Please use this identifier to cite or link to this item:
標題: 植基於固定圓微陣列影像基因表現點自動切割法
Fixed-Circle Based Automatic Gene Spots Segmentation of Microarray Images
作者: 李青武
Li, Ching-Wu
關鍵字: 微陣列影像
Microarray image
Projection profile
Median filter
Fixed-circle segmentation
出版社: 資訊管理學系所
引用: [1] Angulo, J., Automatic analysis of DNA microarray images using mathematical morphology. Bioinformatics, 2003. 19(5): p. 553-562. [2] Antoniol, G., Ceccarelli, M. and Petrosino, A., Microarray image addressing based on the Radon transform. in Image Processing, 2005. ICIP 2005. IEEE International Conference on. 2005. 1: p. 13-16. [3] Chou, Y.L., Statistical analysis. 1969: Holt, Rinehart and Winston. [4] Drăghici, S., Data analysis tools for DNA microarrays. 2003: Chapman & Hall/CRC. [5] Giannakeas, N. and Fotiadis, D.I., An automated method for gridding and clustering-based segmentation of cDNA microarray images. Computerized Medical Imaging and Graphics, 2009. 33(1): p. 40-49. [6] Gonzalez, R.C., Woods R.E., and Eddins S.L., Digital image processing using MATLAB. 2004: Pearson Education India. [7] Gopu, G., Neelaveni, R. and Porkumaran, K., An Improved Iterative Watershed and Morphological Transformation Techniques for Segmentation of Microarray Images. International Journal of Computer Applications IJCA, 2010(2): p. 7-10. [8] Kamberova, G. and Kamberov G., DNA Array Image Analysis: Nuts & Bolts (Nuts & Bolts series). 2005. [9] Liu, Y., Zhang, Y.D. and Sha, X.Z., Automatic Recognition of Microarray Images Using Projection Algorithm. in Bioinformatics and Biomedical Engineering (iCBBE), 2010 4th International Conference on. 2010: p. 1-4. [10] Mastandrea, F. and Pardo, A., Processing of Microarray Images. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, 2009: p. 962-969. [11] Moena Q, D., Microarray Image Gridding by Using Self-Organizing Maps. in Bioinformatics and Biomedical Engineering, (iCBBE) 2011 5th International Conference on. 2011: p. 1-4. [12] Morris, D., Wang Z., and Liu, X., Microarray subgrid detection: a novel algorithm. International Journal of Computer Mathematics, 2007. 84(5): p. 669-678. [13] Otsu, N., A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions On Systems Man And Cybernetics, 1979. 9: p. 62-66. [14] Rezaeian, I. and Rueda L., Sub-grid and spot detection in DNA microarray images using optimal multi-level thresholding. Pattern Recognition in Bioinformatics, 2010: p. 277-288. [15] Rueda L., Vidyadharan V., A Hill-climbing Approach for Automatic Gridding of cDNA microarray Images. IEEE/ACM Transactions on computational Biology and Bioinformatics, 2006. 3(1): p. 72-83. [16] Steinfath, M., et al., Automated image analysis for array hybridization experiments. Bioinformatics, 2001. 17(7): p. 634-641. [17] Tuimala, J. and Laine, M.M., DNA microarray data analysis. 2003: CSC-Scientific Computing. [18] Zhou, Q., et al., cDNA Microarray Images Gridding Based on Projection. Journal of Convergence Information Technology, 2011. 6: p. 188-194.
摘要: 微陣列(Microarray)在基因研究上是一項強而有力的研究工具。微陣列影像處理之主要目的在於建構一個精確且自動化的系統,不需要人類的介入操作即能可靠地探索基因表現點(spot)。在本論文研究中提出一項基於投影圖、形態學及幾何學技術以處理定格和固定圓切割(Fixed-circle segmentation)的方法。即使是不同解析度、不同尺寸大小的微陣列,此方法亦能有效地計算出理論表現點的固定半徑值。本論文所提出的方法適用於處理各式微陣列影像中有各種形狀大小不同的基因表現點,實驗結果顯示二值化投影圖法在處理定格和固定圓切割上較灰階投影圖法更為精確。
Microarray is a powerful tool for genetic research. The major goal of microarray image processing is to construct a precise and automatic system to find the spots reliably without the need of any human intervention. In this paper, a simple and fully automatic approach, based on projection profile, morphology and geometry techniques, has been proposed for gridding and Fixed-circle segmentation. The proposed approach is effective to calculate the fixed diameter of theoretical spot, even though the sizes of different resolution microarrays are different. The experimental results show that the proposed approach is applicable to all kinds of different microarray images with various spot sizes and features. The experimental results also have illustrated the approach based on binary projection profile is more accurate than the approach based on grayscale projection profile in gridding and Fixed-circle segmentation.
其他識別: U0005-1707201200594900
Appears in Collections:資訊管理學系



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.