EchoNet-synthetic: privacy-preserving video generation for safe medical data sharing
File(s)
Accepted version
OA Location
Author(s)
Type
Conference Paper
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.
Editor(s)
Linguraru, MG
Dou, Q
Feragen, A
Giannarou, S
Glocker, B
Lekadir, K
Schnabel, JA
Date Issued
2024-10-03
Date Acceptance
2024-10-01
Citation
Lecture Notes in Computer Science, 2024, 15007, pp.285-295
ISBN
978-3-031-72103-8
ISSN
0302-9743
Publisher
Springer International Publishing AG
Start Page
285
End Page
295
Journal / Book Title
Lecture Notes in Computer Science
Volume
15007
Copyright Statement
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Sponsor
Engineering and Physical Sciences Research Council
Grant Number
EP/S023283/1
Source
27th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Dataset Generation
Echocardiography
Life Sciences & Biomedicine
Radiology, Nuclear Medicine & Medical Imaging
Science & Technology
Technology
Video Diffusion
Publication Status
Published
Start Date
2024-10-06
Finish Date
2024-10-10
Coverage Spatial
Marrakesh, Morocco
Date Publish Online
2024-10-03