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

Mammographic mass detection using a mass template.

Serhat Ozekes1, Onur Osman, A Yilmaz Camurcu

  • 1Istanbul Commerce University, RagIp Gumuspala Cad. No: 84 Eminonu 34378 Istanbul, Turkey. serhat@iticu.edu.tr

Korean Journal of Radiology
|December 24, 2005
PubMed
Summary

This study introduces an automated template-based method for detecting masses in digital mammograms. The new algorithm shows satisfactory performance, potentially improving early diagnosis of mammographic masses.

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

Diagnostic value of machine-learning using conventional magnetic resonance imaging markers for pediatric idiopathic intracranial hypertension: a retrospective study.

Pediatric radiology·2026
Same author

A comprehensive evaluation of non-vascular prepontine cistern anatomy influencing trigeminal nerve vulnerability using machine learning-based morphometric analysis.

Frontiers in medicine·2026
Same author

Risk sensitive twin distributional critics with a lambda lower confidence bound for continuous control reinforcement learning.

Scientific reports·2026
Same author

The digital orchard: advanced data-driven technologies in apple breeding and genetic modification.

Frontiers in plant science·2026
Same author

Transferable CNN-based data mining approaches for medical imaging: application to spine DXA scans for osteoporosis detection.

Frontiers in computational neuroscience·2026
Same author

Fuzzy time series for short-term residential load forecasting in smart grids.

Scientific reports·2026

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Digital mammography is crucial for breast cancer screening.
  • Accurate mass detection is vital for early diagnosis and treatment.
  • Automated analysis methods can enhance mammogram interpretation.

Purpose of the Study:

  • To develop an automated mass detection method for digital mammograms.
  • To utilize template matching for identifying mass morphologies.
  • To improve the efficiency of computer-aided diagnosis systems.

Main Methods:

  • A two-step process involving region of interest (ROI) identification and template-based classification.
  • Scanning mammogram pixels in 8 directions to identify ROIs using thresholds.

Related Experiment Videos

  • Categorizing ROIs as true masses or non-masses based on shape similarity to templates.

    • Main Results:

    • Successfully identified 332 ROIs in 52 mammograms from the MIAS database.
    • Achieved sensitivities of 93%, 90%, and 81% using templates with 10, 20, and 30-pixel diameters, respectively.
    • Reported false positive rates of 1.3, 0.7, and 0.33 per image for the respective template sizes.

    Conclusions:

    • The template-based algorithm demonstrates satisfactory performance for mass detection.
    • This method has the potential to enhance computer-aided analysis of mammographic images.
    • The findings suggest an improvement in the early diagnosis of mammographic masses.