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: Jul 17, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Normal mammogram classification based on a support vector machine utilizing crossed distribution features.

W Chiracharit1, Y Sun, P Kumhom

  • 1Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology, Bangkok, Thailand.

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|February 3, 2007
PubMed
Summary

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

On-microscope staging of live cells reveals changes in the dynamics of transcriptional bursting during differentiation.

Nature communications·2022
Same author

Variable cells with identical genetic codes.

Blood·2020
Same author

A questionnaire study assessing overuse injuries in United Kingdom endoscopists and any effect from the introduction of the National Bowel Cancer Screening Program on these injuries.

Gastrointestinal endoscopy·2011
Same author

A patient with impaired gastric motility.

Gut·2007
Same author

Early endoscopic sphincterotomy in acute cholecystitis in elderly patients with high surgical risk.

Endoscopy·2007
Same author

8 Doublefoot is epistatic to Sonic hedgehog in the developing mouse limb.

Journal of anatomy·2006

This study introduces a new method to improve computer-aided breast cancer diagnosis by transforming non-separable mammogram features. This enhances the accuracy of support vector machine (SVM) classifiers for normal mammogram classification.

Area of Science:

  • Medical Imaging
  • Machine Learning
  • Biomedical Engineering

Background:

  • Automatic classification of normal mammograms is crucial for efficient breast cancer screening.
  • Feature distributions in digitized mammograms can be non-separable, limiting diagnostic algorithms.
  • Current computer-aided diagnosis (CAD) systems face challenges with complex feature data.

Purpose of the Study:

  • To develop a novel method for mapping non-separable features into separable ones for improved mammogram classification.
  • To enhance the performance of support vector machine (SVM) classifiers in breast cancer detection.
  • To address limitations in CAD systems caused by complex feature distributions.

Main Methods:

  • Feature mapping technique to transform non-separable "crossed" distributions into separable ones.

Related Experiment Videos

Last Updated: Jul 17, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

  • Integration of transformed features with existing "uncrossed" features.
  • Utilizing a support vector machine (SVM) classifier for automatic mammogram classification.

    • Main Results:

    • The proposed method successfully mapped non-separable features into a usable format.
    • Improved classification performance was observed using the enhanced feature set.
    • Achieved 80% sensitivity and 95% specificity in classifying normal mammograms.

    Conclusions:

    • The feature mapping technique offers a viable solution for handling non-separable data in mammogram analysis.
    • This approach significantly improves the accuracy of computer-aided diagnosis for breast cancer screening.
    • The method demonstrates potential for more reliable and efficient CAD systems.