Related Experiment Video
Updated: Jul 5, 2025
07:51
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
7.6K
Clinical Validation of Computer-Aided Diagnosis Software for Preventing Retained Surgical Sponges
Ken Kurisaki1, Akihiko Soyama1, Shin Hamauzu2
1From the Department of Surgery, Nagasaki University Graduate School of Biomedical Sciences, Nagasaki City, Japan (Kurisaki, Soyama, Yamaguchi, Matsuguma, Eguchi).
Journal of the American College of Surgeons
|January 23, 2024
Summary
A deep learning computer-aided diagnosis (CAD) system effectively detected retained surgical sponges in a clinical setting. This AI tool shows promise for improving patient safety and preventing surgical item retention.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Surgical Safety
Background:
- Previous development of a deep learning computer-aided diagnosis (CAD) system for detecting retained surgical sponges using simulated data.
- Need to evaluate the CAD system's efficacy in a real-world clinical environment.
Purpose of the Study:
- To validate the clinical performance of a deep learning-based CAD system for identifying retained surgical sponges.
- To assess the system's effectiveness in a prospective manner.
Main Methods:
- Prospective collection of data from 1,053 postoperative radiographs of adult patients.
- Implementation of foreign object detection software on intraoperative portable radiographic devices.
- Evaluation of the CAD system's diagnostic performance.
Main Results:
- The CAD system identified potential retained surgical items in 150 out of 1,053 images.
- Achieved a specificity of 85.8% in the clinical setting, consistent with development phase results.
- Demonstrated comparable efficacy to the system's initial development data.
Conclusions:
- Clinical validation confirms the efficacy of the deep learning CAD system for retained surgical sponge detection.
- The CAD system shows potential to enhance current protocols for preventing surgical item retention.
- This technology can contribute to improved patient safety in surgical settings.
