神經纖維之三維重構在神經學上是一個基礎的研究。在本論文中採用一個新的系統來建構三維神經纖維，包含神經纖維分割與三維神經纖維重構兩個部分。在神經纖維分割過程中，主要為發展一個多階分水嶺分割方法並結合模糊理論系統來自動化分割神經纖維。在此分割過程中，以三組模糊規則分別對神經纖維偵測、給予動態輪廓模型權重、確認神經纖維等部分加入神經纖維的特徵與在影像上的空間資訊，此有助於針對不同的神經纖維狀態，給予適合之分割條件；另外，所採用之粒子群最佳化演算法，對於訓練大量的模糊規則參數將提供有效率之參數估算。
在三維神經纖維重構部份，對位式分割方法先運用到連續顯微影像上，以獲得神經纖維的連接資訊。對位式分割方法是採三階段步驟的對位，從整體的神經束對位、分支神經束裡的神經纖維對位到神經纖維輪廓對位，進而建立起相鄰影像間的對位轉換關係。在神經纖維對位階段，我們提出一套疊代式點對位空間限制演算法，其嵌入模糊理論來找出在連續影像上相對應的神經纖維。經由參考連續影像的資訊，之前未偵測到的神經纖維先被給予一個暫時的輪廓，經由確認步驟後進而彌補回來。最後，神經纖維得以重構並顯示。
雖然顯微影像通常具有雜訊而且灰階的對比度不一，所採用的神經纖維分割方法可以偵測並分割大量的神經纖維於二維顯微影像上。得到分割結果後，對位式分割方法不但可以從連續影像上重構三維神經纖維，更可以藉由相鄰影像間的資訊重新找回一些漏偵測的細胞。另外，所提出的疊代式點對位空間限制演算法，相較於傳統之疊代最近點演算法有明顯之改善。整體而言，依採用的方法所得到的分割結果與專家手動圈選結果做比較，平均的神經纖維分割正確率達九成以上。

The construction of three-dimensional (3D) nerve fiber is an essential task in various neurological studies. This thesis presents a new system for constructing 3D nerve fibers which includes the segmentation of myelinated nerve fiber cross-section (MNFC) and the 3D reconstruction procedure of nerve fiber. In MNFC segmentation, a multi-level watershed scheme iteratively detects the pre-candidates of MNFC, followed by using the detection phase to detect and confirm candidates of MNFC. The contour of candidate MNFC is then refined to obtain the complete shape of MNFC in the refinement phase. The confirmation phase is applied to remove the false alarms at last. Three fuzzy systems are designed to help the decisions with specified rules in the three phases. Particle swarm optimization (PSO) method is employed for efficient training of the relatively high number of parameters in three fuzzy systems.
In 3D nerve fiber reconstruction, a registration-based segmentation method is used to restore the connectivity of nerve fibers between adjacent frames. The registration is accomplished by a three-stage process that aligns the two adjacent frames from the stage of fascicle to fascicle, then cross-section to cross-section, and at last contour to contour registration. During cross-section to cross-section registration, the algorithm of iterative point registration with spatial constraints (IPRSC) is employed and executed with a fuzzy system. After the three-staged registration, the relationships of MNFCs among adjacent frames are constructed. The missing MNFCs can then be created and confirmed by checking the relationships among the previous, current and next frames. Finally, the 3D structure of nerve fiber can be reconstructed and visualized from a sequence of microscopic images.
Although the microscope image is usually noisy and with weak or variable levels of contrast, the proposed MNFCs segmentation method can handle images with large numbers of MNFCs and achieve high accuracy in cross section detection. After MNFCs segmentation, the registration-based segmentation can reconstruct the 3D nerve fiber structure from multi-frame microscopic images. It also recovers most of the missing MNFCs based on the corresponding cross sections in the neighboring image frames. Thus the accuracy of shape reconstruction can be further improved. Moreover, the rate of correct correspondence of MNFCs among adjacent frames was much higher by using the proposed IPRSC method than by the conventional ICP algorithm. Comparing the experimental results between the proposed method and manual segmentation by experts, an average consistency above 90% was achieved for validation with different data sets.

