Extracting the pectoral muscle in screening mammograms using a graph pyramid

Fie Ma; Mariusz Bajger; Murk Bottema

Extracting the pectoral muscle in screening mammograms using a graph pyramid

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

Abstract

A graph based method is introduced to segment the pectoral muscles in screening mammograms. An adaptive pyramid is used to segment the mammogram into a number of components. Components forming the pectoral muscle are identified based on position, intensity, and shape. The boundary of the union of these components forms an initial boundary that is refined via an adaptive deformable contour model. The method is tested on 83 medio-lateral oblique mammograms from the Mini-MIAS database. Segmentation results are evaluated in terms of the proportion of correctly assigned pixels. Performance compares well with existing methods based on Hough transform and on Gabor
wavelets.

Original language	English
Title of host publication	Proceedings of the APRS Workshop on Digital Image Computing
Editors	Brian C Lovell, Anthony J Maeder
Place of Publication	St Lucia, Queensland
Publisher	The University of Queensland
Number of pages	6
ISBN (Print)	0-9580255-3-3
Publication status	Published - Feb 2005
Event	APRS Workshop on Digital Image Computing - Duration: 21 Feb 2005 → …

Conference

Conference	APRS Workshop on Digital Image Computing
Period	21/02/05 → …

Access to Document

http://www.aprs.org.au/wdic2005/fullproceedings.pdfLicence: In Copyright

Fingerprint Dive into the research topics of 'Extracting the pectoral muscle in screening mammograms using a graph pyramid'. Together they form a unique fingerprint.

Cite this

@inproceedings{fd8a913da1ca461e9616233cbfc04d8e,

title = "Extracting the pectoral muscle in screening mammograms using a graph pyramid",

abstract = "A graph based method is introduced to segment the pectoral muscles in screening mammograms. An adaptive pyramid is used to segment the mammogram into a number of components. Components forming the pectoral muscle are identified based on position, intensity, and shape. The boundary of the union of these components forms an initial boundary that is refined via an adaptive deformable contour model. The method is tested on 83 medio-lateral oblique mammograms from the Mini-MIAS database. Segmentation results are evaluated in terms of the proportion of correctly assigned pixels. Performance compares well with existing methods based on Hough transform and on Gaborwavelets.",

author = "Fie Ma and Mariusz Bajger and Murk Bottema",

year = "2005",

month = feb,

language = "English",

isbn = "0-9580255-3-3",

editor = "Lovell, {Brian C} and Maeder, {Anthony J}",

booktitle = "Proceedings of the APRS Workshop on Digital Image Computing",

publisher = "The University of Queensland",

note = "APRS Workshop on Digital Image Computing ; Conference date: 21-02-2005",

}

Extracting the pectoral muscle in screening mammograms using a graph pyramid. / Ma, Fie; Bajger, Mariusz ; Bottema, Murk.

Proceedings of the APRS Workshop on Digital Image Computing. ed. / Brian C Lovell; Anthony J Maeder. St Lucia, Queensland : The University of Queensland, 2005.

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

TY - GEN

T1 - Extracting the pectoral muscle in screening mammograms using a graph pyramid

AU - Ma, Fie

AU - Bajger, Mariusz

AU - Bottema, Murk

PY - 2005/2

Y1 - 2005/2

N2 - A graph based method is introduced to segment the pectoral muscles in screening mammograms. An adaptive pyramid is used to segment the mammogram into a number of components. Components forming the pectoral muscle are identified based on position, intensity, and shape. The boundary of the union of these components forms an initial boundary that is refined via an adaptive deformable contour model. The method is tested on 83 medio-lateral oblique mammograms from the Mini-MIAS database. Segmentation results are evaluated in terms of the proportion of correctly assigned pixels. Performance compares well with existing methods based on Hough transform and on Gaborwavelets.

AB - A graph based method is introduced to segment the pectoral muscles in screening mammograms. An adaptive pyramid is used to segment the mammogram into a number of components. Components forming the pectoral muscle are identified based on position, intensity, and shape. The boundary of the union of these components forms an initial boundary that is refined via an adaptive deformable contour model. The method is tested on 83 medio-lateral oblique mammograms from the Mini-MIAS database. Segmentation results are evaluated in terms of the proportion of correctly assigned pixels. Performance compares well with existing methods based on Hough transform and on Gaborwavelets.

M3 - Conference contribution

SN - 0-9580255-3-3

BT - Proceedings of the APRS Workshop on Digital Image Computing

A2 - Lovell, Brian C

A2 - Maeder, Anthony J

PB - The University of Queensland

CY - St Lucia, Queensland

T2 - APRS Workshop on Digital Image Computing

Y2 - 21 February 2005

ER -