臺灣博碩士論文加值系統

本研究希望能將培養中的細胞連續取像一段時間，再利用機器視覺及影像處理的技術將細胞由影像中分割出來，以進行微觀的活細胞長期行為觀察，希望能進一步了解細胞行，提供未來研究各種培養因子(如：成長因子的濃度、流速、各種外力與刺激)對細胞行為的影響，進而知道如何讓細胞在支架上大量培養，以協助組織工程的研究。
首先，將細胞影像經由變異數運算，利用細胞本身與背景的亮度差異大，變異數值也會比較大的特徵，強化細胞邊緣影像，再以自動閥值選取演算法所求得適當的閥值作二值化運算，接著利用形態學運算中的侵蝕、膨脹作去雜訊之動作，最後再以鏈碼運算作邊界描繪，以描繪出細胞分割所需之初始輪廓。接下來將所描繪出的初始輪廓與原始影像作二值化所得影像作比對，將不必要的背景區域去除，以減少運算量，最後，利用邊界描繪及去除雜訊動作完成初步影像分割。對於特殊的細胞影像如細胞影像灰階不均勻、細胞相黏難以分割等，則分別一一以特殊的方法解將細胞正確分割出。
繼之，將所分割完成的細胞影像，以形心法求得細胞的形心，再利用細胞影像序列中細胞形心的位置及前後兩張影像各細胞封閉區域重疊面積的多寡，來判斷細胞的位移向量，以達成細胞的運動分析。
將所得之連續影像序列運動分析結果與利用人工框選影像序列中細胞邊界求其形心運動路徑結果比較，兩者之間誤差約0~3 。

摘要 I
圖 目 錄 V
表 目 錄 VIII
第一章 緒論 1
1.1 研究動機 1
1.2 文獻回顧 1
1.3 研究方法及步驟 2
1.4 章節概述 3
第二章 實驗設備介紹 5
2.1 顯微鏡系統介紹 5
2.1.1 活細胞培養系統 6
2.1.2 影像擷取系統 8
2.2 軟體架構 10
2.3 實驗架構流程 12
第三章 細胞培養、影像擷取與分割 13
3.1 細胞培養與連續取像 13
3.1.1 細胞培養 14
3.1.2 細胞影像擷取 15
3.2 影像前處理 16
3.2.1 變異數計算 17
3.2.2 邊緣檢測處理 18
3.2.3 二值化 19
3.2.4 去雜訊 22
3.2.5 邊界描繪 24
3.3 細胞影像分割 26
3.3.1 邊界描繪演算法 27
3.3.2 細胞內部亮點造成分割輪廓斷裂 28
3.3.3 兩細胞誤判為同一封閉區域 30
3.3.4 邊界輪廓描繪不規則 31
3.4 連續細胞影像運動分析 31
3.4.1 形心位移 32
3.4.2 面積重疊率 33
第四章 實驗結果與討論 35
4.1 影像前處理結果 35
4.2 細胞影像分割 39
4.2.1 初步分割結果 39
4.2.2 亮度分布不均 42
4.2.3 兩細胞誤判為同一細胞 43
4.2.4 邊界描繪不規則輪廓問題 46
4.3 計算細胞個數及形心座標位置 47
4.4 連續細胞影像運動分析 48
第五章 結論與未來展望 62
5.1 結論 62
5.2 未來展望 62
參考文獻 64

