Related Experiment Video
Updated: May 2, 2026
Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
Published on: October 6, 2023
Do AI-based contouring algorithms influence physicians in the online adaptive radiotherapy of patients with bladder
Nika Guberina1,2, Aymane Khouya1, Christian Hoffmann1
1Department of Radiotherapy, West German Cancer Center, University Hospital Essen, University of Duisburg-Essen, Germany.
Purpose:
In this prospective cross-over study, the precision of manual correction of the clinical target volume (CTV) during online-adaptive radiotherapy (ART) of patients with bladder cancer was investigated in dependence on the input of applied computational algorithms.
Methods And Materials:
Online-adaptive-radiation therapy (ART) fractions were analysed from a prospective registry as a component of a trimodality treatment for bladder cancer. The CBCT-guided adaptive radiation therapy (CBCTgART) workflow uses a CBCT acquired at the beginning of a treatment session (CBCT1) to update the target volume contours of the planning CT (pCT) on the current anatomy of the day. The study comprises radiotherapy fractions with target (CTV) segments showing clinically relevant deviations (>5 mm) when mapped between pre-treatment (CBCT1) and post-adaptation (CBCT2) images. CTValgo1-2 were obtained from two deformable-image-registration algorithms (algo1, algo2) based on AI-generated normal-tissue contours and a rigid copy of the CTVoriginal termed CTValgo3 (algo3). Verification cone-beam-computed-tomography (CBCT2) acquired during ART showed CTValgo1-3 on new anatomical scenarios. The task of 13 physicians was to adjust CTValgo1-3 on CBCT2 to match the CTVoriginal on CBCT1.
Results:
In 151/169 pairwise comparisons, mean-distance-of-segments-to-ground-truth (MDAGT) after adjustment by a physician was larger for the poorer algorithms than for the better ones. The binomial proportion was 0.893, significantly different from 0.5 as null proportion (p < 0.0001, exact-binomial-test), and not dependent on the physician or on the respective patient. In a quantitative analysis by a mixed-model, the MDAGT of the manually adjusted segments between 16% and 50% of the errors were on average corrected by the physicians, with interindividual differences (p < 0.0001,F-test).
Conclusions:
The present study results reveal that the quality of AI-generated contours is of crucial importance for a proper online onboard ART, as errors may bias clinical workflow and contouring. The accuracy of supervised structures strongly depends on the accuracy of the AI generated contours before supervision.
