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

An intelligent MRI-based all-in-one diagnostic strategy for axillary lymph node status in breast cancer.

Nature communications·2026
Same author

The mechanistic of DCBLD2 in inhibiting TGF-β induced endothelial-mesenchymal transition in calcific aortic valve disease.

Journal of molecular and cellular cardiology·2026
Same author

Circulating CTRP9 and aortic valve calcification jointly predict coronary artery calcification in coronary heart disease patients.

Frontiers in nutrition·2026
Same author

An interpretable survival benefit analytics framework for optimizing cancer treatment decision-making.

Medical & biological engineering & computing·2026
Same author

Prognostic prediction in nasopharyngeal carcinoma using multi-region interaction features based on MRI habitat analysis.

Quantitative imaging in medicine and surgery·2026
Same author

Recurrent laryngeal nerve lymph nodes status prediction after neoadjuvant therapy for thoracic esophageal squamous cell carcinoma.

Insights into imaging·2026

Related Experiment Video

Updated: Aug 5, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K

Multiscale feature fusion network for 3D head MRI image registration.

Shixin Yang1, Haojiang Li2, Shuchao Chen1

  • 1School of Life & Environmental Science, Guangxi Colleges and Universities Key Laboratory of Biomedical Sensors and Intelligent Instruments, Guilin University of Electronic Technology, Guilin, China.

Medical Physics
|March 27, 2023
PubMed
Summary

This study introduces a deep learning-based multiscale feature fusion registration for head MRI. The novel method accurately registers complex head images, improving diagnostic support.

Keywords:
deep learningend-to-end registrationfeature fusion subnetworkhead imageimage registrationmagnetic resonance imagingmultiscale feature fusion network

More Related Videos

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

656

Related Experiment Videos

Last Updated: Aug 5, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

1.2K
A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.4K
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

656

Area of Science:

  • Medical Imaging
  • Deep Learning
  • Computer-Aided Diagnosis

Background:

  • Medical image registration is crucial for computer-aided diagnosis.
  • Head MRI analysis requires advanced registration techniques to handle complex spatial information.

Purpose of the Study:

  • To develop a deep learning-based multiscale feature fusion registration method for accurate head MRI registration.
  • To address limitations of general registration methods in capturing complex head MRI spatial and positional information.

Main Methods:

  • A three-module network: affine registration, parallel deformable registration with top-down/bottom-up fusion, and serial deformable registration with two fusion subnetworks.
  • Decomposition of large deformation fields into smaller ones through multiscale registration.
  • Targeted learning of multiscale information in head MRI via connected feature fusion subnetworks.

Main Results:

  • The algorithm achieved high accuracy in registering anterior and posterior lateral pterygoid muscles on 3D head MRIs.
  • Key metrics included a Dice similarity coefficient of 0.745 ± 0.021 and Hausdorff distance of 3.441 ± 0.935 mm.
  • Demonstrated superior registration accuracy compared to existing state-of-the-art methods.

Conclusions:

  • The proposed network enables end-to-end deformable registration for 3D head MRI.
  • Effectively handles large deformation displacements and rich image details in head scans.
  • Provides reliable technical support for diagnosing and analyzing head diseases.