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

Advances in micro-calcification clusters detection in mammography.

L Zhang1, R Sankar, W Qian

  • 1Department of Electrical Engineering, University of South Florida, Tampa, FL 33620 5350, USA.

Computers in Biology and Medicine
|October 3, 2002
PubMed
Summary

A novel multistage method significantly reduces false positives in micro-calcification cluster detection. This approach improves mammogram analysis accuracy, enhancing cancer detection sensitivity to 97%.

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

Biological characterization of nef in long-term survivors of human immunodeficiency virus type 1 infection.

Journal of virology·1995
Same author

Virulence characteristics of Escherichia coli causing first urinary tract infection predict risk of second infection.

The Journal of infectious diseases·1995
Same author

Concordant loss of imprinting of the human insulin-like growth factor II gene promoters in cancer.

The Journal of biological chemistry·1995
Same author

Altered cAMP levels in retinas from transgenic mice expressing a rhodopsin mutant.

Biochemical and biophysical research communications·1995
Same author

Repetitive Ser-Gly sequences enhance heparan sulfate assembly in proteoglycans.

The Journal of biological chemistry·1995
Same author

The angiotensin II type 2 (AT2) receptor antagonizes the growth effects of the AT1 receptor: gain-of-function study using gene transfer.

Proceedings of the National Academy of Sciences of the United States of America·1995

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Mammography is crucial for early breast cancer detection.
  • Micro-calcification clusters (MCCs) are key indicators but can lead to false positives (FP).
  • Existing methods require improved FP reduction for better diagnostic accuracy.

Purpose of the Study:

  • To develop and evaluate a new multistage method for reducing false positives in MCC detection.
  • To enhance the overall performance of MCC detection in mammograms.

Main Methods:

  • Extracted eleven features from spatial and morphology domains, categorized into gray-level, shape, and cluster descriptions.
  • Employed a back-propagation (BP) neural network with a Kalman filter.
  • Implemented a two-stage FP reduction: initial elimination of obvious FPs, followed by cluster-based FP elimination.

Related Experiment Videos

Main Results:

  • Successfully reduced false positives to 3.15 per image.
  • Improved detection sensitivity (true positive rate) to 97%.
  • Validated using a database of 67 patient mammograms.

Conclusions:

  • The proposed mixed-feature, multistage approach effectively reduces false positives in MCC detection.
  • This method enhances diagnostic accuracy in mammography by improving true positive rates.
  • The technique shows significant promise for clinical application in breast cancer screening.