Low-count whole-body PET denoising with deep learning in a multicenter, multi-tracer and externally validated study
This is the first blinded, multicenter reader study evaluating a PET denoising algorithm in a European clinical setting across multiple tracers, incorporating unseen scanner technologies. The denoising algorithm demonstrated robust generalizability and preserved diagnostic accuracy on 50% count data. These findings support the clinical adoption of deep learning-based PET denoising to reduce dose or scan time for four commonly used tracers.
Authors
- G Moulin-Romsee
- Sezgin Üstmert
- John Maes (ORCID: https://orcid.org/0000-0003-3971-4820)
- Yves D’Asseler (ORCID: https://orcid.org/0000-0002-8807-2257)
- Simon DeKeyser (ORCID: https://orcid.org/0000-0002-1322-7621)
- Anass Chaouki (ORCID: https://orcid.org/0000-0001-9980-2254)
- C P Carron (ORCID: https://orcid.org/0000-0002-6561-0104)
- Isaac Kargar Samani
- Thorsten Brants
- Ludovic D’hulst
- Maarten Larmuseau (ORCID: https://orcid.org/0000-0003-0466-099X)
- Laurens Raes (ORCID: https://orcid.org/0000-0003-4544-7001)
- Stefaan Vandenberghe
- Azzam Abdalla Ibrahim
- Camille Steenhout
- Vicky De Ridder
Institutions
- HOGENT University of Applied Sciences and Arts (BE)
- Vrije Universiteit Brussel (BE)
- University of Liège (BE)
- AZ Groeninge (BE)
- Ghent University Hospital (BE)
- Ghent University (BE)
- Royal Pavilion (GB)
- VieCuri Medisch Centrum (NL)
- Province of Antwerp (BE)
- Centre Hospitalier Universitaire de Liège (BE)
- Centre Hospitalier Interrégional Edith Cavell (BE)
- AZ Sint-Lucas (BE)
- Epicura (BE)
- KU Leuven (BE)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2025-11-20
- DOI
- https://doi.org/10.1007/s00259-025-07672-7
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00