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 Video

Updated: Jun 3, 2026

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Kernel regression based feature extraction for 3D MR image denoising.

Ezequiel López-Rubio1, María Nieves Florentín-Núñez

  • 1Department of Computer Languages and Computer Science, School of Computer Engineering, University of Málaga, Bulevar Louis Pasteur, 35. 29071 Málaga, Spain. ezeqlr@lcc.uma.es

Medical Image Analysis
|March 19, 2011
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

Estimating the Speed of Nearby Vehicles with a Single Onboard Camera by Smooth Kernel Regression.

International journal of neural systems·2025
Same author

Consensus-Based 3D View Generation from Noisy Images.

International journal of neural systems·2025
Same author

Representation of Molecules by Sequences of Instructions.

Journal of chemical information and modeling·2025
Same author

Hyperparameter optimization of YOLO models for invasive coronary angiography lesion detection and assessment.

Computers in biology and medicine·2025
Same author

Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks.

International journal of neural systems·2024
Same author

The Impact of Noise and Brightness on Object Detection Methods.

Sensors (Basel, Switzerland)·2024

This study introduces a novel 3D kernel regression method for magnetic resonance imaging (MRI) denoising. The automated approach effectively removes Rician noise, enhancing image quality without manual intervention.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Signal Processing

Background:

  • Non-parametric kernel regression is effective for image denoising.
  • Magnetic resonance 3D (three-dimensional) image denoising presents unique challenges due to its structure and Rician noise.
  • Existing methods may not fully address the specific noise characteristics of MRI data.

Purpose of the Study:

  • To adapt the kernel regression framework for 3D MRI denoising.
  • To develop an automated system for removing Rician noise from MRI scans.
  • To enhance the performance of MRI denoising filters by incorporating directional information.

Main Methods:

  • A zeroth-order 3D kernel regression computes weighted pixel averages.
  • Weights are derived from feature vector similarities, estimated using second-order 3D kernel regression.

Related Experiment Videos

Last Updated: Jun 3, 2026

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers
08:33

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

  • Directional information from gradient vectors is integrated into weight computation.

    • Main Results:

    • The proposed method effectively denoises 3D MRI data with Rician noise.
    • Automatic estimation of Rician noise levels is achieved, requiring no human input.
    • Experimental results show competitive performance against other MRI denoising filters.

    Conclusions:

    • The adapted 3D kernel regression provides a principled and effective approach to MRI denoising.
    • The method's automation and handling of Rician noise offer significant advantages.
    • Incorporating directional features enhances denoising performance in magnetic resonance imaging.