Share Email Print
cover

Proceedings Paper

Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines
Author(s): Walker H. Land; Daniel W. McKee; Frances R. Anderson; Joseph Y. Lo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Mammography is an effective tool for the early detection of breast cancer; however, most women referred for biopsy based on mammographic findings do not, in fact, have cancer. This study is part of an ongoing effort to reduce the number of benign cases referred for biopsy by developing tools to aid physicians in classifying suspicious lesions. Specifically, this study examines the use of an Evolutionary Programming (EP)-derived Support Vector Machine (SVM) with a modified radial basis function (RBF) kernel, and compares this with results using a normal Gaussian radial basis function kernel. Results demonstrate that the modified kernel can provide moderate performance improvements; however, due to its ability to create a more complex decision surface, this kernel can easily begin to memorize the training data resulting in a loss of generalization ability. Nonetheless, these methods could reduce the number of benign cases referred for biopsy by over half, while missing less than 5% of malignancies. Future work will focus on methods to improve the EP process to preserve SVMs which generalize well.

Paper Details

Date Published: 12 May 2004
PDF: 8 pages
Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); doi: 10.1117/12.535864
Show Author Affiliations
Walker H. Land, Binghamton Univ. (United States)
Daniel W. McKee, Binghamton Univ. (United States)
Frances R. Anderson, Our Lady of Lourdes Hospital (United States)
Joseph Y. Lo, Duke Univ. Medical Ctr. (United States)


Published in SPIE Proceedings Vol. 5370:
Medical Imaging 2004: Image Processing
J. Michael Fitzpatrick; Milan Sonka, Editor(s)

© SPIE. Terms of Use
Back to Top