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

Neural Network Analysis of DNA flow cytometry histograms

P M Ravdin1, G M Clark, J J Hough

  • 1Division of Medical Oncology, University of Texas Health Science Center, San Antonio 78284-7884.

Cytometry
|January 1, 1993
PubMed
Summary

Artificial intelligence using Neural Network Analysis improves breast cancer relapse prediction by analyzing DNA flow cytometry histograms. This AI approach identifies high-risk patients more accurately by focusing on specific DNA content regions.

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

A phase I and pharmacokinetic trial of terephthalamidine (NSC 57155) as a 120-hour continuous infusion.

Investigational new drugs·1998
Same author

Chronic study on the neuronal excitability of the cochlear nuclei of the cat following electrical stimulation.

Acta oto-laryngologica·1998
Same author

Studies of prosody perception by cochlear implant patients.

Audiology : official organ of the International Society of Audiology·1998
Same author

Enzyme-linked immunoabsorbent assay-detected p53 protein accumulation: a prognostic factor in a large breast cancer cohort.

Journal of clinical oncology : official journal of the American Society of Clinical Oncology·1998
Same author

Modulation detection interference in cochlear implant subjects.

The Journal of the Acoustical Society of America·1998
Same author

Intracellular responses of the rat anteroventral cochlear nucleus to intracochlear electrical stimulation.

Brain research bulletin·1998

Area of Science:

  • Oncology
  • Bioinformatics
  • Artificial Intelligence

Background:

  • DNA flow cytometry is crucial for analyzing cancer cell DNA content.
  • Conventional analysis categorizes histograms by ploidy and S-phase fraction.
  • Identifying novel predictive features in histograms can improve breast cancer outcome prediction.

Purpose of the Study:

  • To investigate the utility of Neural Network Analysis (a pattern recognition system) in identifying breast cancer relapse risk from DNA flow cytometry histograms.
  • To compare the predictive performance of Neural Network Analysis with conventional methods.

Main Methods:

  • Trained a Neural Network using DNA flow cytometry histograms and clinical data from 796 breast cancer patients.
  • Validated the model on an independent set of 794 patients.

Related Experiment Videos

  • Evaluated histogram features emphasized by Neural Network Analysis, particularly the region right of the diploid G2/M peak.

    • Main Results:

    • Neural Network Analysis identified distinct low-risk and high-risk patient subsets with accuracy comparable to conventional analysis.
    • The number of nuclei with high DNA content (right of the diploid G2/M peak) emerged as a powerful predictor of patient outcome.
    • Both the number of nuclei in this high DNA content region and S-phase fraction were independently predictive of relapse.

    Conclusions:

    • Neural Network Analysis offers a complementary approach to conventional DNA flow cytometry histogram interpretation.
    • Pattern recognition systems like Neural Network Analysis can enhance the predictive power of existing methods for breast cancer relapse.
    • Further studies are warranted to integrate AI-driven insights into routine clinical practice for improved patient stratification.