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

Review of the Research Progress of Human Brain Oxygen Extraction Fraction by Magnetic Resonance Imaging.

Oxidative medicine and cellular longevity·2022
Same author

Dissipative soliton generation and real-time dynamics in microresonator-filtered fiber lasers.

Light, science & applications·2022
Same author

Gastric cancer-derived exosomal miR-519a-3p promotes liver metastasis by inducing intrahepatic M2-like macrophage-mediated angiogenesis.

Journal of experimental & clinical cancer research : CR·2022
Same author

Effects of different modes of exercise on skeletal muscle mass and function and IGF-1 signaling during early aging in mice.

The Journal of experimental biology·2022
Same author

Optimal Control of False Information Clarification System under Major Emergencies Based on Differential Game Theory.

Computational intelligence and neuroscience·2022
Same author

Ionothermal Synthesis of Fully Conjugated Covalent Organic Frameworks for High-Capacity and Ultrastable Potassium-Ion Batteries.

Advanced materials (Deerfield Beach, Fla.)·2022

Related Experiment Video

Updated: Oct 10, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

258

Accurate Instance Segmentation in Pediatric Elbow Radiographs.

Dixiao Wei1, Qiongshui Wu1, Xianpei Wang1

  • 1Electronic Information School, Wuhan University, Wuhan 430072, China.

Sensors (Basel, Switzerland)
|December 10, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a new AI pipeline for segmenting pediatric elbow bones in radiographs. The method uses oriented bounding boxes and a fusion network to accurately identify and separate individual bones, improving diagnostic support.

Keywords:
bone extractionconvolutional networkinstance segmentationpediatric elbowradiography

More Related Videos

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

3.3K
Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
09:36

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

9.5K

Related Experiment Videos

Last Updated: Oct 10, 2025

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects
08:39

Longitudinal Micro-Computed Tomography Image Analysis for User-Defined Region of Interest in Critical-Sized Bone Defects

Published on: June 24, 2025

258
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

3.3K
Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin
09:36

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

9.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Orthopedics

Background:

  • Radiography is crucial for diagnosing pediatric fractures.
  • Interpreting pediatric elbow radiographs is challenging for AI due to bone overlap and orientation.
  • Bone instance segmentation is vital for automated radiograph analysis.

Purpose of the Study:

  • To develop an AI pipeline for accurate pediatric elbow bone instance segmentation.
  • To address challenges posed by arbitrary bone directions and overlapping structures.
  • To enhance the performance of automatic radiograph interpretation.

Main Methods:

  • A detection-segmentation pipeline utilizing Faster R-CNN architecture.
  • Incorporation of Oriented Bounding Boxes (OBB) for improved localization accuracy.
  • A Global-Local Fusion Segmentation Network to integrate contextual information for overlapped bones.

Main Results:

  • The proposed pipeline significantly enhances bone extraction performance.
  • Experiments conducted on a dataset of 1274 pediatric elbow radiographs.
  • Both qualitative and quantitative results demonstrate the network's effectiveness.

Conclusions:

  • The developed methodology shows strong potential for deep learning in radiography bone instance segmentation.
  • The pipeline effectively tackles challenges in pediatric elbow bone segmentation.
  • This approach can aid in more accurate and efficient diagnosis of pediatric elbow abnormalities.