Detection of breast cancer based on texture analysis from digital mammograms

Eun Byeol Jo, Ju Hwan Lee, Jun Young Park, Sung Min Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

In this study, we propose a novel breast cancer detection algorithm based on texture properties of mass area. Proposed method extracts the midpoint of mass area by using AHE (Adaptive Histogram Equalization), and selects the ROI (Region of Interest) in the original image. L1-norm based smoothing filter is then employed to stabilize the mass area, and the form of the mass is determined. Additionally, we measured homogeneity and Ranklet using SVM (Support Vector Machine) to analyze texture properties of the selected mass area. As a result, we observed that the proposed method shows the more stable and outstanding performance for Korean women compared with the existing methods.

Original languageEnglish
Title of host publicationIntelligent Autonomous Systems 12 - Proceedings of the 12th International Conference, IAS 2012
PublisherSpringer Verlag
Pages893-900
Number of pages8
EditionVOL. 2
ISBN (Print)9783642339318
DOIs
StatePublished - 2013
Event12th International Conference on Intelligent Autonomous Systems, IAS 2012 - Jeju Island, Korea, Republic of
Duration: 26 Jun 201229 Jun 2012

Publication series

NameAdvances in Intelligent Systems and Computing
NumberVOL. 2
Volume194 AISC
ISSN (Print)2194-5357

Conference

Conference12th International Conference on Intelligent Autonomous Systems, IAS 2012
Country/TerritoryKorea, Republic of
CityJeju Island
Period26/06/1229/06/12

Keywords

  • breast cancer
  • homogeneity
  • mammogram
  • Ranklet
  • SVM (Support Vector Machine)

Fingerprint

Dive into the research topics of 'Detection of breast cancer based on texture analysis from digital mammograms'. Together they form a unique fingerprint.

Cite this