Vector Median Root Signals Determination for cDNA Microarray Image Segmentation

Abstract

Abstract. This paper presents a new cDNA microarray image segmentation framework. The framework uses robust vector median filtering to generate a root sigLnal which is an image obtained from the input by repeatedly filtering it until no more changes occur. During the convergence to the root signal, the framework classifies the cDNA image data as either microarray spots or image background, and ideally separates the regular spots from the background. Thus, the obtained root signal represents the segmented microarray image. In addition, the framework excellently removes noise present in the cDNA microarray images and normalizes spots' intensities.

cDNA microarray image segmentation using root signals

“…The paper extends the preliminary results presented in the conference publication (Lukac and Plataniotis, 2005). The segmentation is performed using root signals obtained through the utilization of a nonlinear filtering operator.…”

“…(2) and (3), we may consider uniformity in vector magnitude and directionality as the criterion for partitioning the cDNA vector field into disjoint regions corresponding to distinguishable spots. Hence, the cDNA microarray image segmentation process can be defined as follows (Lukac and Plataniotis, 2005):…”

“…Assuming that y n (r,s) is a vector in the image y n obtained after filtering n times the input cDNA image x, the convergence rate expressed as a function of the difference between two successive filtering results can be defined as follow (Lukac and Plataniotis, 2005):…”