脑部CT图像分割算法改进及实现
|
摘要
论文以医学领域的脑部CT (Computed Tomography)图像为研究对象,在医学影像存档与通讯系统PACS (Picture archiving and communication systems)的CT影像工作站环境下,研究了边缘分割算子中的LOG (Gauss-Laplacian Operator)算子、基于形态学分割的分水岭算法的应用和改进,获得了脑部CT图像中头骨的边缘分割图和头骨的区域分割图。
论文根据医学图像的分割特点及方法,分析了脑部CT成像的原理、研究了脑部CT图像的特点、噪声、边缘特征、多阈值形态学特征。完成的主要工作如下：
1.在高斯-拉普拉斯算子(LOG)的基础上,改进了根据高斯函数的平滑因子σ、脑部CT图像的边缘灰度阈值T、滤波器的大小m×n等三个参数控制的LOG算子,利用该改进的算子能根据需要灵活地得到二值化头骨边缘分割结果。
2.以脑部CT图像的灰度多阈值、形态学特征为基础,应用去噪、距离变换、梯度重构、内外部标记条件等综合方法,改进了分水岭分割算法。利用该改进的分水岭分割算法能够得到脑部CT图像的头骨分割图,该改进算法在噪声抑制、区域信息获取和过分割控制等方面效果较好。
3.利用Matlab语言实现了改进的LOG算子和改进的分水岭算法,并对它们的分割效果和运算效率作了分析。
4.用改进LOG算子、改进分水岭算法对一组脑部CT切片图像进行了处理,综合分析了分割质量、运行时间和效率、复杂度等。
论文中的改进算法,在理论上有较全面和深入的研究,在应用上获得了有效的分割结果,其可行性和有效性从理论与实践上得到了验证。
Taking CT image of the brain as the researched subject, under the environment of CT workstation of PACS, the author of this thesis studied and improved the LOG and watershed algorithm in the stage of image segmentation, achieved the results of CT image of the brain on skull edge and region.
According to the feature and approaches, the thesis studied the principle, characteristics, noise, edge feature, morphological feature of multi-threshold values in CT image of the brain's skull segmentation. The main achivements are as follows:
1. According to the feature of edge segmentating on skull, the LOG method is improved, and the binary result can be obtained flexiblely through the improved LOG agorithm, which is controlled by Gaussian function's smoothing factorσ, edge gray threshold value T, and pepper-and-salt filter's size m×n.
2. According to the morphological feature of multi-threshold values, the watershed segmentation algorithm is improved by combining denoising, distance transform, gradient reconstruction with constraint conditions, and the segmentation image of brain skull which is obtained by the improved algorithm is good at noise suppression, region information accepting, and over segmentation controlling.
3. The segmented images from the improved LOG and watershed algorithm realized with Matlab language can be achieved effectively, and the segmemting effect and algorithm efficiency are analyzed.
4. Applied improved LOG and improved watershed algorithm in a group of brain CT slides, and then appraised segmented results, run time, efficiency and complexity and so on.
The improved algorithms of this thesis are studied fully and deeply in theory, and can achieve effective segmentation results in application. So, the feasibility and validity of the improved algorithms are verified from theories and experimentations.
论文根据医学图像的分割特点及方法,分析了脑部CT成像的原理、研究了脑部CT图像的特点、噪声、边缘特征、多阈值形态学特征。完成的主要工作如下：
1.在高斯-拉普拉斯算子(LOG)的基础上,改进了根据高斯函数的平滑因子σ、脑部CT图像的边缘灰度阈值T、滤波器的大小m×n等三个参数控制的LOG算子,利用该改进的算子能根据需要灵活地得到二值化头骨边缘分割结果。
2.以脑部CT图像的灰度多阈值、形态学特征为基础,应用去噪、距离变换、梯度重构、内外部标记条件等综合方法,改进了分水岭分割算法。利用该改进的分水岭分割算法能够得到脑部CT图像的头骨分割图,该改进算法在噪声抑制、区域信息获取和过分割控制等方面效果较好。
3.利用Matlab语言实现了改进的LOG算子和改进的分水岭算法,并对它们的分割效果和运算效率作了分析。
4.用改进LOG算子、改进分水岭算法对一组脑部CT切片图像进行了处理,综合分析了分割质量、运行时间和效率、复杂度等。
论文中的改进算法,在理论上有较全面和深入的研究,在应用上获得了有效的分割结果,其可行性和有效性从理论与实践上得到了验证。
Taking CT image of the brain as the researched subject, under the environment of CT workstation of PACS, the author of this thesis studied and improved the LOG and watershed algorithm in the stage of image segmentation, achieved the results of CT image of the brain on skull edge and region.
