ICTACT Journal on Image and Video Processing

V. G. Biju ¹, P. Mythili ¹

Affiliations
1 School of Engineering, Cochin University of Science and Technology, IN

Abstract

An important stage in microarray image analysis is gridding. Microarray image gridding is done to locate sub arrays in a microarray image and find co-ordinates of spots within each sub array. For accurate identification of spots, most of the proposed gridding methods require human intervention. In this paper a fully automatic gridding method which enhances spot intensity in the preprocessing step as per a histogram based threshold method is used. The gridding step finds co-ordinates of spots from horizontal and vertical profile of the image. To correct errors due to the grid line placement, a grid line refinement technique is proposed. The algorithm is applied on different image databases and results are compared based on spot detection accuracy and time. An average spot detection accuracy of 95.06% depicts the proposed method's flexibility and accuracy in finding the spot co-ordinates for different database images.

Keywords

cDNA Microarray, Gridding, Image Processing, Spot Detection, Grid Line Refinement.

Full Text

     

V. G. Biju ¹, P. Mythili ²

Affiliations
1 Department of Electronics and Communication Engineering, College of Engineering Munnar, IN
2 Division of Electronics Engineering, School of Engineering, CUSAT, IN

Abstract

An automatic cDNA microarray image processing using an improved fuzzy clustering algorithm is presented in this paper. The spot segmentation algorithm proposed uses the gridding technique developed by the authors earlier, for finding the co-ordinates of each spot in an image. Automatic cropping of spots from microarray image is done using these co-ordinates. The present paper proposes an improved fuzzy clustering algorithm Possibility fuzzy local information c means (PFLICM) to segment the spot foreground (FG) from background (BG). The PFLICM improves fuzzy local information c means (FLICM) algorithm by incorporating typicality of a pixel along with gray level information and local spatial information. The performance of the algorithm is validated using a set of simulated cDNA microarray images added with different levels of AWGN noise. The strength of the algorithm is tested by computing the parameters such as the Segmentation matching factor (SMF), Probability of error (pe), Discrepancy distance (D) and Normal mean square error (NMSE). SMF value obtained for PFLICM algorithm shows an improvement of 0.9 % and 0.7 % for high noise and low noise microarray images respectively compared to FLICM algorithm. The PFLICM algorithm is also applied on real microarray images and gene expression values are computed.

Keywords

Gridding, Spot Segmentation, Local Information, Spatial Information, Typicality, Clustering, Gene Expression.

Full Text