Geometric evaluation of a deep learning method for segmentation of urinary OARs on magnetic resonance imaging for prostate cancer radiotherapy
This multicentric study is the first to propose a nnU-Net deep learning model for the delineation of urinary OARs, that can be applied to various image dataset. Further work is needed to assess the dosimetric impact of such variations, in various clinical scenarios.
Authors
- A. Barateau
- Igor Bessières
- Jennifer Le Guévelou (ORCID: https://orcid.org/0000-0002-9589-4873)
- Oscar Acosta (ORCID: https://orcid.org/0000-0002-5447-1479)
- R. de Crevoisier
- Jean‐Claude Nunes (ORCID: https://orcid.org/0000-0001-6560-1518)
- Miguel Castro (ORCID: https://orcid.org/0000-0003-1792-6857)
- Blanche Texier (ORCID: https://orcid.org/0009-0000-9961-4958)
- Richard A. Martin (ORCID: https://orcid.org/0000-0002-6013-2334)
- C. Lafond
Institutions
- Centre Georges François Leclerc (FR)
- Laboratoire Traitement du Signal et de l'Image (FR)
- Centre Eugène Marquis (FR)
Publication Details
- Journal
- Clinical and Translational Radiation Oncology
- Published
- 2025-12-05
- DOI
- https://doi.org/10.1016/j.ctro.2025.101091
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00