進階搜尋


 
系統識別號 U0026-0812200911155219
論文名稱(中文) 應用於顯微影像序列之電腦細胞追蹤與分析系統
論文名稱(英文) Computer Cell Tracking and Analysis System from Microscopic Image Sequence
校院名稱 成功大學
系所名稱(中) 資訊工程學系碩博士班
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 92
學期 2
出版年 93
研究生(中文) 郭建春
研究生(英文) Chien-Chun Kuo
電子信箱 gonginsun@yahoo.com.tw
學號 p7691426
學位類別 碩士
語文別 英文
論文頁數 78頁
口試委員 指導教授-孫永年
口試委員-謝璧妃
口試委員-鄭國順
口試委員-何中良
口試委員-黃博惠
口試委員-吳銘庭
中文關鍵字 細胞週期  拓撲適應可調變模組  主成分分析  細胞之運動 
英文關鍵字 cellular motion  PCA analysis  T-snake  cell cycle 
學科別分類
中文摘要   細胞動力是許多直接牽涉到人體健康狀況的生物過程中重要的一面。生物 學家或病理學家通常藉由分析從顯微鏡所觀測到的細胞,來找出各種病理現象 或其成因。由於長時間的觀察以及手動圈選的方式,是非常秏時間以及繁雜的工作,因此,我們的目的就是希望發展一套自動化分析細胞動能和形態變化的系統,藉以提供生物學家或病理學家相關的量化數據。
  在細胞影像的處理上,一般會遭遇到細胞偽足低對比度、細胞接觸以及細胞分裂的問題。因此,在本篇論文中,我們提出一個結合了細胞週期分析和時間空間資訊的拓撲適應可調變模組,去偵測細胞的輪廓。由於細胞影像特性,在背景區域亮度變化較為單調平滑,因此,影像亮度變異程度高的地方,可視為細胞區域,因此我們可藉由此一特性來決定可調變模組的演化方向。
針對偽足低對比度的問題,我們採用了一個根據canny邊緣偵測的方式提高偽足局部區域的變異程度。針對細胞接觸的問題,我們根據鄰近細胞的輪廓變化,將禁制區域的資訊整合到模組中,當成輪廓演化中的排斥力,一旦輪廓在演化過程中碰觸到這些區域時,便被強迫內縮,藉以得到較好的分割結果。
  由於細胞分裂會造成輪廓在拓撲結構上的改變,將會使細胞追蹤產生錯誤的分割結果。因此,在細胞分裂的問題上,我們針對不同的細胞狀態,採用不同的分割策略。在細胞狀態的辨識上,我們採用主成分分析的辨識技巧來區分細胞目 前的狀態,並作為偵測拓樸結構改變的依據。因此,在處理正常狀態的細胞時,我們可利用傳統的可調變模組,而在處理分裂狀態的細胞時,我們才需使用拓撲適應可調變模組來處理拓樸結構改變的問題。
  經由細胞輪廓追蹤的結果,我們可紀錄細胞的輪廓變化,並進一步分析細胞在整個影像序列中的質心運動軌跡和面積的變化,對細胞之運動加以統計及分析。最後,我們藉由三維視覺化的方式,將細胞在演化過程中的輪廓形變及其質心運動呈現出來,使生物學家或病理學家易於觀測細胞在每一階段的形變過程。
英文摘要   Cell dynamics is an important aspect of many biological processes with direct implications for human health. In order to find each pathological phenomenon or its reasons that cause diseases, biologists or pathologists usually analyze the cells observed from a microscope. However, long time observation and manual work for medical experts is tedious and yields subjective results. Therefore, our goal is to develop an automatic analysis system designed to detect cellular motility and morphology to provide related quantitative data for biologists or pathologists.
  Common problems encountered in the microscopic cell images include low contrast in pseudopods, multiple cell contacts, and cell division. In this thesis, we proposed a framework based on the topology adaptive snake (T-snake) combined with cell cycle analysis. Because high local variation of intensity is exhibited by regions within and near the boundaries of cells, local variation of intensity can be used to identify the regions of cells. This characteristic can be adopted to modify the inflation force in the T-snake indicating the cell regions.
  In the low contrast problem, we adopted a canny-based method to enhance the local variances of these weak cell edges. In multiple cell contact problem, we introduced the forbidden zones imposed on the contour models as the repulsive forces of the processing contour. These forbidden zones are defined according to the temporal information of the neighboring contours. The inflation force in the contour model is set to contract if the processing contour touches these forbidden zones. Therefore, the proposed method is allowed to acquire better segmentation results for the cells in contact.
  The topological changes are common in cell images, and traditional methods can not handle this situation. In the proposed method, we used diverse strategies for cell segmentation based on different cell stages. A PCA based technique is adopted to recognize the cell functional state for detecting possible topological changes. For non-dividing cells, modified snakes are applied for cell tracking. Otherwise, modified T-snakes are applied in cell tracking for possible cell division.
  After cell segmentation and tracking, the cell contours are recorded and can be further used to analyze the cell motion. The cellular centroid trajectories and area variations can be quantified to provide cell motility and shape parameters in the microscopic images. Finally, by visualizing the three-dimensional cellular contour changes and centroid trajectories, we make biologists or pathologists easy to observe the cellular dynamics and deformation.
論文目次 Chapter 1 Introduction....................................1
1.1 Motivation........................................................1
1.2 Related work......................................................3
1.3 Outlines..........................................................4
Chapter 2 Image preprocessing.........................5
2.1 Noise removal.....................................................5
2.2 Edge enhancement..................................................7
Chapter 3 Initial contour detection...................................9
3.1 Variance map......................................................9
3.2 Otsu’s algorithm................................................12
3.3 Boundary tracing.................................................15
Chapter 4 Cell segmentation and tracking based on cell cycle.........18
4.1 The cell cycle...................................................18
4.2 Principal components analysis (PCA) recognition..................21
4.3 Modified topology adaptive snake (T-snake).......................27
4.3.1 T-snake model..................................................27
4.3.2 Halo information...............................................37
4.3.3 Spatial-temporal information...................................38
4.4 Block matching algorithm.........................................39
4.5 Cell segmentation and tracking...................................41
Chapter 5 Experimental results and discussion........................46
5.1 Long time cell tracking..........................................46
5.2 Visualization and motion analysis of the tracking results........68
Chapter 6 Conclusions and future work................................72
6.1 Conclusions......................................................72
6.2 Future work......................................................74
References...........................................................75
參考文獻 [1] G. Fernández and M. Kunt and J-P. Zrÿd, “A new plant cell image segmentation algorithm,”Proceeding of the 8th Int. Conference on Image Analysis and Processing, pp. 229-234, September 13-15, 1995.

