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

Peritoneal strumosis and the role of imaging in the diagnostic workup: A case report.

Radiology case reports·2026
Same author

Near-inertial internal waves funneled into Taylor caps shape seamount tops, with implications for biodiversity in the deep ocean.

Science advances·2026
Same author

U-Net-based reactive center loop-identifier for serpins.

Bioinformatics advances·2026
Same author

Temporal Effects on Intra-operative Bacterial Contamination of Surgical Gloves in Non-Infection Orthopaedic Trauma Cases.

Journal of orthopaedic trauma·2026
Same author

Epithelioid hemangioendothelioma of the inferior vena cava: A case report.

Radiology case reports·2026
Same author

Proximal Junctional Kyphosis Prevention in Adult Spinal Deformity Surgery: A Technical Review of Tethering and Adjunctive Strategies.

Operative neurosurgery (Hagerstown, Md.)·2026

Related Experiment Video

Updated: Mar 25, 2026

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography
06:09

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography

Published on: March 12, 2021

3.9K

Automated Shoulder Radiograph Quality Review to Support Efficient Workflow in the Emergency Department: The SQUIRE

Anthony Taolun Wu1,2,3, Arya Amirhekmat4, Nathan H Choi5

  • 1Department of Computer Science, University of California, Irvine, Irvine, CA, USA. wuat2@hs.uci.edu.

Journal of Imaging Informatics in Medicine
|March 24, 2026
PubMed
Summary

This study developed SQUIRE, an AI tool to automatically assess shoulder radiograph quality, reducing repeat imaging and radiation exposure. The system achieved high accuracy, improving diagnostic consistency and patient care.

Keywords:
Ensemble modelingImage quality assessmentMachine learningPublic datasetShoulder radiographsWorkflow optimization

More Related Videos

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

2.1K
Image Acquisition using Portable Sonography for Emergency Airway Management
07:31

Image Acquisition using Portable Sonography for Emergency Airway Management

Published on: September 28, 2022

3.1K

Related Experiment Videos

Last Updated: Mar 25, 2026

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography
06:09

Measuring 3D In-vivo Shoulder Kinematics using Biplanar Videoradiography

Published on: March 12, 2021

3.9K
Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
05:18

Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant

Published on: October 6, 2023

2.1K
Image Acquisition using Portable Sonography for Emergency Airway Management
07:31

Image Acquisition using Portable Sonography for Emergency Airway Management

Published on: September 28, 2022

3.1K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Suboptimal shoulder radiographs lead to increased radiation exposure, workflow delays, and costs due to repeat imaging.
  • Poor patient positioning and anatomy cutoff are primary reasons for repeat shoulder X-rays.
  • There is a need for automated tools to ensure consistent and high-quality radiographic image acquisition.

Purpose of the Study:

  • To develop and validate an automated system for assessing shoulder radiograph quality in real-world conditions.
  • To create and release the first publicly available expert-verified dataset of shoulder radiograph quality annotations.
  • To establish a benchmark for low-latency, point-of-care radiographic quality assessment.

Main Methods:

  • Expert quality annotations were created for 732 shoulder radiographs from the MURA dataset, focusing on Grashey and axillary views.
  • A real-time heterogeneous ensemble model, SQUIRE (SHoulder QUality Image REviewer), was developed using lightweight architectures.
  • The model was trained and validated using five-fold cross-validation, with external validation on a separate dataset.

Main Results:

  • SQUIRE achieved high internal performance with an average F1 score of 0.943 and accuracy of 0.941.
  • External validation showed robust discrimination in zero-shot (ROC AUC=0.82) and few-shot (ROC AUC=0.85) settings despite domain shift.
  • The study demonstrated the effectiveness of domain-specialized, lightweight architectures for radiographic quality assessment.

Conclusions:

  • SQUIRE provides an effective automated solution for assessing shoulder radiograph quality, addressing a significant clinical challenge.
  • The open release of annotations and code facilitates reproducible research and development in radiographic quality assessment.
  • This work contributes to improving imaging consistency, reducing patient radiation exposure, and optimizing healthcare workflows.