Microarray Images Processing Using the Offset Vector Field and Expectation Maximization Algorithm

Abstract

DNA microarrays provide a simple tool to identify and quantify the gene expression for tens of thousands of genes simultaneously. Image processing is an important step in microarrays experiments. This paper presents a novel technique for removing gene's noises based on the offset vector field and segmenting genes using the expectation maximization algorithm. Simulations show that the new technique for microarray images filtering and segmentation has better performance than most of the common ways. The results of experiments are computationally attractive, have excellent performance and can preserve spots' data while efficiently suppress noises.