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 Experiment Video

Updated: Jan 1, 2026

Augmented Reality Navigation-Guided Core Decompression for Osteonecrosis of Femoral Head
06:17

Augmented Reality Navigation-Guided Core Decompression for Osteonecrosis of Femoral Head

Published on: April 12, 2022

4.1K

Automated detection & classification of knee arthroplasty using deep learning.

Paul H Yi1, Jinchi Wei2, Tae Kyung Kim1

  • 1The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, 601 N Caroline St, Room 4223, Baltimore, MD 21287, United States of America; Radiology Artificial Intelligence Lab (RAIL), Malone Center for Engineering in Healthcare, Johns Hopkins University Whiting School of Engineering, 3400 N Charles St, Baltimore, MD 21218, United States of America.

The Knee
|December 30, 2019
PubMed
Summary

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

Dysfunctional large-scale networks linking PTSD and cognitive impairment.

Journal of psychiatric research·2026
Same author

Relationship between new-onset falls and neuroimaging markers of Alzheimer's disease in the UK Biobank.

Journal of Alzheimer's disease : JAD·2026
Same author

The Perfusion Collateral Impairment Score Provides Complementary Prognostic Information Beyond CTA Collateral Scores and Standard Imaging Predictors in Anterior Circulation Large Vessel Occlusion Stroke.

AJNR. American journal of neuroradiology·2026
Same author

Evaluation for Potential Inequities in Efficacy and Patient Outcomes Following Implementation of a STAT Outpatient Neuroimaging Pathway for Evaluation of Patients with Optic Disc Swelling.

Neuro-ophthalmology (Aeolus Press)·2026
Same author

Disproportionately elevated sulcal index (DESI): An automatically driven index representing disproportionate subarachnoid space enlargement in brain MRI scans.

Brain research bulletin·2026
Same author

Clinical Symptoms of Jugular Venous Outflow Obstruction and Their Modification After Targeted Surgical Treatment.

Neurosurgery practice·2026

A deep learning system (DLS) accurately identifies total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA) on radiographs. This AI can also differentiate between specific TKA models, aiding surgical planning.

Area of Science:

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

Background:

  • Accurate preoperative identification of knee implants is crucial for revision surgery planning.
  • Current methods fail to identify up to 10% of implants before surgery.
  • A deep learning system (DLS) was developed to automate radiographic identification of knee arthroplasty.

Purpose of the Study:

  • To develop and evaluate a DLS for automated radiographic identification of knee arthroplasty.
  • To classify between total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA).
  • To differentiate between two distinct primary TKA models.

Main Methods:

  • A dataset of 237 anteroposterior (AP) knee radiographs (native, TKA, UKA) and 274 AP radiographs (two TKA models) was collected.
Keywords:
Artificial intelligenceDeep learningKnee ArthroplastyKnee prosthesisNeural networks

Related Experiment Videos

Last Updated: Jan 1, 2026

Augmented Reality Navigation-Guided Core Decompression for Osteonecrosis of Femoral Head
06:17

Augmented Reality Navigation-Guided Core Decompression for Osteonecrosis of Femoral Head

Published on: April 12, 2022

4.1K
  • Deep convolutional neural networks (DCNNs) were trained using data augmentation.
  • Performance was assessed using receiver operating characteristic (ROC) curves and area under the curve (AUC); heatmaps visualized decision-making features.

    • Main Results:

    • DCNNs achieved an AUC of 1 for detecting TKA and distinguishing TKA from UKA.
    • An AUC of 1 was achieved when differentiating between the two TKA models.
    • Heatmaps confirmed that DCNNs focused on relevant arthroplasty components and unique design features.

    Conclusions:

    • Deep convolutional neural networks (DCNNs) demonstrate high accuracy in identifying total knee arthroplasty (TKA) and distinguishing between specific arthroplasty designs.
    • This proof-of-concept highlights the potential of DLS in prosthesis identification and complication detection.