According to the feature and approaches, the thesis studied the principle, characteristics, noise, edge feature, morphological feature of multi-threshold values in CT image of the brain's skull segmentation. The main achivements are as follows:
1. According to the feature of edge segmentating on skull, the LOG method is improved, and the binary result can be obtained flexiblely through the improved LOG agorithm, which is controlled by Gaussian function's smoothing factorσ, edge gray threshold value T, and pepper-and-salt filter's size m×n.
2. According to the morphological feature of multi-threshold values, the watershed segmentation algorithm is improved by combining denoising, distance transform, gradient reconstruction with constraint conditions, and the segmentation image of brain skull which is obtained by the improved algorithm is good at noise suppression, region information accepting, and over segmentation controlling.
3. The segmented images from the improved LOG and watershed algorithm realized with Matlab language can be achieved effectively, and the segmemting effect and algorithm efficiency are analyzed.
4. Applied improved LOG and improved watershed algorithm in a group of brain CT slides, and then appraised segmented results, run time, efficiency and complexity and so on.
The improved algorithms of this thesis are studied fully and deeply in theory, and can achieve effective segmentation results in application. So, the feasibility and validity of the improved algorithms are verified from theories and experimentations.
引文
[1]Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins.数字图像处理[M].第二版.阮秋琦等译.北京：电子工业出版社,2009
[2]Pratt, W.K. Digital Image Processing [M].3rd. New York:John Wiley & Sons,2001
[3]Jahne, B. Digital Image Processing:Concepts, Algorithms, and Scientific Applications [M]. New York:Springer-Verlag,1997
[4]Sid-Ahmed, M. A. Image Processing:Theory, Algorithms, and Architectures [M]. New York:McGraw-Hill,1995
[5]Andrews H. C. Computer Techniques in Image Processing [M]. New York:Academic Press,1970
[6]Gonzalez, R. C., Fittes, B. A. Gray-Level Transformations for Interactive Image Enhancement [J]. Machanism and Machine Theory, Vol.12,1997:111-122
[7]Chen, Y.-S., Yu, Y.-T. Thinking Approach for Noisy Digital Patterns [J]. Pattern Recog., vol.29, no.11,1996:1847-1862
[8]Chu, C.-C, Aggarwal, J. K. The Intergration of Image Segmentation Maps Using Regions and Edge Information [J]. IEEE Trans. Pattern Anal. Machine Intell., vol.15, no. 12,1993:1241-1252
[9]Marchand-Maillet, S. and Sharaiha, Y. M. Binary Digital Image Processing:A Ddiscrete Approach [M]. NY:Academic Press,2000
[10]Serra, J. Image Analysis and Mathematical Morphology [M]. New York:Academic Press, 1982
[11]Baccar, M., Gee, L. A., Abidi, M. A., and Gonzalez, R. C. Segmentation of Range Images Via Data Fusion and Morphological Watersheds [J]. Pattern Recog., Vol.29, no.10, 1671-1685
[12]Beucher, S., and Meyer, F. The Morphological Approach of Segmentation:The Watershed Transformation, Mathematical Morphology in Image Processing [C]. E. Dougherty(ed), Marcel Dekker, New York,1992
