End-to-end deep-learning model for the detection of coronary artery stenosis on coronary CT images
Our end-to-end deep-learning model demonstrates, for the LAD artery, excellent discriminatory ability and calibration during internal validation, despite a small dataset used to train the network. The model reliably produces precise, highly interpretable images.
Authors
- Aidin Rawshani (ORCID: https://orcid.org/0000-0002-4509-873X)
- Göran M.L. Bergström (ORCID: https://orcid.org/0000-0003-4289-5722)
- Björn Redfors (ORCID: https://orcid.org/0000-0002-4155-4451)
- Truls Råmunddal (ORCID: https://orcid.org/0000-0001-9483-5962)
- Jan Borén (ORCID: https://orcid.org/0000-0003-0786-8091)
- Carlo Pirazzi (ORCID: https://orcid.org/0009-0003-1572-3789)
- Kristofer Skoglund (ORCID: https://orcid.org/0000-0002-9095-1218)
- Pétur Pétursson (ORCID: https://orcid.org/0000-0003-0807-9406)
- Oskar Angerås (ORCID: https://orcid.org/0000-0002-3474-2438)
- Gustav Smith
- Elmir Ömerovic (ORCID: https://orcid.org/0000-0002-3875-8621)
- Araz Rawshani (ORCID: https://orcid.org/0000-0003-2066-3533)
- Vibha Gupta (ORCID: https://orcid.org/0000-0002-3785-8380)
- Eva A. Andersson (ORCID: https://orcid.org/0009-0001-0567-2020)
- Deepak L Bhatt
- N Sattar
- Lukas Hilgendorf (ORCID: https://orcid.org/0009-0000-9518-3644)
Institutions
- Sahlgrenska University Hospital (SE)
- University of Glasgow (GB)
- University of Gothenburg (SE)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Open Heart
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1136/openhrt-2024-002998
- Citations
- 5
- Primary Topic
- Cardiac Imaging and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 6.80
Funders
- Västra Götalandsregionen
- Knut och Alice Wallenbergs Stiftelse
- Göteborgs Universitet
- Wallenberg Centre for Molecular and Translational Medicine