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 controlled phantom study of a noise equalization algorithm for detecting microcalcifications in digital mammograms.

O O Gürün1, P P Fatouros, G M Kuhn

  • 1Department of Radiology, Medical College of Virginia, Virginia Commonwealth University, Richmond 23298-0072, USA. oogurun@hsc.vcu.edu

Medical Physics
|May 8, 2001
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

Modelling convection-enhanced delivery in normal and oedematous brain.

Journal of medical engineering & technology·2014
Same author

Absorbed radiation dose of the female breast during diagnostic multidetector chest CT and dose reduction with a tungsten-antimony composite breast shield: preliminary results.

Clinical radiology·2008
Same author

Comparison of NAA measures by MRS and HPLC.

Acta neurochirurgica. Supplement·2001
Same author

Contribution of edema and cerebral blood volume to traumatic brain swelling in head-injured patients.

Journal of neurosurgery·2000
Same author

Women's health care centers and the women's imaging subspecialty: emerging frontiers in radiology.

Radiographics : a review publication of the Radiological Society of North America, Inc·1999
Same author

Unusual breast lesions: radiologic-pathologic correlation.

Radiographics : a review publication of the Radiological Society of North America, Inc·1999

This study enhances a microcalcification detection algorithm by modifying its feature space estimation. The improved method better preserves similarity and increases the detectability of microcalcifications in mammograms.

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Microcalcification detection algorithms are crucial for early breast cancer diagnosis.
  • Existing algorithms, like adaptive noise equalization, have limitations in accuracy and similarity preservation.
  • Shortcomings were identified in the estimation of distribution widths within the feature space.

Purpose of the Study:

  • To extend and improve a microcalcification detection algorithm based on adaptive noise equalization.
  • To address limitations in similarity preservation and detectability.
  • To enhance the algorithm's applicability to real mammograms.

Main Methods:

  • Modifying the estimator statistic for feature space distribution width estimation.

Related Experiment Videos

  • Implementing downsampling and alternative local contrast filters to improve detectability.
  • Testing the modified algorithm on tissue-equivalent phantom images with and without microcalcifications.

    • Main Results:

    • The modified algorithm demonstrated improved similarity preservation compared to the original approach.
    • Enhancements in detectability were observed with the modified algorithm and additional filters.
    • The modifications extended the algorithm's generality and applicability.

    Conclusions:

    • The developed modifications significantly improve the microcalcification detection algorithm's performance.
    • The enhanced algorithm shows promise for more accurate and reliable detection in mammography.
    • Further research is warranted for real mammogram applications and continued algorithm refinement.