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

Tagging and Fusion Proteins01:24

Tagging and Fusion Proteins

6.8K
Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...
6.8K
Force Classification01:22

Force Classification

1.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

CARL: A Framework for Equivariant Image Registration.

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition·2026
Same authorSame journal

Inverse Consistency by Construction for Multistep Deep Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same authorSame journal

LiftReg: Limited Angle 2D/3D Deformable Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Erratum for: Prediction of Lobar Emphysema Progression with a CT-Based Foundational Model.

Radiology·2026
Same author

uniGradICON: A Foundation Model for Medical Image Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Prediction of Lobar Emphysema Progression with a CT-Based Foundational Model.

Radiology·2026

Related Experiment Video

Updated: Aug 28, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485

VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation.

Zhipeng Ding1, Xu Han1, Marc Niethammer1,2

  • 1Department of Computer Science, UNC Chapel Hill, USA.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|September 15, 2022
PubMed
Summary

VoteNet, a deep learning (DL) strategy, improves multi-atlas segmentation (MAS) by selecting reliable atlases for fusion. This DL-based approach enhances brain MRI segmentation accuracy over traditional methods and direct DL segmentation.

More Related Videos

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

2.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.2K

Related Experiment Videos

Last Updated: Aug 28, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485
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

2.9K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.2K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Deep learning (DL) excels in medical image segmentation due to its speed and accuracy.
  • Traditional multi-atlas segmentation (MAS) methods are computationally intensive and generally less accurate than DL.
  • Existing DL segmentation approaches often outperform MAS, highlighting the need for improved fusion strategies.

Purpose of the Study:

  • To introduce VoteNet, a novel deep learning-based label fusion strategy for multi-atlas segmentation.
  • To enhance the performance of multi-atlas segmentation by intelligently selecting and fusing atlas labels.
  • To address the computational limitations of traditional MAS methods through a DL-based approach.

Main Methods:

  • Developed VoteNet, a deep learning strategy for selecting reliable atlases for label fusion.
  • Employed plurality voting for fusing selected atlas labels.
  • Utilized a fast deep learning registration method to mitigate the runtime disadvantage of MAS.
  • Conducted experiments on 3D brain MRI data.

Main Results:

  • VoteNet significantly outperformed other label fusion strategies and direct deep learning segmentation.
  • The proposed method demonstrated superior performance when using a well-selected initial atlas set.
  • Analysis indicated potential for further performance improvements, suggesting room for future research.
  • Fast DL registration ensured competitive runtimes compared to traditional MAS.

Conclusions:

  • VoteNet offers a powerful deep learning-based alternative for multi-atlas segmentation, enhancing accuracy and efficiency.
  • The intelligent selection and fusion of atlases represent a significant advancement in medical image segmentation.
  • This approach holds promise for improving the analysis of 3D brain MRI and other medical imaging modalities.