Related Experiment Video
Updated: Aug 5, 2026
05:12
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
Published on: August 12, 2021
A Pilot Study on the Efficacy of Artificial Intelligence-Driven Monocular Three-Dimensional Conversion for Endoscopic
Yosuke Sato1,2, Kosuke Tanaka2
1Neurosurgery, Showa University, Tokyo, JPN.
Cureus
|August 1, 2026
Summary
Artificial intelligence (AI) enhances surgical depth perception by converting 2D to 3D views, improving task success and efficiency. However, AI-3D systems show limitations in deeper surgical spaces, requiring user awareness.
Area of Science:
- Medical Technology
- Surgical Navigation
- Artificial Intelligence
Background:
- Monocular 2D endoscopes lack depth perception, increasing surgeon cognitive load.
- AI offers real-time 2D to 3D video conversion, but depth limitations need study.
- This study assesses an AI-driven monocular 3D conversion system's efficacy and limits.
Purpose of the Study:
- Evaluate the efficacy of an AI system for monocular 3D surgical vision.
- Assess the spatial and depth-dependent limitations of AI-based 3D conversion.
- Compare AI-generated 3D vision to 2D and native 3D systems in a surgical task.
Main Methods:
- Six participants performed a surgical target-grasping task in a simulator.
- Visual conditions included 2D baseline, AI-generated 3D, and native 3D.
- Trials involved targets at 3 cm, 5 cm, and 10 cm working distances.
Main Results:
- AI-3D improved grasping success rate (52.2%) vs. 2D (33.3%), nearing native 3D (68.9%).
- AI-3D significantly reduced task completion time (5.25s) compared to 2D (7.93s).
- AI-3D excelled at 3-5 cm but showed reduced accuracy at 10 cm due to diminished depth cues.
Conclusions:
- AI-driven 3D conversion enhances surgical spatial perception and efficiency.
- The AI system is effective at close working distances (3-5 cm).
- Surgeons must recognize AI-3D system limitations in deeper operative fields (>10 cm).
