Skip to main content

Application of support vector machines to breast cancer screening using mammogram and history data

Publication ,  Journal Article
Land, WH; Akanda, A; Lo, JY; Anderson, F; Bryden, M
Published in: Proceedings of SPIE - The International Society for Optical Engineering
January 1, 2002

Support Vector Machines (SVMs) are a new and radically different type of classifiers and learning machines that use a hypothesis space of linear functions in a high dimensional feature space. This relatively new paradigm, based on Statistical Learning theory (SLT) and Structural Risk Minimization (SRM), has many advantages when compared to traditional neural networks, which are based on Empirical Risk Minimization (ERM). Unlike neural networks, SVM training always finds a global minimum. Furthermore, SVMs have inherent ability to solve pattern classification without incorporating any problem-domain knowledge. In this study, the SVM was employed as a pattern classifier, operating on mammography data used for breast cancer detection. The main focus was to formulate the best learning machine configurations for optimum specificity and positive predictive value at very high sensitivities. Using a mammogram database of 500 biopsy-proven samples, the best performing SVM, on average, was able to achieve (under statistical 5-fold cross-validation) a specificity of 45.0% and a positive predictive value (PPV) of 50.1% at 100% sensitivity. At 97% sensitivity, a specificity of 55.8% and a PPV of 55.2% were obtained. © 2002 SPIE · 1605-7422/02/$15.00.

Duke Scholars

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

January 1, 2002

Volume

4684 I

Start / End Page

636 / 642

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., Akanda, A., Lo, J. Y., Anderson, F., & Bryden, M. (2002). Application of support vector machines to breast cancer screening using mammogram and history data. Proceedings of SPIE - The International Society for Optical Engineering, 4684 I, 636–642. https://doi.org/10.1117/12.467206
Land, W. H., A. Akanda, J. Y. Lo, F. Anderson, and M. Bryden. “Application of support vector machines to breast cancer screening using mammogram and history data.” Proceedings of SPIE - The International Society for Optical Engineering 4684 I (January 1, 2002): 636–42. https://doi.org/10.1117/12.467206.
Land WH, Akanda A, Lo JY, Anderson F, Bryden M. Application of support vector machines to breast cancer screening using mammogram and history data. Proceedings of SPIE - The International Society for Optical Engineering. 2002 Jan 1;4684 I:636–42.
Land, W. H., et al. “Application of support vector machines to breast cancer screening using mammogram and history data.” Proceedings of SPIE - The International Society for Optical Engineering, vol. 4684 I, Jan. 2002, pp. 636–42. Scopus, doi:10.1117/12.467206.
Land WH, Akanda A, Lo JY, Anderson F, Bryden M. Application of support vector machines to breast cancer screening using mammogram and history data. Proceedings of SPIE - The International Society for Optical Engineering. 2002 Jan 1;4684 I:636–642.

Published In

Proceedings of SPIE - The International Society for Optical Engineering

DOI

ISSN

0277-786X

Publication Date

January 1, 2002

Volume

4684 I

Start / End Page

636 / 642

Related Subject Headings

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