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

Parameter estimation in stochastic mammogram model by heuristic optimization techniques.

S Easter Selvan1, C Cecil Xavier, Nico Karssemeijer

  • 1Laboratoire des Sciences de l'Information et des Systèmes, Université de la Méditerranée, 13288 Marseille Cedex 9, France. Easter.Selvan@esil.univ-mrs.fr

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|October 19, 2006
PubMed
Summary
This summary is machine-generated.

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

Development and internal validation of mammography feature-based prognostic models for distant recurrence-free survival of invasive breast cancer in a screening cohort.

NPJ breast cancer·2026
Same author

Mammo-AGE: deep learning estimation of breast age from mammograms.

Nature communications·2025
Same author

Predicting short- to long-term breast cancer risk from longitudinal mammographic screening history.

NPJ breast cancer·2025
Same author

AI as an independent second reader in detection of clinically relevant breast cancers within a population-based screening programme in the Netherlands: a retrospective cohort study.

The Lancet. Digital health·2025
Same author

Breast cancer in women after withdrawing from an increased-risk MRI screening program.

European radiology·2025
Same author

Robotic Resection of an Idiopathic Azygos Vein Aneurysm and the Diagnostic Role of Thoracic Venogram.

Innovations (Philadelphia, Pa.)·2025

This study introduces heuristic optimization, including particle swarm optimization and evolutionary programming, to improve breast density model accuracy for cancer risk assessment. The new method offers more precise parameter estimation than the expectation-maximization algorithm.

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Radiology

Background:

  • High breast density on mammograms is a significant breast cancer risk factor.
  • Accurate breast density modeling is crucial for risk estimation and monitoring.
  • Conventional methods like the expectation-maximization (EM) algorithm have limitations in parameter estimation efficiency.

Purpose of the Study:

  • To propose a novel heuristic optimization approach for more accurate breast density model parameter estimation.
  • To compare the performance of heuristic optimization techniques against the conventional EM algorithm.
  • To enhance the reliability of breast density models for cancer risk assessment.

Main Methods:

  • Mammogram segmentation followed by the construction of a finite generalized Gaussian mixture (FGGM) model.

Related Experiment Videos

  • Parameter estimation using particle swarm optimization (PSO) and evolutionary programming (EP).
  • Minimizing relative entropy between image histogram and estimated density distributions.

    • Main Results:

    • Heuristic optimization achieved lower estimation error rates (97.3% and 99.0%) compared to the EM algorithm for different numbers of image regions.
    • The heuristic approach demonstrated a faster convergence rate.
    • Segmentation results were promising and preserved the number of regions specified by information-theoretic criteria.

    Conclusions:

    • Heuristic optimization provides a more accurate and efficient method for estimating breast density model parameters.
    • This improved accuracy can lead to more reliable breast cancer risk assessment.
    • The proposed method shows potential for clinical application in mammography analysis.