Federated Voxel Scene Graph for Intracranial Hemorrhage

TL;DR

This paper introduces a federated scene graph generation approach for intracranial hemorrhage analysis, improving relation recall across diverse datasets while respecting privacy constraints.

Contribution

It is the first to apply federated scene graph generation in medical imaging, enhancing relation modeling without sharing sensitive data.

Findings

Models recall up to 20% more clinically relevant relations.

Federated training increases data diversity and model robustness.

Structured data representation benefits across multiple clinical datasets.

Abstract

Intracranial Hemorrhage is a potentially lethal condition whose manifestation is vastly diverse and shifts across clinical centers worldwide. Deep-learning-based solutions are starting to model complex relations between brain structures, but still struggle to generalize. While gathering more diverse data is the most natural approach, privacy regulations often limit the sharing of medical data. We propose the first application of Federated Scene Graph Generation. We show that our models can leverage the increased training data diversity. For Scene Graph Generation, they can recall up to 20% more clinically relevant relations across datasets compared to models trained on a single centralized dataset. Learning structured data representation in a federated setting can open the way to the development of new methods that can leverage this finer information to regularize across clients more effectively.