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

Breast tissue classification using diagnostic ultrasound and pattern recognition techniques: I. Methods of pattern

S Finette, A Bleier, W Swindell

    Ultrasonic Imaging
    |January 1, 1983
    PubMed
    Summary

    This study applies statistical pattern recognition to diagnostic ultrasound for computer-aided breast tissue classification. The methods developed help classify in vivo breast tissue and estimate future classification error probabilities.

    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

    Detection on a distributed network using information geometry.

    JASA express letters·2022
    Same author

    Multisensor hyperspectral imaging approach for the microchemical analysis of ultramarine blue pigments.

    Scientific reports·2022
    Same author

    Incoherent optical processor for x-ray transaxial tomography.

    Applied optics·2010
    Same author

    Optical transfer function synthesis: a geometrical optics approach.

    Applied optics·2010
    Same author

    Extraordinary-ray and -wave tracing in uniaxial crystals.

    Applied optics·2010
    Same author

    Effect of environmental changes on the ghosting of distant objects in twin-glazed windows.

    Applied optics·2010

    Area of Science:

    • Medical imaging
    • Biomedical engineering
    • Pattern recognition

    Background:

    • Diagnostic ultrasound is crucial for breast tissue analysis.
    • Accurate classification of breast tissue is essential for diagnosis.
    • Existing methods require enhancement for improved accuracy.

    Purpose of the Study:

    • To apply statistical pattern recognition techniques to diagnostic ultrasound.
    • To develop a system for computer-aided classification of in vivo breast tissue.
    • To introduce a method for estimating classification error probability.

    Main Methods:

    • Feature generation and selection were employed.
    • Classification algorithms were applied to breast tissue data.
    • A novel method for estimating future error probability was developed.

    Related Experiment Videos

    Main Results:

    • The developed system demonstrated effective computer-aided classification of breast tissue.
    • Feature selection improved classification accuracy.
    • The error estimation method provides a measure of confidence in future classifications.

    Conclusions:

    • Statistical pattern recognition offers a powerful approach for diagnostic ultrasound applications.
    • The methods presented can enhance the accuracy and reliability of breast tissue classification.
    • This work contributes to the advancement of computer-aided diagnostic tools in medical imaging.