Feature selection and classifiers for the computerized detection of mass lesions in digital mammography

Matthew A. Kupinski; Maryellen L. Giger

doi:10.1109/ICNN.1997.614543

Feature selection and classifiers for the computerized detection of mass lesions in digital mammography

Matthew A. Kupinski, Maryellen L. Giger

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

19 Scopus citations

Abstract

We have investigated various methods of feature selection for two different data classifiers used in the computerized detection of mass lesions in digital mammograms. Numerous features were extracted from abnormal and normal breast regions from a database consisting of 210 individual mammograms. A step-wise method, a genetic algorithm and individual feature analysis were employed to select a subset of features to be used with linear discriminants. Similar techniques were also employed for an artificial neural network classifier. In both tests the genetic algorithm was able to either outperform or equal the performance of other methods.

Original language	English (US)
Title of host publication	1997 IEEE International Conference on Neural Networks, ICNN 1997
Pages	2460-2463
Number of pages	4
DOIs	https://doi.org/10.1109/ICNN.1997.614543
State	Published - 1997
Externally published	Yes
Event	1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, United States Duration: Jun 9 1997 → Jun 12 1997

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	4
ISSN (Print)	1098-7576

Conference

Conference	1997 IEEE International Conference on Neural Networks, ICNN 1997
Country/Territory	United States
City	Houston, TX
Period	6/9/97 → 6/12/97

ASJC Scopus subject areas

Software

Access to Document

10.1109/ICNN.1997.614543

Cite this

Kupinski, M. A., & Giger, M. L. (1997). Feature selection and classifiers for the computerized detection of mass lesions in digital mammography. In 1997 IEEE International Conference on Neural Networks, ICNN 1997 (pp. 2460-2463). Article 614543 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 4). https://doi.org/10.1109/ICNN.1997.614543

Feature selection and classifiers for the computerized detection of mass lesions in digital mammography. / Kupinski, Matthew A.; Giger, Maryellen L.
1997 IEEE International Conference on Neural Networks, ICNN 1997. 1997. p. 2460-2463 614543 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 4).

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

Kupinski, MA & Giger, ML 1997, Feature selection and classifiers for the computerized detection of mass lesions in digital mammography. in 1997 IEEE International Conference on Neural Networks, ICNN 1997., 614543, IEEE International Conference on Neural Networks - Conference Proceedings, vol. 4, pp. 2460-2463, 1997 IEEE International Conference on Neural Networks, ICNN 1997, Houston, TX, United States, 6/9/97. https://doi.org/10.1109/ICNN.1997.614543

@inproceedings{2b62220d08a94fb5a7171dced3d927cf,

title = "Feature selection and classifiers for the computerized detection of mass lesions in digital mammography",

abstract = "We have investigated various methods of feature selection for two different data classifiers used in the computerized detection of mass lesions in digital mammograms. Numerous features were extracted from abnormal and normal breast regions from a database consisting of 210 individual mammograms. A step-wise method, a genetic algorithm and individual feature analysis were employed to select a subset of features to be used with linear discriminants. Similar techniques were also employed for an artificial neural network classifier. In both tests the genetic algorithm was able to either outperform or equal the performance of other methods.",

author = "Kupinski, {Matthew A.} and Giger, {Maryellen L.}",

year = "1997",

doi = "10.1109/ICNN.1997.614543",

language = "English (US)",

isbn = "0780341228",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "2460--2463",

booktitle = "1997 IEEE International Conference on Neural Networks, ICNN 1997",

note = "1997 IEEE International Conference on Neural Networks, ICNN 1997 ; Conference date: 09-06-1997 Through 12-06-1997",

}

TY - GEN

T1 - Feature selection and classifiers for the computerized detection of mass lesions in digital mammography

AU - Kupinski, Matthew A.

AU - Giger, Maryellen L.

PY - 1997

Y1 - 1997

N2 - We have investigated various methods of feature selection for two different data classifiers used in the computerized detection of mass lesions in digital mammograms. Numerous features were extracted from abnormal and normal breast regions from a database consisting of 210 individual mammograms. A step-wise method, a genetic algorithm and individual feature analysis were employed to select a subset of features to be used with linear discriminants. Similar techniques were also employed for an artificial neural network classifier. In both tests the genetic algorithm was able to either outperform or equal the performance of other methods.

AB - We have investigated various methods of feature selection for two different data classifiers used in the computerized detection of mass lesions in digital mammograms. Numerous features were extracted from abnormal and normal breast regions from a database consisting of 210 individual mammograms. A step-wise method, a genetic algorithm and individual feature analysis were employed to select a subset of features to be used with linear discriminants. Similar techniques were also employed for an artificial neural network classifier. In both tests the genetic algorithm was able to either outperform or equal the performance of other methods.

UR - http://www.scopus.com/inward/record.url?scp=0030707020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030707020&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1997.614543

DO - 10.1109/ICNN.1997.614543

M3 - Conference contribution

AN - SCOPUS:0030707020

SN - 0780341228

SN - 9780780341227

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 2460

EP - 2463

BT - 1997 IEEE International Conference on Neural Networks, ICNN 1997

T2 - 1997 IEEE International Conference on Neural Networks, ICNN 1997

Y2 - 9 June 1997 through 12 June 1997

ER -

Feature selection and classifiers for the computerized detection of mass lesions in digital mammography

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this