Challenges and Strategies for Deep Learning in Cardiovascular Imaging
Both training data and generalization aspects challenge the performance of DL algorithms for automated cardiac measurements. In addition, evaluation metrics challenge the ability to detect underperforming algorithms. By considering evaluation metrics and training data distribution, and incorporating imaging domain knowledge, the design and evaluation of DL models can be improved, leading to more robust models, improved interpretation, and easier comparison across data sets. These findings may guide researchers and clinicians in implementing DL models for cardiovascular imaging.
Authors
- Eirik Skogvoll (ORCID: https://orcid.org/0000-0002-6984-0708)
- Andreas Østvik (ORCID: https://orcid.org/0000-0003-3895-2683)
- Håvard Dalen (ORCID: https://orcid.org/0000-0003-1192-3663)
- Lasse Løvstakken (ORCID: https://orcid.org/0000-0003-2474-9588)
- David Pasdeloup (ORCID: https://orcid.org/0000-0002-0160-1268)
- Sindre Hellum Olaisen (ORCID: https://orcid.org/0009-0005-7931-4145)
Institutions
- SINTEF (NO)
- Norwegian University of Science and Technology (NO)
- Levanger Hospital (NO)
- St Olav's University Hospital (NO)
Publication Details
- Journal
- JACC. Cardiovascular imaging
- Published
- 2025-07-01
- DOI
- https://doi.org/10.1016/j.jcmg.2025.02.011
- Citations
- 2
- Primary Topic
- Cardiac Imaging and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 2.72
Funders
- Norges Forskningsråd