Affiliations: Department of Information Systems, Le Quy Don Technical University, Hanoi, Vietnam | School of Information, Production and Systems, Waseda University, KitaKyushu, Japan
Note: [] Corresponding author. Long Thanh Ngo, Department of Information Systems, Le Quy Don Technical University, No. 236 Hoang Quoc Viet, Cau Giay, Hanoi, Vietnam. Tel.: +84 914 364 064; Fax: +84 43836 0897; E-mails: [email protected] (Long Thanh Ngo), [email protected] (Dzung Dinh Nguyen), [email protected] (Junzo Watada).
Abstract: Multiplex Fluorescent In Situ Hybridization (M-FISH) is a multi-channel chromosome image generating technique that allows colors of the human chromosomes to be distinguished. In this technique, all chromosomes are labelled with 5 fluors and a fluorescent DNA stain called DAPI (4 in, 6-Diamidino-2-phenylindole) that attaches to DNA and labels all chromosomes. Therefore, a M-FISH image consists of 6 images, and each image is the response of the chromosome to a particular fluor. In this paper, we propose a genetic interval type-2 fuzzy c-means (GIT2FCM) algorithm, which is developed and applied to the segmentation and classification of M-FISH images. Chromosome pixels from the DAPI channel are segmented by GIT2FCM into two clusters, and these chromosome pixels are used as a mask for the remaining five channels. Then, the GIT2FCM algorithm is applied to classify the chromosome pixels into 24 classes, which correspond to the 22 pairs of homologous chromosomes and two sexual chromosomes. The experiments performed using the M-FISH dataset show the advantages of the proposed algorithm.
