Swin UNETR-based prediction of [68Ga]Ga-FAPI-46 PET/CT dose rate maps in cancer patients: quantitative comparison with [18F]FDG PET/CT
Saeideh Izadi-Yazdi, Farshid Babapour-Mofrad, Elmira Yazdani, Najme Karamzade-Ziarati, Hossein Arabi, Mahdi Sadeghi · 2026
Read Swin UNETR-based prediction of [68Ga]Ga-FAPI-46 PET/CT dose rate maps in cancer patients: quantitative comparison with [18F]FDG PET/CT by Saeideh Izadi-Yazdi, Farshid Babapour-Mofrad, Elmira Yazdani, Najme Karamzade-Ziarati, Hossein Arabi, Mahdi Sadeghi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13474557.txt.
Description
Saeideh Izadi-Yazdi and co-authors use deep learning in 2026 to predict radiation dose maps for a cancer scan tracer. The tracer lights up tissue that supports tumors, aiding both scans and later targeted radiation care. Dose maps were first built with heavy physics tools from scans of twenty-two cancer patients. Two tracers were compared on uptake and dose to healthy organs.
The newer tracer gave sharper tumor contrast and lower dose to organs at risk than the standard tracer. A transformer model learned to predict dose maps fast, beating a simpler network on accuracy scores. Its error stayed low and nearly all checks passed a strict match test. Fast dose prediction could make personal treatment planning routine.
Catalog record
| CREATOR | Saeideh Izadi-Yazdi, Farshid Babapour-Mofrad, Elmira Yazdani, Najme Karamzade-Ziarati, Hossein Arabi, Mahdi Sadeghi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60125 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |