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

Deep learning-based spinal canal segmentation of computed tomography image for disease diagnosis: A proposed system for spinal stenosis diagnosis.

Medicine·2024
Same author

["Governor vessel <i>daoqi</i> method of acupuncture" combined with estazolam for insomnia: a randomized controlled trial].

Zhongguo zhen jiu = Chinese acupuncture & moxibustion·2018
Same author

[New progress of study on hematopoietic stem cell transplantation for myelodysplastic syndromes].

Zhongguo shi yan xue ye xue za zhi·2012
Same author

A study on voiding pattern of newborns with hypoxic ischemic encephalopathy.

Urology·2012
Same author

Effects of 1,1,1-trichloroethane on enzymatic activity and bacterial community in anaerobic microcosm form sequencing batch reactors.

Ecotoxicology (London, England)·2012
Same author

Effect of silicon and sodium on thermoelectric properties of thallium-doped lead telluride-based materials.

Nano letters·2012

Related Experiment Video

Updated: Jan 15, 2026

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques
09:29

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques

Published on: August 9, 2024

616

Lumbar region perception segmentation: a novel algorithm for automated vertebral motion parameter measurement.

Zhiyi Zhou1, Qian Zhang1, Ruizhang Zhu2

  • 1Department of Orthopaedic, Wuxi Ninth People's Hospital Affiliated to Soochow University, Wuxi, China.

Quantitative Imaging in Medicine and Surgery
|October 13, 2025
PubMed
Summary

A novel deep learning model, VerSeg-Net, accurately quantifies lumbar spine motion from X-ray images. This automated approach aids in diagnosing lower back pain and planning treatments.

Keywords:
Lumbar spinedeep learningdynamic X-rayimage segmentationvertebral motion

More Related Videos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
13:35

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

11.6K
Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
07:44

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

18.8K

Related Experiment Videos

Last Updated: Jan 15, 2026

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques
09:29

Author Spotlight: Improving Percutaneous Vertebroplasty Surgical Accuracy and Efficiency Through Advanced Puncture Techniques

Published on: August 9, 2024

616
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
13:35

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

11.6K
Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis
07:44

Evaluation of Patients' Posture and Gait Profile After Lumbar Fusion Surgery by Video Rasterstereography and Treadmill Gait Analysis

Published on: March 23, 2019

18.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Spine Biomechanics

Background:

  • Lower back pain often stems from irregular lumbar spine movement.
  • Accurate quantification of vertebral motion is vital for diagnosing spinal disorders.
  • Traditional methods for measuring vertebral motion have limitations in accuracy and efficiency.

Purpose of the Study:

  • To develop an automated deep learning method for segmenting lumbar vertebrae.
  • To measure vertebral motion parameters from dynamic X-ray images.
  • To improve the accuracy and efficiency of lumbar spine motion analysis for clinical diagnosis.

Main Methods:

  • Developed the vertebra segmentation network (VerSeg-Net), a deep learning model.
  • VerSeg-Net integrates region-aware (RA) and adaptive receptive field feature fusion (AFF) modules.
  • Trained and evaluated the model on dynamic X-ray sequences from 50 patients with lumbar disorders.

Main Results:

  • VerSeg-Net achieved a mean Dice Similarity Coefficient (DSC) of 96.2%, outperforming other models.
  • Demonstrated high accuracy in measuring vertebral displacement, rotation, and intervertebral height.
  • Achieved a processing speed of 4.2 ms/frame, significantly faster than U-Net++ (18 ms/frame).

Conclusions:

  • VerSeg-Net provides a reliable and accurate method for analyzing lumbar spine motion.
  • The automated approach can significantly aid in clinical diagnosis of lumbar spine disorders.
  • This technology holds potential for improved treatment planning for patients with lower back pain.