Breast density assessment using wavelet features on mammograms

Frank Schebesch, Mathias Unberath, Ingwer Andersen, Andreas Maier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Breast density differs from almost entirely fatty to extremely dense tissue composition. In mammography screenings, physicians are often supported by computer-aided detection and diagnosis systems (CAD) whose detection rate is affected by the density of the breast. An automatic pre-assessment of breast density would enable a specific analysis adapted to each density class. Digital mammograms from the INbreast database [1] are decomposed into Haar-Wavelet components and several levels are used for classification. A random forest classifier is applied on the averaged Wavelet components for four class densities which yields an accuracy of 64.53% in CC-view and 51.22% in MLO-view. The 3-class problem with a combined class of medium densities yields an accuracy of 73.89% in CC-view and 67.80% in MLO-view.

Original languageEnglish (US)
Title of host publicationBildverarbeitung fur die Medizin 2016
Subtitle of host publicationAlgorithmen – Systeme – Anwendungen - Proceedings des Workshops
EditorsThomas M. Deserno, Heinz Handels, Thomas Tolxdorff, Hans-Peter Meinzer
PublisherKluwer Academic Publishers
Pages38-43
Number of pages6
ISBN (Print)9783662494646
DOIs
StatePublished - 2017
Externally publishedYes
EventWorkshops on Image processing for the medicine, 2016 - Berlin, Germany
Duration: Mar 13 2016Mar 15 2016

Publication series

NameInformatik aktuell
ISSN (Print)1431-472X

Conference

ConferenceWorkshops on Image processing for the medicine, 2016
Country/TerritoryGermany
CityBerlin
Period3/13/163/15/16

ASJC Scopus subject areas

  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'Breast density assessment using wavelet features on mammograms'. Together they form a unique fingerprint.

Cite this