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 Experiment Video

Updated: Nov 6, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.3K

2-step deep learning model for landmarks localization in spine radiographs.

Andrea Cina1, Tito Bassani2, Matteo Panico2

  • 1IRCCS Istituto Ortopedico Galeazzi, Via Riccardo Galeazzi 4, 20161, Milan, Italy. andrea.cina@grupposandonato.it.

Scientific Reports
|May 5, 2021
PubMed
Summary

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

Do patients with Degenerative Cervical Myelopathy recover as quickly and as well after surgery as patients suffering from other degenerative disorders of the cervical spine?

Brain & spine·2026
Same author

Scientific award winning paper 2025 of the swiss society of spinal surgery: The impact of Modic changes in recurrent lumbar disc herniation: Persistent Modic type 1 changes represent a high-risk phenotype for early re-herniation.

Brain & spine·2026
Same author

Prediction of Acromial and Scapular Spine Fractures After Reverse Total Shoulder Arthroplasty using Machine Learning: A Retrospective Cohort Study.

Journal of shoulder and elbow surgery·2026
Same author

Uncertainty Quantification of Central Canal Stenosis Deep Learning Classifier From Lumbar Sagittal T2-Weighted MRI.

JOR spine·2026
Same author

Association between vertebral endplate lesions and sagittal spinal alignment: a retrospective imaging analysis in a selected adult patient population.

European radiology experimental·2026
Same author

Outcomes of posterior spinal fusion in AIS: A minimally invasive vs. open technique analysis.

Brain & spine·2026

Deep learning models can now automatically identify vertebral corners in spinal X-rays. This AI tool accurately calculates key radiological parameters, improving measurement reliability in clinical settings.

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate measurement of spinal parameters is crucial for diagnosing and managing thoracolumbar spine conditions.
  • Manual landmark identification and parameter calculation can be subjective and time-consuming.

Purpose of the Study:

  • To develop and validate a Deep Learning model for automatic calculation of vertebral corner coordinates.
  • To derive key radiological parameters, including L1-L5 lordosis, L1-S1 lordosis, and sacral slope, from these landmarks.

Main Methods:

  • A two-step Convolutional Neural Network (CNN) model was trained on 10,193 annotated sagittal thoracolumbar spine X-ray images.
  • Step 1 involved identifying vertebrae and calculating initial landmark coordinates.
  • Step 2 refined localization using cropped vertebra images and geometrical transformations, employing a differentiable spatial to numerical transform (DSNT).

More Related Videos

3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.2K

Related Experiment Videos

Last Updated: Nov 6, 2025

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.3K
3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.2K

Main Results:

  • The model achieved median localization errors of 1.98% (x-coordinate) and 1.68% (y-coordinate) relative to vertebral dimensions.
  • Predicted angles showed high correlation with ground truth, with median absolute errors of 1.84° (L1-L5), 2.43° (L1-S1), and 1.98° (sacral slope).

Conclusions:

  • The developed Deep Learning model accurately calculates vertebral corner coordinates in sagittal spinal X-rays.
  • The model demonstrates significant potential to enhance the reliability and repeatability of radiological measurements for clinical applications.