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

Computer-aided detection in direct digital full-field mammography: initial results.

F Baum1, U Fischer, S Obenauer

  • 1Department of Radiology, Georg-August-Universität Göttingen, Robert-Koch-Strasse 40, 37075 Göttingen, Germany. baumfried@web.de

European Radiology
|November 20, 2002
PubMed
Summary

This study evaluated computer-aided detection (CAD) for full-field digital mammography (FFDM) breast cancer detection. CAD showed 89% sensitivity for microcalcifications and 81% for masses, but false positives need reduction.

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

Arterial spin labelling perfusion MRI of breast cancer using FAIR TrueFISP: initial results.

Clinical radiology·2012
Same author

Missing data on retrospective recall of early-life socio-economic position in surveillance systems: an additional disadvantage?

Public health·2008
Same author

[Determination of renal carcinoma progression in small animals by means of flat-panel volumetric computer tomography].

Der Urologe. Ausg. A·2007
Same author

[Forms of urinary diversion--methods and imaging findings].

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2007
Same author

In vivo imaging in experimental preclinical tumor research--a review.

Cytometry. Part A : the journal of the International Society for Analytical Cytology·2007
Same author

[Characteristics and applications of a flat panel computer tomography system].

RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin·2006

Area of Science:

  • Radiology
  • Medical Imaging
  • Oncology

Background:

  • Full-field digital mammography (FFDM) enables direct digital image acquisition.
  • Computer-aided detection (CAD) systems analyze medical images for abnormalities.
  • Evaluating CAD performance with FFDM is crucial for breast cancer diagnosis.

Purpose of the Study:

  • To assess the efficacy of a specific CAD system (Image Checker V2.3) with FFDM.
  • To determine the sensitivity of CAD for detecting various breast cancer types on FFDM.
  • To evaluate the false-positive rate of CAD when used with FFDM.

Main Methods:

  • Sixty-three histologically confirmed breast cancer cases depicted with FFDM were analyzed.
  • A CAD system (Image Checker V2.3) was used to analyze the FFDM images.

Related Experiment Videos

  • Sensitivity for microcalcifications and masses, and false-positive rates were calculated and confidence intervals estimated.

    • Main Results:

    • The CAD system achieved 89% sensitivity for microcalcifications [95% CI=(70%; 98%)] and 81% for masses [95% CI=(67%; 91%)].
    • Detection rates correlated with BI-RADS categories, being higher for BI-RADS 5 lesions.
    • The overall false-positive rate was 0.61 marks per image (0.35 for microcalcifications, 0.26 for masses).

    Conclusions:

    • CAD analysis of FFDM data offers an optimized workflow.
    • The system's sensitivity for microcalcifications is acceptable, but for masses, it is considered low.
    • Reducing the number of false-positive marks per image is necessary for clinical improvement.