請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/9986
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 胡文聰(Andrew M. Wo) | |
dc.contributor.author | Ting-Chung Lee | en |
dc.contributor.author | 李定中 | zh_TW |
dc.date.accessioned | 2021-05-20T20:53:58Z | - |
dc.date.available | 2016-08-09 | |
dc.date.available | 2021-05-20T20:53:58Z | - |
dc.date.copyright | 2011-08-09 | |
dc.date.issued | 2011 | |
dc.date.submitted | 2011-08-02 | |
dc.identifier.citation | [1] L. Bjerrum, T. Kjaer, and N.B. Ramsing, “Enumerating ammonia-oxidizing bacteria in environmental samples using competitive PCR,” Journal of microbiological methods, vol. 51, 2002, pp. 227–239.
[2] M. Wagner, M. Horn, and H. Daims, “Fluorescence in situ hybridisation for the identification and characterisation of prokaryotes,” Current Opinion in Microbiology, vol. 6, Jun. 2003, pp. 302-309. [3] H. Daims and M. Wagner, “Quantification of uncultured microorganisms by fluorescence microscopy and digital image analysis,” Applied Microbiology and Biotechnology, vol. 75, Mar. 2007, pp. 237-248. [4] J.A. Bilmes, “A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models,” International Computer Science Institute, vol. 4, 1998, p. 126. [5] A.K.C. Wong and P.K. Sahoo, “A gray-level threshold selection method based on maximum entropyprinciple,” IEEE Transactions on Systems, Man and Cybernetics, vol. 19, Aug. 1989, pp. 866-871. [6] C. Carson, S. Belongie, H. Greenspan, and J. Malik, “Blobworld: Image segmentation using Expectation-Maximization and its application to image querying,” IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 24, 1999, p. 1026--1038. [7] H. Hong and D. Schonfeld, “Maximum-entropy expectation-maximization algorithm for image reconstruction and sensor field estimation,” IEEE Transactions on Image Processing: A Publication of the IEEE Signal Processing Society, vol. 17, Jun. 2008, pp. 897-907. [8] R. Gonzalez, Digital image processing, Upper Saddle River N.J.: Pearson/Prentice Hall, 2010. [9] P. Dodwell, Visual pattern recognition, New York: Holt Rinehart and Winston, 1970. [10] R. Moddemeijer, “On estimation of entropy and mutual information of continuous distributions,” Signal Processing, vol. 16, 1989, pp. 233–248. [11] H. Deng, G. Runger, and E. Tuv, “Bias of Importance Measures for Multi-valued Attributes and Solutions,” Artificial Neural Networks and Machine Learning – ICANN 2011, T. Honkela, W. Duch, M. Girolami, and S. Kaski, Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 293-300. [12] T. Zhang, “An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods,” AI MAGAZINE, vol. 22, 2001, pp. 103-104. [13] B. Dasarathy, Nearest neighbor (NN) norms : nn pattern classification techniques, Los Alamitos Calif. ;Washington: IEEE Computer Society Press ;;IEEE Computer Society Press Tutorial, 1991. [14] S.A. Dudani, “The Distance-Weighted k-Nearest-Neighbor Rule,” IEEE Transactions on Systems, Man and Cybernetics, vol. SMC-6, Apr. 1976, pp. 325-327. [15] P. Hall, “Choice of neighbor order in nearest-neighbor classification,” The Annals of Statistics, vol. 36, Oct. 2008, pp. 2135-2152. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/9986 | - |
dc.description.abstract | 細胞計量是生醫研究中不可或缺的基礎項目之一,多數的生醫研究人員必須以人工進行細胞計量與觀察(例如不同細胞數量的統計以及判斷細胞型態),而隨著實驗需求往往耗費大量的人力與時間,在於非理想的影像背景下,不同的研究人員的主觀看法也可能影響到最後的辨認結果。
本研究針對兩種細胞株(HUVEC和Jurkat)之混和樣本螢光標定影像藉由影像處理技術來擷取細胞和多變量統計方法進行分析。在影像處理的部分利用Gaussian mixture model對影像histogram 做分析,利用其結果取得適合的門檻值將圖片二值化,並做適當的雜訊處理後抽離成前景及背景,再對前景擷取到的物件做多張螢光訊號的特徵比對,最後以nearest neighbor method建立訓練資料庫,可利用特徵值對抽離的物件是否為細胞做判準,對於非理想背景下多重螢光標定細胞的影像可得到不錯且客觀的計數結果。 根據實驗結果,以Gaussian mixture model 可有效地對影像作前景背景的分離並不受到原始影像對比度影響,訓練完的特徵對於抽取的細胞株可有97%準確率的辨識度,足以應付生醫研究人員細胞株計數之需求,可望未來再進一步建立病人檢體的特徵資料庫並提供醫生良好的診斷工具。 | zh_TW |
dc.description.abstract | Cell count is among the fundamental information in cytopathology and cell biology and hematology; most of the researchers count cells and observe morphology manually through microscopes to acquire statistical information. In general, cell counting is labor-intensive and time-consuming and often very operator-dependent, especially when counting cells in images with non-ideal background. And commercial products may not be able to facilitate counting for such images, either.
