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

Medical image databases for CAD applications in digital mammography: design issues.

M Kallergi1, R A Clark, L P Clarke

  • 1Department of Radiology, University of South Florida, Tampa 33612, USA.

Studies in Health Technology and Informatics
|December 8, 1996
PubMed
Summary

Creating standardized digital mammography databases is crucial for evaluating computer-assisted diagnosis algorithms. This study addresses the lack of consensus on database guidelines, proposing solutions for consistent algorithm assessment.

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

An Assessment of Imaging Informatics for Precision Medicine in Cancer.

Yearbook of medical informatics·2017
Same author

The Reference Image Database to Evaluate Response to therapy in lung cancer (RIDER) project: a resource for the development of change-analysis software.

Clinical pharmacology and therapeutics·2008
Same author

Improved method for automatic identification of lung regions on chest radiographs.

Academic radiology·2001
Same author

NCI image archive management workshop: a preliminary report.

Academic radiology·2001
Same author

National Cancer Institute initiative: Lung image database resource for imaging research.

Academic radiology·2001
Same author

NCI initiative: development of novel imaging technologies.

IEEE transactions on medical imaging·2000

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Healthcare
  • Radiology Informatics

Background:

  • Evaluating computer-assisted diagnosis (CADx) algorithms in digital mammography necessitates robust image databases for comparative analysis.
  • Current literature reveals a lack of standardized guidelines for establishing these essential databases.
  • Image selection for existing databases often relies on subjective judgment or simple availability, hindering objective algorithm assessment.

Purpose of the Study:

  • To review and discuss critical issues surrounding the creation and utilization of digital mammography image databases for CADx algorithm evaluation.
  • To propose potential solutions and best practices for developing standardized databases that facilitate reliable algorithm comparisons.
  • To address the ongoing challenges related to optimal database size, image resolution, and content selection.

Related Experiment Videos

Main Methods:

  • Literature review of existing guidelines and practices for digital mammography database creation.
  • Analysis of subjective and availability-based image selection methods.
  • Discussion of key database parameters: size, resolution, and content.

Main Results:

  • Identified a significant lack of consensus on database development guidelines in the field.
  • Highlighted the limitations of subjective image selection and the need for objective criteria.
  • Recognized the importance of common, accessible databases for reproducible algorithm evaluation.

Conclusions:

  • Standardized digital mammography databases are essential for the reliable clinical validation of CADx algorithms.
  • Addressing database size, resolution, and content is critical for meaningful algorithm comparisons.
  • Developing community-accepted database guidelines will advance the field of computer-assisted diagnosis in mammography.