Breast density assessment using wavelet features on mammograms

Frank Schebesch; Mathias Unberath; Ingwer Andersen; Andreas Maier

doi:10.1007/978-3-662-49465-3_9

Breast density assessment using wavelet features on mammograms

Frank Schebesch, Mathias Unberath, Ingwer Andersen, Andreas Maier

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	Bildverarbeitung fur die Medizin 2016
Subtitle of host publication	Algorithmen – Systeme – Anwendungen - Proceedings des Workshops
Editors	Thomas M. Deserno, Heinz Handels, Thomas Tolxdorff, Hans-Peter Meinzer
Publisher	Kluwer Academic Publishers
Pages	38-43
Number of pages	6
ISBN (Print)	9783662494646
DOIs	https://doi.org/10.1007/978-3-662-49465-3_9
State	Published - 2017
Externally published	Yes
Event	Workshops on Image processing for the medicine, 2016 - Berlin, Germany Duration: Mar 13 2016 → Mar 15 2016

Publication series

Name	Informatik aktuell
ISSN (Print)	1431-472X

Conference

Conference	Workshops on Image processing for the medicine, 2016
Country/Territory	Germany
City	Berlin
Period	3/13/16 → 3/15/16

ASJC Scopus subject areas

Modeling and Simulation

Access to Document

10.1007/978-3-662-49465-3_9

Cite this

Schebesch, F., Unberath, M., Andersen, I., & Maier, A. (2017). Breast density assessment using wavelet features on mammograms. In T. M. Deserno, H. Handels, T. Tolxdorff, & H.-P. Meinzer (Eds.), Bildverarbeitung fur die Medizin 2016: Algorithmen – Systeme – Anwendungen - Proceedings des Workshops (pp. 38-43). (Informatik aktuell). Kluwer Academic Publishers. https://doi.org/10.1007/978-3-662-49465-3_9

Breast density assessment using wavelet features on mammograms. / Schebesch, Frank; Unberath, Mathias; Andersen, Ingwer et al.
Bildverarbeitung fur die Medizin 2016: Algorithmen – Systeme – Anwendungen - Proceedings des Workshops. ed. / Thomas M. Deserno; Heinz Handels; Thomas Tolxdorff; Hans-Peter Meinzer. Kluwer Academic Publishers, 2017. p. 38-43 (Informatik aktuell).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Schebesch, F, Unberath, M, Andersen, I & Maier, A 2017, Breast density assessment using wavelet features on mammograms. in TM Deserno, H Handels, T Tolxdorff & H-P Meinzer (eds), Bildverarbeitung fur die Medizin 2016: Algorithmen – Systeme – Anwendungen - Proceedings des Workshops. Informatik aktuell, Kluwer Academic Publishers, pp. 38-43, Workshops on Image processing for the medicine, 2016, Berlin, Germany, 3/13/16. https://doi.org/10.1007/978-3-662-49465-3_9

Schebesch F, Unberath M, Andersen I, Maier A. Breast density assessment using wavelet features on mammograms. In Deserno TM, Handels H, Tolxdorff T, Meinzer HP, editors, Bildverarbeitung fur die Medizin 2016: Algorithmen – Systeme – Anwendungen - Proceedings des Workshops. Kluwer Academic Publishers. 2017. p. 38-43. (Informatik aktuell). doi: 10.1007/978-3-662-49465-3_9

Schebesch, Frank ; Unberath, Mathias ; Andersen, Ingwer et al. / Breast density assessment using wavelet features on mammograms. Bildverarbeitung fur die Medizin 2016: Algorithmen – Systeme – Anwendungen - Proceedings des Workshops. editor / Thomas M. Deserno ; Heinz Handels ; Thomas Tolxdorff ; Hans-Peter Meinzer. Kluwer Academic Publishers, 2017. pp. 38-43 (Informatik aktuell).

@inproceedings{f1913258cdb74b8fb2d73eeeaf610d39,

title = "Breast density assessment using wavelet features on mammograms",

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.",

author = "Frank Schebesch and Mathias Unberath and Ingwer Andersen and Andreas Maier",

note = "Funding Information: The authors gratefully acknowledge funding of the Erlangen Graduate School in Advanced Optical Technologies (SAOT) by the German Research Foundation (DFG) in the framework of the German excellence initiative. Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2016.; Workshops on Image processing for the medicine, 2016 ; Conference date: 13-03-2016 Through 15-03-2016",

year = "2017",

doi = "10.1007/978-3-662-49465-3_9",

language = "English (US)",

isbn = "9783662494646",

series = "Informatik aktuell",

publisher = "Kluwer Academic Publishers",

pages = "38--43",

editor = "Deserno, {Thomas M.} and Heinz Handels and Thomas Tolxdorff and Hans-Peter Meinzer",

booktitle = "Bildverarbeitung fur die Medizin 2016",

}

TY - GEN

T1 - Breast density assessment using wavelet features on mammograms

AU - Schebesch, Frank

AU - Unberath, Mathias

AU - Andersen, Ingwer

AU - Maier, Andreas

N1 - Funding Information: The authors gratefully acknowledge funding of the Erlangen Graduate School in Advanced Optical Technologies (SAOT) by the German Research Foundation (DFG) in the framework of the German excellence initiative. Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2016.

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85019860437&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019860437&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-49465-3_9

DO - 10.1007/978-3-662-49465-3_9

M3 - Conference contribution

AN - SCOPUS:85019860437

SN - 9783662494646

T3 - Informatik aktuell

SP - 38

EP - 43

BT - Bildverarbeitung fur die Medizin 2016

A2 - Deserno, Thomas M.

A2 - Handels, Heinz

A2 - Tolxdorff, Thomas

A2 - Meinzer, Hans-Peter

PB - Kluwer Academic Publishers

T2 - Workshops on Image processing for the medicine, 2016

Y2 - 13 March 2016 through 15 March 2016

ER -

Breast density assessment using wavelet features on mammograms

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this