FedEFM: Federated Endovascular Foundation Model with Unseen Data

TL;DR

This paper introduces FedEFM, a federated learning approach for training foundation models in endovascular surgery, addressing privacy concerns and unseen data challenges to improve segmentation of catheters and guidewires in X-ray images.

Contribution

It proposes a novel federated learning framework with differentiable Earth Mover's Distance for unseen data handling, advancing foundation models in medical imaging without compromising patient privacy.

Findings

Achieves state-of-the-art segmentation accuracy

Enhances model initialization for downstream tasks

Addresses data privacy in medical model training

Abstract

In endovascular surgery, the precise identification of catheters and guidewires in X-ray images is essential for reducing intervention risks. However, accurately segmenting catheter and guidewire structures is challenging due to the limited availability of labeled data. Foundation models offer a promising solution by enabling the collection of similar domain data to train models whose weights can be fine-tuned for downstream tasks. Nonetheless, large-scale data collection for training is constrained by the necessity of maintaining patient privacy. This paper proposes a new method to train a foundation model in a decentralized federated learning setting for endovascular intervention. To ensure the feasibility of the training, we tackle the unseen data issue using differentiable Earth Mover's Distance within a knowledge distillation framework. Once trained, our foundation model's weights provide valuable initialization for downstream tasks, thereby enhancing task-specific performance. Intensive experiments show that our approach achieves new state-of-the-art results, contributing to advancements in endovascular intervention and robotic-assisted endovascular surgery, while addressing the critical issue of data sharing in the medical domain.