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: Aug 29, 2025

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement
06:24

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement

Published on: May 11, 2020

8.9K

Data-Driven Detection and Registration of Spine Surgery Instrumentation in Intraoperative Images.

S A Doerr1, A Uneri1, Y Huang1

  • 1Department of Biomedical Engineering, Johns Hopkins University, Baltimore MD.

Proceedings of Spie--The International Society for Optical Engineering
|September 9, 2022
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 authorSame journal

Deep Learning Super-Resolution from Normal to Ultra-High Resolution CT: Conditional Diffusion Model Development and Performance Evaluation in Trabecular Bone Radiomics.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Robot-Assisted Reduction of the Ankle Joint via Multi-Body 3D-2D Image Registration.

IEEE transactions on medical robotics and bionics·2025
Same author

Effects of non-stationary blur on texture biomarkers of bone using Ultra-High Resolution CT.

Proceedings of SPIE--the International Society for Optical Engineering·2024
Same author

Performance assessment of surgical tracking systems based on statistical process control and longitudinal QA.

Computer assisted surgery (Abingdon, England)·2023
Same author

Multi-Stage Adaptive Spline Autofocus (MASA) with a Learned Metric for Deformable Motion Compensation in Interventional Cone-Beam CT.

Proceedings of SPIE--the International Society for Optical Engineering·2023
Same author

Surgical navigation for guidewire placement from intraoperative fluoroscopy in orthopaedic surgery.

Physics in medicine and biology·2023

A deep learning model accurately detects and localizes spine surgery implants, improving 3D-2D registration for enhanced surgical navigation. This AI approach offers robust initialization for known-component registration (KC-Reg) in complex spinal procedures.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neurosurgery

Background:

  • Conventional 3D-2D registration methods face challenges in capture range, model validity, and real-time performance for spine surgery.
  • Accurate 3D localization of spinal implants is crucial for surgical navigation and verification.

Purpose of the Study:

  • To develop a deep convolutional neural network for robust initialization of a known-component registration (KC-Reg) algorithm.
  • To improve the 3D localization of spine surgery implants by combining data-driven speed with model-based accuracy.

Main Methods:

  • A Faster R-CNN architecture was employed to detect and localize spinal pedicle screws in clinical images.
  • Training data were generated using projections from 17 CT scans and screw models; network output provided screw count and 2D poses.
Keywords:
deep learningimage registrationimage-guided surgeryintraoperative imagingspine surgery

More Related Videos

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model
06:18

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Published on: May 24, 2024

2.2K
Intraoperative Ultrasound in Spinal Surgery
05:53

Intraoperative Ultrasound in Spinal Surgery

Published on: August 17, 2022

4.8K

Related Experiment Videos

Last Updated: Aug 29, 2025

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement
06:24

A Spine Robotic-Assisted Navigation System for Pedicle Screw Placement

Published on: May 11, 2020

8.9K
Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model
06:18

Pedicle Screw Placement Using an Augmented Reality Head-Mounted Display in a Porcine Model

Published on: May 24, 2024

2.2K
Intraoperative Ultrasound in Spinal Surgery
05:53

Intraoperative Ultrasound in Spinal Surgery

Published on: August 17, 2022

4.8K
  • The network was tested on two datasets (2,000 images each) with varying anatomical complexity and patient data.

    • Main Results:

    • The pedicle screw detection accuracy was approximately 86.6%, with precision around 92.6%.
    • Screw localization accuracy was within 1.5 mm (median difference), and median intersection-over-union (IOU) exceeded 0.85.
    • The observed accuracy was sufficient for initializing the KC-Reg algorithm within its typical capture range.

    Conclusions:

    • The deep learning approach demonstrates sufficient accuracy for integration into spine surgery implant registration, guidance, and verification systems.
    • This technology has potential applications in surgical navigation, robotic assistance, and large-scale retrospective analysis of implant placement.
    • Future work will focus on multi-view correspondence, 3D localization, screw classification, and expanding the training dataset.