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

Digital mammography: computer-assisted diagnosis method for mass detection with multiorientation and multiresolution

L Li1, W Qian, L P Clarke

  • 1Department of Radiology, College of Medicine, University of South Florida, Tampa 33612-4799, USA.

Academic Radiology
|November 20, 1997
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

Sequences flanking the pentanucleotide T-antigen binding sites in the polyomavirus core origin help determine selectivity of DNA replication.

Journal of virology·1995
Same author

Inactivation and conformation changes of the glycated and non-glycated D-glyceraldehyde-3-phosphate dehydrogenase during guanidine-HCl denaturation.

Biochimica et biophysica acta·1995
Same author

Safe separation of sputum cells from mucoid glycoprotein.

Acta cytologica·1995
Same author

Linkage between sexual orientation and chromosome Xq28 in males but not in females.

Nature genetics·1995
Same author

Dermo-1: a novel twist-related bHLH protein expressed in the developing dermis.

Developmental biology·1995
Same author

Positive regulation of human alpha 1 (I) collagen promoter activity by transcription factor Sp1.

Gene·1995

A new computer-assisted diagnosis (CAD) method using directional wavelet transform (DWT) significantly improved mass detection sensitivity to 98% and reduced false positives. This automated approach aids mammogram interpretation.

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Signal Processing

Background:

  • Mammography is crucial for early breast cancer detection.
  • Computer-assisted diagnosis (CAD) systems aim to enhance mammogram interpretation.
  • Improving sensitivity and reducing false positives in mass detection are key challenges.

Purpose of the Study:

  • To evaluate a modular computer-assisted diagnosis (CAD) method for mass detection.
  • To improve detection sensitivity and reduce false-positive (FP) rates.
  • To assess the utility of directional texture features in CAD.

Main Methods:

  • A directional wavelet transform (DWT) method was developed for feature computation in gray level, morphology, and directional texture domains.
  • The DWT method was applied to a database of 50 normal and 45 abnormal digitized mammograms.

Related Experiment Videos

  • Performance was compared against the Markov random field (MRF) method using free-response receiver operating characteristic (FROC) curves.

    • Main Results:

    • The DWT method achieved a sensitivity of 98% with 1.8 FP findings per image.
    • The MRF method achieved a sensitivity of 90% with 2.0 FP findings per image.
    • The DWT method demonstrated superior performance in both sensitivity and FP rate compared to the MRF method.

    Conclusions:

    • The evaluated CAD method is automatic and mass-type independent.
    • The DWT-based feature extraction shows promise for enhancing mammographic mass detection.
    • Potential for improved visual interpretation aligned with ACR criteria.