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

Get BibTex-formatted data

Author

W Chiracharit, Y Sun, P Kumhom, K Chamnongthai, C Babbs, EJ Delp

Entry type

article

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.

Date

2004 – 09

Journal

Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE

Key alpha

Delp

Pages

1581-1584

Volume

Publication Date

2004-09-01

BibTex-formatted data

To refer to this entry, you may select and copy the text below and paste it into your BibTex document. Note that the text may not contain all macros that BibTex supports.

@Article{ Delp,
	title = " Normal mammogram classification based on a support vector machine utilizing crossed distribution features",
	author = "W Chiracharit, Y Sun, P Kumhom, K Chamnongthai, C Babbs, EJ Delp",
	year = "2004",
	month = "09",
	journal = "Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE",
	pages = "1581-1584",
	volume = "1",
	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.",
}