Various Versions of K-means Clustering Algorithm for Segmentation of Microarray Image

A Deoxyribonucleic Acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as glass, plastic or silicon chip forming an array. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. The DNA microarray image analysis includes three tasks: gridding, segmentation and intensity extraction. The segmentation step of microarray image analysis has been implemented in this paper. We used four versions of clustering algorithms called K-means, Moving Kmeans, Fuzzy K-means and Fuzzy Moving K-means for microarray image segmentation that separate the spots from the background. The experimental results show that Fuzzy Moving K-means have segmented the spots of the microarray image more accurately than other three algorithms.