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

Hydrogel-Coated Clips Are Associated with a Higher Risk of Dislocation After Ultrasound-Guided Breast Biopsy.

Diagnostics (Basel, Switzerland)·2026
Same author

Association of Deep Learning-based Myocardial Infarction Size Quantification in Cardiac MRI with Cardiac Biomarker Levels.

Radiology. Cardiothoracic imaging·2026
Same author

Safety of Endovascular Thrombectomy in Isolated Cervical Internal Carotid Artery Occlusion While on Oral Anticoagulation.

Journal of stroke·2026
Same author

Real-time virtual sonography for prone-position breast MRI: technical feasibility and accuracy in locating 125 breast lesions.

European radiology experimental·2026
Same author

Biological Cardiovascular Age Derived from Coronary CTA Reports Using a Large Language Model: A Novel Predictor of Major Adverse Cardiovascular Events?

Diagnostics (Basel, Switzerland)·2026
Same author

European Stroke Organisation (ESO), European Association of Neurosurgical Societies (EANS) and European Society for Minimally Invasive Neurological Therapy (ESMINT) guideline on aneurysmal subarachnoid haemorrhage.

European stroke journal·2026

Related Experiment Video

Updated: May 7, 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

2.0K

DARE: A Deformable Adaptive Regularization Estimator for learning-based medical image registration.

Ahsan Raza Siyal1, Markus Haltmeier1, Ruth Steiger2

  • 1Department of Mathematics, University of Innsbruck, Austria.

Artificial Intelligence in Medicine
|May 5, 2026
PubMed
Summary

We developed a new method for medical image registration called Deformable Adaptive Regularization Estimator (DARE). DARE improves accuracy and anatomical plausibility by dynamically adjusting regularization for robust brain image alignment.

Keywords:
Adaptive regularizationDeep learningMedical image registrationPhysics informed network

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

1.3K
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

7.6K

Related Experiment Videos

Last Updated: May 7, 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

2.0K
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

1.3K
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

7.6K

Area of Science:

  • Medical Image Analysis
  • Computational Anatomy
  • Machine Learning in Medicine

Background:

  • Deformable medical image registration is crucial for analyzing anatomical changes.
  • Deep learning methods offer high accuracy but often lack robustness and anatomical plausibility due to inadequate regularization.
  • Ensuring robust and anatomically plausible registrations is essential for reliable medical image analysis.

Purpose of the Study:

  • To introduce a novel registration framework, DARE (Deformable Adaptive Regularization Estimator), that enhances robustness and anatomical plausibility.
  • To dynamically adjust elastic regularization based on deformation field characteristics.
  • To improve the accuracy and physiological consistency of deformable image registration.

Main Methods:

  • DARE integrates adaptive strain and shear energy terms, modulated by the deformation gradient norm.
  • A folding-prevention mechanism penalizes negative Jacobian determinants to ensure topological plausibility.
  • The framework was evaluated on IXI, OASIS, and MUI-P datasets for brain image registration.

Main Results:

  • DARE consistently improved registration accuracy and anatomical plausibility across datasets.
  • The method achieved higher Dice scores and reduced folding artifacts compared to existing methods.
  • DARE maintained low strain energy and realistic volume changes in brain structures.

Conclusions:

  • The proposed adaptive regularization mechanism in DARE ensures robust, accurate, and physiologically consistent deformation fields.
  • DARE offers a significant advancement in deformable medical image registration, particularly for brain imaging.
  • The framework's ability to balance deformation stability and flexibility enhances its clinical applicability.