Skip to main content

Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines

Publication ,  Journal Article
Land, WH; McKee, DW; Anderson, FR; Lo, JY
Published in: Proceedings of SPIE - The International Society for Optical Engineering
October 27, 2004

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.

Duke Scholars

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

October 27, 2004

Volume

5370 II

Start / End Page

880 / 887

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Land, W. H., McKee, D. W., Anderson, F. R., & Lo, J. Y. (2004). Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines. Proceedings of SPIE - The International Society for Optical Engineering, 5370 II, 880–887. https://doi.org/10.1117/12.535864
Land, W. H., D. W. McKee, F. R. Anderson, and J. Y. Lo. “Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines.” Proceedings of SPIE - The International Society for Optical Engineering 5370 II (October 27, 2004): 880–87. https://doi.org/10.1117/12.535864.
Land WH, McKee DW, Anderson FR, Lo JY. Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines. Proceedings of SPIE - The International Society for Optical Engineering. 2004 Oct 27;5370 II:880–7.
Land, W. H., et al. “Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines.” Proceedings of SPIE - The International Society for Optical Engineering, vol. 5370 II, Oct. 2004, pp. 880–87. Scopus, doi:10.1117/12.535864.
Land WH, McKee DW, Anderson FR, Lo JY. Breast cancer classification improvements using a new kernel function with evolutionary-programming-configured support vector machines. Proceedings of SPIE - The International Society for Optical Engineering. 2004 Oct 27;5370 II:880–887.

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

October 27, 2004

Volume

5370 II

Start / End Page

880 / 887

Related Subject Headings

  • 5102 Atomic, molecular and optical physics
  • 4009 Electronics, sensors and digital hardware
  • 4006 Communications engineering