[1] B. Weyn and M. V. Remoortere et al., “A multi-parametric Assay for Quantitative Nerve Regeneration Evaluation,” Journal of Microscopy, vol. 219, no. 2, pp. 95-101, 2005.
[2] V. Grau, A. U. J. Mewes, M. Alcañiz, R. Kikinis, and S. K. Warfield, “Improved Watershed Transform for Medical Image Segmentation Using Prior Information,” IEEE Transactions on Medical Imaging, vol. 23, no. 4, pp. 447-458, 2004.
[3] P. R. Hill, C. N. Canagarajah, and D. R. Bull, “Image Segmentation Using a Texture Gradient Based Watershed Transform,” IEEE Transactions on Image Processing, vol. 12, no. 12, pp. 1618-1633, 2003.
[4] M. Nieniewski, “Extraction of Diffuse Objects From Images by Means of Watershed and Region Merging: Example of Solar Images,” IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 34, no. 1, pp. 796-801, 2004.
[5] I. Levner and H. Zhang, “Classification-Driven Watershed Segmentation,” IEEE Transactions on Image Processing, vol. 16, no. 5, pp. 1437-1445, 2007.
[6] P. S. Karvelis, A. T. Tzallas, D. I. Fotiadis and I. Georgiou, “A Multichannel Watershed- Based Segmentation Method for Multispectral Chromosome Classification,” IEEE Transactions on Medical Imaging, vol. 27, no. 5, pp. 697-708, 2008.
[7] L. Vincent and P. Soille, “Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, 1991.
[8] I. Vanhamel, I. Pratikakis and H. Sahli, “Multi-scale Gradient Watersheds of Color Images,” IEEE Transactions on Image Processing, vol. 12, no. 6, pp. 617-626, 2003.
[9] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” International. Journal of Computer Vision, vol. 1, pp. 321-331, 1987.
[10] V. Caselles, F. Catte, T. Coll, and F. Dibos, “A Geometric Model for Active Contours in Image Processing,” Numerische Mathematik , vol. 66, pp. 1-32, 1993.
[11] R. Malladi, J. A. Sethian, B. C. Vemuri, “Shape Modeling with Front Propagation: A Level Set Approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.17, no. 2, pp. 158-175, 1995.
[12] R. Durikovic, K. Kaneda, and H. Yamashita, “Dynamic Contour: A Texture Approach and Contour Operations,” The Visual Computer, vol. 11, pp. 277-289, 1995.
[13] D. Terzopoulos, “The Computation of Visible-Surface Representations,” IEEE Transations on Pattern Analysis and Machine Intelligence, vol. 10, no. 4, pp. 417-438, 1988.
[14] D. Terzopoulos and R. Szeliski, “Tracking With Kalman Snakes,” Active Vision, A. Blake and A. Yuille (eds.), MIT Press, Cambridge, MA, Ch. 1, 3-20, 1992.
[15] T. F. Cootes, C. J. Edwards and C. J. Taylor, “Active Appearance Models,” in H. Brukhardt and B. Neumann, editors, 5th European Conference on Computer Vision, vol. 2, pp 484-498. Springer, Berlin, 1998.
[16] F. Leymarie and M. D. Levine, “Tracking Deformable Objects in the Plane Using an Active Contour Model,” IEEE Transation on Patten Analysis and Machine Intelligence, vol. 15, pp. 617-634, 1993.
[17] A. A. Amini, T. E. Weymouth, and R. C. Jain, “Using Dynamic Programming for Solving Variational Problems in Vision,” IEEE Transation on Pattern Analysis and Machine Intelligence, vol. 12, no. 9, pp. 855-867, 1990.
[18] D. J. Williams and M. Shah, “A Fast Algorithm for Active Contours and Curvature Estimation,” Computer Vision, Graphics, and Image Processing: Image Understanding Archive, vol. 55, no.1, pp. 14-26, 1992.
[19] L. D. Cohen, “On Active Contour Models and Balloons,” Computer Vision, Graphics, and Image Processing: Image Understanding Archive, vol. 53, no. 2, pp. 211-218, 1991.