[2] K. Wu, D. Gauthier, and M. D. Levine, “Live cell image segmentation,” IEEE Transactions on Biomedical Engineering, vol. 42, no. 1, Jan. 1995.

[3] T. Jiang, F. Yang, and Y. Fan, “A parallel genetic algorithm for cell image segmentation,” Electronic Notes on Theoretical Computer Science, vol. 46, 2001.

[4] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,”International Journal of Computer Vision, vol. 1, no. 4, pp. 321-331, 1987.

[5] S. Sun, D. R. Haynor, and Y. Kim, “Semiautomatic video object segmentation using vsnakes,” IEEE Transactions on Circuits Syst. Video Technol., vol.13, no.1, pp.75-82, Jan. 2003.

[6] C. Xu, and J. L. Prince, “Snakes, shapes, and gradient vector flow,” IEEE Transactions on Image Processing, vol. 7, no. 3, March 1998.

[7] W. P. Choi, K. M. Lam and W. C. Siu, “An adaptive active contour model for highly irregular boundaries,” Pattern Recognition, vol. 34, pp. 323-331, 2001.

[8] Y. Fu, A. T. Erdem, and A. M. Tekalp, “Tracking visible boundary of objects using occlusion adaptive motion snake," IEEE Transactions Image Processing, vol. 9, no. 12, pp. 2051-2060, Dec. 2000.

[9] Y. L. Fok, J. C. K. Chan, and R. T. Chin, “Automated analysis of nerve-cell images using active contour models,” IEEE Transactions on Medical Imaging, vol. 15, no. 3, Jun. 1996.

