Comparison between artificial intelligence-based and manual organ delineations in pretreatment computed tomography scans of prostate cancer patients: a visual grading study
Journal article, 2026
This study aimed to evaluate the clinical acceptability of artificial intelligence (AI)-based organ segmentations on pretreatment CT images of prostate cancer patients using manual organ delineations as a reference. Paired AI-based segmentations and manual delineations of the prostate, urinary bladder, and rectum were evaluated by three observers, according to a 4-grade Likert-scale, based on quality criteria, developed through a Delphi process. Visual grading characteristics (VGC) analysis was performed. When comparing the ratings of AI-based (n = 360) and manual delineations (n = 360), the area under the VGC-curve (AUCVGC) was 0.36 (95% CI 0.27–0.44), 0.35 (95% CI 0.28–0.41), and 0.3 (95% CI 0.22–0.40) for the prostate, urinary bladder, and rectum, respectively, indicating inferior ratings for the algorithm. Few AI segmentations (8%) were considered clinically unacceptable, while in 67% no or minor changes were needed. Despite superior ratings for manual delineations, most AI-segmentations needed no or minor changes, indicating clinical acceptability.
Author
Eirini Polymeri
University of Gothenburg
Sahlgrenska University Hospital
Åse (Allansdotter) Johnsson
University of Gothenburg
Sahlgrenska University Hospital
Olof Enqvist
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Eigenvision AB
Johannes Ulén
Eigenvision AB
Jon Kindblom
Sahlgrenska University Hospital
Karin Braide
University of Gothenburg
Hans Jurgen Wiltz
Region Kronoberg
Margareta Tanyasiová
Sahlgrenska University Hospital
E. Tragardh
Skåne University Hospital
L. Edenbrandt
University of Gothenburg
Henrik Kjölhede
University of Gothenburg
Sahlgrenska University Hospital
Angelica Svalkvist
University of Gothenburg
Sahlgrenska University Hospital
Radiation Protection Dosimetry
0144-8420 (ISSN) 17423406 (eISSN)
Vol. 202 3-4 204-213Subject Categories (SSIF 2025)
Cancer and Oncology
Artificial Intelligence
DOI
10.1093/rpd/ncaf184