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

Sharpness matters: Higher image resolution improves generalization and explainability in chest X-ray classification.

Scientific reports·2026
Same author

Distal Phalangeal Physeal Closure Preceding Ossification of the Thumb Adductor Sesamoid: A Case Report.

Journal of orthopaedic case reports·2026
Same author

Radiomics in musculoskeletal imaging: what is its role in the era of deep learning?

Skeletal radiology·2026
Same author

The impact of experience on radiology report uncertainty for early-career musculoskeletal radiologists.

Skeletal radiology·2026
Same author

Diffusion Tensor Imaging Detects Functional and Structural Alterations in Post-Traumatic Distal Tibial Physeal Bars: A Preliminary Study.

Journal of pediatric orthopedics·2026
Same author

Enhancing automated fracture detection in paediatric wrist X-rays with paired and unpaired cast suppression methods.

International journal of computer assisted radiology and surgery·2026

Related Experiment Video

Updated: Oct 3, 2025

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure
15:18

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Published on: July 30, 2009

18.3K

Inferring pediatric knee skeletal maturity from MRI using deep learning.

John R Zech1, Giuseppe Carotenuto2, Diego Jaramillo3

  • 1Department of Radiology, Columbia University Irving Medical Center/New York-Presbyterian Hospital, 622 W 168th St., NY, 10032, New York, USA. jrz2111@columbia.edu.

Skeletal Radiology
|February 20, 2022
PubMed
Summary

A deep learning model can accurately assess skeletal maturity from knee MRI scans, matching radiologist performance. This automated method provides crucial skeletal age information efficiently during routine knee MRIs for children.

Keywords:
Artificial intelligenceBone ageDeep learningKnee MRIMachine learningSkeletal maturity

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography
07:33

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

582

Related Experiment Videos

Last Updated: Oct 3, 2025

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure
15:18

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Published on: July 30, 2009

18.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography
07:33

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

582

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Pediatric Radiology

Background:

  • Knee MRI is common for pediatric trauma evaluation.
  • Skeletal maturity assessment is often not performed concurrently.
  • Accurate skeletal age is vital for treatment planning.

Purpose of the Study:

  • To develop and validate a deep learning model for automated skeletal maturity assessment from knee MRI.
  • To compare the model's performance against radiology residents.

Main Methods:

  • Retrospective analysis of 894 knee MRIs from 783 patients.
  • Deep learning model (LSTM with DenseNet-121 features) trained on T1/PD coronal and sagittal sequences.
  • Comparison with bone age assessments by two radiology residents using a reference atlas.

Main Results:

  • The deep learning model's prediction error for chronological age was not significantly different from that of radiology residents (MSE 1.30 vs. 0.99).
  • High Pearson correlation (0.96) observed between model and resident predictions.
  • The model achieved comparable accuracy in significantly less time than human experts.

Conclusions:

  • Deep learning effectively infers skeletal maturity from knee MRI sequences.
  • This automated approach offers a valuable tool for routine skeletal age evaluation in pediatric patients.
  • Potential to enhance diagnostic efficiency and clinical decision-making in pediatric orthopedics.