Stability analysis and breast tumor classification from 2D ARMA models of ultrasound images

A. Abdulsadda, N. Bouaynaya, K. Iqbal

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

3 Scopus citations

Abstract

Two-dimensional (2D) autoregressive moving average (ARMA) random fields have been proven to be accurate models of ultrasound breast images. However, the stability properties of these models have not been examined. In this paper, we investigate the stability of 2D ARMA models in ultrasound breast images, and use the estimated 2D ARMA coefficients as a basis for statistical inference using artificial neural networks. Specifically, we use the estimated 2D ARMA coefficients as inputs to a Multi layer perceptron (MLP) neural network to classify the ultrasound breast image into three regions: healthy tissue, benign tumor, and cancerous tumor. Our simulation results on various cancerous and benign ultrasound breast images illustrate the power of the proposed algorithm as attested by different learning algorithms and classification accuracy measures.

Original languageEnglish (US)
Title of host publicationProceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publicationEngineering the Future of Biomedicine, EMBC 2009
PublisherIEEE Computer Society
Pages3763-3766
Number of pages4
ISBN (Print)9781424432967
DOIs
StatePublished - Jan 1 2009
Externally publishedYes
Event31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 - Minneapolis, MN, United States
Duration: Sep 2 2009Sep 6 2009

Publication series

NameProceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009

Other

Other31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009
Country/TerritoryUnited States
CityMinneapolis, MN
Period9/2/099/6/09

All Science Journal Classification (ASJC) codes

  • Cell Biology
  • Developmental Biology
  • Biomedical Engineering
  • Medicine(all)

Fingerprint

Dive into the research topics of 'Stability analysis and breast tumor classification from 2D ARMA models of ultrasound images'. Together they form a unique fingerprint.

Cite this