Back to all papers

Comparison between artificial intelligence-based and manual organ delineations in pretreatment computed tomography scans of prostate cancer patients: a visual grading study.

March 13, 2026pubmed logopapers

Authors

Polymeri E,Johnsson ÅA,Enqvist O,UlĂ©n J,Kindblom J,Braide K,Wiltz HJ,TanyasiovĂĄ M,TrĂ€gĂ„rdh E,Edenbrandt L,Kjölhede H,Svalkvist A

Affiliations (13)

  • Department of Radiology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Medicinaregatan 3, Medicinareberget, 413 90, Gothenburg, Region VĂ€stra Götaland, Sweden.
  • Department of Radiology, Sahlgrenska University Hospital, BlĂ„ StrĂ„ket 5, Region VĂ€stra Götaland, 413 45, Gothenburg, Sweden.
  • Department of Electrical Engineering, Chalmers University of Technology, HörsalsvĂ€gen 9-11, Region VĂ€stra Götaland, 412 96, Gothenburg, Sweden.
  • Eigenvision AB, Bredgatan 4, 211 30, Region SkĂ„ne, Malmö, Sweden.
  • Department of Oncology, Sahlgrenska University Hospital, BlĂ„ StrĂ„ket 2, Region VĂ€stra Götaland, 413 45, Gothenburg, Sweden.
  • Department of Oncology, Institute of Clinical Sciences, University of Gothenburg, Medicinaregatan 3, Medicinareberget, 413 90, Gothenburg, Region VĂ€stra Götaland, Sweden.
  • Department of Oncology and Radiotherapy, Region Kronoberg, Central lasarett VĂ€xjö, StrandvĂ€gen 8, 351 85, VĂ€xjö, Sweden.
  • Clinical Physiology and Nuclear Medicine, Lund University and SkĂ„ne University Hospital, 221 85, Malmö, Region SkĂ„ne, Sweden.
  • Department of Molecular and Clinical Medicine, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, BlĂ„ StrĂ„ket 5, 413 45, Region VĂ€stra Götaland, Gothenburg, Sweden.
  • Department of Urology, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Medicinaregatan 5, Medicinareberget, 413 90, Region VĂ€stra Götaland, Gothenburg, Sweden.
  • Department of Urology, Sahlgrenska University Hospital, BlĂ„ StrĂ„ket 5, 413 45, Region VĂ€stra Götaland, Gothenburg, Sweden.
  • Department of Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Medicinaregatan 5, Medicinareberget, 413 90, Region VĂ€stra Götaland, Gothenburg, Sweden.
  • Department of Biomedical Engineering and Medical Physics, Sahlgrenska University Hospital, BlĂ„ StrĂ„ket 5, 413 45, Region VĂ€stra Götaland, Gothenburg, Sweden.

Abstract

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.

Topics

Prostatic NeoplasmsArtificial IntelligenceTomography, X-Ray ComputedRadiographic Image Interpretation, Computer-AssistedJournal ArticleComparative Study

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.