IJCA Special Issue on “Computer Aided Soft Computing Techniques for Imaging and Biomedical Applications” CASCT, 2010. 77 An Improved Iterative Watershed and Morphological Transformation Techniques for Segmentation of Microarray Images A.Sri Nagesh Dr.G.P.S.Varma Dr A Govardhan Assistant Professor, CSE Department, Professor, IT Department, Professor& Principal,CSE Department, R.V.R.& J.C.College of Engineering, S.R.K.R.Engineering College, JNTUCEH, Jagtiyal , Chowdavaram,Guntur. Bhimavaram. Hyderabad. ABSTRACT Microarrays are novel and dominant techniques that are being made use in the analysis of the expression level of DNA, with pharmacology, medical diagnosis, environmental engineering, and biological sciences being its current applications. Studies on microarray have shown that image processing techniques can considerably influence the precision of microarray data. A crucial issue identified in gene microarray data analysis is to perform accurate quantification of spot shapes and intensities of microarray image. Segmentation methods that have been employed in microarray analysis are a vital source of variability in microarray data that directly affects precision and the identification of differentially expressed genes. The effect of different segmentation methods on the variability of data derived from microarray images has been overlooked. This article proposes a methodology to investigate the accuracy of spot segmentation of a microarray image, using morphological image analysis techniques, watershed algorithm and iterative watershed algorithm. The input to the methodology is a microarray image, which is then subjected to spotted microarray image preprocessing and gridding. Subsequently, the resulting microarray sub grid is segmented using morphological operators, watershed algorithm and iterative watershed algorithm. Based on the precision of segmentation and its intensity profile, a formal investigation of the three segmentation algorithms employed (morphological operators, watershed algorithm and iterative watershed algorithm) is performed. The experimental results demonstrate the segmentation effectiveness of the proposed methodology and also the better of the three segmentation algorithms employed for segmentation. General Terms Machine Intelligence, Bio Informatics, Soft Computing, Retrieval, Medical Digital Image Processing, Medical Image Databases. Keywords: Bioinformatics, Microarray, Genes, Spot Segmentation, Threshold, Fast Circular Cross Correlation, Morphological Operator, Morphological Filtering, Watershed Algorithm, Iterative Watershed Algorithm. I. INTRODUCTION In bioinformatics, microarrays have been emerging as vital technologies, proffering support in dealing with an extensive range of problems in medicine, health and environment, and drug development [1]. Microarray technology is being incorporated into fundamental biomedical research and is becoming an elementary molecular monitoring tool in clinical microbiology settings, particularly for diagnostic applications owing to the likelihood of multiplexing the simultaneous detection of a number of pathogens in a single reaction [2, 3, 4]. The utilization of microarrays in measuring gene expression levels in variable conditions offers biologists with a better understanding of gene functions, and has a plenty of applications in life sciences [5], [6]. A considerable number of clinical applications are on the basis of the development of DNA microarrays for the detection of specific genes or gene regions in pathogens, while others are on the basis of protein (ELISA microarrays) or other immobilized molecules [7]. Characteristic applications of microarrays include the quantification of RNA expression profiles of a system under varied experimental conditions, or expression profile comparisons of two systems under one or several conditions. DNA microarrays are an experimental technology for performing exploration of the genome (genotyping experiments). The technology proffers to biomedical investigators a simple tool for monitoring the expression levels of thousands of genes, under the same experimental conditions, and thus a simple way to identify and quantify gene expression levels for all genes in an organism [8]. Microarrays could be made use of to detect genes that are involved in specific diseases, by comparing gene expression in normal and abnormal cells. On course of the biological experiment, the extraction of mRNA corresponding to two biological tissues of interest (i.e. normal and tumor) is performed. Every mRNA sample is reverse transcribed into complementary DNA (cDNA) copy and labeled with two distinct fluorescent dyes resulting in two fluorescence- tagged cDNA (red Cy5 and green Cy3) [9]. Subsequently, the probes on the cDNA array are mixed and cohybridized with the RNA samples. The resulting samples are then scanned to obtain a 16-bit gray-scale image for each dye. The relative profusion of a specific RNA type in the sample is the measure of the relative intensity of the dyes in each spot. The unequal distribution of probe material in the spot, making spots irregular in shape and size, is induced [10] by a plenty of factors like 1) the