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

The predictive value of intraoperative bulbocavernosus reflex monitoring for postoperative voiding function in patients with conus medullaris and cauda equina tumors: a retrospective single center study.

The spine journal : official journal of the North American Spine Society·2024
Same author

Cisplatin resistance-related transcriptome and methylome integration identifies <i>PCDHB4</i> as a novel prognostic biomarker in small cell lung cancer.

iScience·2024
Same author

Regioselective analysis of heat-induced conformational changes of β-lactoglobulin by quantitative liquid chromatography-mass spectrometry analysis of chemical labeling kinetics.

Food chemistry·2024
Same author

The complex effects of miR-146a in the pathogenesis of Alzheimer's disease.

Neural regeneration research·2024
Same author

Effects of nitrile compounds on the structure and function of soil microbial communities as revealed by metagenomes.

Environmental research·2024
Same author

Discovery of the Natural Bibenzyl Compound Erianin in Dendrobium Inhibiting the Growth and EMT of Gastric Cancer through Downregulating the LKB1-SIK2/3-PARD3 Pathway.

International journal of molecular sciences·2024

Related Experiment Video

Updated: May 29, 2026

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities
07:13

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Published on: October 27, 2023

DADWMorph: A Global-Local Collaborative Network for Deformable Medical Image Registration.

Yujie Wang1, Yinjie Su2, Jiajia Liu2

  • 1East China University of Science and Technology, Shanghai, China. W3216440909@163.com.

Journal of Imaging Informatics in Medicine
|May 27, 2026
PubMed
Summary

DADWMorph, a novel deep learning framework, improves deformable image registration accuracy for medical imaging. It addresses challenges in long-range correspondences and fine-grained detail preservation, showing robust performance across modalities.

Keywords:
Complex structural deformationDeformable medical image registrationGlobal and local collaborationLarge deformation

More Related Videos

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

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Related Experiment Videos

Last Updated: May 29, 2026

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities
07:13

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Published on: October 27, 2023

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

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Anatomy

Background:

  • Deformable image registration is crucial for longitudinal disease monitoring, multi-modal fusion, and atlas-based segmentation in clinical imaging informatics.
  • Current Transformer-based methods face limitations in handling large deformations and preserving local details due to challenges with long-range anatomical correspondences and feature interference.

Purpose of the Study:

  • To develop a deep learning framework, DADWMorph, that enhances deformable image registration accuracy and robustness.
  • To address limitations of existing methods in capturing long-range dependencies and preserving fine-grained anatomical details.

Main Methods:

  • Developed DADWMorph, a framework with two key components: the dilation-aggregator block (DAB) for long-range spatial dependencies and the density-weighted block (DWB) for structure-specific feature extraction.
  • DAB utilizes aggregator attention with dilated convolution; DWB employs spatial density function-weighted convolution.

Main Results:

  • On the IXI brain dataset, DADWMorph achieved improved registration accuracy (DSC=76.05%, HD95=3 mm) and a 58% reduction in folding artifacts compared to baselines.
  • Evaluated on cross-modality abdomen MR-CT registration, DADWMorph attained high accuracy (DSC=69.77%, HD95=9.8 mm) with low computational cost, demonstrating generalizability.

Conclusions:

  • DADWMorph demonstrates robust performance in deformable image registration across diverse anatomical structures and imaging modalities.
  • The framework shows potential clinical value for applications such as atlas-based brain parcellation, radiation therapy dose mapping, and multi-modal image fusion.