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

The impact of collimator angle and increment on volumetric modulated arc therapy after modified radical mastectomy for breast cancer.

Scientific reports·2026
Same author

Eudaimonic life values and employment stress: a moderated mediation study in Chinese higher education students.

Frontiers in psychology·2026
Same author

A fast dosimetric optimization method of intensity modulated brachytherapy (IMBT) treatment plans for cervical cancer.

Physics in medicine and biology·2026
Same author

Estimation of organ doses based on patient-specific characteristics undergoing chest-abdomen-pelvis CT examinations of tube current modulation.

Journal of radiological protection : official journal of the Society for Radiological Protection·2026
Same author

Dosimetric characterization of a Varex VF-80/μXHP x-ray unit using open-ended applicators for superficial radiotherapy.

Journal of applied clinical medical physics·2025
Same author

Development of a treatment planning system for superficial x-ray radiotherapy using Monte Carlo database.

Biomedical physics & engineering express·2025

Related Experiment Video

Updated: Dec 15, 2025

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

8.3K

End-to-end unsupervised cycle-consistent fully convolutional network for 3D pelvic CT-MR deformable registration.

Yi Guo1, Xiangyi Wu1, Zhi Wang1,2

  • 1Department of Engineering and Applied Physics, University of Science and Technology of China, Hefei, Anhui, China.

Journal of Applied Clinical Medical Physics
|July 14, 2020
PubMed
Summary

A new deep learning method significantly improves computed tomography (CT)-magnetic resonance (MR) deformable image registration accuracy and efficiency. This unsupervised, end-to-end approach is substantially faster than existing methods.

Keywords:
FCNMR-CTcycle-consistentdeformable registration

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

916
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Related Experiment Videos

Last Updated: Dec 15, 2025

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

8.3K
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

916
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Area of Science:

  • Medical imaging
  • Deep learning
  • Image registration

Background:

  • Deformable image registration is crucial for medical imaging analysis.
  • Existing CT-MR registration methods face challenges in balancing accuracy and efficiency.

Purpose of the Study:

  • To develop a novel deep learning framework for CT-MR deformable image registration.
  • To enhance registration accuracy and significantly reduce processing time.

Main Methods:

  • Proposed two fully convolutional networks (FCNs) utilizing a Cycle-Consistent method for spatial deformable grid generation.
  • Trained and tested on 74 pelvic CT-MR image pairs, comparing with Elastix, MIM software, and FCN without cycle-consistency.
  • Evaluated registration accuracy using Dice coefficients and average surface distance (ASD) for regions of interest.

Main Results:

  • The proposed FCN with Cycle-Consistent method demonstrated superior registration accuracy and stability compared to other tested methods.
  • Achieved significantly faster registration times (<0.1s) compared to Elastix (64s) and MIM software (28s).

Conclusions:

  • The novel method effectively improves CT-MR deformable image registration accuracy and efficiency.
  • Offers a completely unsupervised and end-to-end deep learning solution, outperforming existing methods.