摘要
互补脱氧核糖核酸(cDNA)微阵列是一项广泛应用的技术,该技术现被应用于同时研究数千个基因的表达水平.样点分割是c DNA微阵列图像处理技术中的关键环节.微阵列图像动态范围较高,部分区域对比度较低且包含噪声,因此给分割带来一定难度.本文首先使用规则网格技术,将微阵列图像划分成单个子图像.为了增强对比度,将子图像归一化后在每个网格内使用C-V模型和水平集技术进行分割.为消除噪声造成的干扰,使用样点面积先验知识作为标准,得到最终的样点位置.实验结果表明,与相关算法相比本文算法具有一定的优势.
Complementary DNA(cDNA) microarray technology is widely used on research for the expression of thousands of genes synchronously.The spot segmentation of cDNA microarray image is one of the important steps for microimage analysis.It is not an easy thing as the image has a high dynamic range and a poor contrast in some regions.And it is disturbed by some noise.In this paper,C-V model and the level set technique are applied in the normalized sub-image which is obtained by a regular gridding technique.The previous knowledge on the spot area is used to remove the effect by noise before locating the final spot positions.The experimental results show that the proposed algorithm performances better when compared to some related methods.
引文
[1]Peng Q,Plevritis S K.Reconstructing directed signed gene regulatory network from microarray data[J].Biomedical Engineering IEEE Transactions on,2011,58(12):3518-3521.
[2]Wu Zao-quan,Chen Xi,Lou Yan-yang,et al.Research of incline correction algorithm in microarray image[J].Journal of Central South University(Science and Technology),2014,45(4):1091-1097.
[3]Duan Hui-long,Deng Ning.A survey on image-based microarray analysis[J].Chinese Journal of Biomedical Engineering,2006,25(6):780-785+792.
[4]Bariamis D,Iakovidis D K,Maroulis D.M3G:maximum margin microarray gridding[J].Bmc Bioinformatics,2010,11(4):1-11.
[5]Ye Ping,Weng Gui-rong.Microarray image segmentation using region growing algorithm and mathematical morphology[C].5th International Conference on Information Assurance and Security,IAS2009:373-376.
[6]Weng Gui-rong.cDNA microarray image processing using mathematical morphological segmentation[C].Proceedings of the 29th Chinese Control Conference(CCC'10),2010:2660-2664.
[7]Nagarajan R.Intensity-based segmentation of microarray images,in medical imaging[J].IEEE Transactions on,2003,22(7):882-889.
[8]Uslan,Volkan,Bucak,Ihsan Omür.Clustering-based spot segmentation of cDNA microarray images[C].2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society(EMBC'10),2010:1828-1831.
[9]Wang Zi-dong,Zineddin,Bachar,Liang Jin-ling,et al.CDNA microarray adaptive segmentation[J].Neurocomputing,2014,142:408-418,October 22,2014.
[10]Wang T N,Li T J,Shao G F4,et al.An improved K-means clustering method for cDNA microarray image segmentation[J].Genetics and Molecular Research,2015,14(3):7771-7781.
[11]Mendhurwar,Kaustubha A.Kakumani,Rajasekhar;Devabhaktuni,Vijay.Microarray image segmentation using Chan-Vese active contour model and level set method[C].Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society:Engineering the Future of Biomedicine,EMBC,2009:3629-3632.
[12]A.K.Helmy a,Gh.S.El-taweel.Regular gridding and segmentation for microarray images[J].Computers and Electrical Engineering,2013,39(7):2173-2182.
[13]Katsigiannis S,Zacharia E,Maroulis D.Grow-Cut based automatic cDNA microarray image segmentation[C].In NanoBioscience,IEEE Transactions on Nanobioscience,2015:137-144.
[14]Zacharia,Eleni;Maroulis,Dimitris.An original genetic approach to the fully automatic gridding of microarray images[J].IEEE Transactions on Medical Imaging,2008,27(6):805-813.
[15]Chan,Tony F.Vese,Luminita A.Active contours without edges[J].IEEE Transactions on Image Processing,2001,10(2):266-277.
[16]Shen Xuan-jing,Long Jian-wu,Chen Hai-peng,et al.Otsu thresholding algorithm based on rebuilding and dimension reduction of the3-dimensional histogram[J].Tien Tzu Hsueh Pao/Acta Electronica Sinica,2011,39(5):1108-1114.
[17]Chambolle A.An algorithm for total variation minimization and applications[J].Math.Imaging and Vision,2004,20(1-2):89-97.
[2]吴灶全,陈熹,娄艳阳,等.生物芯片微阵列图像倾斜校正算法研究[J].中南大学学报(自然科学版),2014,45(4):1091-1097.
[3]段会龙,邓宁.基于图像的微阵列生物芯片分析[J].中国生物医学工程学报,2006,25(6):780-785+792.