In this thesis, sample was prepared from mixing two kind of cell lines (HUVEC labeled with fluorescence and Jurkat not), and cells in the micrograph of samples were analyzed and recognized by image processing techniques and multivariate statistic. First, the histogram of image was classified by Gaussian mixture model method for foreground and background extraction and processed with morphological filter for noise removal. Nearest Neighbor method was used to identify targets according to their features extracted from images. The robustness of classifier was verified by k-fold cross validation. This algorithm can analyze and count cells for two fluorescence-stained cells out of non-ideal background. Results show the image segmentation by Gaussian mixture model is virtually independent to the environmental condition of images (exposure time, contrast, and etc.) and the accuracy of recognition is around to 97% for extracting cell according to the built feature database. The algorithm serves the needs of cell counting of medical research very well. | en |
dc.description.provenance | Made available in DSpace on 2021-05-20T20:53:58Z (GMT). No. of bitstreams: 1 ntu-100-R98543002-1.pdf: 12448573 bytes, checksum: 23b7be3d199cacadaaee091dec62cfce (MD5) Previous issue date: 2011 | en |
dc.description.tableofcontents | 中文摘要 I
Abstract II 目錄 III 圖目錄 V 表目錄 VII Chapter 1. Introduction 1 1.1. Background of cell counting 1 1.2. Motivation 3 Chapter 2. Material & Method 5 2.1. Cells on a microfluidic disk 5 2.2. Procedures of cell counting from images 7 2.3. Pre-processing image of stained cells 8 2.3.1. Adjustment on image intensity 9 2.3.2. Distinguishing foreground and background from images 10 2.3.2.1. Intensity classification based on Gaussian mixture model 11 2.3.2.2. Thresholding and morphological image processing 14 2.4. Extracting objects from images 18 2.4.1. Labeling objects 18 2.4.2. Local features comparison 20 2.4.3. Extracting features 21 2.4.3.1. Mutual information 21 2.4.3.2. Correlation 22 2.4.3.3. Area of cell 22 2.4.3.4. Axis length of cell 23 2.5. Feature Selection and Classification 24 2.5.1. Classify Method 24 2.5.2. Nearest neighbor method 25 2.5.3. Feature selection 25 Chapter 3. Results and Discussion 26 3.1. Results of feature selection 26 3.2. Cell identification from single view field images 29 3.3. Strategies for cell recognition 31 3.4. Cell sorting for merged image 31 3.5. Region detection of inlet reservoir of the disk 33 Chapter 4. Conclusion and Future Aspects 36 Reference 37 | |
dc.language.iso | en | |
dc.title | 在非理想背景螢光影像中細胞自動計數演算法之研究 | zh_TW |
dc.title | An Automatic Cell Counting Algorithm for Fluorescent Images with Non-ideal Background | en |
dc.type | Thesis | |
dc.date.schoolyear | 99-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 陳中明(Chung-Ming Chen) | |
dc.contributor.oralexamcommittee | 江伯倫 | |
dc.subject.keyword | 細胞計數, | zh_TW |
dc.subject.keyword | Cell count, | en |
dc.relation.page | 38 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2011-08-02 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 應用力學研究所 | zh_TW |
顯示於系所單位: | 應用力學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-100-1.pdf | 12.16 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。