A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation

This paper presents a method for breast cancer diagnosis in digital mammogram images. The wavelet is used to transform the mammogram images into a long vector of coefficients. A matrix is constructed by putting wavelet coefficients of each image in row vector, where the number of row is the num...

Full description

Bibliographic Details
Main Authors: Brahim Belhaouari, samir, Ibrahima, faye, Mohamed, meselhy
Format: Conference or Workshop Item
Language:English
Published: 2010
Subjects:
Online Access:http://scholars.utp.edu.my/id/eprint/2171/
http://scholars.utp.edu.my/id/eprint/2171/1/Paper_USA.pdf
_version_ 1848659209891086336
author Brahim Belhaouari, samir
Ibrahima, faye
Mohamed, meselhy
author_facet Brahim Belhaouari, samir
Ibrahima, faye
Mohamed, meselhy
author_sort Brahim Belhaouari, samir
building UTP Institutional Repository
collection Online Access
description This paper presents a method for breast cancer diagnosis in digital mammogram images. The wavelet is used to transform the mammogram images into a long vector of coefficients. A matrix is constructed by putting wavelet coefficients of each image in row vector, where the number of row is the number of images, and the number of columns is the number of coefficients. A feature extraction method is developed based on the statistical ttest method. The method is ranking the columns (features) according to its capability to distinguish between the different classes. The method depends on extracting the features that can maximize the ability to discriminate between different classes. Thus, the dimensionality of data features is reduced and the classification accuracy rate is improved. Then a dynamic threshold is applied to optimize the number of feature which can achieve the maximum classification accuracy rate. Support vector machine (SVM) is used to classify between the normal and abnormal and to distinguish between benign and malignant. The obtained classification accuracy rates reach to 100%.
first_indexed 2025-11-13T07:26:48Z
format Conference or Workshop Item
id oai:scholars.utp.edu.my:2171
institution Universiti Teknologi Petronas
institution_category Local University
language English
last_indexed 2025-11-13T07:26:48Z
publishDate 2010
recordtype eprints
repository_type Digital Repository
spelling oai:scholars.utp.edu.my:21712017-01-19T08:23:52Z http://scholars.utp.edu.my/id/eprint/2171/ A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation Brahim Belhaouari, samir Ibrahima, faye Mohamed, meselhy TK Electrical engineering. Electronics Nuclear engineering This paper presents a method for breast cancer diagnosis in digital mammogram images. The wavelet is used to transform the mammogram images into a long vector of coefficients. A matrix is constructed by putting wavelet coefficients of each image in row vector, where the number of row is the number of images, and the number of columns is the number of coefficients. A feature extraction method is developed based on the statistical ttest method. The method is ranking the columns (features) according to its capability to distinguish between the different classes. The method depends on extracting the features that can maximize the ability to discriminate between different classes. Thus, the dimensionality of data features is reduced and the classification accuracy rate is improved. Then a dynamic threshold is applied to optimize the number of feature which can achieve the maximum classification accuracy rate. Support vector machine (SVM) is used to classify between the normal and abnormal and to distinguish between benign and malignant. The obtained classification accuracy rates reach to 100%. 2010-08-01 Conference or Workshop Item PeerReviewed application/pdf en http://scholars.utp.edu.my/id/eprint/2171/1/Paper_USA.pdf Brahim Belhaouari, samir and Ibrahima, faye and Mohamed, meselhy (2010) A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation. In: INTERNATIONAL CONFERENCE ON IMAGE AND VIDEO PROCESSING AND COMPUTER VISION.
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Brahim Belhaouari, samir
Ibrahima, faye
Mohamed, meselhy
A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title_full A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title_fullStr A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title_full_unstemmed A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title_short A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation
title_sort statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation
topic TK Electrical engineering. Electronics Nuclear engineering
url http://scholars.utp.edu.my/id/eprint/2171/
http://scholars.utp.edu.my/id/eprint/2171/1/Paper_USA.pdf