臺灣博碩士論文加值系統

雜訊去除在影像處理中一直是一個很重要的技術，特別在醫學影像的分析上，去除磁振影像的雜訊對於之後的處理、分析與應用是相當重要的。本研究使用三邊濾波器，其為一延伸雙邊濾波器且更能有效地去除腦部磁振影像中的隨機雜訊。然而，三邊濾波處理過程相當耗費時間且需要做數個參數的調整以得到最佳去除雜訊之影像。因此，本研究使用GPU平行運算來加速整個濾波處理時間，利用GPU強大的平行處理能力，搭配NVIDIA所開發的CUDA架構來加速原本的三邊濾波演算法。接著藉由人工智慧技術來自動最佳化濾波處理，藉由擷取磁振影像的特徵資料，結合類神經網路與支持向量機，訓練出一個可預測最佳三邊濾波模型，進一步建立自動化三邊濾波用於去除腦部磁振影像雜訊的系統。本研究使用t檢定方法加上循序前進浮動選取演算法選取最佳的特徵組合，再將此特徵組合用於訓練自動化去雜訊系統。本實驗使用Brain Web腦部模擬資料庫的磁振影像來分析三邊濾波器之效能與驗證本研究提出的自動化去除雜訊架構。實驗結果顯示本研究所提的方法不僅能大幅地加速傳統三邊濾波演算法，一張磁振影像可以達到34倍之加速。比較其他除雜訊方法，也能有效地自動化去除腦部磁振影像中的雜訊，最後獲得的重建影像有相當不錯的品質。

Noise removal is one of the fundamental and essential tasks within image processing. In medical imaging, finding an effective algorithm that can remove random noise in magnetic resonance (MR) images is important. This thesis proposes an effective noise reduction method for brain MR images. The proposed is based on the trilateral filter, which is a more powerful method than the bilateral filter in many cases. However, the computation of the trilateral filter is quite time-consuming and the choice of the filter parameters is also laborious. To address these problems, the trilateral filter algorithm is implemented using parallel computing with GPU. The CUDA, an application programming interface for GPU by NVIDIA is adopted, to accelerate the computation. Subsequently, the optimal filter parameters are selected by artificial intelligence techniques. Artificial neural networks and support vector machines associated with image feature analysis are proposed to establish the automatic mechanism. The best feature combination is selected by the t-test and the sequential forward floating selection (SFFS) methods. Experimental results indicated that not only did the proposed GPU-based version run dramatically faster than the traditional trilateral filter, but this automatic system also effectively removed the noise in various brain MR images. We believe that the proposed framework has established a general blueprint for achieving fast and automatic filtering in a wide variety of MR image denoising applications.

致謝 i
中文摘要 ii
ABSTRACT iii
目錄 iv
圖目錄 vii
表目錄 x
符號表 xii
第 1 章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 論文架構 3
第 2 章 相關理論 4
2.1 磁振造影介紹 4
2.2 磁振影像雜訊 5
2.3 消除磁振影像雜訊之濾波器 6
2.3.1 高斯濾波器(Gaussian Filter) 8
2.3.2 雙邊濾波器(Bilateral Filter) 9
2.3.3 三邊濾波器(Trilateral Filter) 10
2.3.4 非等向性擴散濾波器(Anisotropic Diffusion Filter) 12
2.3.5 線性最小均方誤差檢測濾波器(LMMSE Estimation Filter) 12
2.3.6 雜訊估測之疊代雙邊濾波器(Iterative Bilateral Filter) 14
2.4 GPU加速運算與CUDA 14
2.4.1 CUDA平行運算架構 16
2.4.2 CUDA程式設計模型 18
2.5 類神經網路(Artificial Neural Network) 19
2.5.1 生物神經元模型 20
2.5.2 類神經元模型 20
2.5.3 倒傳遞類神經網路(Back Propagation Network) 23
2.6 支持向量機(Support Vector Machine) 28
第 3 章 研究設計與方法 32
3.1 基於GPU加速之三邊濾波器 32
