A multi-model deep learning approach for the identification of coronary artery calcifications within 2D coronary angiography images
This is the first attempt to propose a clinical decision support system to assist the identification of CAC within 2DCA. The proposed workflow holds the potential to improve both the accuracy and efficiency of CAC quantification, with promising clinical applications. As future work, the concurrent use of multiple auxiliary tasks could be explored to further improve the segmentation performance.
Authors
- Pierangela Bruno (ORCID: https://orcid.org/0000-0002-0832-0151)
- Maria Francesca Spadea (ORCID: https://orcid.org/0000-0002-5339-9583)
- Francesco Calimeri (ORCID: https://orcid.org/0000-0002-0866-0834)
- Salvatore De Rosa (ORCID: https://orcid.org/0000-0001-5388-942X)
- Ahmad Rasheed (ORCID: https://orcid.org/0000-0003-3730-1715)
- Paolo Zaffino (ORCID: https://orcid.org/0000-0002-0219-0157)
- Edoardo De Rose (ORCID: https://orcid.org/0000-0002-0032-9434)
- Ciro Benito Raggio (ORCID: https://orcid.org/0009-0008-2443-4029)
Institutions
- Karlsruhe Institute of Technology (DE)
- Magna Graecia University (IT)
- University of Calabria (IT)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2025-05-08
- DOI
- https://doi.org/10.1007/s11548-025-03382-5
- Citations
- 2
- Primary Topic
- Coronary Interventions and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 4.01
Funders
- Ministero della Salute
- Ministero dell'Università e della Ricerca