Breast cancer detection based on statistical textural features classification

Al Mutaz M. Abdalla, Safaai Deris, Nazar Zaki, Doaa M. Ghoneim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)

Abstract

Localized textural analysis of breast tissue on mammograms has recently gained considerable attention by researchers studying breast cancer detection. Despite the research progress to solve the problem, detecting breast cancer based on textural features has not been investigated in depth. In this paper we study the breast cancer detection based on statistical texture features using Support Vector Machine (SVM). A set of textural features was applied to a set of 120 digital mammographic images, from the Digital Database for Screening Mammography. These features are then used in conjunction with SVMs to detect the breast cancer. Other linear and non-linear classifiers were also employed to be compared to the SVM performance. SVM was able to achieve better classification accuracy of 82.5%.

Original languageEnglish
Title of host publicationInnovations'07
Subtitle of host publication4th International Conference on Innovations in Information Technology, IIT
PublisherIEEE Computer Society
Pages728-730
Number of pages3
ISBN (Print)9781424418411
DOIs
Publication statusPublished - Jan 1 2007
EventInnovations'07: 4th International Conference on Innovations in Information Technology, IIT - Dubai, United Arab Emirates
Duration: Nov 18 2007Nov 20 2007

Publication series

NameInnovations'07: 4th International Conference on Innovations in Information Technology, IIT

Other

OtherInnovations'07: 4th International Conference on Innovations in Information Technology, IIT
Country/TerritoryUnited Arab Emirates
CityDubai
Period11/18/0711/20/07

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'Breast cancer detection based on statistical textural features classification'. Together they form a unique fingerprint.

Cite this