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

Protocol for Novel Perioperative Optimization of Obese Osteoarthritic Patients pending Total Knee Replacement with glucagon-like peptide-1 receptor agonist (NPO-OOPS-TKR) : a pilot randomized controlled trial.

Bone & joint open·2026
Same author

Sustained Hypoxia-Inducible Factor 1-Alpha Accumulation Disrupts the Articular Niche to Promote Osteoarthritis Pathogenesis.

Aging cell·2026
Same author

CT-based 3D bone shape modes are associated with clinically meaningful functional improvement after total knee arthroplasty.

Osteoarthritis and cartilage open·2026
Same author

Unconventional auricular reconstruction using controlled scaffold buckling and chondrogenic cocktail containing muscle-derived cells.

Bioactive materials·2026
Same author

Microfluidics-Enabled Nanoparticle for Multiscale Synergetic Osteoarthritis Therapy.

ACS nano·2026
Same author

Patient perceptions of remotely-delivered exercise services for osteoarthritis: A cross-sectional study in Hong Kong.

Osteoarthritis and cartilage open·2026

Related Experiment Video

Updated: Jan 18, 2026

A Reproducible Cartilage Impact Model to Generate Post-Traumatic Osteoarthritis in the Rabbit
08:42

A Reproducible Cartilage Impact Model to Generate Post-Traumatic Osteoarthritis in the Rabbit

Published on: November 21, 2023

1.8K

Diffusion model-empowered patella shape analysis predicts knee osteoarthritis outcomes.

Sing-Hin Lau1, Lok-Chun Chan1, Tianshu Jiang1

  • 1Department of Biomedical Engineering, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China.

Osteoarthritis and Cartilage Open
|September 8, 2025
PubMed
Summary

Artificial intelligence using diffusion models enhances knee osteoarthritis prognosis by analyzing patella shape changes on radiographs. This AI approach improves prediction of disease onset and knee replacement risk.

Keywords:
Deep learningDiffusion modelGenerative modelLateral knee radiographMorphologyPatella

More Related Videos

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis
06:28

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis

Published on: September 2, 2025

1.1K
Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis
07:06

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

5.6K

Related Experiment Videos

Last Updated: Jan 18, 2026

A Reproducible Cartilage Impact Model to Generate Post-Traumatic Osteoarthritis in the Rabbit
08:42

A Reproducible Cartilage Impact Model to Generate Post-Traumatic Osteoarthritis in the Rabbit

Published on: November 21, 2023

1.8K
Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis
06:28

Anterior Cruciate Ligament Transection and Synovial Fluid Lavage in a Rodent Model to Study Joint Inflammation and Posttraumatic Osteoarthritis

Published on: September 2, 2025

1.1K
Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis
07:06

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

5.6K

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Osteoarthritis Research

Background:

  • Knee osteoarthritis (OA) poses a significant health burden, necessitating improved prognostic tools.
  • Current radiographic assessments have limitations in predicting OA progression.
  • Longitudinal analysis of anatomical changes offers potential for enhanced prognostication.

Purpose of the Study:

  • To develop and validate an AI pipeline for enhanced knee OA prognostic assessment.
  • To leverage diffusion models for analyzing longitudinal patella shape changes on knee radiographs.
  • To improve prediction of OA onset and end-stage disease, including knee replacement risk.

Main Methods:

  • Retrospective analysis of 2,913 participants' knee radiographs from the Multicenter Osteoarthritis Study.
  • AI pipeline involving automatic patella shape segmentation and diffusion models to predict 60-month shape trajectories.
  • Development of the Synthetic Patella Shape Incorporated Convolutional Neural Network (SynPatNet) for outcome prediction.

Main Results:

  • The diffusion model generated synthetic patella shapes predicting deformations and osteophyte development.
  • SynPatNet significantly improved prediction of patellofemoral OA onset (AUC 0.909) and knee replacement (AUC 0.823) compared to baseline models.
  • Integrating SynPatNet with Kellgren-Lawrence grade further enhanced knee replacement prediction (AUC 0.838).

Conclusions:

  • Generative diffusion modeling of patellar morphology offers valuable prognostic information for knee OA.
  • This AI-driven approach complements conventional metrics, substantially improving knee OA prognostication.
  • The developed pipeline shows potential for earlier and more accurate prediction of OA progression and treatment needs.