Comprehensive evaluation of a deep learning-based synthetic CT model for MR-only radiotherapy across multiple anatomical sites
Xiao Liang, Chanwoong Lee, Andrew Godley, Junjie Wu, Mu-Han Lin, Trung Truong, Weiguo Lu, Viktor Iakovenko, Steve Jiang, Jie Deng · 2026
Read Comprehensive evaluation of a deep learning-based synthetic CT model for MR-only radiotherapy across multiple anatomical sites by Xiao Liang, Chanwoong Lee, Andrew Godley, Junjie Wu, Mu-Han Lin, Trung Truong, Weiguo Lu, Viktor Iakovenko, Steve Jiang, Jie Deng (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/pmc-13273862.txt.
Description
Xiao Liang, Jie Deng, and co-authors test one deep model that fakes CT scans from MR scans for beam care at all body sites, in work from 2026. MR lone plans cut dose and fuse steps, but dose math needs CT like maps. One all sites model beats a shelf of site lone tools for clinic flow.
Fake scans were graded on image truth, dose math truth, and pose match. Soft tissue truth was best, while bone truth was least sharp. Dose gaps in aim zones were small, and pass rates were high save for the chest. Pose was most firm in head and spine zones.
Catalog record
| CREATOR | Xiao Liang, Chanwoong Lee, Andrew Godley, Junjie Wu, Mu-Han Lin, Trung Truong, Weiguo Lu, Viktor Iakovenko, Steve Jiang, Jie Deng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |