Automatic detection of breast masses in digital mammograms using pattern matching

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

5 Citations (Scopus)

Abstract

The work in this paper focuses on the automatic detection of masses in digital mammograms. The proposed system consists of two main stages; the first stage is the breast segmentation to remove the background and labels. The second stage is to determine the masses region. The proposed method utilizes the correlation between a typical mass region and the mammogram image in order to determine and extract the suspicious region in the tested image. The system is developed and evaluated with 116 mammogram images from the mammographic image analysis society (MIAS) Dataset. The results show that the proposed algorithm has a sensitivity of 89.30% for mass detection, and the classification accuracy rate reach 94.66%.

Original languageEnglish
Title of host publicationProceedings of 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010
Pages73-76
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010 - Kuala Lumpur, Malaysia
Duration: 30 Nov 20102 Dec 2010

Publication series

NameProceedings of 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010

Conference

Conference2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010
Country/TerritoryMalaysia
CityKuala Lumpur
Period30/11/102/12/10

Keywords

  • Digital mammogram
  • Mass detection
  • Pattern matching
  • Region of interest extraction

Fingerprint

Dive into the research topics of 'Automatic detection of breast masses in digital mammograms using pattern matching'. Together they form a unique fingerprint.

Cite this