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

Genetic variation of human papillomavirus type 39 E6 and E7 genes in central China.

Virology journal·2026
Same author

Generating synthetic CT from MR images for radiation-free computer-assisted quantification of hip morphology.

European journal of radiology·2026
Same author

A case of synchronous double primary combined hepatocellular-cholangiocarcinoma complicated with gallbladder adenocarcinoma: a rare case report.

Frontiers in oncology·2026
Same author

CIM-VTP: Correlation-Guided Image Modeling With Visual-Textual Task Prompt for Universal Medical Image Registration.

IEEE transactions on medical imaging·2026
Same author

TPDPM: Text promptable diffusion probabilistic model for referring surgical instrument segmentation.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same author

Primary extranodal marginal zone non-hodgkin lymphoma of the prostate: a case report.

Frontiers in oncology·2026

Related Experiment Video

Updated: Jul 6, 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

SMILE: Siamese Multi-scale Interactive-representation LEarning for Hierarchical Diffeomorphic Deformable image

Xiaoru Gao1, Guoyan Zheng1

  • 1Institute of Medical Robotics, School of Biomedical Engineering, 800 DongChuan Road, Shanghai Jiao Tong University, Shanghai, 200240, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|December 29, 2023
PubMed
Summary

This study introduces a novel deep learning method for deformable medical image registration, improving accuracy and preserving image topology. The approach enhances correspondence matching and handles large spatial displacements effectively.

Keywords:
Deep learningDeformable image registrationDiffeomorphic deformationRepresentation learning

More Related Videos

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K
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

612

Related Experiment Videos

Last Updated: Jul 6, 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
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.4K
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

612

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Deformable medical image registration is crucial for clinical applications, enabling point-wise correspondences between images.
  • Unsupervised deep learning methods offer fast inference but face limitations in feature correspondence, handling large displacements, and preserving transformation properties.
  • Existing methods often overlook explicit feature correspondence modeling and desirable properties like topology-preservation and invertibility.

Purpose of the Study:

  • To propose a novel Convolutional Neural Network (CNN) for unsupervised deformable medical image registration.
  • To address limitations of existing methods, including overlooked feature correspondences, limited performance on large displacements, and ignored topology-preservation and invertibility.
  • To develop a method that achieves high registration accuracy while ensuring desirable transformation properties.

Main Methods:

  • A novel CNN architecture featuring a Siamese Multi-scale Interactive-representation LEarning (SMILE) encoder and a Hierarchical Diffeomorphic Deformation (HDD) decoder.
  • The SMILE encoder focuses on learning effective feature representations and establishing spatial correspondences.
  • The HDD decoder regresses the dense deformation field hierarchically (coarse-to-fine) and incorporates a Local Invertible Loss (LIL) for topology-preservation and local invertibility.

Main Results:

  • The proposed method demonstrated superior performance compared to state-of-the-art approaches on two public brain image datasets.
  • Achieved an average Dice Similarity Coefficient (DSC) of 0.815 and an average Average Surface Distance (ASSD) of 0.633 mm on the Neurite-OASIS dataset.
  • The method effectively addresses limitations in feature correspondence, large spatial displacements, and ensures topology-preservation and invertibility.

Conclusions:

  • The novel CNN with SMILE encoder and HDD decoder significantly advances unsupervised deformable medical image registration.
  • The proposed Local Invertible Loss (LIL) is effective in promoting topology-preservation and local invertibility without compromising accuracy.
  • The method shows strong potential for various clinical applications requiring accurate and reliable image registration.