Generating synthetic CEM from low-energy images using deep learning: A future without contrast media? A proof-of-concept study
Our deep learning model generated synthetic iodine-enhanced images that visually resembled the clinical iodine-enhanced images. Radiologists could use the synthetic images to perform clinical tasks, such as lesion detection and BPE evaluation. Our model can improve image quality by removing common artifacts, including the breast-in-breast (halo). Our method is a way to combine the benefits of CEM while sparing the need for contrast media.
Authors
- Paolo Belli (ORCID: https://orcid.org/0000-0001-7979-2466)
- Gianluca Franceschini (ORCID: https://orcid.org/0000-0002-2950-3395)
- Reza Kalantar (ORCID: https://orcid.org/0000-0002-6211-9475)
- Anna D’Angelo (ORCID: https://orcid.org/0000-0001-5970-1010)
- Matteo Mancino (ORCID: https://orcid.org/0000-0001-7565-7531)
- Ludovica Iaccarino
- Konstantinos Zormpas-Petridis
- Paola Clauser
- Valentina Longo
- Evis Sala
Institutions
- Università Cattolica del Sacro Cuore (IT)
- Institute of Cancer Research (GB)
- Agostino Gemelli University Polyclinic (IT)
- Royal Marsden Hospital (GB)
- Medical University of Vienna (AT)
Publication Details
- Journal
- European Radiology Experimental
- Published
- 2026-03-16
- DOI
- https://doi.org/10.1186/s41747-026-00681-7
- Primary Topic
- Digital Radiography and Breast Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00