Welcome to the InfoSci Platform
Reference Hub5
Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing

Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing

Rafael do Espírito Santo, Roseli de Deus Lopes, Rangaraj M. Rangayyan
Copyright: © 2009 |Volume: 3 |Issue: 3 |Pages: 12
ISSN: 1557-3958|EISSN: 1557-3966|ISSN: 1557-3958|EISBN13: 9781616920654|EISSN: 1557-3966|DOI: 10.4018/jcini.2009070103
Cite Article Cite Article

MLA

do Espírito Santo, Rafael, et al. "Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing." IJCINI vol.3, no.3 2009: pp.27-38. http://doi.org/10.4018/jcini.2009070103

APA

do Espírito Santo, R., de Deus Lopes, R., & Rangayyan, R. M. (2009). Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 3(3), 27-38. http://doi.org/10.4018/jcini.2009070103

Chicago

do Espírito Santo, Rafael, Roseli de Deus Lopes, and Rangaraj M. Rangayyan. "Classification of Breast Masses in Mammograms Using Radial Basis Functions and Simulated Annealing," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 3, no.3: 27-38. http://doi.org/10.4018/jcini.2009070103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

We present pattern classification methods based upon nonlinear and combinational optimization techniques, specifically, radial basis functions (RBF) and simulated annealing (SA), to classify masses in mammograms as malignant or benign. Combinational optimization is used to pre-estimate RBF parameters, namely, the centers and spread matrix. The classifier was trained and tested, using the leave-one-out procedure, with shape, texture, and edge-sharpness measures extracted from 57 regions of interest (20 related to malignant tumors and 37 related to benign masses) manually delineated on mammograms by a radiologist. The classifier’s performance, with preestimation of the parameters, was evaluated in terms of the area Az under the receiver operating characteristics curve. Values up to Az = 0.9997 were obtained with RBF-SA with pre-estimation of the centers and spread matrix, which are better than the results obtained with pre-estimation of only the RBF centers, which were up to 0.9470. Overall, the results with the RBF-SA method were better than those provided by standard multilayer perceptron neural networks.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.