臺灣博碩士論文加值系統

影像分割是醫學影像處理中主要研究題材之一，從醫學影像序列中，準確的分離出目標物件是醫學影像臨床應用上三維重建的基石，準確的分割表示能將各種正常或病變的組織以直觀的方式做顯示及分析，進而提高醫學診斷的準確性。
由於醫學成像設備的物理性及成像源的運動，造成醫學影像普遍具有信號不均勻與邊緣模糊的特點，使得醫學影像的切割有著一定的困難度。近年內對於傳統影像切割技術的改良文獻仍未曾間斷地發表著，但其方法上還是無法避免傳統切割方法的與生俱有的缺點，如該演算法需要足夠的先期知識或是使用者本身需要具備基礎的分析知識才能透過人機介面完成切割工作。若使用者對影像本身及算法參數的認知不夠，則切割結果可能會變差或結果分析變的困難。
本文的目的在於討論如何在切割中提升自動化程度且不會對切割結果造成重大影響。藉由探討近年來新開發的一種模糊連接度切割方法，並加上調控式閥值選擇法，使得該算法能在需要最少的使用者互動中，完成醫學影像切割工作。

Medical image segmentation is the major research topic among medical applications. It is clinically demanding, especially, to accurately partition a medical image into regions of interest (ROIs) and the background. Accurate medical image partition means we can identify normal and pathological tissues or organs and the analysis result is intuitively close to expert observations. Due to the mechanism of the medical imaging devices, scanned images normally contain noise and blurred edges, and thus significantly hamper the efficacy of medical-image analysis. The quest for the improvement of image segmentation never ceases, but there are still intrinsic problems of the various algorithms. For example, the employment of most algorithms needs the user’s in priori understanding of the image. The direct consequence is that the segmentation parameters are required to be manually pre-specified with special expertise. The purpose of this thesis is to maximally automate the segmentation parameter-selection process while preserving accuracy. Incorporation with fuzzy connectedness as the means to improve the capacity of alleviating scanning-introduced anomaly of medical image, we have achieved headstart success. In additions, the implementation and exploitation of an intuitive user-interface have helped create a more friendly software environment for clinical diagnosis.

Table of Contents i
List of Figures ii
List of Tables iii
摘要 iv
Abstract v
Chapter 1 Introduction 1
Chapter 2 Background and Significance 4
2.1 Image Segmentation 4
2.2 Characteristics of Medical Images 7
2.2.1 Modalities of medical images 7
2.2.2 Main difficult of segmenting medical image 11
2.3 Thresholding methods 11
2.4 Significance of this research 13
Chapter 3 Adaptive Threshold Selection of Fuzzy Connectedness Segmentation 14
3.1 Method Overview 14
3.2 Fuzzy Connectedness Theory 16
3.2.1 Implementation of Fuzzy Connectedness 20
3.2.2 Influence of Threshold Selection of Fuzzy Connectedness 21
3.3 Threshold selection and Fuzzy Measures 23
3.3.1 Otsu’s Method 23
3.3.2 Image thresholding by minimizing the measures of fuzziness 24
3.3.3 Threshold selection by minimizing the measures of fuzziness 28
3.3.4 Modified Entropy method 30
Chapter 4 Results 33
4.1 Test datasets and Phantom images 33
4.2 Results and Discussions 34
Chapter 5 Conclusion and future work 40

[1] J. K. Udupa, G. T. Herman, “3D Imaging in medicine,” CRC Press, Boca Raton, FL, 2nd Ed, 1999.
[2] R. C. Gonzalez, R. E. Woods, “Digital Image Processing,” Prentice Hall, 2002.
[3] K. S Fu, J. K. Mui, “A survey on image segmentation,” Pattern Recognition, vol. 13, pp. 3-16, 1981.
[4] S. W. Zucker, “Region growing: childhood and adolescence,” Computer Graphics and Image Processing, vol. 5, no. 3, pp. 382-399, 1976.
[5] R. Adams and L. Bischof, “Seeded region growing,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 16, no. 6, 1994.
