Title | Feature analysis and centromere segmentation of human chromosome images using an iterative fuzzy algorithm |
Publication Type | Journal Article |
Year of Publication | 2002 |
Authors | Mousavi, P., R. K. Ward, S. S. Fels, M. Sameti, and P. M. Lansdorp |
Journal | Biomedical Engineering, IEEE Transactions on |
Volume | 49 |
Pagination | 363 -371 |
Date Published | apr. |
ISSN | 0018-9294 |
Keywords | algorithm validation, Algorithms, cancer, Centromere, centromere segmentation, Chromosomes, fluorescence, fluorescence in-situ hybridization technique, fuzzy logic, fuzzy membership value, genetics, heteromorphic chromosome, homolog classification, Human, human chromosome images, Humans, image segmentation, In Situ Hybridization, iterative fuzzy algorithm, iterative methods, medical image processing, Metaphase, Microscopy, morphological differences, optical microscopy, Pair 22, pixel, segmented centromere intensities |
Abstract | 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. |
URL | http://dx.doi.org/10.1109/10.991164 |
DOI | 10.1109/10.991164 |