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

Artificial Intelligence in Image Assisted Radiation Oncology.

Cancers·2026
Same author

Targeted autonomic testing for radiation‑induced baroreflex failure in head and neck cancer survivors: index case and early program experience.

Cardio-oncology (London, England)·2026
Same author

Feasibility of longitudinal relaxation rate mapping with non-Cartesian sampling and compressed sensing on a 1.5 T magnetic resonance linear accelerator.

Physics and imaging in radiation oncology·2026
Same author

Neck adiposity on standard oncologic CT predicts radiation-induced carotid disease in oropharyngeal cancer.

Cardio-oncology (London, England)·2026
Same author

Expiratory Muscle Strength Training in Head and Neck Cancer Survivors With Radiation-Associated Dysphagia: Results of a Pilot Prospective Trial.

Head & neck·2026
Same author

Technical Development and Implementation of 3D-QALAS on a 1.5T MR-Linac for the Brain: A Prospective R-IDEAL Stage 0/1 Technology Development Report.

medRxiv : the preprint server for health sciences·2026

Related Experiment Video

Updated: Jul 18, 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 transformer-based hierarchical registration framework for multimodality deformable image registration.

Yao Zhao1, Xinru Chen1, Brigid McDonald1

  • 1Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences, Houston, TX, USA.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|August 25, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces Patch-RegNet, a new deep learning method for deformable image registration in head and neck radiotherapy. It significantly improves accuracy for CT-MR and MR-MR image alignment, crucial for adaptive treatments.

Keywords:
CT/MR deformable registrationMulti-modality registrationPatch-based registrationVision transformer

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

628
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

8.0K

Related Experiment Videos

Last Updated: Jul 18, 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
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

628
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

8.0K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Deep Learning

Background:

  • Deformable image registration (DIR) is vital for adaptive radiotherapy.
  • Traditional DIR methods struggle with accuracy in complex head and neck regions.
  • Deep learning offers faster and more robust registration but faces challenges in large, multi-anatomic sites.

Purpose of the Study:

  • To develop a hierarchical deep learning framework, Patch-RegNet, for accurate and fast CT-MR and MR-MR deformable image registration.
  • To improve registration performance specifically for head and neck adaptive radiotherapy using MR-Linac treatments.

Main Methods:

  • Developed Patch-RegNet, a hierarchical framework with global, patch-based rigid, and patch-based deformable registration steps.
  • Utilized a ViT-Morph model (CNN + Vision Transformer) for patch-based DIR with a modality-independent neighborhood descriptor.
  • Trained models on 242 CT-MR and 213 MR-MR image pairs, testing on 24 pairs.

Main Results:

  • Patch-RegNet outperformed VoxelMorph by 6% for CT-MR registration and 4% for MR-MR registration (DSC measurements).
  • The hierarchical approach achieved significantly improved DIR accuracy for both CT-MR and MR-MR image pairs.
  • Demonstrated enhanced registration accuracy for critical organs in head and neck regions.

Conclusions:

  • The Patch-RegNet framework offers a significant advancement in DIR accuracy and speed for head and neck adaptive radiotherapy.
  • This method is particularly beneficial for CT-MR and MR-MR registration in MR-guided adaptive treatments.
  • The hierarchical approach effectively addresses challenges in registering large, multi-anatomic regions.