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

Mid-term outcomes in patients younger than 65 years undergoing reverse total shoulder arthroplasty demonstrate favourable functional results with high rates of return to activity and work.

Journal of experimental orthopaedics·2026
Same author

MRI-guided detection of knee injuries as a concomitant lesion of femoral shaft fractures: a systematic review and meta-analysis.

EFORT open reviews·2026
Same author

Joint-specific measures improve risk adjustment in total knee arthroplasty: A machine learning approach.

Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA·2026
Same author

Clinical Outcomes, Return to Sport and Psychological Readiness After Arthroscopic Bankart Repair Using Knotless All-Suture Anchors at a Minimum 2Year Follow-up.

Archives of orthopaedic and trauma surgery·2026
Same author

[Use of artificial intelligence for next-gen anamnesis and communication in orthopedics & trauma surgery : From chatbots to ambient intelligence].

Orthopadie (Heidelberg, Germany)·2026
Same author

Multi-omics analysis reveals the key role of STIL in Li-Fraumeni syndrome and osteosarcoma.

NPJ precision oncology·2026

Related Experiment Video

Updated: Jun 29, 2025

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

Multicentric development and validation of a multi-scale and multi-task deep learning model for comprehensive lower

Nikolas J Wilhelm1, Claudio E von Schacky2, Felix J Lindner3

  • 1Department of Orthopedics and Sports Orthopedics, Klinikum rechts der Isar, School of Medicine, Munich, Germany; Munich Institute of Robotics and Machine Intelligence, Department of Electrical and Computer Engineering, Technical University of Munich, Munich, Germany.

Artificial Intelligence in Medicine
|March 29, 2024
PubMed
Summary

A new deep learning model automates knee osteoarthritis leg alignment assessment using long leg radiographs (LLR). This AI tool matches surgeon accuracy while significantly improving efficiency and consistency in orthopedic analysis.

Keywords:
Deep learningLower extremityMechanical alignmentMultiscaleMultitaskObject detection

More Related Videos

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.1K
Evaluating Postural Control and Lower-extremity Muscle Activation in Individuals with Chronic Ankle Instability
07:52

Evaluating Postural Control and Lower-extremity Muscle Activation in Individuals with Chronic Ankle Instability

Published on: September 18, 2020

8.4K

Related Experiment Videos

Last Updated: Jun 29, 2025

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
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.1K
Evaluating Postural Control and Lower-extremity Muscle Activation in Individuals with Chronic Ankle Instability
07:52

Evaluating Postural Control and Lower-extremity Muscle Activation in Individuals with Chronic Ankle Instability

Published on: September 18, 2020

8.4K

Area of Science:

  • Orthopedic surgery
  • Medical imaging analysis
  • Artificial intelligence in healthcare

Background:

  • Osteoarthritis of the knee is a leading cause of disability, often requiring orthopedic intervention.
  • Accurate assessment of lower extremity mechanical alignment using weight-bearing long leg radiographs (LLR) is crucial for knee injury management.
  • Current LLR analysis methods are time-consuming and prone to errors, necessitating improved techniques.

Purpose of the Study:

  • To develop and validate a deep learning (DL) model for fully automated assessment of leg alignment on anterior-posterior LLR.
  • To enhance the reliability and efficiency of leg alignment analysis in orthopedic preoperative planning.
  • To compare the performance of the DL model against orthopedic surgeons in terms of accuracy, reliability, and speed.

Main Methods:

  • A multicentric study developed a DL model using 594 LLRs, employing a detection network and nine specialized networks for comprehensive alignment assessment.
  • The DL model was trained, validated, and tested on distinct institutional datasets.
  • Performance metrics including accuracy, interrater reliability (ICC), and analysis duration were compared between the DL model and three orthopedic surgeons.

Main Results:

  • The DL model demonstrated equivalent alignment accuracy (DL: 0.21 ± 0.18° to 1.06 ± 1.3° vs. OS: 0.21 ± 0.16° to 1.72 ± 1.96°) and interrater reliability (DL ICC: 0.90 ± 0.05 to 1.0 ± 0.0 vs. OS ICC: 0.90 ± 0.03 to 1.0 ± 0.0) compared to orthopedic surgeons.
  • Clinically acceptable accuracy ranged from 53.9%-100% for the DL model versus 30.8%-100% for surgeons.
  • Automated analysis time was significantly reduced (DL: 22 ± 0.6 s vs. OS: 101.7 ± 7 s, p ≤ 0.01).

Conclusions:

  • The developed deep learning algorithm provides an accurate and reliable method for automated leg alignment assessment on LLR.
  • The AI model matches the precision of expert orthopedic surgeons while significantly improving analysis speed and consistency.
  • This research highlights AI's potential to enhance clinical efficiency and decision-making in orthopedic practice.