Shorter SPECT scans using self-supervised coordinate learning to synthesize skipped projection views
The proposed method, SpeRF, shows potential for significant reduction in acquisition time (up to a factor of 4) while maintaining quantitative accuracy in clinical SPECT protocols by allowing for the collection of fewer projections. The self-supervised nature of SpeRF, with data processed independently on each patient's projection data, eliminates the need for extensive training datasets. The reduction in acquisition time is particularly relevant for imaging under low-count conditions and for protocols that require multiple-bed positions such as whole-body imaging.
Authors
- Yixuan Jia (ORCID: https://orcid.org/0000-0002-3651-9387)
- Jeffrey A. Fessler (ORCID: https://orcid.org/0000-0001-9998-3315)
- Zongyu Li (ORCID: https://orcid.org/0000-0002-0661-0040)
- Yuni K. Dewaraja (ORCID: https://orcid.org/0000-0002-3920-6925)
- Jason Hu (ORCID: https://orcid.org/0000-0001-5709-1909)
- Xiaojian Xu (ORCID: https://orcid.org/0000-0002-5264-8963)
Institutions
- University of Michigan (US)
- Michigan Medicine (US)
Publication Details
- Journal
- EJNMMI Physics
- Published
- 2025-05-20
- DOI
- https://doi.org/10.1186/s40658-025-00762-3
- Citations
- 1
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- National Institutes of Health
- National Cancer Institute
- National Institute of Biomedical Imaging and Bioengineering