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

Impact of Radiomics Parameters and Clinical Integration on Prognostication in Head and Neck Squamous Cell Carcinoma: A Multicenter Study.

Life (Basel, Switzerland)·2026
Same author

Molecular characterization and pathogenicity of a HP-like PRRSV strain and a NADC30 recombinant strain.

Microbial pathogenesis·2026
Same author

Microbial ecology and flavor formation mechanisms of high-temperature Daqu in the Huang-Huai River basin and adjacent regions: A comparative study from eastern Henan, Jiaodong peninsula, and southern Anhui.

Food research international (Ottawa, Ont.)·2026
Same author

A malignant symbiosis: The neuro-metabolic symphony rewires the tumor microenvironment.

Neoplasia (New York, N.Y.)·2026
Same author

The Synergistic Refinement of Primary Si in Hypereutectic Al-Si Alloys Using Ce and Er Elements.

Materials (Basel, Switzerland)·2026
Same author

A mutational signature for brain metastasis tropism in lung adenocarcinoma.

Discover oncology·2026

Related Experiment Video

Updated: Jan 13, 2026

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

1.6K

Foundation model-enhanced unsupervised 3D deformable medical image registration.

Zhuoran Jiang1, Zhendong Zhang2, Lei Xing1

  • 1Department of Radiation Oncology, Stanford University, Stanford, CA, United States of America.

Physics in Medicine and Biology
|January 8, 2026
PubMed
Summary

This study introduces a novel unsupervised deep learning method for deformable image registration (DIR) by integrating vision foundation models. The approach enhances accuracy and robustness for medical image analysis, particularly for complex structures.

Keywords:
cardiac MR registrationdeep learningdeformable image registrationfoundation modelliver CT registrationunsupervised learning

More Related Videos

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

8.4K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.6K

Related Experiment Videos

Last Updated: Jan 13, 2026

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

1.6K
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

8.4K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.6K

Area of Science:

  • Medical image analysis
  • Deep learning
  • Computer vision

Background:

  • Unsupervised deep learning methods for deformable image registration (DIR) show promise but struggle with ill-conditioning due to structural ambiguities.
  • Existing methods lack implicit anatomical understanding, limiting accuracy and robustness.

Purpose of the Study:

  • To develop an accurate and robust unsupervised DIR framework by integrating vision foundation models.
  • To address challenges of structural ambiguities and ill-conditioning in unsupervised DIR.

Main Methods:

  • A multi-scale unsupervised framework leveraging pre-trained vision foundation model encoders.
  • Integration of convolutional adaptors for inductive bias and correlation-aware MLPs for deformation vector field (DVf) decoding.
  • Utilized a pyramid architecture for multi-range dependency capture and evaluated on cardiac MRI and liver CT datasets.

Main Results:

  • The proposed method generates realistic and accurate DVFs, achieving high registration similarity.
  • Achieved a Dice score of 0.869 ± 0.093 for cardiac MRI and 1.60±1.44 mm landmark error for liver CT.
  • Demonstrated significant improvement over state-of-the-art methods, with foundation feature integration proving effective (p<0.05).

Conclusions:

  • The novel approach advances DIR for multi-modality images with complex structures and low contrasts.
  • Offers a powerful tool for diverse medical image analysis applications.
  • Highlights the potential of integrating foundation models for improved DIR performance.