3.1.1 濾波器平行計算 32
3.1.2 使用共享記憶體 34
3.2 影像特徵擷取 39
3.2.1 影像灰階值基本統計特徵 39
3.2.2 灰階共生矩陣(Gray Level Co-occurrence Matrix)特徵 41
3.2.3 灰階連續長度矩陣(Gray Level Run-Length Matrix)特徵 44
3.2.4 田村特徵(Tamura Feature) 47
3.2.5 雜訊估測(Noise Estimation)數值特徵 49
3.3 特徵篩選方法 58
3.3.1 T檢定 59
3.3.2 循序前進浮動搜尋法(Sequential Forward Floating Selection) 60
3.4 自動化三邊濾波系統之模型 62
第 4 章 實驗結果與討論 65
4.1 實驗說明 65
4.1.1 實驗設備 65
4.1.2 資料集 66
4.1.3 評估標準 67
4.2 GPU加速效能分析 71
4.2.1 最佳區塊大小選取 71
4.2.2 執行速度比較 72
4.3 最佳特徵之選取 80
4.3.1 特徵差異辨別分析 80
4.3.2 最佳特徵組合 81
4.4 系統評估 83
4.4.1 重建影像評估 83
4.4.2 預測能力評估 90
4.4.3 不同方法比較 95
第 5 章 結論與未來展望 105
5.1 結論 105
5.2 未來展望 106
參考文獻 107

[1]K. Van Leemput, F. Maes, D. Vandermeulen, and P. Suetens, "Automated model-based tissue classification of MR images of the brain," IEEE transactions on medical imaging, vol. 18, pp. 897-908, 1999.
[2]Z. Liang, J. R. MacFall, and D. P. Harrington, "Parameter estimation and tissue segmentation from multispectral MR images," IEEE transactions on Medical Imaging, vol. 13, pp. 441-449, 1994.
[3]C. A. Pelizzari, G. T. Chen, D. R. Spelbring, R. R. Weichselbaum, and C.-T. Chen, "Accurate three-dimensional registration of CT, PET, and/or MR images of the brain," Journal of computer assisted tomography, vol. 13, pp. 20-26, 1989.
[4]A. Macovski, "Noise in MRI," Magnetic Resonance in Medicine, vol. 36, pp. 494-497, 1996.
[5]R. A. Haddad and A. Akansu, "A class of fast Gaussian binomial filters for speech and image processing," Signal Processing, IEEE Transactions on, vol. 39, pp. 723-727, 1991.
[6]H. Lili and R. Greenshields Ian, "A Nonlocal Maximum Likelihood Estimation Method for Rician Noise Reduction in MR Images," Medical Imaging, IEEE Transactions on, vol. 28, pp. 165-172, 2009.
[7]G. Gerig, O. Kubler, R. Kikinis, and F. A. Jolesz, "Nonlinear anisotropic filtering of MRI data," Medical Imaging, IEEE Transactions on, vol. 11, pp. 221-232, 1992.
[8]C. Tomasi and R. Manduchi, "Bilateral filtering for gray and color images," in Computer Vision, 1998. Sixth International Conference on, 1998, pp. 839-846.
[9]H.-H. Chang and W.-C. Chu, "Collateral filtering of magnetic resonance images," in 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2010, pp. 728-731.
[10]K. N. Chaudhury, D. Sage, and M. Unser, "Fast bilateral filtering using trigonometric range kernels," IEEE Transactions on Image Processing, vol. 20, pp. 3376-3382, 2011.
[11]Q. Yang, K.-H. Tan, and N. Ahuja, "Real-time O (1) bilateral filtering," in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 2009, pp. 557-564.
[12]C. Richardt, D. Orr, I. Davies, A. Criminisi, and N. A. Dodgson, "Real-time spatiotemporal stereo matching using the dual-cross-bilateral grid," in European Conference on Computer Vision, 2010, pp. 510-523.