[20] C. Xu and J. L. Prince, “Snakes, Shapes, and Gradient Vector Flow,” IEEE Transation on Image Processing, vol. 7, no. 3, pp. 359-369, 1998.
[21] C. Xu and J. L. Prince, “Generalized Gradient Vector Flow External Forces for Active Contours,” International Journal of Signal Processing, vol. 71, no. 2, pp. 131-139, 1998.
[22] T. Mouroutis, S.J. Roberts and A.A. Bharath, “Robust Cell Nuclei Segmentation Using Statistical Modeling,” Bioimaging, vol. 6, no. 2, pp. 79-91, 1998.
[23] 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, pp. 353-368, 1996.
[24] A. Garrido and N. Perez, “Applying Deformable Templates for Cell Image Segmentation,” Pattern Recognition, vol. 33, no.5, pp. 821-832, 2000.
[25] U. Grenander, Y. Chow and D.M. Keenan, A Pattern Theoretic Study of Biological Shapes, Springer, Berlin, 1991.
[26] A.K. Yousef, L. Wiem and W. Lee et al., “Improved Automatic Detection and Segmentation of Cell Nuclei in Histopathology Images,” IEEE Transactions on Biomedical Engineering, vol. 57, no. 4, pp. 841-852, 2010.
[27] C. Zanella, M. Campana and B. Rizzi et al., “Cells Segmentation From 3-D Confocal Images of Early Zebrafish Embryogenesis,” IEEE Transactions on Image Processing, vol. 19, no. 3, pp.770-781, 2010.
[28] X. Zhou, F. Li, J. Yan and S.T. Wong, “A Novel Cell Segmentation Method and Cell Phase Identification Using Markov Model,” IEEE Transactions on Information Technology in Biomedicine, vol. 13, issue 2, pp. 152-157, 2009.
[29] J. Cheng and J.C. Rajapakse, “Segmentation of Clustered Nuclei with Shape Markers and Marking Function,” IEEE Transactions on Biomedical Engineering, vol. 56, no. 3, pp. 741-748, 2009.
[30] B.C. Ko, M.S. Seo and J.Y. Nam, “Microscopic Cell Nuclei Segmentation Based on Adaptive Attention Window,” Journal of Digital Imaging, vol.22, no.3, pp. 259-274, 2008.
[31] F.B. Tek, A.G. Dempster and I. Kale, “Blood Cell Segmentation Using Minimum Area Watershed and Circle Radon Transformations,” Computational Imaging and Vision, vol. 30, pp. 441-454, 2004.
[32] S. Colantonio, O. Salvetti, and I.B. Gurevich, “A Two-Step Approach for Automatic Microscopic Image Segmentation Using Fuzzy Clustering and Neural Discrimination,” Pattern Recognition and Image Analysis, vol. 17, no. 3, pp. 428-437, 2007.
[33] C. D. Ruberto and A. Dempster et al., “Analysis of Infected Blood Cell Images Using Morphological Operators,” Image and Vision Computing, vol. 20, no. 2, pp. 133-146, 2002.
[34] L. Yang and P. Meer et al., “Unsupervised Segmentation Based on Robust Estimation and Color Active Contour Models,” IEEE Transactions on Information Technology in Biomedicine, vol. 9, no. 3, pp. 475-486, 2005.
[35] S. Wang, and M. Wang, “A New Detection Algorithm (NDA) Based on Fuzzy Cellular Neural Networks for White Blood Cell Detection,” IEEE Transactions on Information Technology in Biomedicine, vol.10, no.1, pp. 5-10, 2006.
[36] K. Althoff, J. Degerman and T. Gustavsson, “Combined Segmentation and Tracking of Neural Stem-Cells,” Image Analysis, vol. 3540, pp. 282-291, 2005.
[37] M. Li, H. Du, Q. Zhang, and J. Wang, “Improved Particle Image Velocimetry Through Cell Segmentation and Competitive Survival,” IEEE Transactions on Instrumentation and Measurement, vol. 57, no. 6, pp. 1221-1229, 2008.
