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

CD11b-Based Pre-Targeted SPECT/CT Imaging Allows for the Detection of Inflammation in Aortic Aneurysm.

Journal of inflammation research·2022
Same author

Coronary Artery Disease and Atrial Fibrillation: A Bidirectional Mendelian Randomization Study.

Journal of cardiovascular development and disease·2022
Same author

Mini-Invasive Bentall Procedure Performed <i>via</i> a Right Anterior Thoracotomy Approach With a Costochondral Cartilage Sparing.

Frontiers in cardiovascular medicine·2022
Same author

Captopril alleviates glucocorticoid-induced osteonecrosis of the femoral head by mediating the ACE2/ Ang-(1-7)/Mas receptor cascade.

European journal of pharmacology·2022
Same author

Gender differences in the dissection properties of ascending thoracic aortic aneurysms.

Interactive cardiovascular and thoracic surgery·2022
Same author

High-energy and low-cost membrane-free chlorine flow battery.

Nature communications·2022
Same journal

Clinical and radiological factors associated with recurrent shoulder dislocation after conservative treatment of traumatic primary anterior shoulder dislocation.

Journal of orthopaedic surgery and research·2026
Same journal

Preoperative MRI and clinical indicators for predicting meniscal repairability: a machine learning-based study.

Journal of orthopaedic surgery and research·2026
Same journal

Pelvic tilt ratio correlates with distinct spinopelvic muscle patterns in adult spinal deformity with sagittal imbalance: a retrospective cohort study.

Journal of orthopaedic surgery and research·2026
Same journal

Novel artificial transverse atlantal ligament reconstruction for atlantoaxial instability: a finite element analysis.

Journal of orthopaedic surgery and research·2026
Same journal

Medial wall/arthroscopy/posterior facet (MAP) strategy for displaced intra-articular calcaneal fractures: evaluation of a novel minimally invasive protocol in a retrospective comparative cohort.

Journal of orthopaedic surgery and research·2026
Same journal

Tumor survivors' musculoskeletal health assessment: advances in imaging biomarkers for cancer treatment-related sequelae.

Journal of orthopaedic surgery and research·2026
See all related articles

Related Experiment Video

Updated: Jun 24, 2025

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study
07:51

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

16.8K

Deep learning-based automatic measurement system for patellar height: a multicenter retrospective study.

Zeyu Liu1, Jiangjiang Wu2, Xu Gao3

  • 1Department of Bone and Joint Surgery, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi, China.

Journal of Orthopaedic Surgery and Research
|June 1, 2024
PubMed
Summary
This summary is machine-generated.

A new deep learning system automatically measures patellar height from knee X-rays, offering a faster and more consistent alternative to manual methods. This AI tool shows high accuracy and generalizability for clinical use in knee condition assessment.

Keywords:
Deep learningKeypoint detectionPatellar height indexRadiographic imaging

More Related Videos

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
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

Related Experiment Videos

Last Updated: Jun 24, 2025

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study
07:51

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

16.8K
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
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

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Orthopedics

Background:

  • Patellar height index is crucial for knee assessment but manual measurements are time-consuming and variable.
  • Existing methods for measuring patellar height lack efficiency and consistency.

Purpose of the Study:

  • To develop and evaluate a deep learning-based automatic measurement system for patellar height index.
  • To assess the system's performance, accuracy, and generalizability in measuring patellar height.

Main Methods:

  • A dataset of 3,923 lateral knee X-ray images was curated from three tertiary hospitals.
  • A deep learning model utilizing High-Resolution Network (HRNet) architecture was trained on manually labeled key points.
  • Performance was evaluated using metrics like Root Mean Square Error (RMSE), Object Keypoint Similarity (OKS), and Percentage of Correct Keypoint (PCK).

Main Results:

  • The HRNet model demonstrated excellent performance in keypoint detection.
  • The pose_hrnet_w48 model achieved high accuracy with strong consistency (ICC, 0.809-0.885) in calculating the Insall-Salvati index compared to manual measurements.
  • The system showed significant accuracy and generalizability for practical applications.

Conclusions:

  • A deep learning system for automatic patellar height measurement was successfully developed.
  • The system offers accuracy comparable to experienced radiologists and robust generalizability.
  • This AI tool can aid in early knee disease assessment, treatment, and post-operative monitoring.