Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms

Mariusz Bajger; Fie Ma; Murk Bottema

doi:10.1109/DICTA.2005.55

Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms

Mariusz Bajger, Fie Ma, Murk Bottema

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

13 Citations (Scopus)

Abstract

Image segmentation based on minimum spanning trees (MST) is used to identify the pectoral muscle in screening mammograms. The segmentation found using the MST is used to initialise an active contour for finding an anatomically reasonable estimate of the boundary of the pectoral muscle. The error is reported in terms of the number of in-correctly assigned pixels. Out of 83 images, 25 images have error rates less than 5 percent and 56 images have error rates less than 10 percent. The nature of the errors encountered indicates that the accuracy of computer algorithms for this task is approaching its practical limit.

Original language	English
Title of host publication	Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	47
Number of pages	1
ISBN (Print)	0-7695-2490-7
DOIs	https://doi.org/10.1109/DICTA.2005.55
Publication status	Published - Dec 2005
Event	Digital Image Computing Techniques and Applications 2005 - Cairns Convention Centre, Cairns, Australia Duration: 6 Dec 2005 → 8 Dec 2005

Conference

Conference	Digital Image Computing Techniques and Applications 2005
Country/Territory	Australia
City	Cairns
Period	6/12/05 → 8/12/05

Access to Document

10.1109/DICTA.2005.55Licence: In Copyright

Cite this

@inproceedings{ca729aaa8565439e9762d9d0aa1cd0ce,

title = "Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms",

abstract = "Image segmentation based on minimum spanning trees (MST) is used to identify the pectoral muscle in screening mammograms. The segmentation found using the MST is used to initialise an active contour for finding an anatomically reasonable estimate of the boundary of the pectoral muscle. The error is reported in terms of the number of in-correctly assigned pixels. Out of 83 images, 25 images have error rates less than 5 percent and 56 images have error rates less than 10 percent. The nature of the errors encountered indicates that the accuracy of computer algorithms for this task is approaching its practical limit.",

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

year = "2005",

month = dec,

doi = "10.1109/DICTA.2005.55",

language = "English",

isbn = "0-7695-2490-7",

pages = "47",

booktitle = "Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Digital Image Computing Techniques and Applications 2005 ; Conference date: 06-12-2005 Through 08-12-2005",

}

Bajger, M, Ma, F & Bottema, M 2005, Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms. in Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA). Institute of Electrical and Electronics Engineers Inc., Piscataway, NJ , pp. 47, Digital Image Computing Techniques and Applications 2005, Cairns, Queensland, Australia, 6/12/05. https://doi.org/10.1109/DICTA.2005.55

Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms. / Bajger, Mariusz; Ma, Fie; Bottema, Murk.

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA). Piscataway, NJ : Institute of Electrical and Electronics Engineers Inc., 2005. p. 47.

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

TY - GEN

T1 - Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms

AU - Bajger, Mariusz

AU - Ma, Fie

AU - Bottema, Murk

PY - 2005/12

Y1 - 2005/12

N2 - Image segmentation based on minimum spanning trees (MST) is used to identify the pectoral muscle in screening mammograms. The segmentation found using the MST is used to initialise an active contour for finding an anatomically reasonable estimate of the boundary of the pectoral muscle. The error is reported in terms of the number of in-correctly assigned pixels. Out of 83 images, 25 images have error rates less than 5 percent and 56 images have error rates less than 10 percent. The nature of the errors encountered indicates that the accuracy of computer algorithms for this task is approaching its practical limit.

AB - Image segmentation based on minimum spanning trees (MST) is used to identify the pectoral muscle in screening mammograms. The segmentation found using the MST is used to initialise an active contour for finding an anatomically reasonable estimate of the boundary of the pectoral muscle. The error is reported in terms of the number of in-correctly assigned pixels. Out of 83 images, 25 images have error rates less than 5 percent and 56 images have error rates less than 10 percent. The nature of the errors encountered indicates that the accuracy of computer algorithms for this task is approaching its practical limit.

U2 - 10.1109/DICTA.2005.55

DO - 10.1109/DICTA.2005.55

M3 - Conference contribution

SN - 0-7695-2490-7

SP - 47

BT - Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway, NJ

T2 - Digital Image Computing Techniques and Applications 2005

Y2 - 6 December 2005 through 8 December 2005

ER -

Minimum spanning trees and active contours for identification of the pectoral muscle in screening mamograms

Abstract

Conference

Access to Document

Fingerprint

Cite this