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

Pattern recognition methods for optimizing multivariate tissue signatures in diagnostic ultrasound.

M F Insana, R F Wagner, B S Garra

    Ultrasonic Imaging
    |July 1, 1986
    PubMed
    Summary

    This study introduces a supervised parametric method using acoustic data for disease detection and classification. It effectively discriminates between normal and diseased liver tissues using ultrasonic parameters and statistical pattern recognition.

    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

    Dermatological depictions in animated movies.

    The British journal of dermatology·2018
    Same author

    Twenty-first-century skin findings response.

    Journal of the European Academy of Dermatology and Venereology : JEADV·2018
    Same author

    Exogenous ghrelin administration increases alcohol self-administration and modulates brain functional activity in heavy-drinking alcohol-dependent individuals.

    Molecular psychiatry·2017
    Same author

    Methylomic profiling and replication implicates deregulation of PCSK9 in alcohol use disorder.

    Molecular psychiatry·2017
    Same author

    Defining the role of corticotropin releasing factor binding protein in alcohol consumption.

    Translational psychiatry·2016
    Same author

    Indentation Analysis of Biphasic Viscoelastic Hydrogels.

    Mechanics of materials : an international journal·2015

    Area of Science:

    • Medical Imaging
    • Biomedical Engineering
    • Acoustic Signal Processing

    Background:

    • Disease detection and classification from acoustic data is crucial for medical diagnostics.
    • Ultrasonic tissue signatures offer a non-invasive approach to assessing tissue health.
    • Statistical pattern recognition can enhance the accuracy of diagnostic tools.

    Purpose of the Study:

    • To develop and evaluate a supervised parametric approach for disease detection using acoustic data.
    • To identify optimal combinations of ultrasonic tissue parameters for discriminating between normal and diseased liver.
    • To assess the performance of diagnostic tools using statistical pattern recognition techniques.

    Main Methods:

    • Implemented statistical pattern recognition for designing ultrasonic tissue signatures.

    Related Experiment Videos

  • Utilized combinations of four ultrasonic tissue parameters for in vivo discrimination.
  • Applied the Bayes decision rule for minimum risk, incorporating prior probabilities and misclassification costs.
  • Evaluated classification performance using the Hotelling trace criterion (HTC) and receiver operating characteristic (ROC) analysis.

    • Main Results:

    • Demonstrated significant differences in classification performance among various tissue parameter combinations.
    • Showcased the effectiveness of HTC and ROC analysis in evaluating discriminability.
    • Validated the approach for distinguishing between normal liver and chronic active hepatitis.

    Conclusions:

    • The supervised parametric approach provides a robust method for disease detection and classification from acoustic data.
    • Ultrasonic tissue parameter combinations significantly impact diagnostic accuracy.
    • The framework allows for direct evaluation of additional measurements' impact on discriminability.