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

Ultrasound Slice-to-Volume Registration via Artifact-Suppressed Ultra-Feature Learning.

IEEE journal of biomedical and health informatics·2026
Same author

Three-dimensional Liver Respiratory Motion Tracking in Ultrasound Images via Vascular Structural Projection Optimization and Multi-path Constrained Estimation.

Ultrasound in medicine & biology·2026
Same author

Robot-Assisted Osteotomy and Reconstruction with AR Guidance in Maxillofacial Reconstructive Surgery.

Cyborg and bionic systems (Washington, D.C.)·2026
Same author

Point-Supervised Coronary Semantic Segmentation in X-Ray Angiographic Images.

IEEE journal of biomedical and health informatics·2026
Same author

Multimodal hybrid mamba classification model for tumor pathological grade prediction using magnetic resonance images.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Iterative joint learning integrating temporal and geometric information for vessel segmentation in X-ray coronary angiography.

Medical physics·2026

Related Experiment Video

Updated: Oct 9, 2025

Intravital Longitudinal Imaging of Vascular Dynamics in the Calvarial Bone Marrow
10:49

Intravital Longitudinal Imaging of Vascular Dynamics in the Calvarial Bone Marrow

Published on: April 11, 2025

583

Skull Segmentation from CBCT Images via Voxel-Based Rendering.

Qin Liu1, Chunfeng Lian1, Deqiang Xiao1

  • 1Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Machine Learning in Medical Imaging. MLMI (Workshop)
|December 20, 2021
PubMed
Summary
This summary is machine-generated.

A new VR-U-Net method improves skull segmentation in 3D cone-beam CT images. This approach enhances accuracy and efficiency, addressing limitations of current deep learning models for craniomaxillofacial applications.

Keywords:
CBCT imageHigh-resolution segmentationVoxelRend

More Related Videos

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.3K
Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
08:41

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

8.7K

Related Experiment Videos

Last Updated: Oct 9, 2025

Intravital Longitudinal Imaging of Vascular Dynamics in the Calvarial Bone Marrow
10:49

Intravital Longitudinal Imaging of Vascular Dynamics in the Calvarial Bone Marrow

Published on: April 11, 2025

583
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.3K
Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning
08:41

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

8.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Accurate skull segmentation in 3D cone-beam CT (CBCT) is vital for diagnosing and planning treatments for craniomaxillofacial (CMF) deformities.
  • Current deep learning methods, while powerful, face challenges with large volumetric image sizes and limited GPU memory, often sacrificing accuracy through down-sampling or patch cropping.

Purpose of the Study:

  • To develop a novel, memory-efficient network for high-quality skull segmentation in 3D CBCT images.
  • To overcome the computational inefficiencies of traditional methods operating on regular grids.

Main Methods:

  • Proposed a novel VoxelRend-based network (VR-U-Net) combining a memory-efficient 3D U-Net variant with a voxel-based rendering module.
  • The VoxelRend module refines local details using predictions on non-regular grids, operating on coarse feature maps for efficiency.

Main Results:

  • The VR-U-Net achieved significant improvements in segmentation accuracy.
  • Demonstrated substantial memory savings compared to existing methods.
  • Produced high-quality skull segmentation results on a high-resolution CBCT dataset.

Conclusions:

  • The proposed VR-U-Net offers a practical and memory-efficient solution for skull segmentation in 3D CBCT.
  • Highlights the potential of voxel-based rendering for improving volumetric image segmentation accuracy and efficiency.