# Anatomical phenotyping and staging of brain arteriovenous malformations

## TL;DR

This study introduces a new method to analyze brain AVMs by combining anatomical features and developmental patterns to improve risk prediction and treatment planning.

## Contribution

The paper proposes a multidimensional framework integrating anatomical phenotyping and ontogenetic mapping to create a biologically informed staging system for AVMs.

## Key findings

- Unsupervised analysis identified six biologically plausible meta-topologies in a pilot dataset of 416 patients.
- The approach supports the feasibility of using meta-topologies for AVM risk stratification.
- The study aims to expand to 1000 patients to improve the robustness and clinical utility of the framework.

## Abstract

Brain arteriovenous malformations (AVMs) are potentially life-threatening vascular anomalies that pose significant clinical challenges due to their heterogeneous anatomy and unpredictable natural history. Existing risk stratification models largely rely on isolated imaging markers and fail to account for the dynamic spatial–temporal complexity of AVMs. Building on our prior work, demonstrating how ontogenesis dictates clinical outcomes of neuroepithelial tumours, we hypothesize that AVMs are similarly influenced by developmental processes that define their spatial distribution, vascular architecture and susceptibility to complications. Here, we present the protocol and pilot data of our multicentre, retrospective and prospective observational study, which introduces a multidimensional approach integrating precise anatomical phenotyping with ontogenetic mapping and the analysis of dynamic structural changes over time. By leveraging unsupervised non-negative matrix factorization, we identified six biologically plausible meta-topologies in our single-centre pilot dataset of 416 patients, supporting the feasibility of this approach. We now seek to expand the study into a multicentre effort with both retrospective and prospective enrollment, aiming for a total sample size of ∼1000 patients. This expansion is essential to enhance the granularity, reproducibility and clinical utility of the meta-topologies. Ultimately, the objective of this integrative framework is to facilitate the development of a robust biologically informed risk-stratifying staging system, enhancing personalized treatment strategies and optimizing patient outcomes.

Beyersdorf et al. present the protocol and pilot data of a multicentre observational study that integrates precise anatomical phenotyping and dynamic structural features with ontogenetic mapping and the identification of higher-order meta-topologies, to develop a biologically informed staging system for risk stratification and personalized treatment guidance in brain arteriovenous malformations.

Graphical Abstract