Defining ground truth for prostate segmentation of transrectal ultrasound images: Inter‐ and intra‐observer variability of manual versus semi‐automatic methods
The semi-automatic segmentation method evaluated in this study demonstrated comparable accuracy to manual segmentation while reducing inter- and intra-individual variability. These findings suggest that the tested semi-automatic approach can serve as a reliable reference standard for AI training in prostate segmentation.
Authors
- Pierre Mozer
- Clément Beitone (ORCID: https://orcid.org/0000-0003-4081-4247)
- Louis Lenfant (ORCID: https://orcid.org/0000-0001-9852-4002)
- G. Fiard (ORCID: https://orcid.org/0000-0003-3049-5318)
- Jocelyne Troccaz (ORCID: https://orcid.org/0000-0001-5921-9419)
- Sandrine Voros (ORCID: https://orcid.org/0000-0002-7418-2367)
- Bernard Malavaud
Institutions
- Institut polytechnique de Grenoble (FR)
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Centre Hospitalier Universitaire de Grenoble (FR)
- Sorbonne Université (FR)
- Assistance Publique – Hôpitaux de Paris (FR)
- Institut universitaire du cancer de Toulouse Oncopole (FR)
- Pitié-Salpêtrière Hospital (FR)
- Institut Systèmes Intelligents et de Robotique (FR)
- Onco-Urologie Prédictive (FR)
- Université Grenoble Alpes (FR)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-08-01
- DOI
- https://doi.org/10.1002/mp.18025
- Citations
- 1
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.52