GA based optimisation of a multi-agent soft computing model for segmentation and classification of unstained mammalian cell images

C. Lai, R. Khosla, Y. Mitsukura

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

Most existing approaches for determining serious pathological conditions involve analysis of stained images of human tissue. Recently, unstained methods have been used for classification and analysis of cells in human and mammalian tissues. The classifications accuracies have been have been quite poor. We describe a novel application of genetic algorithms for significantly improving the segmentation and classification of cells in unstained Chinese hamster ovarian image samples. The multiagent soft computing model represents a symbiotic relationship between soft computing agents like genetic algorithms, neural networks and water immersion and morphological agents for segmentation and classification of cells in unstained Chinese hamster ovarian image samples.

Original languageEnglish
Pages1192-1198
Number of pages7
DOIs
Publication statusPublished - 2003 Jan 1
Externally publishedYes
Event2003 Congress on Evolutionary Computation, CEC 2003 - Canberra, ACT, Australia
Duration: 2003 Dec 82003 Dec 12

Other

Other2003 Congress on Evolutionary Computation, CEC 2003
CountryAustralia
CityCanberra, ACT
Period03/12/803/12/12

    Fingerprint

ASJC Scopus subject areas

  • Computational Mathematics

Cite this

Lai, C., Khosla, R., & Mitsukura, Y. (2003). GA based optimisation of a multi-agent soft computing model for segmentation and classification of unstained mammalian cell images. 1192-1198. Paper presented at 2003 Congress on Evolutionary Computation, CEC 2003, Canberra, ACT, Australia. https://doi.org/10.1109/CEC.2003.1299804