Fed-Sim: Federated Simulation for Medical Imaging

TL;DR

Fed-Sim introduces a physics-driven, federated learning framework for medical imaging that synthesizes realistic 3D cardiac CT data across multiple centers, enhancing segmentation accuracy and addressing data scarcity and heterogeneity.

Contribution

The paper presents a novel federated simulation framework with disentangled geometry and sensor models for improved medical image synthesis across centers.

Findings

Enhanced segmentation performance on multiple datasets.

Effective training across diverse medical centers.

Addresses data scarcity and heterogeneity issues.

Abstract

Labelling data is expensive and time consuming especially for domains such as medical imaging that contain volumetric imaging data and require expert knowledge. Exploiting a larger pool of labeled data available across multiple centers, such as in federated learning, has also seen limited success since current deep learning approaches do not generalize well to images acquired with scanners from different manufacturers. We aim to address these problems in a common, learning-based image simulation framework which we refer to as Federated Simulation. We introduce a physics-driven generative approach that consists of two learnable neural modules: 1) a module that synthesizes 3D cardiac shapes along with their materials, and 2) a CT simulator that renders these into realistic 3D CT Volumes, with annotations. Since the model of geometry and material is disentangled from the imaging sensor, it can effectively be trained across multiple medical centers. We show that our data synthesis framework improves the downstream segmentation performance on several datasets. Project Page: https://nv-tlabs.github.io/fed-sim/ .