Open‐source deep‐learning models for segmentation of normal structures for prostatic and gynecological high‐dose‐rate brachytherapy: Comparison of architectures
Both UNet-derived architectures perform similarly on the bladder and rectum and are adequately accurate to reduce contouring time in a review-and-edit context during HDR brachytherapy planning. The UNet++ models were chosen for implementation at our institution due to lower computing hardware requirements and are in routine clinical use.
Authors
- James Lamb (ORCID: https://orcid.org/0000-0002-0440-4972)
- J. Neylon
- Jonathan M. Pham (ORCID: https://orcid.org/0000-0002-4617-5143)
- Andrew J. Krupien (ORCID: https://orcid.org/0000-0002-7524-5569)
- Dishane C. Luximon (ORCID: https://orcid.org/0000-0003-0568-5865)
- Hui‐Ming Dong (ORCID: https://orcid.org/0000-0003-2695-4251)
- D O’Connell (ORCID: https://orcid.org/0000-0002-0752-5825)
- John Charters (ORCID: https://orcid.org/0000-0001-7907-8748)
- Yasin Abdulkadir
Institutions
- University of California, Los Angeles (US)
Publication Details
- Journal
- Journal of Applied Clinical Medical Physics
- Published
- 2025-04-05
- DOI
- https://doi.org/10.1002/acm2.70089
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00