SASVi: segment any surgical video
SASVi can serve as a new baseline for smooth and temporally consistent segmentation of surgical videos with scarcely available annotation data. Our method allows us to leverage scarce annotations and obtain complete annotations for full videos of the large-scale counterpart datasets. We make those annotations publicly available, providing extensive annotation data for the future development of surgical data science models.
Authors
- Anirban Mukhopadhyay (ORCID: https://orcid.org/0000-0001-8128-3521)
- Amin Ranem (ORCID: https://orcid.org/0000-0003-0783-6903)
- Sanjeev Sivakumar (ORCID: https://orcid.org/0000-0002-4846-4301)
- Yannik Frisch (ORCID: https://orcid.org/0009-0005-8097-0158)
Institutions
- Johannes Gutenberg University Mainz (DE)
- Fraunhofer Institute for Computer Graphics Research (DE)
- Technische Universität Darmstadt (DE)
- Fraunhofer Institute for Secure Information Technology (DE)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2025-05-20
- DOI
- https://doi.org/10.1007/s11548-025-03408-y
- Citations
- 3
- Primary Topic
- Surgical Simulation and Training
- Type
- article
- Field-Weighted Citation Impact
- 6.02
Funders
- Bundesministerium für Bildung und Forschung