SMART-PET: a Self-SiMilARiTy-aware generative adversarial framework for reconstructing low-count [18F]-FDG-PET brain imaging
In general, SMART-PET shows promise in reducing noise in PET images and can synthesize diagnostic quality images with a 90% reduction in standard of care injected activity. These results make it a potential candidate for clinical applications in radiosensitive populations and for longitudinal neurological studies.
Authors
- Jorge Cabello (ORCID: https://orcid.org/0000-0002-2042-616X)
- Udunna Anazodo (ORCID: https://orcid.org/0000-0001-8864-035X)
- Paulien Moyaert
- Michael O. Dada (ORCID: https://orcid.org/0000-0003-4563-3867)
- Andrea Soddu (ORCID: https://orcid.org/0000-0001-6833-745X)
- Jorge G. Burneo (ORCID: https://orcid.org/0000-0002-3644-2826)
- Justin W. Hicks (ORCID: https://orcid.org/0000-0003-0269-9364)
- Elizabeth C. Finger (ORCID: https://orcid.org/0000-0003-4461-7427)
- Michael T. Jurkiewicz (ORCID: https://orcid.org/0000-0002-4641-3172)
- Confidence Raymond (ORCID: https://orcid.org/0000-0003-3927-9697)
- Dong Zhang (ORCID: https://orcid.org/0000-0002-3404-5173)
- Linshan Liu (ORCID: https://orcid.org/0000-0003-1203-0031)
- Andrea Andrade (ORCID: https://orcid.org/0000-0002-2735-7558)
Institutions
- Western University (CA)
- Montreal Neurological Institute and Hospital (CA)
- University of British Columbia (CA)
- Ghent University Hospital (BE)
- Siemens (United States) (US)
- McGill University (CA)
- Federal University of Technology Minna (NG)
Publication Details
- Journal
- Frontiers in Nuclear Medicine
- Published
- 2024-11-19
- DOI
- https://doi.org/10.3389/fnume.2024.1469490
- Citations
- 5
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 2.02