[13]J. V. Manjón, J. Carbonell-Caballero, J. J. Lull, G. García-Martí, L. Martí-Bonmatí, and M. Robles, "MRI denoising using Non-Local Means," Medical Image Analysis, vol. 12, pp. 514-523, 2008.
[14]S. Aja-Fernández, M. Niethammer, M. Kubicki, M. E. Shenton, and C.-F. Westin, "Restoration of DWI data using a Rician LMMSE estimator," IEEE transactions on medical imaging, vol. 27, pp. 1389-1403, 2008.
[15]S. Zimmer, S. Didas, and J. Weickert, "A rotationally invariant block matching strategy improving image denoising with non-local means," in Proc. 2008 International Workshop on Local and Non-Local Approximation in Image Processing, 2008, pp. 135-142.
[16]J. V. Manjón, P. Coupé, L. Martí‐Bonmatí, D. L. Collins, and M. Robles, "Adaptive non‐local means denoising of MR images with spatially varying noise levels," Journal of Magnetic Resonance Imaging, vol. 31, pp. 192-203, 2010.
[17]X.-z. LIU, C.-x. FU, and G. YANG, "An MRI Image Denoising Algorithm Using Neural Network Analysis and Wavelet Transformation," Chinese Journal of Magnetic Resonance, vol. 2, p. 012, 2008.
[18]I. Frosio, K. Egiazarian, and K. Pulli, "Machine learning for adaptive bilateral filtering," in SPIE/IS&T Electronic Imaging, 2015, pp. 939908-939908-12.
[19]C. Westbrook and C. K. Roth, MRI in Practice: Wiley-Blackwell, 2011.
[20]R. H. Hashemi, W. G. Bradley, and C. J. Lisanti, MRI: the basics: LWW, 2012.
[21](2016, 7/11). MRI 磁振造影. Available: http://www.fyh.mohw.gov.tw/?aid=53&pid=25&page_name=detail&iid=18
[22]H. Gudbjartsson and S. Patz, "The Rician distribution of noisy MRI data," Magnetic Resonance in Medicine, vol. 34, pp. 910-914, 1995.
[23]S. O. Rice, "Mathematical analysis of random noise-conclusion," Bell Systems Tech. J., Volume 24, p. 46-156, vol. 24, pp. 46-156, 1945.
[24]A. Papoulis and S. U. Pillai, Probability, random variables and stochastic processes: Tata McGraw-Hill Education, 2002.
[25]R. C. Gonzalez and R. E. Woods, Digital image processing, 3rd ed.: Prentice Hall: Pearson Education, Inc, 2003.
[26]R. C. Gonzalez, R. E. Woods, and S. L. Eddins, Digital image processing using MATLAB vol. 2: Gatesmark Publishing Tennessee, 2009.
[27]P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Transactions on pattern analysis and machine intelligence, vol. 12, pp. 629-639, 1990.
[28]M. Bomans, K.-H. Hohne, U. Tiede, and M. Riemer, "3-D segmentation of MR images of the head for 3-D display," IEEE transactions on medical imaging, vol. 9, pp. 177-183, 1990.
[29]R. Riji, J. Rajan, J. Sijbers, and M. S. Nair, "Iterative bilateral filter for Rician noise reduction in MR images," Signal, Image and Video Processing, vol. 9, pp. 1543-1548, 2015.
[30]C. Nvidia, "NVIDIA Tesla K80 Accelerator Performance," ed.
[31]J. D. Owens, D. Luebke, N. Govindaraju, M. Harris, J. Krüger, A. E. Lefohn, et al., "A survey of general‐purpose computation on graphics hardware," in Computer graphics forum, 2007, pp. 80-113.
[32]C. Nvidia. CUDA Zone. Available: https://developer.nvidia.com/cuda-zone
[33]D. Kirk, "NVIDIA CUDA software and GPU parallel computing architecture," in ISMM, 2007, pp. 103-104.
[34]C. Nvidia, "NVIDIAs next generation CUDA compute architecture: Kepler GK110," Technical report, Technical report, 2012.
