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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

5.1K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.1K
Imaging Studies I: CT and MRI01:14

Imaging Studies I: CT and MRI

229
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
229

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Reinforcement learning-guided segment anything model for MRI prostate and dominant intraprostatic lesions auto-segmentation.

Physics in medicine and biology·2026
Same author

Impact of harmonization on predicting complications in head and neck cancer after radiotherapy using MRI radiomics and machine learning techniques.

Medical physics·2025
Same author

Assessment of automated non-coplanar stereotactic radiosurgery planning in single isocenteric linac-based treatment for brain metastases with respect to planner's experience.

Medical dosimetry : official journal of the American Association of Medical Dosimetrists·2025
Same author

A comparison of different machine learning classifiers in predicting xerostomia and sticky saliva due to head and neck radiotherapy using a multi-objective, multimodal radiomics model.

Biomedical physics & engineering express·2025
Same author

CT-based synthetic contrast-enhanced dual-energy CT generation using conditional denoising diffusion probabilistic model.

Physics in medicine and biology·2024
Same author

CT-based synthetic iodine map generation using conditional denoising diffusion probabilistic model.

Medical physics·2024

Related Experiment Video

Updated: Jun 25, 2025

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

580

Diffeomorphic transformer-based abdomen MRI-CT deformable image registration.

Yang Lei1, Luke A Matkovic1, Justin Roper1

  • 1Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.

Medical Physics
|May 31, 2024
PubMed
Summary

A new deep learning model accurately registers MRI and CT scans for liver stereotactic body radiotherapy (SBRT). This deformable image registration (DIR) improves treatment planning by precisely defining tumor volumes and sparing healthy organs.

Keywords:
abdomen SBRTdeep learningdeformable image registration

More Related Videos

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

1.1K
Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.5K

Related Experiment Videos

Last Updated: Jun 25, 2025

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

580
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

1.1K
Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

19.5K

Area of Science:

  • Medical Imaging
  • Radiotherapy Physics
  • Artificial Intelligence in Medicine

Background:

  • Stereotactic body radiotherapy (SBRT) is crucial for liver metastases when surgery isn't an option.
  • Accurate imaging (CT and MRI) is vital for precise target delineation and minimizing radiation toxicity to organs at risk (OAR).
  • Deformable image registration (DIR) is essential for transferring MRI-based contours to CT for liver SBRT planning.

Purpose of the Study:

  • To develop a novel deep learning model for estimating the deformation vector field (DVF) for direct MRI-CT registration in abdominal imaging.
  • To enhance the accuracy of image registration for improved liver SBRT treatment planning.

Main Methods:

  • A diffeomorphic deformation model incorporating Swin transformers and CNNs was used for DVF estimation.
  • The model was optimized using cross-modality image similarity (MIND) and surface matching losses.
  • Performance was evaluated on 50 liver cases using Target Registration Error (TRE), Dice Similarity Coefficient (DSC), and Mean Surface Distance (MSD).

Main Results:

  • The proposed DIR method significantly improved mean DSC for the liver (0.850 to 0.903) and portal vein (0.628 to 0.763) compared to rigid registration.
  • Mean Surface Distance (MSD) for the liver decreased from 7.216 mm to 3.232 mm.
  • Target Registration Error (TRE) was reduced from 26.238 mm to 8.492 mm.

Conclusions:

  • The developed diffeomorphic transformer-based DIR method offers an effective and efficient approach for accurate DVF generation from abdominal MRI-CT pairs.
  • This method has the potential to be integrated into current liver SBRT treatment planning workflows.