Incremental 2D self-labelling for effective 3D medical volume segmentation with minimal annotations
Our framework demonstrates that a computationally efficient 2D model can be leveraged through self-labelling to achieve robust 3D segmentation performance and coherence from extremely sparse annotations, offering a viable solution to reduce the annotation burden in medical imaging.
Authors
- Matthew Anderson (ORCID: https://orcid.org/0000-0001-8884-3448)
- David Steel (ORCID: https://orcid.org/0000-0001-8734-3089)
- Bogusław Obara (ORCID: https://orcid.org/0000-0003-4084-7778)
- Maged Habib
Institutions
- Sunderland Eye Infirmary (GB)
- Newcastle University (GB)
Publication Details
- Journal
- BMC Medical Imaging
- Published
- 2025-11-07
- DOI
- https://doi.org/10.1186/s12880-025-01991-9
- Primary Topic
- 3D Shape Modeling and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bayer
- Engineering and Physical Sciences Research Council