[35]W. G. Baxt, "Use of an artificial neural network for data analysis in clinical decision-making: the diagnosis of acute coronary occlusion," Neural computation, vol. 2, pp. 480-489, 1990.
[36]W. G. Baxt, "Application of artificial neural networks to clinical medicine," The lancet, vol. 346, pp. 1135-1138, 1995.
[37]J. J. Jiang, M. Zhong, and G. Klein, "Marketing Category Forecasting: An Alternative of BVAR‐Artificial Neural Networks*," Decision Sciences, vol. 31, pp. 789-812, 2000.
[38]蘇木春、張孝德, 機器學習:類神經網路、模糊系統以及基因演算法則: 全華科技圖書股份有限公司, 2006.
[39]W. S. McCulloch and W. Pitts, "A logical calculus of the ideas immanent in nervous activity," The Bulletin of Mathematical Biophysics, vol. 5, pp. 115-133, 1943.
[40]J. L. McClelland, D. E. Rumelhart, and P. R. Group, "Parallel distributed processing," Explorations in the microstructure of cognition, vol. 2, 1986.
[41]S. S. Haykin, Neural networks: a comprehensive foundation: Prentice Hall Englewood Cliffs, NJ, 2007.
[42]R. Hecht-Nielsen, "Theory of the backpropagation neural network," in Neural Networks, 1989. IJCNN., International Joint Conference on, 1989, pp. 593-605.
[43]K. Levenberg, "A method for the solution of certain problems in least squares," Quarterly of applied mathematics, vol. 2, pp. 164-168, 1944.
[44]D. W. Marquardt, "An algorithm for least-squares estimation of nonlinear parameters," Journal of the Society for Industrial & Applied Mathematics, vol. 11, pp. 431-441, 1963.
[45]I. Newton, The Method of Fluxions and Infinite Series: With Its Application to the Geometry of Curve Lines, 1736.
[46]C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, pp. 273-297, 1995.
[47]Y. Fan, D. Shen, and C. Davatzikos, "Classification of structural images via high-dimensional image warping, robust feature extraction, and SVM," in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2005, pp. 1-8.
[48]H. Selvaraj, S. T. Selvi, D. Selvathi, and L. Gewali, "Brain MRI slices classification using least squares support vector machine," International Journal of Intelligent Computing in Medical Sciences & Image Processing, vol. 1, pp. 21-33, 2007.
[49]Student, "The probable error of a mean," Biometrika, pp. 1-25, 1908.
[50]R. A. Fisher, S. Genetiker, S. Genetician, G. Britain, and S. Généticien, Statistical methods for research workers vol. 14: Oliver and Boyd Edinburgh, 1970.
[51]P. Pudil, J. Novovičová, and J. Kittler, "Floating search methods in feature selection," Pattern recognition letters, vol. 15, pp. 1119-1125, 1994.
[52]R. M. Haralick, K. Shanmugam, and I. H. Dinstein, "Textural features for image classification," Systems, Man and Cybernetics, IEEE Transactions on, pp. 610-621, 1973.
[53]J. Zhang, L. Wang, and L. Tong, "Feature reduction and texture classification in MRI-Texture analysis of multiple sclerosis," in Complex Medical Engineering, 2007. CME 2007. IEEE/ICME International Conference on, 2007, pp. 752-757.
[54]A. K. Mohanty, S. Beberta, and S. K. Lenka, "Classifying benign and malignant mass using GLCM and GLRLM based texture features from mammogram," International Journal of Engineering Research and Applications, vol. 1, pp. 687-693, 2011.
[55]M. M. Galloway, "Texture analysis using gray level run lengths," Computer graphics and image processing, vol. 4, pp. 172-179, 1975.
[56]K. R. Krishnan and R. Sudhakar, "Automatic classification of liver diseases from ultrasound images using GLRLM texture features," in Soft Computing Applications, ed: Springer, 2013, pp. 611-624.
[57]X. Tang, "Texture information in run-length matrices," Image Processing, IEEE Transactions on, vol. 7, pp. 1602-1609, 1998.
