Neuro-Oncology Advances
. 2025 Aug 31;7(Suppl 3):iii8. doi: 10.1093/noajnl/vdaf166.033

34 RISK STRATIFICATION USING DEEP FEATURES IN IDH-MUTANT GLIOMAS

K Rich 1,✉, K Chornenka Martin 2, H Farahani 3, C Ma 4, S Yip 5, A Bashashati 6
PMCID: PMC12398763

Abstract

BACKGROUND

The current diagnostic framework for IDH-mutant gliomas relies on molecular biomarkers, the most important of which being driver mutations in IDH1/2 and whole arm codeletion in chromosomes 1p and 19q. Despite these molecular indicators, a subset of patients with favourable prognosis still have poor outcomes. In this work, we explore whether morphological features, extracted using pathology foundation models, can be used to stratify IDH-mutant cases into high and low-risk cases.

DESIGN

Our dataset consisted of 886 IDH-mutant glioma cases from the The Cancer Genome Atlas Low Grade Glioma and Glioblastoma (TCGA-LGGGBM) studies, as well as two external validation sets of 145 patients (VIENNA) and 82 patients (VGH). We trained a self-supervised feature extractor on 256x256 pixel patches extracted at 20x magnification. These features were then used to train a multiple-instance learning model for survival prediction.

RESULTS

We achieved a c-index of 0.77 on the TCGA-LGG test dataset, and 0.63/0.65 on the two external datasets. Further analysis found that these risk scores can be used to identify two distinct risk groups, agnostic of the current diagnostic framework, that exhibit inherent morphological and genomic variation.

CONCLUSIONS

Our findings suggest that deep learning-based features can be used to predict outcome, and identify distinct risk groups in gliomas. These findings could lead to further refinement of the current diagnostic categories of IDH-mutant gliomas, and guide more targeted treatments in the future.


Articles from Neuro-Oncology Advances are provided here courtesy of Oxford University Press

RESOURCES