Related Experiment Video
Updated: May 2, 2026
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
646
Adapting monocular SLAM for surface-trace free 3D registration in navigated arthroscopy
Tânia Baptista1, Carolina Raposo2, Miguel Marques2
1Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal. tania.baptista@isr.uc.pt.
Summary
This study shows that while visual markers are essential for accurate surgical navigation, the digitizing tool can be removed. A new Simultaneous Localization and Mapping (SLAM) method allows for contactless registration in video-based surgical navigation.
Area of Science:
- Medical technology
- Computer vision
- Surgical robotics
Background:
- Video-based surgical navigation (VBSN) uses preoperative 3D models and intraoperative data for real-time guidance.
- Current VBSN registration relies on two visual markers and manual point collection, which is time-consuming and potentially risky.
Purpose of the Study:
- To investigate the feasibility of removing visual markers from VBSN systems.
- To improve the efficiency and safety of surgical navigation registration.
Main Methods:
- Adapted monocular Simultaneous Localization and Mapping (SLAM) techniques for the arthroscopic surgical environment.
- Estimated camera pose and generated 3D scene reconstructions from arthroscopic videos.
Main Results:
- Simultaneous Localization and Mapping (SLAM) alone did not provide the required accuracy and real-time performance for camera pose estimation, necessitating the anatomy marker.
- A SLAM-based variant enabled contactless registration by eliminating the digitizing tool.
- SLAM facilitated structure and motion recovery, allowing for inspection of anatomical regions without continuous marker visibility.
Conclusions:
- The SLAM-based approach enables real-time, contactless registration for VBSN, meeting clinical requirements.
- This advancement was validated in cadaveric arthroscopy experiments, demonstrating on-the-fly registration capabilities.
