A competition-proven deep learning-based dual-domain framework for low-dose CBCT reconstruction
Xuzhi Zhao, Muliang Li, Yi Du · 2026
Read A competition-proven deep learning-based dual-domain framework for low-dose CBCT reconstruction by Xuzhi Zhao, Muliang Li, Yi Du (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-13654160.txt.
Description
Xuzhi Zhao, Muliang Li, and Yi Du present a learning system that cleans up low-dose cone-beam scans. These scans guide daily cancer treatment and surgery. Cutting the dose spares patients radiation but fills the images with noise.
Their system works in two domains in sequence. A first network cleans the raw projections before the image is built. A second network then refines the built image. The design won first place in the low-dose task of a 2024 imaging challenge. It was trained on scans from 800 patients and tested on 110 more. The two-stage layout attacks noise at both its source and its visible end. Cleaner low-dose scans could make daily image guidance safer for long treatment courses.
Catalog record
| CREATOR | Xuzhi Zhao, Muliang Li, Yi Du |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |