Federated Voxel Scene Graph for Intracranial Hemorrhage
This addresses the challenge of improving diagnostic accuracy for intracranial hemorrhage across diverse clinical centers while maintaining patient privacy, representing an incremental advance in federated learning for medical imaging.
The paper tackles the problem of limited generalization in deep learning models for intracranial hemorrhage diagnosis due to privacy restrictions on medical data sharing, by proposing the first application of Federated Scene Graph Generation, which recalls up to 20% more clinically relevant relations across datasets compared to centralized training.
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.