Impact of a new deep-learning image reconstruction algorithm on potential dose reduction and quality of chest CT images: a phantom study
Compared to IR-5, noise magnitude and detectability values were better, but noise texture and spatial resolution values were degraded, and this degradation increased as the DLR level increased. The results obtained with this new DLR algorithm open up new possibilities for improving image quality and offer significant potential for radiation dose reduction.
Authors
- Djamel Dabli (ORCID: https://orcid.org/0000-0003-1003-1196)
- Skander Sammoud (ORCID: https://orcid.org/0000-0001-7612-5924)
- Joël Greffier (ORCID: https://orcid.org/0000-0002-1735-5129)
- Jean Paul Beregi
- Fabien de Oliveira
Institutions
- Centre Hospitalier Universitaire de Nîmes (FR)
- Université de Nîmes (FR)
Publication Details
- Journal
- Physica Medica
- Published
- 2026-01-16
- DOI
- https://doi.org/10.1016/j.ejmp.2026.105736
- Primary Topic
- Radiation Dose and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00