Related Experiment Video
Updated: Jul 5, 2025
07:43
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
Published on: July 2, 2021
3.1K
Real-time Pose Tracking for a Continuum Guidewire Robot under Fluoroscopic Imaging
Sharan R Ravigopal1, Achraj Sarma1, Timothy A Brumfiel1
1Medical Robotics and Automation (RoboMed) Laboratory, Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA.
IEEE Transactions on Medical Robotics and Bionics
|January 22, 2024
Summary
This study presents a new real-time tracking method for continuum guidewire robots used in treating atherosclerosis. The system accurately visualizes and controls guidewire robots during catheter placements, improving surgical precision.
Area of Science:
- Medical Robotics
- Image-Guided Surgery
- Biomedical Engineering
Background:
- Atherosclerosis necessitates interventions like angioplasty with catheter placements.
- Continuum guidewire robots offer enhanced dexterity for complex catheter navigation.
- Real-time tracking of guidewire robots is crucial for accurate visualization and control during procedures.
Purpose of the Study:
- To develop and evaluate algorithms for real-time tracking of continuum guidewire robots.
- To enable precise visualization of guidewire shape, orientation, and workspace.
- To assess the suitability of the tracking method for clinical applications in image-guided interventions.
Main Methods:
- Utilized a semantic segmentation architecture (MobileNetv2 with Tversky loss) for guidewire shape detection.
- Applied medial axis filtering and parametric curve fitting for pose estimation.
- Estimated joint variables in real-time for a tendon-actuated COaxially Aligned STeerable (COAST) guidewire robot.
- Tracked the guidewire robot's traversal within an aortic bifurcation phantom under C-arm fluoroscopy.
Main Results:
- Achieved approximately 90% accuracy in real-time guidewire tracking.
- Demonstrated execution times within 100ms, confirming real-time feasibility.
- Successfully tracked the guidewire robot's pose and shape through a complex phantom model.
Conclusions:
- The developed real-time tracking method is accurate and efficient for continuum guidewire robots.
- This technology can enhance visualization and control in image-guided surgical procedures.
- The method shows significant potential for improving outcomes in treating vascular diseases like atherosclerosis.
