Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

Ping Zhang, Brijesh Verma, Kuldeep Kumar

Research output: Contribution to journalArticleResearchpeer-review

93 Citations (Scopus)

Abstract

Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.

Original languageEnglish
Pages (from-to)909-919
Number of pages11
JournalPattern Recognition Letters
Volume26
Issue number7
DOIs
Publication statusPublished - 15 May 2005

Fingerprint

Feature extraction
Classifiers
Genetic algorithms
Mammography
Biopsy
Statistical Models

Cite this

@article{9a906ca9296741aca5aafc3bdae69772,
title = "Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection",
abstract = "Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.",
author = "Ping Zhang and Brijesh Verma and Kuldeep Kumar",
year = "2005",
month = "5",
day = "15",
doi = "10.1016/j.patrec.2004.09.053",
language = "English",
volume = "26",
pages = "909--919",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection. / Zhang, Ping; Verma, Brijesh; Kumar, Kuldeep.

In: Pattern Recognition Letters, Vol. 26, No. 7, 15.05.2005, p. 909-919.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Neural vs. statistical classifier in conjunction with genetic algorithm based feature selection

AU - Zhang, Ping

AU - Verma, Brijesh

AU - Kumar, Kuldeep

PY - 2005/5/15

Y1 - 2005/5/15

N2 - Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.

AB - Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas containing benign and malignant microcalcifications. However, it is very difficult to distinguish benign and malignant microcalcifications. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists in assessment of microcalcifications. The research in this paper proposes and investigates a neural-genetic algorithm for feature selection in conjunction with neural and statistical classifiers to classify microcalcification patterns in digital mammograms. The obtained results show that the proposed approach is able to find an appropriate feature subset and neural classifier achieves better results than two statistical models.

UR - http://www.scopus.com/inward/record.url?scp=17444397485&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2004.09.053

DO - 10.1016/j.patrec.2004.09.053

M3 - Article

VL - 26

SP - 909

EP - 919

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -