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

SamRobNODDI:<i>q</i>-space sampling-augmented continuous representation learning for robust and generalized NODDI.

Physics in medicine and biology·2025
Same author

Semi-supervised temporal attention network for lung 4D CT ventilation estimation.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

Study on risk assessment of tunnel construction across mined-out region based on combined weight-two-dimensional cloud model.

Scientific reports·2025
Same author

Prior knowledge-based multi-task learning network for pulmonary nodule classification.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025
Same author

A multiomics investigation into the evolution and specialized metabolisms of three Toxicodendron cultivars.

The Plant journal : for cell and molecular biology·2024
Same author

A Precise Pulmonary Airway Tree Segmentation Method Using Quasi-Spherical Region Constraint and Tracheal Wall Gap Sealing.

Sensors (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jun 7, 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

534

Pulmonary CT Registration Network Based on Deformable Cross Attention.

Meirong Ren1, Peng Xue1, Huizhong Ji1

  • 1Shool of Mechanical, Electrical & Information Engineering, Shandong University, Weihai, 264,209, China.

Journal of Imaging Informatics in Medicine
|November 11, 2024
PubMed
Summary

This study introduces a novel Cascaded Swin Deformable Cross Attention Transformer (SD-CATU) for lung CT registration. The method achieves superior accuracy and consistency in handling large deformations, outperforming existing techniques.

Keywords:
Cross attentionInverse consistencyLung CT registrationTransformer

More Related Videos

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
06:59

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation

Published on: June 3, 2018

10.5K
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

7.9K

Related Experiment Videos

Last Updated: Jun 7, 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

534
Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation
06:59

Improved Registration of 3D CT Angiography with X-ray Fluoroscopy for Image Fusion During Transcatheter Aortic Valve Implantation

Published on: June 3, 2018

10.5K
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

7.9K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Transformer models, using self-attention, impact medical image registration.
  • Current Transformer use in lung CT registration is limited, focusing on single image features and neglecting cross-image correspondence.

Purpose of the Study:

  • To propose a novel cascaded registration method, SD-CATU, for challenging large deformation lung CT registration.
  • To improve registration performance by capturing across-image correspondence and reducing computational complexity.

Main Methods:

  • Introduced a Cross Attention-based Transformer (CAT) block with Shifted Regions Multihead Cross-attention (SR-MCA) for flexible feature exchange.
  • Employed a cascaded U-shape structure (SD-CATU) to handle large deformations.
  • Incorporated a consistency constraint in the loss function for topology and inverse consistency preservation.

Main Results:

  • The proposed SD-CATU method achieved state-of-the-art performance on public lung datasets.
  • Achieved a Dice Similarity Coefficient of 93.19% and a Target Registration Error of 0.98 mm.
  • Demonstrated excellent registration accuracy, smoothness, and consistency in deformed images.

Conclusions:

  • The novel SD-CATU method effectively addresses limitations in current Transformer-based lung CT registration.
  • The approach shows significant potential for high-accuracy medical image registration with improved consistency.
  • SD-CATU offers a promising solution for complex lung CT registration tasks.