Improving deep learning organ segmentation accuracy in cone-beam CT-guided radiotherapy using a robust scatter suppression method
Rupesh Dotel, Farhang Bayat, Junxiao Hu, Uttam Pyakurel, Ryan Sabounchi, Roy Bliley, Ryan Lanning, Brian Kavanagh, Tyler Robin, Cem Altunbas · 2026
Read Improving deep learning organ segmentation accuracy in cone-beam CT-guided radiotherapy using a robust scatter suppression method by Rupesh Dotel, Farhang Bayat, Junxiao Hu, Uttam Pyakurel, Ryan Sabounchi, Roy Bliley, Ryan Lanning, Brian Kavanagh, Tyler Robin, Cem Altunbas (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-13602047.txt.
Description
Rupesh Dotel and co-authors test in 2026 whether cleaning up scatter in cone beam scans during radiotherapy improves deep learning outlines of organs. Scatter blurs these scans and can throw off automatic contouring, which guides dose checks and treatment adaptation. Their method pairs a new anti scatter grid with a matched rebuild pipeline. Twenty six patients with prostate, head and neck, or pelvic cancers got both standard and cleaned scans.
A general segmentation model then outlined thirteen organs and targets on both scan types. Outlines from cleaned scans scored closer to clinician drawn ones on standard overlap and distance measures. Gains were clear in organs such as the prostate, bladder, and rectum. The authors argue image quality work pays off in AI accuracy.
Catalog record
| CREATOR | Rupesh Dotel, Farhang Bayat, Junxiao Hu, Uttam Pyakurel, Ryan Sabounchi, Roy Bliley, Ryan Lanning, Brian Kavanagh, Tyler Robin, Cem Altunbas |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |