Transfer learning‑based attenuation correction in 99mTc-TRODAT-1 SPECT for Parkinson’s disease using realistic simulation and clinical data
TLAC is feasible for DAT SPECT with a pre-trained model generated purely based on simulation data. TLAC-MC demonstrates superior performance over other DL-based AC methods, particularly when limited clinical datasets are available. The closer the pre-training data is to the target domain, the better the performance of the TLAC model.
Authors
- Wenbo Huang (ORCID: https://orcid.org/0000-0002-6664-1172)
- Greta S. P. Mok (ORCID: https://orcid.org/0000-0002-2962-2087)
- Guang‐Uei Hung (ORCID: https://orcid.org/0000-0002-8668-0283)
- Han Jiang (ORCID: https://orcid.org/0000-0002-7023-1846)
- Hao Sun
- Yu Du
- Haiyan Wang (ORCID: https://orcid.org/0009-0002-5232-9644)
Institutions
- Fujian Medical University (CN)
- Chinese Academy of Sciences (CN)
- University of Macau (MO)
- Chang Bing Show Chwan Memorial Hospital (TW)
- Shenzhen Institutes of Advanced Technology (CN)
- Union Hospital (CN)
- Southern Medical University (CN)
Publication Details
- Journal
- EJNMMI Physics
- Published
- 2025-05-06
- DOI
- https://doi.org/10.1186/s40658-025-00756-1
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- United Mitochondrial Disease Foundation
- Universidade de Macau
- Fundo para o Desenvolvimento das Ciências e da Tecnologia
- Research Services and Knowledge Transfer Office, University of Macau