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

Automatic computer detection of clustered calcifications in digital mammograms.

D H Davies1, D R Dance

  • 1Joint Department of Physics, Institute of Cancer Research, London, UK.

Physics in Medicine and Biology
|August 1, 1990
PubMed
Summary

This study introduces an automated method for detecting calcification clusters in digital mammograms. The computer system achieved high accuracy, correctly identifying all positive cases with minimal false positives.

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

Mr. Davies's Case of Poison by Arsenic.

The Medical and physical journal·2018
Same author

On Calomel and Opium in Rheumatism.

The Medical and physical journal·2018
Same author

Effect of Mercury in Acute Rheumatism.

The Medical and physical journal·2018
Same author

Mr. Davies on the Good Effects of Calomel in a Case of Obstinate Vomiting.

The Medical and physical journal·2018
Same author

Case of Tumor on the Nose, by Mr. Davies.

The Medical and physical journal·2018
Same author

Mr. Davies on Mineral Poisons Entering the Circulation.

The Medical and physical journal·2018

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Radiology

Background:

  • Early detection of breast cancer is crucial.
  • Calcifications in mammograms can indicate malignancy.
  • Automated analysis of mammograms can aid radiologists.

Purpose of the Study:

  • To develop and evaluate an automated system for detecting calcification clusters in digital mammograms.
  • To assess the accuracy of the image analysis technique in classifying mammograms.

Main Methods:

  • Utilized image analysis techniques for automatic detection of calcification clusters.
  • Employed a local area thresholding process to segment calcifications from normal breast tissue.
  • Analyzed digital image properties of segmented objects.

Related Experiment Videos

  • Trained and tested the system on 75 digitized clinical mammograms (25 training, 50 testing).

    • Main Results:

    • The system achieved a 100% true positive rate for detecting films with calcification clusters in the test set (25/25).
    • False positive clusters were detected in only 4 out of 50 mammograms.
    • No false negative classifications were recorded, meaning all positive cases were identified.

    Conclusions:

    • The developed computer system demonstrates high accuracy and reliability for automatic detection of calcification clusters in digital mammograms.
    • This automated approach shows potential for improving the efficiency and accuracy of breast cancer screening.
    • Further validation on larger datasets is warranted to confirm clinical utility.