AN INTELLIGENT SEGMENTATION ALGORITHM FOR MICROARRAY IMAGE PROCESSING

Microarray technology consists of an array of thousands of microscopic spots of DNA oligonucleotides attached to a solid surface. It is a very powerful technique for analyzing gene expressions as well as to explore the underlying genetic causes of many human diseases. There are numerous applications of this technology, including environmental health research, drug design and discovery, clinical diagnosis and treatment and in cancer detection. The spots, which represent genes in microarray experiment contains the quantitative information that needs to be extracted accurately. For this process, preprocessing of microarray plays an essential role and it is also influential in future steps of the analysis. The three microarray preprocessing steps include gridding, segmentation and quantification. The first step is gridding, refers to the identification of the centre coordinates of each spot. The second step is segmentation, refers to the process of separating foreground and background fluorescence intensities. Segmentation is very important step as it directly affects the accuracy of gene expression analysis in the data mining process that follows. Accurate segmentation is one of the vital steps in microarray image processing. A novel method for segmentation of microarray image is proposed which accurately segment the spots from background when compared with adaptive threshold, combined global and local threshold and fuzzy c-means clustering methods. Experimental results show that our proposed method provides better segmentation and improved intensity values than the above existing methods. Keywords-Microarray; Gridding; Segmentation; Quantification; Fuzzy c-means clustering; Soft Threshold

[1]  Guirong Weng,et al.  Microarray Images Processing Using the Offset Vector Field and Expectation Maximization Algorithm , 2010, 2010 4th International Conference on Bioinformatics and Biomedical Engineering.

[2]  Radhakrishnan Nagarajan,et al.  Intensity-based segmentation of microarray images , 2003, IEEE Transactions on Medical Imaging.

[3]  K. Marias,et al.  Improved Microarray Spot Segmentation by Combining two Information Channels , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  W. Dai,et al.  Spotted cDNA microarray image segmentation using ACWE , 2009 .

[5]  Luis Rueda,et al.  An Improved Iterative Watershed and Morphological Transformation Techniques for Segmentation of Microarray Images , 2010 .

[6]  Ronald W. Davis,et al.  Quantitative Monitoring of Gene Expression Patterns with a Complementary DNA Microarray , 1995, Science.

[7]  A.O. Hero,et al.  Mathematical morphology applied to spot segmentation and quantification of gene microarray images , 2002, Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002..

[8]  Pantelis Georgiadis,et al.  Segmentation of Complementary DNA Microarray Images by Wavelet-Based Markov Random Field Model , 2009, IEEE Transactions on Information Technology in Biomedicine.

[9]  G. Sagerer,et al.  Methods for automatic microarray image segmentation , 2003, IEEE Transactions on NanoBioscience.

[10]  A. Sreedevi,et al.  Automatically Locating Spots in DNAMicroarray Image Using Genetic Algorithm without Gridding , 2009, 2009 International Association of Computer Science and Information Technology - Spring Conference.

[11]  Tsung-Han Tsai,et al.  Error Reduction on Automatic Segmentation in Microarray Image , 2007, 2007 IEEE Workshop on Signal Processing Systems.

[12]  B. Belean,et al.  Hardware implementation of microarray image segmentation , 2008, 2008 IEEE International Conference on Automation, Quality and Testing, Robotics.

[13]  Aggelos K. Katsaggelos,et al.  DNA Microarray Image Intensity Extraction using Eigenspots , 2007, 2007 IEEE International Conference on Image Processing.

[14]  Wang Yu-Ping,et al.  Automated Segmentation of Microarray Spots Using Fuzzy Clustering Approaches , 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

[15]  O. Demirkaya,et al.  Segmentation of microarray cDNA spots using MRF-based method , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[16]  D. Maroulis,et al.  3-D Spot Modeling for Automatic Segmentation of cDNA Microarray Images , 2010, IEEE Transactions on NanoBioscience.

[17]  D.I. Fotiadis,et al.  Multichannel Segmentation of cDNA Microarray Images using the Bayes Classifier , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Tessamma Thomas,et al.  Automatic segmentation of DNA microarray images using an improved seeded region growing method , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[19]  Volkan Uslan,et al.  Microarray Image Segmentation Using Clustering Methods , 2010 .

[20]  V. Devabhaktuni,et al.  Microarray image segmentation using chan-vese active contour model and level set method , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[21]  Dimitrios I. Fotiadis,et al.  Image Processing and Machine Learning Techniques for the Segmentation of cDNA Microarray Images , 2012 .

[22]  Wen-Liang Hwang,et al.  Segmenting Microarray Image Spots using an Active Contour Approach , 2007, 2007 IEEE International Conference on Image Processing.

[23]  J. Harikiran,et al.  Fuzzy C-means with Bi-dimensional Empirical Mode Decomposition for Segmentation of Microarray Image , 2012 .

[24]  Gonzalo Vegas-Sanchez-Ferrero,et al.  Soft thresholding for medical image segmentation , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[25]  S. Shirani,et al.  Segmentation of DNA microarray images using an adaptive graph-based method , 2010 .

[26]  G BijuV.  A Genetic Algorithm based Fuzzy C Mean Clustering Model for Segmenting Microarray Images , 2012 .

[27]  Chiao-Ling Shih,et al.  Automatic spot detection of cDNA microarray images using mathematical morphology methods , 2003, IEEE EMBS Asian-Pacific Conference on Biomedical Engineering, 2003..

[28]  N. D. Londhe,et al.  Automatic Liver Tumour Detection in Abdominal CT Images , .