Application of Gabor wavelet and Locality Sensitive Discriminant Analysis for automated identification of breast cancer using digitized mammogram images

U. Raghavendra, U. Rajendra Acharya, Hamido Fujita, Anjan Gudigar, Jen Hong Tan, Shreesha Chokkadi

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Breast cancer is one of the prime causes of death in women. Early detection may help to improve the survival rate to a great extent. Mammography is considered as one of the most reliable methods to prescreen of breast cancer. However, reading the mammograms by radiologists is laborious, taxing, and prone to intra/inter observer variability errors. Computer Aided Diagnosis (CAD) helps to obtain fast, consistent and reliable diagnosis. This paper presents an automated classification of normal, benign and malignant breast cancer using digitized mammogram images. The proposed method used Gabor wavelet for feature extraction and Locality Sensitive Discriminant Analysis (LSDA) for data reduction. The reduced features are ranked using their F-values and fed to Decision Tree (DT), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), k-Nearest Neighbor (k-NN), Naïve Bayes Classifier (NBC), Probabilistic Neural Network (PNN), Support Vector Machine (SVM), AdaBoost and Fuzzy Sugeno (FSC) classifiers one by one to select the highest performing classifier using minimum number of features. The proposed method is evaluated using 690 mammogram images taken from a benchmarked Digital Database for Screening Mammography (DDSM) dataset. Our developed method has achieved mean accuracy, sensitivity, specificity of 98.69%, 99.34% and 98.26% respectively for k-NN classifier using eight features with 10-fold cross validation. This system can be employed in hospitals and polyclinics to aid the clinicians to cross verify their manual diagnosis.

Original languageEnglish
Pages (from-to)151-161
Number of pages11
JournalApplied Soft Computing Journal
Volume46
DOIs
Publication statusPublished - 01-09-2016

Fingerprint

Discriminant analysis
Classifiers
Mammography
Computer aided diagnosis
Adaptive boosting
Decision trees
Support vector machines
Feature extraction
Data reduction
Screening
Neural networks

All Science Journal Classification (ASJC) codes

  • Software

Cite this

@article{34ae33d8d5f44135bc2f09bce5f5b2e5,
title = "Application of Gabor wavelet and Locality Sensitive Discriminant Analysis for automated identification of breast cancer using digitized mammogram images",
abstract = "Breast cancer is one of the prime causes of death in women. Early detection may help to improve the survival rate to a great extent. Mammography is considered as one of the most reliable methods to prescreen of breast cancer. However, reading the mammograms by radiologists is laborious, taxing, and prone to intra/inter observer variability errors. Computer Aided Diagnosis (CAD) helps to obtain fast, consistent and reliable diagnosis. This paper presents an automated classification of normal, benign and malignant breast cancer using digitized mammogram images. The proposed method used Gabor wavelet for feature extraction and Locality Sensitive Discriminant Analysis (LSDA) for data reduction. The reduced features are ranked using their F-values and fed to Decision Tree (DT), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), k-Nearest Neighbor (k-NN), Na{\"i}ve Bayes Classifier (NBC), Probabilistic Neural Network (PNN), Support Vector Machine (SVM), AdaBoost and Fuzzy Sugeno (FSC) classifiers one by one to select the highest performing classifier using minimum number of features. The proposed method is evaluated using 690 mammogram images taken from a benchmarked Digital Database for Screening Mammography (DDSM) dataset. Our developed method has achieved mean accuracy, sensitivity, specificity of 98.69{\%}, 99.34{\%} and 98.26{\%} respectively for k-NN classifier using eight features with 10-fold cross validation. This system can be employed in hospitals and polyclinics to aid the clinicians to cross verify their manual diagnosis.",
author = "U. Raghavendra and {Rajendra Acharya}, U. and Hamido Fujita and Anjan Gudigar and Tan, {Jen Hong} and Shreesha Chokkadi",
year = "2016",
month = "9",
day = "1",
doi = "10.1016/j.asoc.2016.04.036",
language = "English",
volume = "46",
pages = "151--161",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Application of Gabor wavelet and Locality Sensitive Discriminant Analysis for automated identification of breast cancer using digitized mammogram images

AU - Raghavendra, U.

AU - Rajendra Acharya, U.

AU - Fujita, Hamido

AU - Gudigar, Anjan

AU - Tan, Jen Hong

AU - Chokkadi, Shreesha

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Breast cancer is one of the prime causes of death in women. Early detection may help to improve the survival rate to a great extent. Mammography is considered as one of the most reliable methods to prescreen of breast cancer. However, reading the mammograms by radiologists is laborious, taxing, and prone to intra/inter observer variability errors. Computer Aided Diagnosis (CAD) helps to obtain fast, consistent and reliable diagnosis. This paper presents an automated classification of normal, benign and malignant breast cancer using digitized mammogram images. The proposed method used Gabor wavelet for feature extraction and Locality Sensitive Discriminant Analysis (LSDA) for data reduction. The reduced features are ranked using their F-values and fed to Decision Tree (DT), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), k-Nearest Neighbor (k-NN), Naïve Bayes Classifier (NBC), Probabilistic Neural Network (PNN), Support Vector Machine (SVM), AdaBoost and Fuzzy Sugeno (FSC) classifiers one by one to select the highest performing classifier using minimum number of features. The proposed method is evaluated using 690 mammogram images taken from a benchmarked Digital Database for Screening Mammography (DDSM) dataset. Our developed method has achieved mean accuracy, sensitivity, specificity of 98.69%, 99.34% and 98.26% respectively for k-NN classifier using eight features with 10-fold cross validation. This system can be employed in hospitals and polyclinics to aid the clinicians to cross verify their manual diagnosis.

AB - Breast cancer is one of the prime causes of death in women. Early detection may help to improve the survival rate to a great extent. Mammography is considered as one of the most reliable methods to prescreen of breast cancer. However, reading the mammograms by radiologists is laborious, taxing, and prone to intra/inter observer variability errors. Computer Aided Diagnosis (CAD) helps to obtain fast, consistent and reliable diagnosis. This paper presents an automated classification of normal, benign and malignant breast cancer using digitized mammogram images. The proposed method used Gabor wavelet for feature extraction and Locality Sensitive Discriminant Analysis (LSDA) for data reduction. The reduced features are ranked using their F-values and fed to Decision Tree (DT), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), k-Nearest Neighbor (k-NN), Naïve Bayes Classifier (NBC), Probabilistic Neural Network (PNN), Support Vector Machine (SVM), AdaBoost and Fuzzy Sugeno (FSC) classifiers one by one to select the highest performing classifier using minimum number of features. The proposed method is evaluated using 690 mammogram images taken from a benchmarked Digital Database for Screening Mammography (DDSM) dataset. Our developed method has achieved mean accuracy, sensitivity, specificity of 98.69%, 99.34% and 98.26% respectively for k-NN classifier using eight features with 10-fold cross validation. This system can be employed in hospitals and polyclinics to aid the clinicians to cross verify their manual diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=84973377012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973377012&partnerID=8YFLogxK

U2 - 10.1016/j.asoc.2016.04.036

DO - 10.1016/j.asoc.2016.04.036

M3 - Article

VL - 46

SP - 151

EP - 161

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

ER -