Mutual information-based SVM-RFE for diagnostic classification of digitized mammograms

Authors:
Sejong Yoon;Saejoon Kim
Affiliations:
Department of Computer Science and Engineering, Sogang University, 1 Shinsu-dong, Mapo-gu, Seoul 121-742, Republic of Korea;Department of Computer Science and Engineering, Sogang University, 1 Shinsu-dong, Mapo-gu, Seoul 121-742, Republic of Korea
Venue:
Pattern Recognition Letters
Year:
2009

Citing 7
Cited 1

Optimal brain damage

Advances in neural information processing systems 2
Gene Selection for Cancer Classification using Support Vector Machines

Machine Learning
Analysis of recursive gene selection approaches from microarray data

Bioinformatics
A novel neural-genetic algorithm to find the most significant combination of features in digital mammograms

Applied Soft Computing
SVM-RFE with relevancy and redundancy criteria for gene selection

PRIB'07 Proceedings of the 2nd IAPR international conference on Pattern recognition in bioinformatics
Characterization of breast abnormality patterns in digital mammograms using auto-associator neural network

ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
Computerized classification can reduce unnecessary biopsies in BI-RADS category 4a lesions

IWDM'06 Proceedings of the 8th international conference on Digital Mammography

A modified two-stage SVM-RFE model for cancer classification using microarray data

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.10

Visualization

Abstract

Computer aided diagnosis (CADx) systems for digitized mammograms solve the problem of classification between benign and malignant tissues while studies have shown that using only a subset of features generated from the mammograms can yield higher classification accuracy. To this end, we propose a mutual information-based Support Vector Machine Recursive Feature Elimination (SVM-RFE) as the classification method with feature selection in this paper. We have conducted extensive experiments on publicly available mammographic data and the obtained results indicate that the proposed method outperforms other SVM and SVM-RFE-based methods.