Urethra contours on MRI: Multidisciplinary consensus educational atlas and reference standard for artificial intelligence benchmarking
We established a multidisciplinary consensus benchmark for segmentation of the urethra. The deep-learning model performs comparably to specialist physicians and demonstrates consistent results across multiple institutions. It shows promise as a clinical decision-support tool for accurate and reliable urethra segmentation in prostate cancer radiotherapy planning and studies of dose-toxicity associations.
Authors
- Mukesh G. Harisinghani (ORCID: https://orcid.org/0000-0003-0993-1947)
- Lily Nguyen (ORCID: https://orcid.org/0009-0004-0076-1640)
- Anna M. Dornisch (ORCID: https://orcid.org/0009-0007-2602-7323)
- Sophia C. Kamran (ORCID: https://orcid.org/0000-0001-9283-6515)
- Tristan Barrett (ORCID: https://orcid.org/0000-0002-1180-1474)
- Sean Woolen (ORCID: https://orcid.org/0000-0003-4951-2173)
- Robert Timothy Dess (ORCID: https://orcid.org/0000-0003-2331-3758)
- Michael A. Liss (ORCID: https://orcid.org/0000-0001-6978-1026)
- Daniel Margolis (ORCID: https://orcid.org/0000-0001-8212-707X)
- Tyler M. Seibert (ORCID: https://orcid.org/0000-0002-4089-7399)
- Eric Weinberg (ORCID: https://orcid.org/0000-0003-4951-7142)
- Anders M. Dale (ORCID: https://orcid.org/0000-0002-6126-2966)
- Yuze Song (ORCID: https://orcid.org/0000-0001-5803-1254)
- Madison Baxter
Institutions
- Harvard University (US)
- University of California, San Francisco (US)
- Cornell University (US)
- University of Cambridge (GB)
- University of Michigan (US)
- University of California System (US)
- University of Rochester Medical Center (US)
- University of California San Diego (US)
- Massachusetts General Hospital (US)
Publication Details
- Journal
- Radiotherapy and Oncology
- Published
- 2025-10-25
- DOI
- https://doi.org/10.1016/j.radonc.2025.111231
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00