Towards a cardiovascular magnetic resonance foundation model for multi-task cardiac image analysis
Vision FM specialized for medical imaging can improve accuracy and robustness over NI-FM. Self-supervised pretraining offers a resource-efficient, unified framework for CMR assessment, with the potential to accelerate the development of deep learning-based solutions for image analysis tasks, even with few annotated data available.
Authors
- Daniel Rueckert (ORCID: https://orcid.org/0000-0002-5683-5889)
- Indraneel Borgohain
- Dorin Comaniciu (ORCID: https://orcid.org/0000-0002-5238-8647)
- Teodora Chițiboi (ORCID: https://orcid.org/0000-0001-5106-1549)
- Athira Jacob (ORCID: https://orcid.org/0000-0002-5948-3655)
- Puneet Sharma (ORCID: https://orcid.org/0000-0002-4295-1379)
Institutions
- Siemens (Germany) (DE)
- Siemens (United States) (US)
- Siemens Healthcare (United States) (US)
- Siemens Healthineers (Germany) (DE)
- Imperial College London (GB)
- Technical University of Munich (DE)
Publication Details
- Journal
- Journal of Cardiovascular Magnetic Resonance
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.jocmr.2025.101967
- Citations
- 1
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.36