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

A-eye: Automated 3D MRI segmentation and morphometric feature extraction for eye and orbit atlas construction.

PloS one·2026
Same author

Interdisciplinary consensus statements on imaging of scaphoid fractures.

European radiology·2026
Same author

Standardized maps - an emerging approach to leverage quantitative information in knee imaging.

Osteoarthritis imaging·2026
Same author

Editorial for the Special -Issue on Biomechanics and Imaging.

Osteoarthritis imaging·2026
Same author

Imaging of cartilage, meniscus, and beyond: Role of Magnetic Resonance Imaging (MRI) and Computed Tomography (CT).

Osteoarthritis imaging·2026
Same author

Musculoskeletal Computed Tomography Imaging: A 30-Year Perspective.

Seminars in musculoskeletal radiology·2026

Related Experiment Video

Updated: Jun 29, 2025

Software-Assisted Quantitative Measurement of Osteoarthritic Subchondral Bone Thickness
08:52

Software-Assisted Quantitative Measurement of Osteoarthritic Subchondral Bone Thickness

Published on: March 18, 2022

3.0K

Detection and Grading of Radiographic Hand Osteoarthritis Using an Automated Machine Learning Platform.

Leo Caratsch1,2,3, Christian Lechtenboehmer1,2,3,4, Matteo Caorsi3

  • 1Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.

ACR Open Rheumatology
|April 5, 2024
PubMed
Summary
This summary is machine-generated.

Automated machine learning (autoML) platforms enable automated detection of distal hand osteoarthritis (OA). While feasible and usable, grading OA severity using this model remains challenging for clinical trials.

More Related Videos

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model
07:32

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model

Published on: May 6, 2020

12.1K
Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis
06:31

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis

Published on: October 6, 2023

2.1K

Related Experiment Videos

Last Updated: Jun 29, 2025

Software-Assisted Quantitative Measurement of Osteoarthritic Subchondral Bone Thickness
08:52

Software-Assisted Quantitative Measurement of Osteoarthritic Subchondral Bone Thickness

Published on: March 18, 2022

3.0K
Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model
07:32

Standardized Histomorphometric Evaluation of Osteoarthritis in a Surgical Mouse Model

Published on: May 6, 2020

12.1K
Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis
06:31

Author Spotlight: Enhancing Rheumatoid Arthritis Research Through HR-pQCT Imaging Analysis

Published on: October 6, 2023

2.1K

Area of Science:

  • Artificial Intelligence in Medicine
  • Radiology and Medical Imaging
  • Rheumatology and Musculoskeletal Diseases

Background:

  • Automated machine learning (autoML) platforms empower healthcare professionals to develop machine learning (ML) algorithms tailored to clinical needs.
  • Distal hand osteoarthritis (OA) diagnosis and grading can benefit from advanced computational tools.

Purpose of the Study:

  • To develop and evaluate an autoML model for the automated detection and grading of distal interphalangeal osteoarthritis (DIP-OA).
  • To assess the feasibility and usability of an autoML-driven system for radiographic OA assessment.

Main Methods:

  • Utilized a large dataset of 13,690 hand radiographs from the Swiss Cohort of Quality Management (SCQM) and external data.
  • Employed the Giotto (Learn to Forecast [L2F]) autoML platform to train convolutional neural networks for DIP joint extraction and Kellgren/Lawrence (K/L) score classification.
  • Generated heatmaps and evaluated user experience via a web application with rheumatologists and radiologists.

Main Results:

  • The model achieved 79% sensitivity and 86% specificity for DIP-OA detection.
  • Overall accuracy for grading K/L scores was 75% (κ = 0.76), with varying accuracy across different OA severity levels.
  • Rheumatologists showed moderate to high demand for automated DIP-OA scoring, while radiologists favored heatmap visualization.

Conclusions:

  • AutoML platforms offer a viable pathway for developing end-to-end clinical ML algorithms.
  • Automated radiographic detection of DIP-OA is demonstrated as feasible and usable.
  • Accurate grading of individual K/L scores for clinical trial purposes presents ongoing challenges.