Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms

Tomasz Arodź; Marcin Kurdziel; Erik O.D. Sevre; David A. Yuen

doi:10.1016/j.cmpb.2005.03.009

Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms

Tomasz Arodź, Marcin Kurdziel, Erik O.D. Sevre, David A. Yuen

Earth and Environmental Sciences-Twin Cities

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

20 Scopus citations

Abstract

We have employed two pattern recognition methods used commonly for face recognition in order to analyse digital mammograms. The methods are based on novel classification schemes, the AdaBoost and the support vector machines (SVM). A number of tests have been carried out to evaluate the accuracy of these two algorithms under different circumstances. Results for the AdaBoost classifier method are promising, especially for classifying mass-type lesions. In the best case the algorithm achieved accuracy of 76% for all lesion types and 90% for masses only. The SVM based algorithm did not perform as well. In order to achieve a higher accuracy for this method, we should choose image features that are better suited for analysing digital mammograms than the currently used ones.

Original language	English (US)
Pages (from-to)	135-149
Number of pages	15
Journal	Computer Methods and Programs in Biomedicine
Volume	79
Issue number	2
DOIs	https://doi.org/10.1016/j.cmpb.2005.03.009
State	Published - Aug 2005

Bibliographical note

Funding Information:
We thank Professor Robert Hollebeck, University of Pennsylvania, for his encouragement and suggestions and Dr. T. Popiela from Department of Radiology, Collegium Medicum, Jagiellonian University, Krakow (Poland) for medical consultations. We thank Ben Holtzmann and Lilli Yang for contributing to Fig. 1. This research has been supported by the Math-Geo program of National Science Foundation and the Digital Technology Center of Univ. Minnesota.

Keywords

Computer-aided diagnosis
Machine learning
Mammogram analysis

Access

10.1016/j.cmpb.2005.03.009

OpenUrl availability

Full text

Cite this

@article{3594fa51baf04535a515dd4b2497c93d,

title = "Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms",

abstract = "We have employed two pattern recognition methods used commonly for face recognition in order to analyse digital mammograms. The methods are based on novel classification schemes, the AdaBoost and the support vector machines (SVM). A number of tests have been carried out to evaluate the accuracy of these two algorithms under different circumstances. Results for the AdaBoost classifier method are promising, especially for classifying mass-type lesions. In the best case the algorithm achieved accuracy of 76% for all lesion types and 90% for masses only. The SVM based algorithm did not perform as well. In order to achieve a higher accuracy for this method, we should choose image features that are better suited for analysing digital mammograms than the currently used ones.",

keywords = "Computer-aided diagnosis, Machine learning, Mammogram analysis",

author = "Tomasz Arod{\'z} and Marcin Kurdziel and Sevre, {Erik O.D.} and Yuen, {David A.}",

note = "Funding Information: We thank Professor Robert Hollebeck, University of Pennsylvania, for his encouragement and suggestions and Dr. T. Popiela from Department of Radiology, Collegium Medicum, Jagiellonian University, Krakow (Poland) for medical consultations. We thank Ben Holtzmann and Lilli Yang for contributing to Fig. 1. This research has been supported by the Math-Geo program of National Science Foundation and the Digital Technology Center of Univ. Minnesota. ",

year = "2005",

month = aug,

doi = "10.1016/j.cmpb.2005.03.009",

language = "English (US)",

volume = "79",

pages = "135--149",

journal = "Computer Methods and Programs in Biomedicine",

issn = "0169-2607",

publisher = "Elsevier Ireland Ltd",

number = "2",

}

TY - JOUR

T1 - Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms

AU - Arodź, Tomasz

AU - Kurdziel, Marcin

AU - Sevre, Erik O.D.

AU - Yuen, David A.

N1 - Funding Information: We thank Professor Robert Hollebeck, University of Pennsylvania, for his encouragement and suggestions and Dr. T. Popiela from Department of Radiology, Collegium Medicum, Jagiellonian University, Krakow (Poland) for medical consultations. We thank Ben Holtzmann and Lilli Yang for contributing to Fig. 1. This research has been supported by the Math-Geo program of National Science Foundation and the Digital Technology Center of Univ. Minnesota.

PY - 2005/8

Y1 - 2005/8

N2 - We have employed two pattern recognition methods used commonly for face recognition in order to analyse digital mammograms. The methods are based on novel classification schemes, the AdaBoost and the support vector machines (SVM). A number of tests have been carried out to evaluate the accuracy of these two algorithms under different circumstances. Results for the AdaBoost classifier method are promising, especially for classifying mass-type lesions. In the best case the algorithm achieved accuracy of 76% for all lesion types and 90% for masses only. The SVM based algorithm did not perform as well. In order to achieve a higher accuracy for this method, we should choose image features that are better suited for analysing digital mammograms than the currently used ones.

AB - We have employed two pattern recognition methods used commonly for face recognition in order to analyse digital mammograms. The methods are based on novel classification schemes, the AdaBoost and the support vector machines (SVM). A number of tests have been carried out to evaluate the accuracy of these two algorithms under different circumstances. Results for the AdaBoost classifier method are promising, especially for classifying mass-type lesions. In the best case the algorithm achieved accuracy of 76% for all lesion types and 90% for masses only. The SVM based algorithm did not perform as well. In order to achieve a higher accuracy for this method, we should choose image features that are better suited for analysing digital mammograms than the currently used ones.

KW - Computer-aided diagnosis

KW - Machine learning

KW - Mammogram analysis

UR - http://www.scopus.com/inward/record.url?scp=22044451229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22044451229&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2005.03.009

DO - 10.1016/j.cmpb.2005.03.009

M3 - Article

C2 - 15925425

AN - SCOPUS:22044451229

SN - 0169-2607

VL - 79

SP - 135

EP - 149

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

IS - 2

ER -

Pattern recognition techniques for automatic detection of suspicious-looking anomalies in mammograms

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this