EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing

TL;DR

This paper introduces EchoNet-Synthetic, a diffusion model-based method for generating high-fidelity, privacy-preserving echocardiogram videos, enabling safe data sharing for medical research without compromising patient privacy.

Contribution

The paper presents a novel diffusion model approach for de-identifying medical videos, producing realistic synthetic datasets with preserved clinical features and supporting downstream tasks.

Findings

Synthetic dataset achieves comparable fidelity to real data.

Supports accurate ejection fraction regression.

Enables privacy-preserving medical data sharing.

Abstract

To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced constraints in terms of fidelity, spatio-temporal coherence, and the length of generation, failing to capture the complete details of dataset distributions. We present a model designed to produce high-fidelity, long and complete data samples with near-real-time efficiency and explore our approach on a challenging task: generating echocardiogram videos. We develop our generation method based on diffusion models and introduce a protocol for medical video dataset anonymization. As an exemplar, we present EchoNet-Synthetic, a fully synthetic, privacy-compliant echocardiogram dataset with paired ejection fraction labels. As part of our de-identification protocol, we evaluate the quality of the generated dataset and propose to use clinical downstream tasks as a measurement on top of widely used but potentially biased image quality metrics. Experimental outcomes demonstrate that EchoNet-Synthetic achieves comparable dataset fidelity to the actual dataset, effectively supporting the ejection fraction regression task. Code, weights and dataset are available at https://github.com/HReynaud/EchoNet-Synthetic.