利用二維度K-means切割微陣列影像

Robust Segmentation of Microarray Images based on Two-Dimensional K-means

胡瑾纖(Jin-Sian Hu)

指導教授 ： 謝文萍

國立清華大學/理學院/統計學研究所/碩士(2006年)

https://doi.org/10.6843/NTHU.2006.00045

摘要

微陣列技術利用雜合(Hybridization)反應偵測RNA在樣本中的基因表現量，微陣列影像資料分析對推估基因表現量是非常重要的一個步驟。不同影像資料分析方法所得之結果，將會嚴重影響後續的統計分析和結論。在此研究中，我們利用二維度K-means切割微陣列影像，並且移除干擾因子以得到更準確的估計量。最後我們和混合模型切割方法比較replicates之間的相關係數和變異數，可以得知我們整體上有較高的相關係數，並且在整個影像強度上有較一致的變異程度。

關鍵字

微陣列影像 ； 影像切割 ； 生物晶片

並列摘要

DNA microarray experiment is a high throughout technology to assay gene expression level that is proportional to the intensities. Accurate image analysis is important to explore differential expressed genes. Different image analysis will influent statistical conclusion. In our study, we segment image by two-dimensional K-means with removal of unreliable pixels to obtain more accurate estimates. We compare our results with those obtained by mixture model. Our method results in higher correlation and consistent variance across replicates.

並列關鍵字

microarray ； k-means ； segmentation

參考文獻

Adams, R. and L. Bischof. (1994). Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16, 641-647

Ahmed, A. A., M. Vias, N. G. Iyer, C. Caldas, and J. D. Brenton (2004). Microarray segmentation methods significantly influence data precision. Nucleic Acids Research 32, e50.

Angulo, J. and J. Serra (2003). Automatic analysis of DNA microarray images using mathematical morphology. Bioinformatics, 19, 553-562.

Bozinov, D. and J. Rahnenführer (2002). Unsupervised 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.