Self-organizing maps for masking mammography images

H. E. Rickard, G. D. Tourassi, A. S. Elmaghraby

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

7 Scopus citations

Abstract

This paper describes a new image segmentation algorithm for masking the breast region from the background in digital mammograms. The algorithm is applied to 160 images and shows promising results. Evaluation is based on comparisons with a histogram/region-growing algorithm. A self-organizing map is used to obtain an initial segmentation. The weight vectors of the self-organizing map are then clustered using the K-means method. Knowledge-based refinement provides the final binary mask that segments the image. Results indicated that the proposed approach could be used as the first stage in a computer-aided diagnostic system.

Original languageEnglish
Title of host publicationConference Proceedings - 4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine 2003
Subtitle of host publicationNew Solutions for New Challenges, ITAB 2003
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages302-305
Number of pages4
ISBN (Electronic)0780376676
DOIs
StatePublished - 2003
Externally publishedYes
Event4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine 2003, ITAB 2003 - Birmingham, United Kingdom
Duration: Apr 24 2003Apr 26 2003

Publication series

NameProceedings of the IEEE/EMBS Region 8 International Conference on Information Technology Applications in Biomedicine, ITAB
Volume2003-January

Conference

Conference4th International IEEE EMBS Special Topic Conference on Information Technology Applications in Biomedicine 2003, ITAB 2003
Country/TerritoryUnited Kingdom
CityBirmingham
Period04/24/0304/26/03

Keywords

  • Medical image segmentation
  • clustering methods
  • mammography
  • self-organizing maps

Fingerprint

Dive into the research topics of 'Self-organizing maps for masking mammography images'. Together they form a unique fingerprint.

Cite this