[6] R. K. Justice, E. M. Stokely, J. S. Strobel, R. E. Ideker, W. M. Smith, “Medical image segmentation using 3-D seeded region growing,” Proceedings of SPIE - The International Society for Optical Engineering, 3034: 900-910, 1997.
[7] S. Y. Wan, W. Higgins, “Symmetric region growing,” IEEE International Conference on Image Processing (ICIP2000), 10-13, pp. II-439-II-442, 2000, Vancouver, BC, Canada, Sept.
[8] S. Y. Wan, C. M. Ma, E. Nung, “Multi-dimensional image segmentation using seed-invariant region growing,” Proceedings of National Computer Symposium 2001, pp. D269-D279, Dec. 20-21, 2001, Taiwan, R.O.C.
[9] S. Y. Wan, E. Nung, “Seed-invariant region growing: its properties and applications to 3-D medical CT images,” 2001 IEEE International Conference on Image Processing (ICIP2001), vol. 1, pp. 710-713, Oct. 7-10, 2001, Thessaloniki, Greece.
[10] J. Canny, “A computational approach to edge detection,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-696, Nov 1986.
[11] A. Martelli, “Edge detection using heuristic search methods,” Computer Graphics and Image Processing, vol. 1, pp. 169-182, 1972.
[12] A. X. Falcao, J. K. Udupa, S. Samarasekera and Shoba Sharma, “User-steered image segmentation paradigms: live wire and live lane,” Graphic Models and Image Processing, vol. 60, pp. 233-260, 1998.
[13] D. H. Ballard, “Generalizing the Hough transform to detect arbitrary shapes,” Pattern Recognition, vol. 13, pp. 111-122, 1981.
[14] E. Gose, R. Johnsonbaugh, S. Jost, “Pattern recognition and image analysis,” Prentice Hall, 1996.
[15] L. C. Bezdek, “Pattern recognition with fuzzy objective function algorithm,” New York: Plenum Press, 1981.
[16] W. R. Hendee, E. R. Ritenour, “Medical imaging physics,” New York: John Wiley & Sons, 2002.
[17] S. U. Le, S. Y. Chung, R. H. Park, “A comparative performance study of several global thresholding techniques for segmentation,” Graphical Models and Image Processing, vol. 52, pp. 171-190, 1990.
[18] J. S. Weszka, A. Rosenfeld, “Threshold evaluation techniques,” IEEE Transaction on System Man Cybernetics, SMC-8, no. 8, pp. 627-629, 1978.
[19] P. K. Sahoo, S. Soltani, A. K. C. Wong, and Y. Chen, “A survey of thresholding techniques,” Computer Vision Graphics Image Processing, vol. 41, pp. 233-260, 1988.
[20] C. A. Glasbey, “An analysis of histogram-based thresholding algorithms,” Graphical Models and Image Processing, vol. 55, pp. 532-537, 1993.
[21] C. Lee, S. Hun, T. A. Ketter, M. Unser, “Unsupervised connectivity-based thresholding segmentation of midsaggital brain MR images,” Computers in Biology and Medicine, vol. 28, pp. 309-338, 1998.
[22] H. D. Li, M. Kallergi, L. P. Clarke, V. K. Jain, R. A. Clark, “Markov random field for tumor detection in digital mammography,” IEEE Transaction on Medical Imaging, vol. 14, pp. 565-576, 1995.
[23] E. N. Mortensen, and W. A. Barrett, “Interactive segmentation with intelligent scissors,” Graphical Models and Image Processing, vol. 60, pp. 349-384, 1998.
[24] J. Udupa and S. Samarasekera, “Fuzzy connectedness and object definition: theory, algorithms, and applications in image segmentation,” Graphical Models and Image Processing, vol. 58, no. 3, pp. 246-261, May 1996.
[25] S. G. Dellepiane, F. Fontana, G. L. Vernazza, “Nonlinear image labeling for multivalued segmentation,” IEEE Transaction on Image Processing, vol. 5, pp. 429-446, 1996.
[26] B. M. Carvalho, C. J. Gau, G. T. Herman, T. Yung Kong, “Algorithms for fuzzy segmentation,” Pattern Analysis & Applications, vol. 2, pp. 73-81, 1999.
