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 Experiment Videos

Mutual information-based multimodal image registration using a novel joint histogram estimation.

Xuesong Lu1, Su Zhang, He Su

  • 1Department of Biomedical Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Min Hang, Shanghai 200240, PR China. luxsyyl@sjtu.edu.cn

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|January 25, 2008
PubMed
Summary
This summary is machine-generated.

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

Tandem duplication-driven expansion and UV-B stress adaptation of the LHC gene family in Artemisia annua L.

BMC plant biology·2026
Same author

Design and evaluation of an intuitive distal-flexible endoscope for constrained surgical environments.

Surgical endoscopy·2026
Same author

Design and Preliminary Evaluation of a Hand-Held Surgical Robot for Enhanced Intuitive Control in Laparoscopy.

The international journal of medical robotics + computer assisted surgery : MRCAS·2026
Same author

The interplay between gastrointestinal dysfunction and gut microbiota dynamics in sepsis.

Frontiers in cellular and infection microbiology·2026
Same author

Construction of donkey skin fibroblast immortalized cell line and comparative analysis with primary cells.

Tissue & cell·2026
Same author

Polarization-normalized differential Fano response in phosphorene metasurfaces for ultra-highly sensitive sensing.

Optics letters·2026
Same journal

RGCNN-nnUNet: Recurrent group equivariant nnU-Net for robust brain tissue segmentation on stroke NCCT.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Self-supervised isotropic reconstruction for abnormality detection in anisotropic MRI.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

WDBDM: Wavelet-based dual-branch diffusion model for low-dose CT and PET denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

ScribSAM: A robust scribble-supervised framework for spatiotemporal segmentation of breast lesions in ultrasound videos.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Anatomically and biochemically guided deep image prior for sodium MRI denoising.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
Same journal

Segment Anything Model for medical image segmentation: A review.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
See all related articles

This study introduces a new partial volume interpolation method for joint histogram estimation in multimodal medical image registration. The novel approach reduces local extremes, enhancing registration accuracy for both rigid and non-rigid applications.

Area of Science:

  • Medical image analysis
  • Computational imaging
  • Biomedical engineering

Background:

  • Mutual Information (MI)-based image registration is crucial for multimodal medical imaging.
  • Traditional joint histogram estimation methods (linear, partial volume interpolation) can cause local extremes in the MI function, hindering registration accuracy.
  • These local extremes can impede optimization and reduce the reliability of medical image registration.

Purpose of the Study:

  • To develop a novel joint histogram estimation method to mitigate local extremes in MI-based image registration.
  • To improve the accuracy and robustness of both rigid and non-rigid medical image registration.
  • To introduce an improved method for estimating the gradient of mutual information during non-rigid registration.

Main Methods:

Related Experiment Videos

  • A new partial volume (PV) interpolation method using a Hanning windowed sinc function as the kernel was developed for joint histogram estimation.
  • The proposed method, termed HPV, was applied to both rigid and non-rigid image registration tasks.
  • A novel approach for estimating the gradient of mutual information with respect to model parameters in non-rigid registration was also introduced.

Main Results:

  • Experiments on synthetic and real medical images demonstrated that the HPV method effectively reduces local extremes in the MI registration function.
  • The proposed method significantly improved registration accuracy compared to conventional techniques.
  • The new gradient estimation method contributed to more stable and accurate non-rigid registration.

Conclusions:

  • The novel HPV joint histogram estimation method offers a robust solution to the local extreme problem in MI-based medical image registration.
  • This approach enhances registration accuracy and reliability for both rigid and non-rigid transformations.
  • The developed techniques provide valuable advancements for multimodal medical image analysis and clinical applications.