Temporal analysis of mammograms based on graph matching

Fei Ma; Mariusz Bajger; Murk Bottema

doi:10.1007/978-3-540-70538-3_23

Temporal analysis of mammograms based on graph matching

Fei Ma, Mariusz Bajger, Murk Bottema

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

6 Citations (Scopus)

Abstract

A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.

Original language	English
Title of host publication	Digital Mammography
Subtitle of host publication	9th International Workshop, IWDM 2008 Tucson, AZ, USA, July 20-23, 2008 Proceedings
Editors	Elizabeth A Krupinski
Place of Publication	Berlin
Publisher	Springer
Pages	89-92
Number of pages	4
ISBN (Electronic)	978-3-540-70538-3
ISBN (Print)	978-3-540-70537-6
DOIs	https://doi.org/10.1007/978-3-540-70538-3_23
Publication status	Published - 2008
Event	9th International Workshop on Digital Mammography - Tucson, United States Duration: 20 Jul 2008 → 23 Jul 2008

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	5116

Workshop

Workshop	9th International Workshop on Digital Mammography
Country/Territory	United States
City	Tucson
Period	20/07/08 → 23/07/08

Access to Document

10.1007/978-3-540-70538-3_23Licence: In Copyright

https://rdcu.be/dA8FFLicence: In Copyright

Cite this

@inproceedings{ec1493d6b4884ad7bb1f736d245ef2b8,

title = "Temporal analysis of mammograms based on graph matching",

abstract = "A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.",

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

year = "2008",

doi = "10.1007/978-3-540-70538-3_23",

language = "English",

isbn = "978-3-540-70537-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "89--92",

editor = "Krupinski, {Elizabeth A}",

booktitle = "Digital Mammography",

note = "9th International Workshop on Digital Mammography ; Conference date: 20-07-2008 Through 23-07-2008",

}

Ma, F, Bajger, M & Bottema, M 2008, Temporal analysis of mammograms based on graph matching. in EA Krupinski (ed.), Digital Mammography: 9th International Workshop, IWDM 2008 Tucson, AZ, USA, July 20-23, 2008 Proceedings. Lecture Notes in Computer Science, vol. 5116, Springer , Berlin, pp. 89-92, 9th International Workshop on Digital Mammography, Tucson, Arizona, United States, 20/07/08. https://doi.org/10.1007/978-3-540-70538-3_23

Temporal analysis of mammograms based on graph matching. / Ma, Fei; Bajger, Mariusz ; Bottema, Murk.
Digital Mammography: 9th International Workshop, IWDM 2008 Tucson, AZ, USA, July 20-23, 2008 Proceedings. ed. / Elizabeth A Krupinski. Berlin: Springer , 2008. p. 89-92 (Lecture Notes in Computer Science; Vol. 5116).

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

TY - GEN

T1 - Temporal analysis of mammograms based on graph matching

AU - Ma, Fei

AU - Bajger, Mariusz

AU - Bottema, Murk

PY - 2008

Y1 - 2008

N2 - A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.

AB - A method is proposed for detecting masses in screening mammograms by analyzing changes between current and previous mammograms. The method uses graph matching in order to circumvent the problem of registering images of the same breast taken up to three years apart. Ninety five temporal pairs of images were separated into a training set (51 pairs) and a testing set (44 pairs). A small increase in performance, as measured by the area under the ROC curve, was found for the testing set when detection rates with graph matching were compared to detection rates without graph matching.

U2 - 10.1007/978-3-540-70538-3_23

DO - 10.1007/978-3-540-70538-3_23

M3 - Conference contribution

SN - 978-3-540-70537-6

T3 - Lecture Notes in Computer Science

SP - 89

EP - 92

BT - Digital Mammography

A2 - Krupinski, Elizabeth A

PB - Springer

CY - Berlin

T2 - 9th International Workshop on Digital Mammography

Y2 - 20 July 2008 through 23 July 2008

ER -

Temporal analysis of mammograms based on graph matching

Abstract

Publication series

Workshop

Access to Document

Fingerprint

Cite this