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

SST subseasonal-to-seasonal forecasting: A heterogeneous three-path fusion model with wavelet decomposition.

PloS one·2026
Same author

Dual-Channel Inhibition With Rivaroxaban and Aspirin for Thromboprophylaxis in Patients With Long-Term Inferior Vena Cava Filter Implantation: A Two-Center Cohort Study.

Clinical and applied thrombosis/hemostasis : official journal of the International Academy of Clinical and Applied Thrombosis/Hemostasis·2026
Same author

Genetic and biological characterization of a reassortant H3N2 swine influenza virus isolated in China with internal genes from the 2009 pandemic H1N1.

BMC microbiology·2026
Same author

Remote Sensing of Soil Water Retention Signatures Using Sentinel-2 Time-Series and Exponential Decay Fitting Model.

Sensors (Basel, Switzerland)·2026
Same author

A Programmable Multi‑Modal Information Encryption System Based on the Dynamic Wetting Behavior of Liquid Metal.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Self-adaptive hetero-phase superlattices in TaS<sub>2</sub> via layer-resolved 1T-to-1H transformations.

National science review·2026

Related Experiment Video

Updated: May 28, 2025

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model
07:12

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model

Published on: September 28, 2017

8.1K

A fully automated U-net based ROIs localization and bone age assessment method.

Yuzhong Zhao1, Yihao Wang1, Haolei Yuan2

  • 1Institute of Natural Sciences, School of Mathematical Sciences, MOE-LSC & Shanghai National Center for Applied Mathematics (SJTU Center), Shanghai Jiao Tong University, Shanghai 200030, China.

Mathematical Biosciences and Engineering : MBE
|February 14, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces an automated deep learning method for bone age assessment (BAA), improving accuracy and efficiency over traditional techniques. The novel approach precisely locates skeletal regions, enabling reliable biological development evaluation in adolescents.

Keywords:
ROIs localizationU-netbone age assessmentinterpretability

More Related Videos

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.0K
Automated Quantification of Hematopoietic Cell &#8211; Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.5K

Related Experiment Videos

Last Updated: May 28, 2025

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model
07:12

Semiautomated Longitudinal Microcomputed Tomography-based Quantitative Structural Analysis of a Nude Rat Osteoporosis-related Vertebral Fracture Model

Published on: September 28, 2017

8.1K
In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

3.0K
Automated Quantification of Hematopoietic Cell &#8211; Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

11.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Pediatric Endocrinology

Background:

  • Bone age assessment (BAA) is crucial for evaluating adolescent biological development.
  • Traditional methods like the Tanner Whitehouse (TW) require manual region of interest (ROI) extraction, which is time-consuming and subjective.
  • Existing automated methods may lack interpretability or struggle with capturing both local and global skeletal features.

Purpose of the Study:

  • To develop a fully automated deep learning system for precise ROI localization and accurate bone age prediction.
  • To integrate the strengths of ROI-based and global feature-based BAA methods into a single, interpretable model.
  • To validate the proposed method's performance against established datasets and clinical standards.

Main Methods:

  • A U-net-based deep learning architecture was employed for semantic segmentation to achieve automatic and precise localization of skeletal ROIs.
  • An InceptionResNetV2 network was utilized for robust feature extraction from both localized ROIs and the entire hand radiograph.
  • The BAA model synergistically combines localized ROI features with global image features for enhanced prediction accuracy.

Main Results:

  • The automated ROI localization achieved a high precision of 99.1% on the public RSNA dataset.
  • The BAA model demonstrated a low mean absolute error (MAE): 0.38 years (males) and 0.45 years (females) on the RSNA dataset.
  • Comparable MAE values were observed on an in-house dataset (0.41 years for males, 0.44 years for females), confirming the method's generalizability and accuracy.

Conclusions:

  • The proposed deep learning method offers a highly accurate and automated solution for bone age assessment.
  • This approach enhances efficiency by eliminating manual ROI extraction and provides interpretable results.
  • The validated performance suggests significant potential for clinical integration in pediatric endocrinology and developmental assessment.