[27] T. Lei, J. K. Udupa, P. K. Saha , D. Odhner, “Artery-Vein separation via MRA - An image processing approach,” IEEE Transactions on Medical Imaging, vol. 20 no. 8 , pp. 689-703, 2001.
[28] J. Liu, J. K. Udupa, D. Odhner, J. M. McDonough, R. Arens, “Upper airway segmentation and measurement in MRI using fuzzy connectedness,” Medical Imaging 2002: Physiology and Function from Multidimensional Images, SPIE Proceedings vol. 4683.
[29] T. Lei, J. K. Udupa, P. K. Saha, D. Odhner, R. Baum, S. T. Tadikonda, E. K. Yucel, “3D MRA visualization and artery-vein separation using blood-pool contrast agent MS-325,” Academic Radiology, 9, S127-S133, 2002.
[30] C. Imielinska, D. Metaxas, J. Udupa, Y. Jin, T. Chen, “Hybrid segmentation of the visible human data,” Visible Human Project Conference III, Bethesda MD, October 2000.
[31] J. C. Bezdek, S. K. Pal, “Fuzzy models for pattern recognition: methods that search for structures in data,” New York: Institute of Electrical and Electronics Engineers, 1992.
[32] J. C. Bezdek, J. Keller, R. Krishnapuram, N. R. Pal, “Fuzzy Models and algorithms for pattern recognition and image processing,” Kluwer, Boston, 1999.
[33] T. H. Cormen, C. E. Leiserson,R. L. Rivest, “Introduction to algorithms,” The MIT Press, 1990.
[34] N. Otsu, “A threshold selection method from gray-level histogram,” IEEE Transaction on System Man Cybernetics, vol. SMC-9, no. 1, pp. 62-66, 1979.
[35] A. Kaufmann, “Introduction to the theory of fuzzy subsets fundamental theoretical elements,” Academic Press, New York, vol. 1, 1975.
[36] A. Rosenfeld, “The fuzzy geometry of image subsets,” Pattern Recognition Letter, vol. 2, pp. 311-317, 1984.
[37] A. Rosenfeld, S. Haber, “The perimeter of a fuzzy set,” Pattern Recognition, vol. 18, pp. 47-50, 1984.
[38] A. Rosenfeld, “The diameter of a fuzzy set,” Fuzzy sets and systems, vol. 13, pp. 241-246, 1984.
[39] A. De Luca, S. Termini, “A definition of non probabilistic entropy in the setting of fuzzy sets theory,” Information and Control System, vol. 20, pp. 301-312, May 1972.
[40] http://www.bic.mni.mcgill.ca/brainweb/.
[41] C. A. Cocosco, V. Kollokian, R. K. S. Kwan, A. C. Evans, “BrainWeb: online interface to a 3D MRI simulated brain database,” NeuroImage, Proceedings of 3-rd International Conference on Functional Mapping of the Human Brain, Copenhagen, vol. 5, no. 4, part 2/4, S425, May 1997.
[42] R. K. S. Kwan, A. C. Evans, G. B. Pike, “MRI simulation-based evaluation of image-processing and classification methods,” IEEE Transactions on Medical Imaging, vol. 18, no. 11, pp. 1085-97, Nov 1999.
[43] R. K. S. Kwan, A. C. Evans, G. B. Pike, “An extensible MRI simulator for post-processing evaluation,” Visualization in Biomedical Computing (VBC''96), Lecture Notes in Computer Science, Springer-Verlag, vol. 1131, pp. 135-140, 1996.
[44] D. L. Collins, A. P. Zijdenbos, V. Kollokian, J. G. Sled, N. J. Kabani, C. J. Holmes, A. C. Evans, “Design and construction of a realistic digital brain phantom,” IEEE Transactions on Medical Imaging, vol. 17, no. 3, pp. 463-468, June 1998.
[45] L. A. Zadeh, “Fuzzy sets and their applications to cognitive and decision processes,” Academic Press, London, 1975.
[46] L. K. Huang, M. J. Wang, “Image thresholding by minimizing the measure of fuzziness,” Pattern Recognition, vol. 28, no. 1, pp. 41-51, 1995.