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

X-ray Imaging01:24

X-ray Imaging

6.9K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
6.9K

You might also read

Related Articles

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

Sort by
Same author

LiquidGAN for Handwriting-Based Detection and Severity Classification of Extrapyramidal Symptoms.

Sensors (Basel, Switzerland)·2026
Same author

Vertebra-Level Completeness Analysis in Thoracolumbar Ultrasound Using a YOLO-Based Detection Framework.

Sensors (Basel, Switzerland)·2026
Same author

Edge Extension for Missing Anatomical Features: A Mask-Guided Spatial Diffusion Framework for Ultrasound Scoliosis Image Outpainting.

IEEE journal of biomedical and health informatics·2026
Same author

A meta-analysis of smoking and fracture risk to update the FRAX® tool.

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2026
Same author

Transformer-based hybrid systems to combat BCI illiteracy.

Computers in biology and medicine·2025
Same author

SA<sup>2</sup>Net: Scale-adaptive structure-affinity transformation for spine segmentation from ultrasound volume projection imaging.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025

Related Experiment Video

Updated: Sep 10, 2025

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts
07:56

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

17.7K

Artificial intelligence system for predicting areal bone mineral density from plain X-rays.

Huy Gia Nguyen1,2, Dinh-Tan Nguyen1,2, Thach Son Tran1

  • 1School of Biomedical Engineering, University of Technology Sydney (UTS), City Campus (Broadway) Building 11, Level 10, PO BOX 123, Broadway, NSW, 2007, Australia.

Osteoporosis International : a Journal Established As Result of Cooperation Between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA
|August 27, 2025
PubMed
Summary
This summary is machine-generated.

Artificial intelligence (AI) can now estimate bone density from X-rays, offering a promising alternative to DXA scans for osteoporosis screening. This AI tool accurately predicts fracture risk, especially in underserved regions.

Keywords:
Artificial intelligence; bone mineral densityFractureOsteoporosisPlain radiographyXBMD

More Related Videos

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population
09:02

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

632
Assessment of Bone Fracture Healing Using Micro-Computed Tomography
12:04

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

2.0K

Related Experiment Videos

Last Updated: Sep 10, 2025

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts
07:56

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

17.7K
Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population
09:02

Cortical Bone Assessment Using Ultrasonic Guided Waves: A Reproducibility Study in a Healthy Population

Published on: January 31, 2025

632
Assessment of Bone Fracture Healing Using Micro-Computed Tomography
12:04

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

2.0K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Bone Health and Osteoporosis Research

Background:

  • Dual-energy X-ray absorptiometry (DXA) is the gold standard for bone mineral density assessment but has limited availability in resource-poor settings.
  • Osteoporosis diagnosis and fracture risk prediction are crucial for public health, yet current methods face accessibility challenges.
  • Standard radiographs are widely available and could potentially be leveraged for bone health assessment.

Purpose of the Study:

  • To develop and validate an artificial intelligence (AI) system for estimating areal bone mineral density (aBMD) from standard X-ray images.
  • To assess the AI system's accuracy in predicting bone density compared to DXA.
  • To evaluate the AI system's efficacy in identifying individuals at high risk for fractures.

Main Methods:

  • Utilized data from the Vietnam Osteoporosis Study, including 7060 digital radiographs (pelvis and spine) and DXA measurements from 3783 participants.
  • Developed an ensemble of seven deep-learning models to analyze radiographs and predict bone mineral density, termed "xBMD".
  • Correlated AI-predicted aBMD (xBMD) with DXA-measured aBMD using Pearson's correlation coefficients and evaluated fracture risk prediction accuracy using ROC analysis.

Main Results:

  • The AI system (xBMD) showed strong correlations with DXA-measured aBMD: r = 0.90 at the femoral neck and r = 0.87 at the lumbar spine.
  • High accuracy was observed in identifying individuals at high risk for hip fractures, with AUC values of 0.96 (femoral neck) and 0.97 (lumbar spine).
  • The AI's performance remained consistent across diverse age groups and genders.

Conclusions:

  • AI can accurately predict areal bone mineral density from standard radiographs, demonstrating strong correlations with DXA.
  • The developed AI system effectively identifies individuals at high risk for fractures, showing high AUC values.
  • This AI technology offers a potential, efficient, and accessible alternative to DXA for osteoporosis screening, particularly in resource-limited environments.