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

[Implementation of mutual information based medical image registration methods].

Zhiyong Gao1, Bin Gu, Jiarui Lin

  • 1Institute of Biomedical Engineering, Huazhong University of Science and Technology, Wuhan 430074.

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi = Journal of Biomedical Engineering = Shengwu Yixue Gongchengxue Zazhi
|October 21, 2003
PubMed
Summary

Normalized mutual information offers a more stable and robust solution for intra-modal image registration, overcoming fluctuations that hinder standard mutual information methods.

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

A pH-Calibrated Multi-Analyte MXene Aerogel Electrochemical Platform Assisted by Interpretable Machine Learning for CSF-Based Prescreening of Postoperative Bacterial Meningitis.

Analytical chemistry·2026
Same author

Expert Augmented Prediction of Circulatory and Respiratory Instability from High Resolution Vital Signs.

NPJ digital medicine·2026
Same author

Mediating effects of lipid metabolic and inflammatory factors on skeletal muscle mass in adults: A cross-sectional study.

Medicine·2026
Same author

Sarcopenia-associated traits and sepsis risk: a Mendelian Randomization and Prospective Observational Study.

Shock (Augusta, Ga.)·2026
Same author

A Biomimetic Dual-Targeting Nano-APA-Editor Reprograms the 3'UTR Landscape for Tongue Squamous Cell Carcinoma Therapy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

International Validation of Temperature-Trajectory Sepsis Subphenotypes With Longitudinal Immune and Coagulation Patterns and Its Implications for Immunoglobulin Therapy.

Critical care medicine·2026

Area of Science:

  • Medical imaging
  • Computer vision
  • Signal processing

Context:

  • Mutual information (MI) and normalized mutual information (NMI) are leading methods for image registration.
  • Intra-modal registration, particularly, faces challenges due to fluctuations in registration functions.
  • These fluctuations can impede optimization and cause registration failures.

Purpose:

  • To investigate the causes of fluctuations in mutual information-based image registration.
  • To evaluate the stability and robustness of normalized mutual information compared to standard mutual information.
  • To identify factors contributing to registration failures in intra-modal scenarios.

Summary:

  • Fluctuations in image registration functions, stemming from interpolation artifacts and entropy uncertainty with overlap changes, hinder optimization.

Related Experiment Videos

  • While interpolation artifacts can be mitigated, entropy uncertainty poses a persistent challenge for standard mutual information.
  • Normalized mutual information demonstrates greater stability and robustness, making it a more reliable approach for intra-modal registration.

    • Impact:

    • Improved accuracy and reliability in intra-modal image registration.
    • Potential for wider application of normalized mutual information in medical imaging and other fields.
    • Reduced instances of registration failure, leading to more efficient image analysis workflows.