Non-invasive arterial input function estimation using an MRA atlas and machine learning
This study introduces a new approach for AIF estimation in dynamic PET using brain PET images, a probabilistic vascular atlas, and machine learning techniques. The findings demonstrate the feasibility of non-invasive and subject-specific AIF estimation for SAFOV scanners.
Authors
- Rajat Vashistha (ORCID: https://orcid.org/0000-0001-6800-7661)
- David C. Reutens (ORCID: https://orcid.org/0000-0002-1652-9369)
- Hasan Sari (ORCID: https://orcid.org/0000-0002-1504-1767)
- Kieran O’Brien (ORCID: https://orcid.org/0000-0003-1996-3563)
- Viktor Vegh (ORCID: https://orcid.org/0000-0002-4310-1421)
- Axel Rominger (ORCID: https://orcid.org/0000-0002-1954-736X)
- Kuangyu Shi (ORCID: https://orcid.org/0000-0002-8714-3084)
- Hamed Moradi (ORCID: https://orcid.org/0000-0001-6757-6694)
- Amanda Hammond
Institutions
- University of Bern (CH)
- Queensland University of Technology (AU)
- The University of Queensland (AU)
- University Hospital of Bern (CH)
- National Imaging Facility (AU)
- Siemens (Australia) (AU)
- Siemens (Switzerland) (CH)
Publication Details
- Journal
- EJNMMI Research
- Published
- 2025-05-23
- DOI
- https://doi.org/10.1186/s13550-025-01253-3
- Primary Topic
- Advanced MRI Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Australian Government
- Australian Research Council