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

An Interactive Model of Target and Context for Aspect-Level Sentiment Classification.

Computational intelligence and neuroscience·2020
Same author

Dual Toroidal Dipole Resonance Metamaterials under a Terahertz Domain.

Materials (Basel, Switzerland)·2018
Same author

Therapeutic effects of tyroserleutide on lung metastasis of human hepatocellular carcinoma SK-HEP-1 and its mechanism affecting ICAM-1 and MMP-2 and -9.

Drug design, development and therapy·2018
Same author

Reduced Imaging Radiation Exposure and Costs Associated with Anti-Tumor Necrosis Factor Therapy in Crohn's Disease.

Digestive diseases and sciences·2018
Same author

The Augment of the Stability in Locking Compression Plate with Intramedullary Fibular Allograft for Proximal Humerus Fractures in Elderly People.

BioMed research international·2018
Same author

Gray Matter Structural Alterations in Social Anxiety Disorder: A Voxel-Based Meta-Analysis.

Frontiers in psychiatry·2018

Related Experiment Video

Updated: Mar 9, 2026

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

1.1K

A Parallel Nonrigid Registration Algorithm Based on B-Spline for Medical Images.

Xiaogang Du1, Jianwu Dang1, Yangping Wang2

  • 1School of Electronic & Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China.

Computational and Mathematical Methods in Medicine
|January 6, 2017
PubMed
Summary
This summary is machine-generated.

This study introduces a faster nonrigid registration algorithm using B-spline Free-Form Deformation (FFD) and parallel computing. The enhanced method significantly reduces computation time for medical image registration, achieving 17x speedup with improved accuracy.

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

1.7K
Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

20.2K

Related Experiment Videos

Last Updated: Mar 9, 2026

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

1.1K
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

1.7K
Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease
09:30

Quantitative Magnetic Resonance Imaging of Skeletal Muscle Disease

Published on: December 18, 2016

20.2K

Area of Science:

  • Medical Image Processing
  • Computational Imaging
  • Scientific Computing

Background:

  • Nonrigid registration using B-spline Free-Form Deformation (FFD) is crucial for medical imaging but computationally intensive.
  • Accurate registration of large medical image datasets requires significant processing time.

Purpose of the Study:

  • To develop a parallel nonrigid registration algorithm based on B-splines to accelerate medical image processing.
  • To enhance registration precision and reduce computational complexity.

Main Methods:

  • Implemented a parallel computing strategy utilizing Graphics Processing Unit (GPU) capabilities.
  • Incorporated Logarithm Squared Difference (LSD) as the similarity metric for improved precision.
  • Utilized lookup tables (LUTs) and the Nonlinear Conjugate Gradient (NCG) method to optimize B-spline interpolation, LSD computation, and gradient calculation.

Main Results:

  • Achieved significant reduction in computation time for key steps like B-spline interpolation and LSD gradient computation.
  • Demonstrated superior registration accuracy compared to ground truth deformation fields.
  • Reported a 17-fold speedup over single-threaded CPU implementations on large medical image datasets.

Conclusions:

  • The proposed parallel B-spline registration algorithm offers a substantial improvement in both speed and accuracy for medical image processing.
  • Leveraging GPU parallel computing effectively addresses the computational demands of nonrigid registration.