Potential radiation dose reduction in computed tomography with deep learning reconstruction: a retrospective monocentric study
This large-scale study confirms that DLR can significantly reduce the radiation dose in routine CT imaging while maintaining or enhancing diagnostic image quality. Its consistent performance across multiple protocols supports broader clinical adoption. Notably, the greatest dose reductions were observed in high-use protocols such as chest and CAP CT, underscoring DLR's potential to improve both individual patient care and long-term population-level radiation safety.
Authors
- Catherine Roy (ORCID: https://orcid.org/0000-0003-0527-5305)
- Luc Mertz (ORCID: https://orcid.org/0000-0001-9115-2111)
- François Séverac (ORCID: https://orcid.org/0000-0002-6611-1921)
- Melike Zeynep Akış (ORCID: https://orcid.org/0009-0008-0442-7315)
- Mickaël Ohana (ORCID: https://orcid.org/0000-0003-0179-5784)
- Serhat Akış (ORCID: https://orcid.org/0009-0001-7899-9251)
- Lucas Graber
Institutions
- Dokuz Eylül University (TR)
- Hôpital Civil, Strasbourg (FR)
- Université de Strasbourg (FR)
Publication Details
- Journal
- Diagnostic and Interventional Radiology
- Published
- 2025-12-05
- DOI
- https://doi.org/10.4274/dir.2025.253513
- Primary Topic
- Radiation Dose and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00