[38] J. Kan, Q.M. Liao and X. Yuan, “A Novel White Blood Cell Segmentation Scheme Based on Feature Space Clustering,” Soft Computing, vol. 10, pp. 12-19, 2006.
[39] P. Bamford and B. Lovell, “Unsupervised Cell Nucleus Segmentation with Active Contours,” Signal Processing, vol. 71, issue 2, pp. 203-213, 1998.
[40] Y.Y. Wang, Y.N. Sun, C.C. K. Lin, and M.S. Ju, “Nerve Cell Segmentation via Multi-scale Gradient Watershed Hierarchies,” 28th Annual International Conf. IEEE Engineering in Medicine and Biology Society, pp. 6698-6701, Sept., 2006.
[41] Y. Y. Wang, Y. N. Sun, C.C.K. Lin and M. S. Ju, “Segmentation of Nerve Fibers via Multi-level Gradient Watershed and Fuzzy Systems,” Artificial Intelligence in Medicine, revised, March, 2010.
[42] O. Gerard, A.C. Billon, J.M. Rouet and M. Jacob et al., “Efficient Model-based Quantification of Left Ventricular Function in 3-D Echocardiography,” IEEE Transactions on Medical Imaging, vol. 21, no. 9, pp. 1059-1068, 2002.
[43] A.F. Frangi, D. Rueckert, J.A. Schnabel, and W.J. Niessen, “Automatic Construction of Multiple-object Three-dimensional Statistical Shape Models: Application to Cardiac Modeling,” IEEE Transactions on Medical Imaging, vol. 21, no. 9, pp. 1151-1166, 2002.
[44] A. Yezzi, L. Zollei, and T. Kapur, “A Variational Framework for Integrating Segmentation and Registration Through Active Contours,” Medical image analysis, vol. 7, no. 2, pp. 171-185, 2003.
[45] S. Gorthi, V. Duay, and N. Houhou, et al., “Segmentation of Head and Neck Lymph Node Regions for Radiotherapy Planning, Using Active Contour Based Atlas Registration,” IEEE Journal of selected topics in signal processing, vol. 3, no. 1, pp. 135-147, 2009.
[46] H.C. Chen, I.M. Jou, C.K. Wang, F.C. Su and Y.N. Sun, “Registration-based Segmentation with Articulated Model from Multipostural Magnetic Resonance Images for Hand Bone Motion Animation,” Medical Physics, vol. 37, pp. 2670-2682, 2010.
[47] V. Zagrodsky, V. Walimbe et al., “Registration-Assisted Segmentation of Real-Time 3-D Echocardiographic Data Using Deformable Models,” IEEE Transactions on Medical Imaging, vol. 21, no. 9, pp. 1089-1099, 2005.
[48] S. Ying, J. Peng, S. Du, and H. Qiao, “A Scale Stretch Method Based on ICP for 3D Data Registration,” IEEE Transactions Automation Science and Engineering, vol. 6, no.3, pp.559-565, 2009.
[49] D. Kim and D. Kim, “A Fast ICP Algorithm for 3-D Human Body Motion Tracking,” IEEE Signal Processing Letters, vol. 17, no. 4, pp. 403-405, 2010.
[50] G. Yang, C. V. Stewart, et al., “Registration of Challenging Image Pairs: Initialization, Estimation, and Decision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 11, pp.1973-1989, 2007.
[51] C. L. Tsai, C. Y. Li, G. Yang and K. S. Lin, “The Edge-Driven Dual-Bootstrap Iterative Closest Point Algorithm for Registration of Multimodal Fluorescein Angiogram Sequence,” IEEE Transactions on Medical Imaging, vol.29, no.3, pp. 636-649, 2010.
[52] M. Rogers and J. Graham, “Robust and Accurate Registration of 2-D Electrophoresis Gels Using Point-Matching,” IEEE Transactions on Image Processing, vol. 16, no. 3, pp.624-635, 2007.
[53] G.C. Sharp, S.W. Lee, and D.K. Wehe, “ICP Registration Using Invariant Features,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 90-102, 2002.
