Impact of deep learning denoising on kinetic modelling for low-dose dynamic PET: application to single- and dual-tracer imaging protocols
This study demonstrates that applying DL-DN trained on static [<sup>18</sup>F]FDG PET images to dynamic [<sup>18</sup>F]FDG and [<sup>18</sup>F]FGln PET can permit significantly reduced doses, preserving accurate FDG K<sub>i</sub> and FGln V<sub>T</sub> measurements, and enhancing parametric image quality. DL-DN shows promise for improving dynamic PET quantification at reduced doses, including novel dual-tracer studies.
Authors
- Margaret E. Daube-Witherspoon (ORCID: https://orcid.org/0000-0002-6318-2054)
- Jacob G. Dubroff (ORCID: https://orcid.org/0000-0002-0732-2374)
- Florence M. Muller (ORCID: https://orcid.org/0000-0001-5287-7355)
- Austin R. Pantel (ORCID: https://orcid.org/0000-0001-8649-9970)
- Stefaan Vandenberghe (ORCID: https://orcid.org/0000-0002-2377-3968)
- Christian Vanhove (ORCID: https://orcid.org/0000-0002-3988-5980)
- Corinde E. Wiers (ORCID: https://orcid.org/0000-0002-2934-8794)
- Joel S. Karp (ORCID: https://orcid.org/0000-0002-6154-8585)
- Elizabeth Li (ORCID: https://orcid.org/0000-0003-2365-0594)
Institutions
- Ghent University (BE)
- University of Pennsylvania (US)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2025-03-12
- DOI
- https://doi.org/10.1007/s00259-025-07182-6
- Citations
- 6
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 8.16
Funders
- Belgian American Educational Foundation
- University of Pennsylvania
- Institute for Translational Medicine and Therapeutics
- Fonds Wetenschappelijk Onderzoek
- Vlaamse regering
- National Institutes of Health