An Improved Clustering-Based Approach for DNA Microarray Image Segmentation

DNA Microarrays are powerful techniques that are used to analyze the expression of DNA in organisms after performing experiments. One of the key issues in the experimental approaches that utilize microarrays is to extract quantitative information from the spots, which represent the genes in the experiments. In this process, separating the background from the foreground is a fundamental problem in DNA microarray data analysis. In this paper, we present an optimized clustering-based microarray image segmentation approach. As opposed to traditional clustering-based methods, we use more than one feature to represent the pixels. The experiments show that our algorithm performs microarray image segmentation more accurately than the previous clustering-based microarray image segmentation methods, and does not need a post-processing stage to eliminate the noisy pixels.