# MRI Reflects Meningioma Biology and Molecular Risk

## TL;DR

This study explores how MRI scans can non-invasively predict meningioma molecular risk and chromosomal changes, offering potential decision support before surgery.

## Contribution

It demonstrates that MRI radiomic features can predict molecular risk and 1p loss with high accuracy, but not WHO grade, suggesting a role as a pre-surgical decision-support tool.

## Key findings

- MRI radiomic features predicted molecular risk with 91% accuracy.
- 1p chromosomal loss was identified with 87.5% accuracy using MRI data.
- WHO grade prediction had lower accuracy (76.8%) compared to molecular features.

## Abstract

Meningiomas are the most common primary brain tumors. Molecular testing has become crucial for estimating tumor behavior, but such testing requires tissue and specialized laboratories. This study examines whether information from routine magnetic resonance imaging can indicate key molecular features non-invasively before surgery. Using computer-assisted analysis of tumor shape and texture on preoperative scans, the models differentiated lower from higher molecular risk and identified loss of chromosome 1p with high accuracy, with limited accuracy in distinguishing high-grade meningiomas for the current WHO classification. Therefore, it is not yet ready for clinical use, complementing but not replacing pathology. By offering valuable insights into tumor biology, it may function as an early decision-support tool, supporting counseling and prioritization of confirmatory testing. Prospective studies are needed to validate these results for clinical implementation.

Background/Objectives: Large-scale (epi)genomic studies have substantially advanced our understanding of the molecular landscape of meningiomas, most recently embedded in the cIMPACT-NOW update 8. As a result, molecular data are increasingly integrated into risk-adapted treatment algorithms. However, it remains uncertain to what extent non-invasive MRI can capture underlying molecular variation and risk. Methods: We assembled a large, single-institution cohort of 225 newly diagnosed meningiomas (WHO grades 1–3) with available preoperative MRI, as well as comprehensive epigenome-wide methylation and copy-number profiling. Tumors were segmented into core and edema regions using a state-of-the-art automated pipeline from the BraTS challenge. Radiomic features were extracted and used to train Random Forest classifiers to predict WHO grade, molecular risk, and specific alterations such as 1p loss in a hold-out test set. Results: Our models achieved accuracy above 91% for integrated molecular risk classification, 87.5% for 1p chromosomal status, and 76.8% for WHO grade prediction, with corresponding AUCs of 0.91, 0.90, and 0.89, underscoring the robustness of radiomic features in capturing histopathological and, especially, molecular characteristics. Conclusions: Preoperative MRI effectively captures the underlying molecular biology of meningiomas and may enable rapid molecular assessment to inform decision-making and prioritization of confirmatory testing. However, it is not yet ready for clinical use, showing lower accuracy for current WHO grade classification.