Spot segmentation is a crucial step in microarray image processing. A reliable and robust quantification of spot intensity can help to better identify the important genes and to reflect the true information. Most of the widely adopted methods do not perform well in terms of the reproducibility across replicates and the huge variation in the background. We propose a robust method to estimate the foreground and background intensities based on kernel density estimation without specifically segment the foreground and background pixels. We will discuss our method of gridding and expression summary for cDNA microarray images with an experiment of technical replicates. Our method is compared to K-means and Model-Based Clustering and has better accuracy across replicates.

Spot segmentation is a crucial step in microarray image processing. A reliable and robust quantification of spot intensity can help to better identify the important genes and to reflect the true information. Most of the widely adopted methods do not perform well in terms of the reproducibility across replicates and the huge variation in the background. We propose a robust method to estimate the foreground and background intensities based on kernel density estimation without specifically segment the foreground and background pixels. We will discuss our method of gridding and expression summary for cDNA microarray images with an experiment of technical replicates. Our method is compared to K-means and Model-Based Clustering and has better accuracy across replicates.

REFERENCES
Adams, R. and L. Bischof. (1994). Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16, 641-647
Angulo, J. and J. Serra (2003). Automatic analysis of DNA microarray images using mathematical morphology. Bioinformatics, 19, 553-562
Bengtsson, H., G.. Jönsson, J. Vallon-Christersson (2004). Calibration and assessment of channel-specific biases in microarray data with extended dynamical range. BMC Bioinformatics, 5, 177.
Bengtsson, A. and H. Bengtsson (2006). Microarray image analysis: background estimation using quantile and morphological filters. BMC Bioinformatics, 7, 96.
Beucher, S. and F. Meyer (1993). The morphological approach to segmentation: the watershed transformation. In Mathematical morphology in image processing, volume 34 of Optical Engineering, 12, 433-481. Marcel Dekker, New York.
Blekas, K., N. P. Galatsanos, A. Likas and I. E. Lagaris (2005). Mixture model analysis of DNA microarray images. IEEE Transactions on Medical imaging, 24, NO. 7.
Bozinov, D. (2003). Autonomous system for Web-Based microarray image analysis. IEEE. Transactions on Nanobioscience, 2, 215–220
Bozinov, D. and J. Rahnenfüher (2002). Unspervised technique for robust target separation and analysis of DNA microarray spots through adaptive pixel clustering. Bioinformatics 18, 747-756
Dasgupta, A. and A. E. Raftery (1998). Detecting features in spatial point process with cluster via model-based clustering. Journal of the American Statistical Association 93,294-302.
Daniel Bozinov (2003). Autonomous system for Web-Based microarray image analysis. IEEE. Transactions on Nanobioscience, 2, 215–220
Deheuvels, P. (1977). Estimation non paramétrique de la densité par histrogrammes généralisés II, Publ. Inst. Statist. Univ. Paris, 22, 1-23
Demirkaya,O., M. H. Asyali, and M. M. Shoukri (2005). Segmentation of cDNA microarray spots using markov random field modeling. Bioinformatics, 21, 2994–3000.
Fraley, C. and A. E. Raftery (1998). How many clusters? Which clustering method? – answers via model-based cluster analysis. The Computer Journal 41, 578-588.
Fraley, C. and A. E. Raftery (2002). Model-based clustering, discriminant analysis and density estimation. Journal of the American Statistical Association 97,611-631.
GenePix [ http://www.axon.com ]
GSI Lumonics (1999). QuantArray Analysis Software, Operator’s Manual.
Hall, P. and Wand, M.P. (1994). On the accuracy of binned kernel density estimators. Submitted for publication.
Härdle, W. and Scott, D.W. (1992). Smoothing in low and high dimensions by weighted averaging using rounded points. Comput. Statist., 7, 97-128.
Hartigan, J. (1975). Clutering Algorithm. Wiley, New York.
Lan, H. J. and H. S. Lu (2005). Segmentation of microarray images by mixture models. M. S. Thesis, Institute of Statistics, National Chiao Tung University.
Lehmussola, A., P. Ruusuvuori and O. Yli-Harja (2006). Evaluating the performance of microarray segmentation algoritnms. Bioinformatics, 22, 2910-2917.
Li, Q.,C. Fraley, E. B. Roger, K. Y. Yeung, and A. E. Raftery(2005).Donuts, scratches and blanks: robust model-based segmentation of microarray images. Bioinformatics, 21, 2875–2882.
Lonardi, S. and Y. Luo (2004). Gridding and compression microarray images. IEEE. Computational Systems Bioinformatics Conference, 0, 122 – 130.
Jung, H. Y. and H. G. Cho (2002). An automatic block and spot indexing with k-nearest neighbors graph for microarray image analysis. Bioinformatics, 18, 141-151.
MacQueen, J. B.(1967). Some methods for classification and analysis of multivariate observations. Proc. Symp. Math. Statist. and Probability, 5th, 1, 281-297.
McLachlan, G. and D. Peel (2000). Finite Mixture Models. John Wiley & Sons.
Park, B.U. and Marron, S.J. (1990). Comparison of data-driven bandwidth selectiors. J.Amer. Statist. Assoc. 85, 66-72.
R [http://www.r-project.org ]
Rahnenführer, J. and Bozinov, D. (2004). Hybrid clustering for microarray image analysis combining intensity and shape features. BMC Bioinformatics, 5, 1–11.
Scanalyze [ http://rana.lbl.gov/EisenSoftware.htm ]
Scott, D.W. and Sheather, S.J. (1985). Kernel density estimation with binned data. Comm. Statist. Theory Meth. 14, 1353-1359.
Silverman, B.W (1982). Kernel density estimation using the fast Fourier transform. Appl. Statist., 27, 26-33.
Soille, P (2002). On morphological operators based on rank filters. Pattern recognition, 35, 527-535.
Spot [ http://www.cmis.csiro.au/IAP/Spot/spotmanual.htm ]
Yang, Y. H., M. Buckley, S. Dudoit and T. Speed (2002). Comparison of methods for image analysis on cDNA microarray data. J. Comput. Graph. Stat., 11, 108–136.
Yin, W., T. Chen, XS. Zhou, A. Chakraborty (2005). Background correlation for cDNA microarray images using the TV+L1 model. Bioinformatics, 2, 2410-2416.