[54] F.L. Chung, Z. Deng, and S. Wang, “An Adaptive Fuzzy-Inference-Rule-Based Flexible Model for Automatic Elastic Image Registration,” IEEE Transactions on Fuzzy Systems, vol. 17, no. 5, pp.995-1010, 2009.
[55] S. Kobashi and Y. Fujiki et al., “Interactive Segmentation of the Cerebral Lobes with Fuzzy Inference in 3T MR Images,” IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybernetics, vol. 36, no. 1, pp. 74-86, 2006.
[56] X. Chen and J. Tian et al., “A New Algorithm for Distorted Fingerprints Matching Based on Normalized Fuzzy Similarity Measure,” IEEE Transactions on Image Processing, vol.15, no. 3, pp.767-776, 2006.
[57] J. Kennedy, R. C. Eberhart, “Particle Swarm Optimization,” Proceedings of the 1995 IEEE International Conference on Neural Networks, pp. 1942-1948, 1995.
[58] L. A. Zadeh, “Fuzzy Sets as a Basis for a Theory of Possibility,” Fuzzy Sets and Systems, vol. 100, pp. 9-34, 1999.
[59] L. A. Zadeh, “Toward a Theory of Fuzzy Information Granulation and Its Centrality in Human Reasoning and Fuzzy Logic,” Fuzzy Sets and Systems, vol. 90, no. 2, pp. 111-127, 1997.
[60] H. Ishibuchi and T. Nakashima, “Improving the Performance of Fuzzy Classifier Systems for Pattern Classification Problems with Continuous Attributes,” IEEE Transactions on Industrial Electronics, vol. 46, no. 6, pp. 1057-1068, 1999.
[61] H. Ishibuchi and T. Nakashima, “Effect of Rule Weights in Fuzzy Rule-based Classification Systems,” IEEE Transactions on Fuzzy Systems, vol. 9, no. 4, pp. 506-515, 2001.
[62] M. Hamidi and A. Borji, “Color Image Segmentation with CLPSO-based Fuzzy,” International Journal of Computer Science and Network Security, vol. 7, no. 6, pp. 215-221, 2007.
[63] P.J. Besl and N.D. Mckay, “A Method for Registration of 3D Shapes,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp.239-256, 1992.
[64] L. Guibas, and J. Stolfi, “Primitives for the Manipulation of General Subdivisions and the Computations of Voronoi Diagrams,” ACM Trans. Graphics, vol. 4, issue 2, 74-123, 1985.
[65] F. Aurenhammer, “Voronoi Diagrams - A Survey of a Fundamental Geometric Data Structure,” ACM Computing Surveys, pp. 345-405 vol. 23, no. 3, 1991.
[66] A. Bowyer, “Computing Dirichlet tessellations,” The Computer Journal, vol. 24, no. 2, pp.162-166, 1981.
[67] D. F. Watson, “Computing the N-dimensional Tessellation with Application to Voronoi Polytopes,” The Computer Journal, vol. 2, no. 24, pp.167-172, 1981.
[68] A. Okabe, B. Boots, and K. Sugihara, “Spatial Tessellations Concepts and Applications of Voronoi Diagrams,” John Wiley & Sons Ltd, 1992.
[69] W. Yang and J. Feng, “2D Shape Manipulation via Topology-aware Rigid Grid,” Computer Animation and Virtual Worlds, vol. 20, no. 2, pp. 175-184, 2009.
[70] T. Igarashi, T. Moscovich and J. F. Hughes, “As-rigid-as-possible Shape Manipulation,” ACM Transactions on Graphics, vol. 24 , no. 3, pp. 1134-1141, 2005.
[71] M. Dubuisson and A.K. Jain, “A Modified Hausdorff Distance for Object Matching,” Proceedings of 12th International Conference on Pattern Recognition A: Computer Vision and Image Processing, vol. 1, pp. 566-568, 1994.
[72] N. Otsu, “A Threshold Selection Method from Gray-level Histograms,” IEEE Transactions on Systems, Man and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[73] L. A. Zadeh and J. Kacprzyk, Fuzzy Logic for the Management of Uncertainty. John Wiley & Sons, Inc., New York, NY, USA.