Echo-ODE: A dynamics modeling network with neural ODE for temporally consistent segmentation of video echocardiograms
Echo-ODE addresses the critical need for temporal coherence in clinical video analysis. This framework establishes a versatile backbone extendable beyond segmentation tasks. Its ability to model cardiac dynamics demonstrates great potential for enabling reliable, fully automated video echocardiogram interpretation. The code is publicly available at https://github.com/luwenlianglu/EchoODE.
Authors
- Hao Xu (ORCID: https://orcid.org/0000-0001-9847-7904)
- Wenliang Lu (ORCID: https://orcid.org/0000-0002-4761-6772)
- Yuan Wang (ORCID: https://orcid.org/0000-0001-5589-4556)
- Dexing Kong (ORCID: https://orcid.org/0000-0001-9339-8086)
- Wenli Dai
- Yingnan Wu (ORCID: https://orcid.org/0000-0003-4349-9879)
Institutions
- Zhejiang Sci-Tech University (CN)
- Zhejiang Normal University (CN)
- Puyang Vocational and Technical College (CN)
- Hangzhou Medical College (CN)
- Zhejiang University (CN)
Publication Details
- Journal
- Frontiers in Physiology
- Published
- 2025-08-18
- DOI
- https://doi.org/10.3389/fphys.2025.1629121
- Primary Topic
- Cardiovascular Health and Disease Prevention
- Type
- article
- Field-Weighted Citation Impact
- 0.00