Fully automatic tracking of native knee kinematics from stereo-radiography with digitally reconstructed radiographs
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study presents an automated method for tracking knee movement from X-rays, significantly reducing manual effort. The new approach accelerates kinematic tracking for orthopaedics and biomechanics research.
Area Of Science
- Biomechanics
- Medical Imaging
- Orthopaedics
Background
- Accurate measurement of joint motion from stereo-radiography is crucial for understanding human movement.
- Current kinematic tracking methods are manual, time-consuming, and labor-intensive.
Purpose Of The Study
- To introduce a fully automated framework for tracking native knee kinematics from stereo-radiography sequences.
- To accelerate the process of kinematic tracking for biomechanical and orthopaedic applications.
Main Methods
- A convolutional neural network annotates radiograph frames with segmentation maps and key points.
- Bone pose estimation is achieved through polynomial optimization and semidefinite relaxation.
- Pose refinement uses computed tomography-based digitally reconstructed radiographs registered to masked radiographs.
Main Results
- The automated framework demonstrated pose estimates comparable to manual tracking.
- Pose errors were below 1.0 degree or millimeter for all femur and tibia degrees of freedom in phantom trials.
- A novel rendering method was developed for digitally reconstructed radiographs with variable slice widths.
Conclusions
- The developed framework offers a fully automatic solution for knee kinematic tracking.
- This method has the potential to significantly benefit orthopaedics and biomechanics by accelerating kinematic analysis.
- The system achieves high accuracy and efficiency in tracking joint-level motion.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.