[58]H. Tamura, S. Mori, and T. Yamawaki, "Textural features corresponding to visual perception," Systems, Man and Cybernetics, IEEE Transactions on, vol. 8, pp. 460-473, 1978.
[59]L. Zong, L. Ying, and L. Daxiang, "A new texture feature extraction method for image retrieval," in Intelligent Control and Information Processing (ICICIP), 2013 Fourth International Conference on, 2013, pp. 482-486.
[60]P. Howarth and S. Rüger, "Robust texture features for still-image retrieval," IEE Proceedings-Vision, Image and Signal Processing, vol. 152, pp. 868-874, 2005.
[61]D. Marr and E. Hildreth, "Theory of edge detection," Proceedings of the Royal Society of London B: Biological Sciences, vol. 207, pp. 187-217, 1980.
[62]J. Immerkaer, "Fast noise variance estimation," Computer vision and image understanding, vol. 64, pp. 300-302, 1996.
[63]K. Kutty and S. Ojha, "A generic transfer function based technique for estimating noise from images," International Journal of Computer Applications, vol. 51, 2012.
[64]S. Aja-Fernández, A. Tristán-Vega, and C. Alberola-López, "Noise estimation in single-and multiple-coil magnetic resonance data based on statistical models," Magnetic resonance imaging, vol. 27, pp. 1397-1409, 2009.
[65]S. Aja-Fernández, C. Alberola-López, and C.-F. Westin, "Noise and signal estimation in magnitude MRI and Rician distributed images: a LMMSE approach," IEEE transactions on image processing, vol. 17, pp. 1383-1398, 2008.
[66]M. E. Brummer, R. M. Mersereau, R. L. Eisner, and R. R. Lewine, "Automatic detection of brain contours in MRI data sets," IEEE transactions on Medical Imaging, vol. 12, pp. 153-166, 1993.
[67]J. Sijbers, D. Poot, A. J. den Dekker, and W. Pintjens, "Automatic estimation of the noise variance from the histogram of a magnetic resonance image," Physics in medicine and biology, vol. 52, p. 1335, 2007.
[68]K. Sim, M. Lai, C. Tso, and C. Teo, "Single image signal-to-noise ratio estimation for magnetic resonance images," Journal of medical systems, vol. 35, pp. 39-48, 2011.
[69]H. Vafaie and K. De Jong, "Robust feature selection algorithms," in Tools with Artificial Intelligence, 1993. TAI''93. Proceedings., Fifth International Conference on, 1993, pp. 356-363.
[70]I.-S. Oh, J.-S. Lee, and B.-R. Moon, "Hybrid genetic algorithms for feature selection," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 26, pp. 1424-1437, 2004.
[71]A. W. Whitney, "A direct method of nonparametric measurement selection," Computers, IEEE Transactions on, vol. 100, pp. 1100-1103, 1971.
[72]T. Marill and D. M. Green, "On the effectiveness of receptors in recognition systems," Information Theory, IEEE Transactions on, vol. 9, pp. 11-17, 1963.
[73]M. Stone, "Cross-validatory choice and assessment of statistical predictions," Journal of the Royal Statistical Society. Series B (Methodological), pp. 111-147, 1974.
[74]楊敦翔, "以類神經網路與特徵選取技巧處理空氣能見度預測問題之研究," 碩士, 機械與機電工程學系研究所, 國立中山大學, 2003.
[75]H. Baltzakis and N. Papamarkos, "A new signature verification technique based on a two-stage neural network classifier," Engineering applications of Artificial intelligence, vol. 14, pp. 95-103, 2001.
[76]C. Nvidia, "Tesla K40 GPU Accelerator Overview," 2014.
[77]M. Sokolova and G. Lapalme, "A systematic analysis of performance measures for classification tasks," Information Processing & Management, vol. 45, pp. 427-437, 2009.
[78](5/22). LONI Test Archeive V1.0. Available: http://www.loni.usc.edu/