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

Multiscale modeling of vascular adaptation: methodological advances and open challenges.

Journal of biomechanics·2026
Same author

Automatic early detection of pathological signs following primary total hip arthroplasty using radiographs, clinical scores, and comorbidities.

PloS one·2026
Same author

Deep Learning-Based Metal Artifact Reduction in Cardiac Computed Tomography: A Preliminary Study Enabling Radiomic Analysis in Patients with Implantable Defibrillators.

Journal of imaging informatics in medicine·2026
Same author

High-risk carotid plaque detection using a novel radio-morphometric analysis of the carotid bifurcation.

Physics in medicine and biology·2026
Same author

Debridement, Antibiotics and Implant Retention in the Management of Periprosthetic Joint Infection: One-Year Outcomes, Epidemiology and Predictors of Failure.

Journal of clinical medicine·2026
Same author

CardioRadNet: Cardiac mass diagnosis through integrated segmentation and radiomic analysis.

Computer methods and programs in biomedicine·2026

Related Experiment Video

Updated: May 30, 2025

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report
07:45

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report

Published on: August 4, 2022

3.3K

Hip prosthesis failure prediction through radiological deep sequence learning.

Francesco Masciulli1, Anna Corti1, Alessia Lindemann1

  • 1Department of Electronics, Information and Bioengineering, Politecnico di Milano, Via Golgi 39, 20131 Milan, MI, Italy.

International Journal of Medical Informatics
|January 30, 2025
PubMed
Summary
This summary is machine-generated.

This study developed artificial intelligence models using multiple hip X-rays to predict implant failure. The models show potential for improving early detection of hip prosthesis complications.

Keywords:
Artificial intelligenceHip replacementImage classificationTemporal dependency

More Related Videos

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
Imaging of the Microstructural Failure Mechanism in the Human Hip
08:43

Imaging of the Microstructural Failure Mechanism in the Human Hip

Published on: September 29, 2023

759

Related Experiment Videos

Last Updated: May 30, 2025

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report
07:45

The Use of Mixed Reality in Custom-Made Revision Hip Arthroplasty: A First Case Report

Published on: August 4, 2022

3.3K
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
Imaging of the Microstructural Failure Mechanism in the Human Hip
08:43

Imaging of the Microstructural Failure Mechanism in the Human Hip

Published on: September 29, 2023

759

Area of Science:

  • Orthopedic surgery
  • Medical imaging
  • Artificial intelligence

Background:

  • Current deep learning for hip prosthesis failure detection uses single images.
  • Longitudinal data, combining temporal and spatial information, can enhance prediction accuracy.
  • Predicting hip implant failure requires analyzing changes over time.

Purpose of the Study:

  • To develop artificial intelligence models for predicting hip implant failure.
  • To utilize multiple sequential plain radiographs for improved prediction.
  • To leverage longitudinal data for enhanced detection of prosthesis complications.

Main Methods:

  • Developed models using a combination of convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
  • Employed pretrained autoencoders, DenseNets, Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) blocks.
  • Trained and validated models on cohorts of 224 and 14 patients, respectively, using 2-3 sequential radiographs per patient.

Main Results:

  • A 3-image model achieved a positive predictive value (PPV) of 0.966 and an f1 score of 0.933 on the validation set.
  • 2-image models using postoperative and last images yielded PPV of 0.933 and f1 score of 0.918.
  • The 3-image model demonstrated an accuracy of 0.786 on the external validation set.

Conclusions:

  • The developed artificial intelligence models show significant potential for predicting hip prosthesis failure.
  • Utilizing sequential plain radiographs improves the prediction of implant failure.
  • This approach offers a promising tool for early detection and management of hip implant complications.