Normal mammogram classification based on a support vector machine utilizing crossed distribution features

W Chiracharit; Y Sun; P Kumhom; K Chamnongthai; C Babbs; E Delp

doi:10.1109/IEMBS.2004.1403481

Normal mammogram classification based on a support vector machine utilizing crossed distribution features

Conf Proc IEEE Eng Med Biol Soc. 2004:2004:1581-4. doi: 10.1109/IEMBS.2004.1403481.

Authors

W Chiracharit¹, Y Sun, P Kumhom, K Chamnongthai, C Babbs, E Delp

Affiliation

¹ Department of Electronics and Telecommunication Engineering, King Mongkut's University of Technology, Bangkok, Thailand.

PMID: 17272001
DOI: 10.1109/IEMBS.2004.1403481

Abstract

Automatic classification of normal mammograms, which constitute a majority of screening mammograms, is a new approach to computer-aided diagnosis of breast cancer. This approach may be limited, however, by non-separable "crossed" distributions of features that are extracted from digitized mammograms. This work presents a method of mapping such non-separable input features into a new set of separable features that can be utilized, together with ordinary "uncrossed" features, by a support vector machine (SVM) classifier. The results of the proposed scheme show improved performance with 80% sensitivity and 95% specificity.