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

Functional Classification of Joints01:09

Functional Classification of Joints

3.8K
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses  or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An...
3.8K
Uncertainty: Overview00:59

Uncertainty: Overview

526
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
526

You might also read

Related Articles

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

Sort by
Same author

Determining the Mechanical Axis of the Femur from a Standard Antero-posterior Knee Radiograph with Deep Learning.

The Journal of arthroplasty·2026
Same author

Time to Reimplantation: Waiting Longer May Increase the Risk of Subsequent Failure.

The Journal of arthroplasty·2026
Same author

Lumbar, thoracic, and bilateral vertebral body tethering: do surgical outcomes differ?

Spine deformity·2026
Same author

Deep Learning-Based Comparison of Knee Minimum Joint Space Width in Patients With Rheumatoid Arthritis and Osteoarthritis Before Total Knee Arthroplasty.

The Journal of rheumatology·2026
Same author

The Assessment of Coronal Plane Lower-Limb Alignment on Pre- and Postoperative Long-Leg Radiographs Using Deep Learning.

The Journal of arthroplasty·2026
Same author

Calming the Mind to Heal the Hip: Commentary on an article by Boyi Jiang, MD, et al.: "Significant Anxiolytic Effect and Enhanced Recovery Benefits of Perioperative Low-Dose Olanzapine in Patients with Anxiety Undergoing THA. A Randomized Controlled Trial".

The Journal of bone and joint surgery. American volume·2026

Related Experiment Video

Updated: Jun 9, 2025

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

7.9K

Uncertainty-Aware Deep Learning Characterization of Knee Radiographs for Large-Scale Registry Creation.

Kellen L Mulford1, Austin F Grove1, Elizabeth S Kaji1

  • 1Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota.

The Journal of Arthroplasty
|October 30, 2024
PubMed
Summary

An automated pipeline accurately characterizes knee radiographs using a multilabel classifier and object detection. Conformal prediction enhances model transparency by quantifying uncertainty in image analysis.

Keywords:
conformal predictiondeep learningknee radiographymultilabel classificationobject detectionuncertainty quantification

More Related Videos

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

2.0K
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

Related Experiment Videos

Last Updated: Jun 9, 2025

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

7.9K
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

2.0K
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

Area of Science:

  • Medical imaging analysis
  • Machine learning in radiology
  • Orthopedic imaging informatics

Background:

  • Developing an automated image ingestion pipeline for a knee radiography registry is crucial for efficient data management and analysis.
  • Integrating advanced machine learning models, including multilabel image-semantic classifiers and object detection, can significantly enhance the characterization of knee radiographs.
  • Uncertainty quantification using conformal prediction provides essential transparency into model confidence, particularly for critical clinical applications.

Purpose of the Study:

  • To develop and validate an automated image ingestion pipeline for knee radiography.
  • To implement a multilabel image-semantic classifier with uncertainty quantification for knee radiograph analysis.
  • To integrate an object detection model for identifying knee hardware within radiographs.

Main Methods:

  • Annotated 26,000 knee images for presence, laterality, prostheses, and views; annotated surgical construct locations in 11,841 images.
  • Trained an uncertainty-aware multilabel EfficientNet-based classifier for identifying knee laterality, implants, and views, and a domain detection classifier.
  • Developed an object detection model for 20 different knee implants, assessing performance using F1 score, accuracy, sensitivity, and specificity on internal and external datasets.

Main Results:

  • The classification model achieved F1 scores > 0.98 with > 0.99 coverage and 0.97 efficiency using conformal prediction.
  • The domain detection model demonstrated an F1 score of 0.99, with 0.99 precision and recall for knee radiographs.
  • The object detection model achieved a mean average precision of 0.945 across all implant classes, with average precision and recall of 0.950 and 0.886, respectively.

Conclusions:

  • An automated pipeline integrating a multilabel classifier, domain detection, and object detection effectively characterizes knee radiographs.
  • Conformal prediction significantly enhances transparency by providing reliable uncertainty estimates for the classification models.
  • This approach offers a robust solution for automated analysis and data management in knee radiography registries.