Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Accuracy of glenohumeral joint center of rotation estimates using traditional motion capture versus bi-plane fluoroscopy.

Journal of biomechanics·2026
Same author

Neural Implicit Shape and Intensity Models for Scan-Free 2D-3D Registration in Dynamic Stereo-Radiography.

Annals of biomedical engineering·2025
Same author

Contributions of Muscle Forces to Stability and Mobility in Radiography-Driven Models of Total Shoulder Arthroplasty.

Journal of biomechanical engineering·2025
Same author

Hip contact forces can be directed outside of a well-oriented cup during common activities; implications for implant testing.

Clinical biomechanics (Bristol, Avon)·2025
Same author

Towards markerless robot-assisted navigation with 2D-3D registration for anterior cruciate ligament reconstruction.

Computers in biology and medicine·2025
Same author

Correction: Scan-Free and Fully Automatic Tracking of Native Knee Anatomy from Dynamic Stereo-Radiography with Statistical Shape and Intensity Models.

Annals of biomedical engineering·2024

Related Experiment Video

Updated: Jun 29, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.0K

Scan-Free and Fully Automatic Tracking of Native Knee Anatomy from Dynamic Stereo-Radiography with Statistical Shape

William Burton1, Casey Myers2, Margareta Stefanovic3

  • 1Center for Orthopaedic Biomechanics, University of Denver, 2155 E Wesley Ave, Denver, CO, 80208, USA. Will.Burton@du.edu.

Annals of Biomedical Engineering
|April 1, 2024
PubMed
Summary

This study presents an automated framework for tracking knee anatomy from stereo-radiography, eliminating the need for manual effort and volumetric scans. The method achieves high accuracy in pose estimation and surface error for human movement analysis.

Keywords:
2D-3D registrationDigitally reconstructed radiographsGlobal optimizationMachine learningSemidefinite relaxationsStatistical shape and intensity models

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.2K

Related Experiment Videos

Last Updated: Jun 29, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.0K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.0K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.2K

Area of Science:

  • Biomechanics
  • Medical Imaging
  • Computer Vision

Background:

  • Quantitative human movement analysis relies on kinematic tracking of native anatomy.
  • Conventional methods require manual effort and volumetric medical images.
  • A need exists for automated, efficient tracking without volumetric data.

Purpose of the Study:

  • To introduce a framework for fully automatic tracking of native knee anatomy from dynamic stereo-radiography.
  • To eliminate the reliance on subject-specific volumetric scans in kinematic tracking.
  • To reduce manual effort in human movement evaluation.

Main Methods:

  • A three-step computational framework: CNN-based annotation, polynomial optimization for initial estimates, and global optimization for refinement.
  • Utilizes segmentation maps and anatomic landmarks for pose and anatomy estimation.
  • Employs statistical shape and intensity models for digitally reconstructed radiographs.

Main Results:

  • Anatomic surface errors consistently below 1.0 mm in evaluations.
  • Median absolute errors for bone pose estimates were below 1.0 mm for 15/18 degrees of freedom.
  • Demonstrated accurate pose estimation without volumetric scans.

Conclusions:

  • The proposed framework enables accurate pose estimation of native knee anatomy from stereo-radiography.
  • Significant reduction in manual effort is achievable compared to conventional methods.
  • The method successfully bypasses the requirement for volumetric scans.