Two graph theory based methods for identifying the pectoral muscle in mammograms

Fei Ma; Mariusz Bajger; John P. Slavotinek; Murk J. Bottema

doi:10.1016/j.patcog.2006.12.011

Two graph theory based methods for identifying the pectoral muscle in mammograms

Fei Ma, Mariusz Bajger, John P. Slavotinek, Murk J. Bottema^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

78 Citations (Scopus)

Abstract

Two image segmentation methods based on graph theory are used in conjunction with active contours to segment the pectoral muscle in screening mammograms. One method is based on adaptive pyramids (AP) and the other is based on minimum spanning trees (MST). The algorithms are tested on a public data set of mammograms and results are compared with previously reported methods. In 80% of the images, the boundary of the segmented regions has average error less than 2 mm. In 82 of 84 images, the boundary of the pectoral muscle found by the AP algorithm has average error less than 5 mm.

Original language	English
Pages (from-to)	2592-2602
Number of pages	11
Journal	Pattern Recognition
Volume	40
Issue number	9
DOIs	https://doi.org/10.1016/j.patcog.2006.12.011
Publication status	Published - Sept 2007
Externally published	Yes

Keywords

Adaptive pyramid
Computer-aided diagnosis
Mammography
Minimum spanning tree
Pectoral muscle
Segmentation

Access to Document

10.1016/j.patcog.2006.12.011

Cite this

@article{be07713f3ad94246893f1e8ecd08d55b,

title = "Two graph theory based methods for identifying the pectoral muscle in mammograms",

abstract = "Two image segmentation methods based on graph theory are used in conjunction with active contours to segment the pectoral muscle in screening mammograms. One method is based on adaptive pyramids (AP) and the other is based on minimum spanning trees (MST). The algorithms are tested on a public data set of mammograms and results are compared with previously reported methods. In 80% of the images, the boundary of the segmented regions has average error less than 2 mm. In 82 of 84 images, the boundary of the pectoral muscle found by the AP algorithm has average error less than 5 mm.",

keywords = "Adaptive pyramid, Computer-aided diagnosis, Mammography, Minimum spanning tree, Pectoral muscle, Segmentation",

author = "Fei Ma and Mariusz Bajger and Slavotinek, {John P.} and Bottema, {Murk J.}",

year = "2007",

month = sep,

doi = "10.1016/j.patcog.2006.12.011",

language = "English",

volume = "40",

pages = "2592--2602",

journal = "Pattern Recognition",

issn = "0031-3203",

number = "9",

}

TY - JOUR

T1 - Two graph theory based methods for identifying the pectoral muscle in mammograms

AU - Ma, Fei

AU - Bajger, Mariusz

AU - Slavotinek, John P.

AU - Bottema, Murk J.

PY - 2007/9

Y1 - 2007/9

N2 - Two image segmentation methods based on graph theory are used in conjunction with active contours to segment the pectoral muscle in screening mammograms. One method is based on adaptive pyramids (AP) and the other is based on minimum spanning trees (MST). The algorithms are tested on a public data set of mammograms and results are compared with previously reported methods. In 80% of the images, the boundary of the segmented regions has average error less than 2 mm. In 82 of 84 images, the boundary of the pectoral muscle found by the AP algorithm has average error less than 5 mm.

AB - Two image segmentation methods based on graph theory are used in conjunction with active contours to segment the pectoral muscle in screening mammograms. One method is based on adaptive pyramids (AP) and the other is based on minimum spanning trees (MST). The algorithms are tested on a public data set of mammograms and results are compared with previously reported methods. In 80% of the images, the boundary of the segmented regions has average error less than 2 mm. In 82 of 84 images, the boundary of the pectoral muscle found by the AP algorithm has average error less than 5 mm.

KW - Adaptive pyramid

KW - Computer-aided diagnosis

KW - Mammography

KW - Minimum spanning tree

KW - Pectoral muscle

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=34247586627&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2006.12.011

DO - 10.1016/j.patcog.2006.12.011

M3 - Article

AN - SCOPUS:34247586627

SN - 0031-3203

VL - 40

SP - 2592

EP - 2602

JO - Pattern Recognition

JF - Pattern Recognition

IS - 9

ER -

Two graph theory based methods for identifying the pectoral muscle in mammograms

Abstract

Keywords

Access to Document

Other files and links

Cite this