[10] D. P. Mukherjee, N. Ray, and S. T. Acton, “Level set analysis for leukocyte detection and tracking,” IEEE Transactions on Image Processing, vol. 13, no. 4, Apr. 2004

[11] N. Ray, S. T. Acton, and K. Ley, “Tracking leukocytes in vivo with shape and size constrained active contours,” IEEE Transactions on Medical Imaging, vol. 21, no. 10, Oct. 2002.

[12] C. Zimmer, E. Labruyère, V. Meas-Yedid, N. Guillén, and J.-C. Olivo-Marin, “Segmentation and tracking of migrating cells in videomicroscopy with parametric active contours: a tool for cell-based drug testing,” IEEE Transactions on Medical Imaging, vol. 21, no. 10, 2002.

[13] F. Germain, A. Doisy, X. Ronot, and P. Tracqui, “Characterization of cell deformation and migration using a parametric estimation of image motion,”IEEE Transactions on Biomedical Engineering, vol. 46, no. 5, May 1999.

[14] H. Hiral, R. Umegaki, M. Kino-Oka, and M. Taya, “Characterization of cellular motions through direct observation of individual cells at early stage,” Journal of Bioscience and Bioengineering, vol. 94, no. 4, pp. 351-356, 2002.

[15] D. R. Soll, “Computer-assisted three-dimensional reconstruction and motion analysis of living, crawling cells,” Computerized Medical Imaging and Graphics, vol. 23, no. 1, pp. 3-14, Jan. 1999.

[16] Y. Sato, J. Chen, S. Tamura, N. Harada, and T. Shiga, “Automatic extraction and measurement of leukocyte motion in microvessels using spatiotemporal image analysis”, IEEE Transactions on Biomedical Engineering, vol. 4, no. 4, pp. 225-236, 1997.

[17] V. M. Yedidand, et.al., “Active contours for the movement and motility analysis of biological objects,” Proceedings IEEE Intern. Conf. on Image Processing, vol. 1, pp.196-199, 2000.

[18] J. Canny, “A computational approach to edge detection,” IEEE Transactions on pattern Analysis and Machine Intelligence, vol., no. 6, pp. 679-698, Nov. 1986.

[19] N. Otsu, “A threshold selection method from gray-level histogram,” IEEE Transactions on System, vol. 9, no.1, pp. 62-66, Jan. 1979.

[20] R. C. Gonzalez and R. E. Woods, Digital Image Processing Second Edition, Prentice-Hall, 2002.

[21] L. I. Smith, “A tutorial on principal component analysis,” Feb. 2002.

[22] M. Kirby and L. Sirovich, “Application of the karhunen-loeve procedure for the characterization of Human Faces,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, 1990.

[23] M. A. Turk and A. Pentland, “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.

[24] T. Mcinerney and D. Terzopoulos, “T-Snakes: topology adaptive snakes,”Medical Image Analysis, pp. 73-91, 2000.

[25] T. Mcinerney, and D. Terzopoulos, “Topology adaptive deformable surfaces for medical image volume segmentation,” IEEE Transactions on Medical Imaging, vol. 18, no. 10, Oct. 1999.

[26] G. A. Giraldi, E. S, A. A. Oliveira, “A boundary extraction method based on dual-t-snakes and dynamic programming,” Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, vol.1, pp. 44-49, 2000.

[27] T. Mcinerney and D. Terzopoulos, “Topologically adaptable snakes,” Proc. Fifth International Conf. on Computer Vision (ICCV'95), pp. 840-845, Jun. 1995.

[28] C. W. Ngo, T. C. Pong, and H. J. Zhang, “Motion analysis and segmentation through spatio-temporal slices processing,” IEEE Transactions on Image Processing, vol. 12, no.3, Mar. 2003.

[29] H. Moon, R. Chellappa, and A. Rosenfeld, “Optimal edge-based shape detection,” IEEE Transactions on Image Processing, vol. 11, no. 11, Nov. 2002.

[30] R. Malladi, J. A. Sethian, and B. C. Vemuri, “Shape modeling with front propagation: a level set approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2, Feb. 1995.

[31] S. E. Chen and R. E. Parent, “Shape averaging and its applications to industrial design,” IEEE Computer Graphics and Applications, vol. 9, no.1, pp.47-54, Jan. 1989.

[32] D. Bray, Cell Movements Second Edition, Garland Publishing, 2001.

論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2008-08-19起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2008-08-19起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw