Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Dec 22, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Classifying shoulder implants in X-ray images using deep learning.

Gregor Urban¹, Saman Porhemmat¹, Maya Stark²

¹University of California, Irvine School of Information and Computer Sciences, Irvine, CA, USA.

Computational and Structural Biotechnology Journal

|May 6, 2020

Summary

This summary is machine-generated.

Related Concept Videos

Classification of Bones

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...

You might also read

Related Articles

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

Sort by

Same author

Conserved trans-regulatory logic and evolving cis-modules drive the diversification of inducible diterpenoid biosynthetic gene clusters across the Oryzoideae.

Plant & cell physiology·2026

Same author

Genomic Basis of Lifestyle Divergence in Rice-Associated <i>Burkholderia</i>: From Pathogenesis to Plant Growth Promotion.

International journal of molecular sciences·2026

Same author

Rice Genotype-Dependent Phyllosphere Microbiome Assembly and Isolation of Antagonistic <i>Burkholderia</i> for Sheath Blight Biocontrol.

International journal of molecular sciences·2026

Same author

Identification of essential residues for the biosynthesis of momilactone intermediate diterpene in wild rice Oryza officinalis.

The Biochemical journal·2026

Same author

Structural characterization of the native oligomerization mode of MvaT proteins in <i>Pseudomonas</i>.

Microbiology spectrum·2026

Same author

Preoperative antibiotic prophylaxis in primary shoulder arthroplasty patients: a systematic review.

JSES international·2026

Same journal

From Pixels to Patterns: A Multidimensional Framework to Decode Cytoskeletal Organization.

Computational and structural biotechnology journal·2026

Same journal

A Large Concept Model for Mechanistic Simulation of Disease Trajectories: A Hypothesis-Generating Exemplar for Pediatric Acute Lymphoblastic Leukemia.

Computational and structural biotechnology journal·2026

Same journal

Adversarial Sequence Mutations in AlphaFold and ESMFold Reveal Nonphysical Structural Invariance, Confidence Failures, and Concerns for Protein Design.

Computational and structural biotechnology journal·2026

Same journal

High-Throughput Prediction of Protein-Protein Interactions Uncovers Hidden Molecular Networks in Biosynthetic Gene Clusters.

Computational and structural biotechnology journal·2026

Same journal

A Region-Aware Structured Framework Improves Prediction of Gene Expression from DNA Methylation.

Computational and structural biotechnology journal·2026

Same journal

Ensemble Machine Learning Approaches Predict Survival in Lower-Grade Glioma Based on Glycosphingolipid Gene Expression and Metabolic Modeling.

Computational and structural biotechnology journal·2026

See all related articles

Accurately identifying shoulder implant models in X-ray images is crucial for revision surgery. Deep learning models, pre-trained on diverse datasets, significantly outperform traditional methods in classifying total shoulder arthroplasty (TSA) prostheses.

Area of Science:

Orthopedic Surgery
Medical Imaging
Artificial Intelligence

Background:

Total Shoulder Arthroplasty (TSA) prostheses may require servicing or replacement years after implantation.
Identifying the exact model and manufacturer of a TSA prosthesis can be challenging, especially when patient history or records are unavailable.
Accurate implant identification is critical for selecting appropriate surgical equipment and planning revision procedures.

Purpose of the Study:

To develop and evaluate a novel method for automatically classifying shoulder implant models using X-ray images.
To compare the performance of deep learning models against traditional classifiers for implant identification.
To assess the impact of pre-training on out-of-domain datasets for improving classification accuracy.

Main Methods:

Keywords:

Computer vision Deep learning Orthopedics Total shoulder arthroplasty X-ray imaging

Related Experiment Videos

Last Updated: Dec 22, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Utilized deep convolutional neural networks (CNNs) for automatic classification of shoulder implants in X-ray images.
Compared CNN performance against alternative classifiers including random forests and gradient boosting.
Employed 10-fold cross-validation on a dataset of X-ray images from 4 manufacturers and 16 distinct implant models.

Main Results:

Deep learning models, when pre-trained on out-of-domain data like ImageNet, significantly outperformed other classifiers.
CNNs achieved approximately 80% accuracy in identifying the correct manufacturer of shoulder implants.
Traditional classifiers (random forests, gradient boosting) achieved 56% accuracy or less.

Conclusions:

Deep learning, particularly CNNs pre-trained on diverse datasets, offers a highly effective solution for automated shoulder implant classification from X-ray images.
This AI-driven approach demonstrates superior performance compared to conventional methods, enhancing diagnostic capabilities in orthopedic surgery.
The methodology shows promise for clinical application and potential adaptation to classifying other types of orthopedic prostheses.