Related Experiment Video
Updated: Jan 9, 2026
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
[Investigation of the Effect of Defining Quantitative Acceptance Criteria Using AI-based Retake Decision Support
Riho Tsuruoka1, Sono Kanoya1, Shohei Kudomi1
1Department of Radiological Technology, Yamaguchi University Hospital.
Purpose:
To reduce the number of retakes in lateral knee radiography, we defined a retake rule using a commercially available artificial intelligence (AI)-based retake decision support system (RDSS) and investigated the frequency and causes of retakes before and after its introduction.
Methods:
From the 3591 images of patients who underwent lateral knee joint radiography from March 1, 2023, to September 30, 2023, we extracted the retake images using the X-ray image management system and classified the causes of retakes. The retake rate before and after defining retake rules were calculated and compared.
Results:
Positioning errors were the most common cause of retakes of lateral knee radiographs, and unnecessary retakes were the second most common cause. The retake rate due to unnecessary retakes decreased from 7.1% to 1.9% with the defining retake rules.
Conclusion:
Our study revealed that positioning errors are the main cause of most of the retakes, and there were many unnecessary retakes. Determining objective retake criteria using RDSS was effective in reducing unnecessary retakes.
