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

Secondary metabolism in <i>Irpex lacteus</i> (Fr.) Fr.: biosynthetic logic and redox integration.

Critical reviews in biochemistry and molecular biology·2026
Same author

Fragmentation-Driven Optical Darkening of Nanoplastics during Atmospheric Microplastic Photoaging.

Environmental science & technology·2026
Same author

Dynamical Control of Quantum Photon-Photon Interaction with Phase Change Material.

Physical review letters·2026
Same author

Fungal Metabolomics and Genomics: Integrating Multi-Omics to Decipher Function, Diversity, and Application.

Journal of fungi (Basel, Switzerland)·2026
Same author

Ultra-low-loss 180° adiabatic tapered waveguide bend based on higher-order Bézier curve.

Optics letters·2026
Same author

A study on the relationship between mMRC dyspnea scale and both risk stratification and poor prognosis in patients with acute pulmonary embolism.

Frontiers in cardiovascular medicine·2026

Related Experiment Video

Updated: Jan 5, 2026

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

3.3K

Automatic Lumbar Spine Tracking Based on Siamese Convolutional Network.

Yuan Liu1, Xiubao Sui2, Chengwei Liu1

  • 1School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China.

Journal of Digital Imaging
|October 12, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning method for robust lumbar spine tracking in digitalized video fluoroscopic imaging (DVFI). The siamese neural network tracks lumbar vertebrae without needing annotated sequences, improving diagnosis of lumbar instability.

Keywords:
Lumbar trackingRotation angle estimationSiamese convolutional networkSimilarity learningSpine motion

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

715
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.2K

Related Experiment Videos

Last Updated: Jan 5, 2026

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

3.3K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

715
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.2K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Deep Learning

Background:

  • Accurate lumbar spine motion analysis is crucial for diagnosing lumbar instability.
  • Existing digitalized video fluoroscopic imaging (DVFI) tracking methods lack robustness and steadiness.
  • Deep learning shows promise for advanced computer vision tasks.

Purpose of the Study:

  • To develop an automated and robust method for tracking lumbar vertebrae in DVFI sequences.
  • To enable quantitative analysis of spinal motion modes for instability diagnosis.
  • To utilize rotated bounding boxes for precise lumbar spine localization.

Main Methods:

  • Training a full-convolutional siamese neural network offline using transfer learning.
  • Learning a similarity function to compare target and candidate image patches.
  • Employing the learned similarity function for online tracking without adaptation.
  • Evaluating candidate rotated patches around the previous target position.

Main Results:

  • The proposed siamese convolutional network tracker demonstrated steady and robust tracking of lumbar vertebrae (L1-L4).
  • The method successfully tracked lumbar vertebrae without requiring annotated lumbar image sequences.
  • The approach enables precise localization using rotated bounding boxes.

Conclusions:

  • A novel siamese convolutional network-based tracker provides a robust solution for lumbar spine tracking in DVFI.
  • This method eliminates the need for annotated sequences, simplifying the training process.
  • The developed tracker facilitates quantitative analysis for lumbar instability diagnosis.