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

An automatic microcalcification detection system based on a hybrid neural network classifier.

A Papadopoulos1, D I Fotiadis, A Likas

  • 1Department of Medical Physics, Medical School, University of Ioannina, GR 45110, Ioannina, Greece. fotiadis@cs.uoi.gr

Artificial Intelligence in Medicine
|May 29, 2002
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

First Evidence for Mixing-Induced CP Violation in B_{s}^{0}→J/ψϕ(1020) Decays in pp Collisions at sqrt[s]=13  TeV.

Physical review letters·2026
Same author

Measurement of D^{0} Meson Photoproduction in Ultraperipheral Heavy Ion Collisions.

Physical review letters·2026
Same author

Black Hole Spectroscopy and Tests of General Relativity with GW250114.

Physical review letters·2026
Same author

Observation of Coherent ϕ(1020) Meson Photoproduction in Ultraperipheral PbPb Collisions at sqrt[s_{NN}]=5.36  TeV.

Physical review letters·2026
Same author

Position Paper: Artificial Intelligence in Medical Image Analysis: Advances, Clinical Translation, and Emerging Frontiers.

IEEE journal of biomedical and health informatics·2025
Same author

Search for New Physics in Jet Multiplicity Patterns of Multilepton Events at sqrt[s]=13  TeV.

Physical review letters·2025

This study introduces a hybrid intelligent system for detecting microcalcification clusters in mammograms, achieving high accuracy (A(z) of 0.91-0.92) and reducing false positives for improved breast cancer screening.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer-Aided Diagnosis

Background:

  • Accurate identification of microcalcification clusters in digital mammograms is crucial for early breast cancer detection.
  • Reducing false positive findings in mammography is essential to minimize patient anxiety and unnecessary biopsies.

Purpose of the Study:

  • To develop and evaluate a hybrid intelligent system for automated identification of microcalcification clusters in digital mammograms.
  • To enhance the accuracy and specificity of microcalcification detection while reducing false positive rates.

Main Methods:

  • A three-step procedure involving preprocessing, segmentation, region of interest (ROI) specification, feature extraction, and classification.
  • Utilizing a hybrid intelligent system with rule-based and neural network sub-systems for false positive reduction.

Related Experiment Videos

  • Employing Principal Component Analysis (PCA) for feature reduction from an initial set of 22 computed features.

    • Main Results:

    • The system achieved high performance on the Nijmegen and MIAS mammographic databases, with Area Under the Curve (A(z)) values of 0.91 and 0.92, respectively.
    • High sensitivity levels (greater than 0.90) were maintained with low false positive rates: 1.80 and 1.15 false positive clusters per image for Nijmegen and MIAS datasets, respectively.

    Conclusions:

    • The proposed hybrid intelligent system demonstrates significant potential for accurate and reliable detection of microcalcification clusters in digital mammograms.
    • The method effectively reduces false positives, contributing to more efficient and effective breast cancer screening programs.