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

Classification of Bones01:18

Classification of Bones

15.1K
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...
15.1K

You might also read

Related Articles

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

Sort by
Same author

Safety and efficacy of Efbemalenograstim alfa for patients at risk for chemotherapy-induced neutropenia: A Systematic review and Meta-analysis.

Pharmacology·2026
Same author

Current Scenarios and Future Perspectives of Therapeutic Drug Monitoring in India: A Narrative Review.

Cureus·2026
Same author

Safety and Efficacy of Givinostat for Patients with Muscular Dystrophy: A Systematic Review.

Pharmacology·2025
Same author

Ensuring safe and effective pharmacotherapy: The role of "community pharmacology" in attaining "health for all" from the Indian perspective.

Journal of family medicine and primary care·2025
Same author

Impact of Sensitization on School Teachers' Knowledge and Attitudes Towards Adverse Drug Reaction Reporting During National Deworming Day: A Prospective Quasi-Experimental Study.

Cureus·2024
Same author

Oxidative nanopeeling chemistry-based synthesis and photodynamic and photothermal therapeutic applications of plasmonic core-petal nanostructures.

Journal of the American Chemical Society·2014

Related Experiment Video

Updated: Apr 11, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

283

Predicting Osteoporosis Risk from Knee Radiographs and Clinical Features through Deep Learning: A Multimodal

Kaushik Mukhopadhyay1, Alapan Das2, Sundhodeep Roy3

  • 1Department of Pharmacology, All India Institute of Medical Sciences, Kalyani, Nadia, West Bengal, India.

Annals of African Medicine
|April 9, 2026
PubMed
Summary

This study presents a cost-effective deep learning method for osteoporosis screening using knee X-rays and clinical data, offering a viable alternative to DEXA scans in resource-limited areas.

Keywords:
Artificial intelligenceIntelligence artificielledeep learninggenoukneeosteoporosisostéoporoseradiographradiographie

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.7K

Related Experiment Videos

Last Updated: Apr 11, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

283
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.7K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Skeletal Health Diagnostics

Background:

  • Osteoporosis poses a significant global health burden, particularly in developing nations with limited access to dual-energy X-ray absorptiometry (DEXA).
  • Current diagnostic methods like DEXA are often inaccessible or costly in resource-limited settings.
  • There is a critical need for accessible and affordable osteoporosis screening tools.

Purpose of the Study:

  • To develop and evaluate a cost-effective deep learning-based approach for osteoporosis screening.
  • To investigate the efficacy of analyzing knee radiographs combined with clinical data.
  • To provide a viable alternative to DEXA scanning in underserved regions.

Main Methods:

  • A dual-stream deep learning model was developed using 239 knee X-rays and clinical data.
  • Seven convolutional neural network (CNN) architectures were assessed for image classification.
  • The best CNN model's probability scores were integrated with clinical parameters and tested using twelve machine learning algorithms.

Main Results:

  • AlexNet showed superior performance in osteoporosis detection (recall 0.83).
  • The multimodal AdaBoost classifier achieved 72% test accuracy and an AUC of 0.88.
  • The model demonstrated high sensitivity for osteoporosis (0.84) and effective discrimination across BMD categories.

Conclusions:

  • A multimodal approach integrating deep learning radiographic features and clinical data shows promise for osteoporosis screening.
  • This method offers a potential solution for osteoporosis diagnosis in resource-limited settings.
  • The study highlights the feasibility of using AI and readily available X-rays for skeletal health assessment.