Pixel-by-pixel classification of MFISH images

Author

Sampat, Mehul P. ; Castleman, K.R. ; Bovik, A.C.

Author_Institution

Texas Univ., Austin, TX, USA

Volume

2

fYear

2002

fDate

2002

Firstpage

999

Abstract

Multiplex Fluorescence In-Situ Hybridization (M-FISH) is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and is also counterstained with DAPI. This paper proposes an automatic pixel by pixel classification algorithm for M-FISH images using a Bayes classifier. The M-FISH pixel classification was approached as a 25 class 6 feature pattern recognition problem. The classifier was trained and tested on non-overlapping data sets and an overall classification accuracy of 95% was obtained.

Keywords

Bayes methods; biomedical optical imaging; cellular biophysics; dyes; fluorescence; genetics; image classification; medical image processing; Bayes classifier; automatic pixel by pixel classification algorithm; chromosome analysis technique; counterstaining; fluors; human being health information; multiplex fluorescence in-situ hybridization; nonoverlapping data sets; overall classification accuracy; Biological cells; Classification algorithms; Covariance matrix; Density functional theory; Digital images; Fluorescence; Optical filters; Optical imaging; Pixel; Probability distribution;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint

ISSN

1094-687X

Print_ISBN

0-7803-7612-9

Type

conf

DOI

10.1109/IEMBS.2002.1106245

Filename

1106245