Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination

Saejoon Kim; Sejong Yoon; Donghyuk Shin

doi:10.1109/FBIT.2007.9

Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination

Saejoon Kim, Sejong Yoon, Donghyuk Shin

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

Abstract

In the analysis of digital or digitized mammographic images, a requirement is to learn to separate benign calcifications from malignant ones. Such an activity could form part of a computer-aided diagnosis (CAD) tool. We present a CAD study of calcification lesions to demonstrate that CAD of same-institutional mammograms provides significantly higher accuracy compared to that of cross-institutional mammograms. Moreover, using only a subset of the widely used six BI-RADS features together with patient age and subtlety value describing each calcification lesion is shown to increase the accuracy of CAD.

Original language	English (US)
Title of host publication	Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
Pages	396-400
Number of pages	5
DOIs	https://doi.org/10.1109/FBIT.2007.9
State	Published - 2007
Externally published	Yes
Event	Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 - Jeju Island, Korea, Republic of Duration: Oct 11 2007 → Oct 13 2007

Publication series

Name	Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

Conference

Conference	Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007
Country/Territory	Korea, Republic of
City	Jeju Island
Period	10/11/07 → 10/13/07

ASJC Scopus subject areas

Computer Science Applications
Information Systems

Access to Document

10.1109/FBIT.2007.9

Cite this

Kim, S., Yoon, S., & Shin, D. (2007). Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination. In Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 (pp. 396-400). Article 4524139 (Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007). https://doi.org/10.1109/FBIT.2007.9

Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination. / Kim, Saejoon; Yoon, Sejong; Shin, Donghyuk.
Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. p. 396-400 4524139 (Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007).

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

Kim, S, Yoon, S & Shin, D 2007, Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination. in Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007., 4524139, Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007, pp. 396-400, Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007, Jeju Island, Korea, Republic of, 10/11/07. https://doi.org/10.1109/FBIT.2007.9

Kim S, Yoon S, Shin D. Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination. In Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. p. 396-400. 4524139. (Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007). doi: 10.1109/FBIT.2007.9

Kim, Saejoon ; Yoon, Sejong ; Shin, Donghyuk. / Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination. Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007. 2007. pp. 396-400 (Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007).

@inproceedings{55b8f8811b4c4521a80119517f37c5e6,

title = "Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination",

abstract = "In the analysis of digital or digitized mammographic images, a requirement is to learn to separate benign calcifications from malignant ones. Such an activity could form part of a computer-aided diagnosis (CAD) tool. We present a CAD study of calcification lesions to demonstrate that CAD of same-institutional mammograms provides significantly higher accuracy compared to that of cross-institutional mammograms. Moreover, using only a subset of the widely used six BI-RADS features together with patient age and subtlety value describing each calcification lesion is shown to increase the accuracy of CAD.",

author = "Saejoon Kim and Sejong Yoon and Donghyuk Shin",

year = "2007",

doi = "10.1109/FBIT.2007.9",

language = "English (US)",

isbn = "0769529992",

series = "Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007",

pages = "396--400",

booktitle = "Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007",

note = "Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007 ; Conference date: 11-10-2007 Through 13-10-2007",

}

TY - GEN

T1 - Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination

AU - Kim, Saejoon

AU - Yoon, Sejong

AU - Shin, Donghyuk

PY - 2007

Y1 - 2007

N2 - In the analysis of digital or digitized mammographic images, a requirement is to learn to separate benign calcifications from malignant ones. Such an activity could form part of a computer-aided diagnosis (CAD) tool. We present a CAD study of calcification lesions to demonstrate that CAD of same-institutional mammograms provides significantly higher accuracy compared to that of cross-institutional mammograms. Moreover, using only a subset of the widely used six BI-RADS features together with patient age and subtlety value describing each calcification lesion is shown to increase the accuracy of CAD.

AB - In the analysis of digital or digitized mammographic images, a requirement is to learn to separate benign calcifications from malignant ones. Such an activity could form part of a computer-aided diagnosis (CAD) tool. We present a CAD study of calcification lesions to demonstrate that CAD of same-institutional mammograms provides significantly higher accuracy compared to that of cross-institutional mammograms. Moreover, using only a subset of the widely used six BI-RADS features together with patient age and subtlety value describing each calcification lesion is shown to increase the accuracy of CAD.

UR - http://www.scopus.com/inward/record.url?scp=49349108929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49349108929&partnerID=8YFLogxK

U2 - 10.1109/FBIT.2007.9

DO - 10.1109/FBIT.2007.9

M3 - Conference contribution

AN - SCOPUS:49349108929

SN - 0769529992

SN - 9780769529998

T3 - Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

SP - 396

EP - 400

BT - Proceedings of the Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

T2 - Frontiers in the Convergence of Bioscience and Information Technologies, FBIT 2007

Y2 - 11 October 2007 through 13 October 2007

ER -

Computer-aided diagnosis of cross-institutional mammograms using support vector machines with feature elimination

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this