Related Experiment Video
Updated: Oct 17, 2025
10:25
Technical Approach for Infrared Tracking for Soft Tissue Navigation with a Holographic Head-Mounted Display and Preclinical Validation
Published on: September 2, 2025
161
Autonomously Navigating a Surgical Tool Inside the Eye by Learning from Demonstration
Ji Woong Kim1, Changyan He1, Muller Urias2
1Laboratory for Computing + Sensing (LCSR) dept. at the Johns Hopkins University, Baltimore, MD 21218 USA.
IEEE International Conference on Robotics and Automation : ICRA : [Proceedings]. IEEE International Conference on Robotics and Automation
|October 8, 2021
Summary
This study introduces an automated surgical tool navigation system for retinal surgery. The deep learning system accurately guides surgical needles to target locations, minimizing tissue damage and human error.
Area of Science:
- Ophthalmology
- Robotics
- Machine Learning
Background:
- Retinal surgery demands high precision (tens of microns) for tool navigation, posing challenges due to reliance on surgeon's depth perception.
- Existing methods offer surgeon assistance but do not fully automate tool navigation, leaving a gap in procedural safety and efficiency.
Purpose of the Study:
- To develop and evaluate an autonomous system for precise surgical tool navigation on the retinal surface.
- To reduce the risk of tissue damage and streamline complex retinal surgical procedures through automation.
Main Methods:
- A deep learning network was trained to mimic expert surgical demonstrations for tool navigation.
- The system learned to imitate expert trajectories using recorded visual servoing data to reach user-defined retinal goals.
Main Results:
- The autonomous navigation system achieved an average accuracy of 137 μm in physical experiments and 94 μm in simulation.
- The system demonstrated generalization capabilities in the presence of varying surgical conditions and auxiliary tools.
Conclusions:
- Automating surgical tool navigation in retinal surgery is feasible using deep learning imitation.
- This technology has the potential to enhance safety, accuracy, and efficiency in delicate ophthalmic procedures.
