A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography

Ping Zhang, Brijesh Verma, Kuldeep Kumar

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

25 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. However, it is very difficult to distinguish benign and malignant cases, especially for the small size lesions in the early stage of cancer. 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. This paper proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier. It also combined the computer-extracted statistical features from the mammogram with the human-extracted features for classifying different types of small size breast abnormalities. It obtained 90.5% accuracy rate for calcification cases and 87. 2% for mass cases with different feature subsets. The obtained results show that different types of breast abnormality should use different features for classification.

Original languageEnglish
Title of host publication2004 IEEE International Joint Conference on Neural Networks - Proceedings
Pages2303-2308
Number of pages6
Volume3
DOIs
Publication statusPublished - 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary
Duration: 25 Jul 200429 Jul 2004

Conference

Conference2004 IEEE International Joint Conference on Neural Networks - Proceedings
CountryHungary
CityBudapest
Period25/07/0429/07/04

Fingerprint

Mammography
Feature extraction
Genetic algorithms
Biopsy
Classifiers
Neural networks

Cite this

Zhang, P., Verma, B., & Kumar, K. (2004). A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography. In 2004 IEEE International Joint Conference on Neural Networks - Proceedings (Vol. 3, pp. 2303-2308) https://doi.org/10.1109/IJCNN.2004.1380985
Zhang, Ping ; Verma, Brijesh ; Kumar, Kuldeep. / A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography. 2004 IEEE International Joint Conference on Neural Networks - Proceedings. Vol. 3 2004. pp. 2303-2308
@inproceedings{094e1bee22864f0986b22c6a16fb3797,
title = "A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography",
abstract = "Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas. However, it is very difficult to distinguish benign and malignant cases, especially for the small size lesions in the early stage of cancer. 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. This paper proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier. It also combined the computer-extracted statistical features from the mammogram with the human-extracted features for classifying different types of small size breast abnormalities. It obtained 90.5{\%} accuracy rate for calcification cases and 87. 2{\%} for mass cases with different feature subsets. The obtained results show that different types of breast abnormality should use different features for classification.",
author = "Ping Zhang and Brijesh Verma and Kuldeep Kumar",
year = "2004",
doi = "10.1109/IJCNN.2004.1380985",
language = "English",
isbn = "0780383591",
volume = "3",
pages = "2303--2308",
booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

}

Zhang, P, Verma, B & Kumar, K 2004, A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography. in 2004 IEEE International Joint Conference on Neural Networks - Proceedings. vol. 3, pp. 2303-2308, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 25/07/04. https://doi.org/10.1109/IJCNN.2004.1380985

A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography. / Zhang, Ping; Verma, Brijesh; Kumar, Kuldeep.

2004 IEEE International Joint Conference on Neural Networks - Proceedings. Vol. 3 2004. p. 2303-2308.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography

AU - Zhang, Ping

AU - Verma, Brijesh

AU - Kumar, Kuldeep

PY - 2004

Y1 - 2004

N2 - Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas. However, it is very difficult to distinguish benign and malignant cases, especially for the small size lesions in the early stage of cancer. 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. This paper proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier. It also combined the computer-extracted statistical features from the mammogram with the human-extracted features for classifying different types of small size breast abnormalities. It obtained 90.5% accuracy rate for calcification cases and 87. 2% for mass cases with different feature subsets. The obtained results show that different types of breast abnormality should use different features for classification.

AB - Digital mammography is one of the most suitable methods for early detection of breast cancer. It uses digital mammograms to find suspicious areas. However, it is very difficult to distinguish benign and malignant cases, especially for the small size lesions in the early stage of cancer. 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. This paper proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier. It also combined the computer-extracted statistical features from the mammogram with the human-extracted features for classifying different types of small size breast abnormalities. It obtained 90.5% accuracy rate for calcification cases and 87. 2% for mass cases with different feature subsets. The obtained results show that different types of breast abnormality should use different features for classification.

UR - http://www.scopus.com/inward/record.url?scp=10844273163&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380985

DO - 10.1109/IJCNN.2004.1380985

M3 - Conference contribution

SN - 0780383591

VL - 3

SP - 2303

EP - 2308

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

ER -

Zhang P, Verma B, Kumar K. A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography. In 2004 IEEE International Joint Conference on Neural Networks - Proceedings. Vol. 3. 2004. p. 2303-2308 https://doi.org/10.1109/IJCNN.2004.1380985