[1] Axiovert 200 / Axiovert 200M Operating Manual, Carl ZEISS Light Microscopy, 2001.
[2] AxioVision Manual Release 3.1, Carl ZEISS, 2002.
[3] AxioVision 3.1 Reference, Carl ZEISS, 2000.
[4] D. J. Stephens and V. J. Allan, ”Light Microscopy Techniques for Live Cell Imaging,” BIOLOGICAL IMAGING SCIENCE, Vol. 300, pp. 82-86, 2003.
[5] F. Germain, A. Doisy, X. Ronot et. al. “Characterization of Cell Deformation and Migration Using a Parametric Estimation of Image Motion,” IEEE Trans. on Biomedical Engineering, Vol. 46, No. 5, pp. 584-600, 1999.
[6] F. Siegert, C. J. Weijer, A. Nomura et. al., “A Gradient Method for the quantitative Analysis of Cell movement and Tissue Flow and its Application to the Analysis of Multicelluar Dictyostelium Development,” Journal of Cell Science, Vol. 107, pp. 97-104, 1999.
[7] F. Chang and C. J. Chen, “A Component-Labeling Algorithm Using Contour Tracing Technique,” Seventh International Conference on Document Analysis and Recognition, Vol. 2, pp. 741-745, 2003.
[8] J. A. Withers and K. A. Robbins, “Tracking Cell Splits and Merges,” Proceedings IEEE Southwest Symposium on Image Analysis and Interpretation, pp.117-122, 1996.
[9] J. H. Velduis, G. W. Brodland, “A Deformable Block-Matching Algorithm for Tracking Epithelial Cells,” Image and Vision Computing, Vol. 17, pp. 905-911, 1999.
[10] J. M. Odobez and P. Bouthemy, “Robust Multiresolution Estimation of Parametric Motion Models,” Journal of Visual Communication and Image Representation, Vol. 6, No. 4, pp. 348-365, 1995.
[11] J. R. Swedlow, I. Goldberg, E. Brauner et. al. ”Informatics and Quantitative Analysis in Biological Image,” BIOLOGICAL IMAGING SCIENCE, Vol. 300, pp. 100-102, 2003.
[12] K. Wu, D. Gauthier and M. D. Levine, “Live Cell Image Segmentation,” IEEE Trans. on Biomedical Engineering, Vol. 42, No. 1, pp.1-12, January 1995. Proceedings IEEE Southwest Symposium on Image Analysis and Interpretation pp. 117-122, 1996.
[13] L. Liu and S. Sclaroff, “Medical Image Segmentation and Retrieval via Deformable Models,” in Proceedings IEEE International Conference on Image Processing, Vol. 2, pp.1071-1074, 2001.
[14] M. Sonka, V. Hlavac and R. Boyle, Image Processing, Analysis and Machine Vision Second Edition, PWS Publishing, 1998.
[15] N. OTSU, “A Threshold Selection Method from Gray-level Histogram,” IEEE Trans. on System, Man, and Cybernetics, Vol. 9, No. 1, pp.62-66, 1979.
[16] N. Ray, S. T. Acton, and K. Ley, “Tracking Leukocytes In Vivo With Shape And Size Constrained Active Contours,” IEEE Trans. on Medical Imaging, Vol. 21, No. 10, pp.1222-1235, 2002.
[17] N. Lassouaoui, L. Hamami, A. Zerguerras, “Segmentation and classification of biological cell images by a multifractal approach,” International Journal of Intelligent Systems, Vol. 18, No. 6, pp. 657-678, 2003.
[18] O. Cuisenaire, E. Romero, C. Veraart et. al., “Automatic segmentation and measurement of axons in microscopic images,” SPIE Medical Imaging, San Diego, USA, Vol. 3661, pp. 920-929, 1999.
[19] P. F. Fung, W. S. Lee, I. King, “Randomized generalized Hough transform for 2-D grayscale object detection,” In: ICPR. Vol. 3, pp. 511-515, 1996.
[20] P. Roy, Z. Rajfur, P. Pomorski et. al., ”Microscope-based techniques to study cell adhesion and migration,” technology review, NATURE CELL BIOLOGY, Vol. 4, pp. 91-94, 2002.
[21] R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, 1992.
[22] T. Mouroutis, S. J. Roberts, A. A. Bharath, “Compact Hough transform and a maximum likelihood approach to cell nuclei detection,” Proceedings 13th International Conference on Digital Signal Processing, Vol. 2, pp. 869-872, 1997.
[23] 邵得晉,“電腦視覺技術於細胞影像序列運動分析之研究”, 碩士論文, 國立成功大學資訊工程學系碩士班, 2003.