Mousavi Parvin, Ward Rabab Kreidieh, Fels Sidney S, Sameti Mohammad, Lansdorp Peter M
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada.
IEEE Trans Biomed Eng. 2002 Apr;49(4):363-71. doi: 10.1109/10.991164.
Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.
同源染色体的分类对于癌症遗传学的深入研究至关重要。着丝粒强度被认为是同源染色体之间的一个重要区分特征。因此，着丝粒的分割是实现同源染色体分类的重要一步。本文描述了一种迭代模糊算法，该算法成功地从使用荧光原位杂交技术制备的人类染色体图像中分割出着丝粒。该算法基于为着丝粒图像中的每个像素分配一个模糊隶属度值。然后，一种迭代算法更新并最小化定义的误差函数。22号染色体是一条高度异形的染色体，用于验证着丝粒分割方法。基于分割后的着丝粒强度以及形态差异对该染色体的同源染色体进行分类。这两种方法的分类结果完全一致，并用于验证我们开发的算法。
