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

A semi-local paradigm for wavelet denoising.

Richard Charnigo1, Jiayang Sun, Raymond Muzic

  • 1Department of Statistics, University of Kentucky, Lexington, KY 40506-0027, USA. richc@ms.uky.edu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|March 8, 2006
PubMed
Summary

This study introduces a semi-local wavelet denoising method for 3D images like PET scans. This approach offers superior image denoising by processing image blocks individually, improving upon standard techniques.

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

Infective Endocarditis Hospitalizations in Kentucky, 2008-2018: Spatial and Temporal Trends.

Journal of Appalachian health·2026
Same author

Behavioral and transcriptomic markers of susceptibility to escalate fentanyl intake.

Translational psychiatry·2026
Same author

Towards an understanding of disturbed sleep phenotypes after traumatic spinal cord injury.

Journal of rehabilitation medicine·2026
Same author

Age-dependent gut microbiota associated with intramuscular fat deposition in Longdong cashmere goats.

Animal microbiome·2026
Same author

Comparison of Machine Learning Models for Colon Cancer Survival: Predictive Modeling Approach.

JMIR cancer·2025
Same author

Anion-Regulated Helmholtz Layer Enables Rigid-Yet-Flexible SEI for Ultrastable Silicon Anodes in Lithium-Ion Batteries.

ACS applied materials & interfaces·2025

Area of Science:

  • Medical Imaging
  • Signal Processing
  • Computational Science

Background:

  • Wavelet denoising is effective for 1D and 2D data.
  • Extending wavelet denoising to 3D, like volumetric PET images, faces challenges in regional denoising flexibility.
  • Existing methods may not adequately address the need for varied denoising intensity across different image regions.

Purpose of the Study:

  • To propose a novel semi-local paradigm for wavelet denoising in three-dimensional (3D) imaging.
  • To enhance the flexibility of wavelet denoising for applications such as volumetric positron emission tomography (PET) image analysis.
  • To improve denoising performance by allowing differential treatment of image regions.

Main Methods:

  • Image segmentation into smaller, manageable blocks.

Related Experiment Videos

  • Individual denoising of each block using modified generalized cross-validation (GCV).
  • Development of risk estimators to guide parameter selection and implementation choices.

    • Main Results:

    • The proposed semi-local paradigm demonstrated superior denoising performance on phantom PET images compared to standard GCV techniques.
    • Asymptotic analysis confirmed the method's consistency on a logarithmic scale under specific regularity conditions.
    • Experimental results indicate enhanced image quality and noise reduction.

    Conclusions:

    • The semi-local wavelet denoising paradigm offers a more flexible and effective approach for 3D image denoising, particularly for PET imaging.
    • This method addresses the limitations of traditional techniques by enabling region-specific denoising intensity.
    • Future research directions include further exploration of the semi-local denoising nature and its applications.