[13]Blweau, A. and Leno, L. J. Watershed-Based Segmentation and Region Merging [J]. Computer Vision and Image Understanding, vol.77, no.3,2000:317-370
[14]Marr, D., Hildreth, E. Theory of Edge Detection [C]. Proc. R. Soc. Lnd., vol. B207,1980: 187-217
[15]Canny, J. A. Computation Approach for Edge Detection [J]. IEEE Trans. Pattern Anal Machine Intell., vol.8, no.6,1986:679-698
[16]Clark, J. J. Authentication Edges Produced by Zero-crossing Crossing Algorithms [J]. IEEE Trans. Pattern Anal. Machine Intell., vol.12, no.8,1989:830-831
[17]Gunn, S. R. Edge Detection Error in the Discrete Laplacian of a Gaussian [C]. Proc. of 1998 Int 1 Conference on Image Processing, vol.Ⅱ,1998:515-519
[18]程广斌.应用于数字化诊断的若干医学图像分析方法研究[D].博士论文.南方医科大学,2008
[19]史英杰.医学图像辅助诊断系统中图像分割技术的研究[D].硕士论文.华中科技大学,2007
[20]程琼.基于二维CT图像的三维重建及其应用[D].硕士论文.同济大学,2006
[21]何培培.脑部CT图像处理研究[D].硕士论文.长沙理工大学,2008
[22]袁丽婷.基于Matlab的医学图像增强与边缘检测算法的实验研究[D].硕士论文.第四军医大学,2007
[23]刘慧.医学图像处理中的分割与检索关键技术研究[D].博士论文.山东大学,2008
[24]沈阳.基于形态学的图像边缘检测技术研究[D].硕士论文.电子科技大学,2008
[25]卢官明.一种计算图像形态梯度的多尺度算法[J].中国图像图形学报,2001,6(3)：214-218
[26]汪军峰,郭佑民等.图像分割在医学图像中的研究方法及应用[J].中国医学影像技术,2005,21(10)：1627-1630
[27]Lehmann, T. M., Gonner, C., Spitzer, K. Survey:Interpolation Methods in Medical Image Processing[J]. IEEE Trans Medical Imaging, vol.18, no.11,1999:1049-1076
[28]张太发,程东旭,石瑞银.基于Log算子的一种新的边界轮廓线提取方法[J].计算机工程与应用,2008,44(22)：183-185
[29]刘晨,张东.边缘检测算子研究及其在医学图像中的应用[J].计算机技术与发展,2006,16(8)：128-131
[30]Haralick, R. M., and Lee, J. S. J. Context Dependent Edge Detection and Evaluation [J]. Patter Recog.,vol.23, no.1-2,1990:1-20
[31]王宇,陈殿仁,沈美丽等.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11)：2176-2180
[32]吴雷磊,王卫星.一种改进的分水岭图像分割算法[J].通讯和计算机,2007,4(6)：48-52
[33]吴昊,刘正熙,罗以宁等.改进多尺度分水岭算法在医学图像分割中的应用研究[J].计算机应用,2006,26(8)：1975-1976
[34]王蜀,李永宁,陈楷民等.基于数学形态学的医学图像分割[J].计算机应用,2005, 25(10)：2381-2383
[35]刘喜英,吴淑泉,徐向民.基于改进分水岭算法的医学图像分割的研究[J].微电子技术,2003,31(4)：39-42
[36]夏平,刘馨琼,向学军,等.复合形态滤波和改进型分水岭算法的图像分割[J].三峡大学学报,2008,30(5)：60-64
[37]Goutsias, J, Vincent, L., Bloomberg, D. S. (eds). Mathematical Morphology and Its Applications to Image and Signal Processing[M]. Kluwer Academic Publishers, Boston, Mass,2000
[38]Haddon, J. F., and Boyce, J. F. Image Segmentation by Unifying Region and Boundary Information[J]. IEEE Trans. Pattern Anal. Machine Intell., vol,12, no.10,1990:929-948
[39]曹加恒,舒风笛,张凯,彭敏,叶可.基于多媒体数据库的数据挖掘系统原型[J].武汉大学学报(自然科学版),2000,46(5)：567-570
[40]Fayyad U, Smyth P. Image database exploration:Progress and challenges [C]. Proceedings of 1993 Knowledge Discovery in Databases Workshop, Washington, DC, 1993:14-27
[41]Zaiane O.R., Han J., Li Z.N., and et al. Multimedia Miner:A system prototype for multimedia data mining [C]. Proceesings of 1998 ACM-SIGMOD Conference on Management of Data(SIGMOD'98), Seattle, WA, June 1998,581-583
[42]David Hand, Heikki Mannila, Padhraic Smyth.数据挖掘原理[M].张银奎,寥丽,宋俊等译.机械工业出版社,中信出版社,2003
[43]Zaiane O.R. Resource and Knowledge Discovery from the Internetand Multimedia Repositories [D]. Doctoral Dissertation. Simon Fraser University, Canada,1999
[44]Antonie M. L., Zaiane O. R., Coman A. Application of Data Mining Techniques for Medical Image Classification [C]. MDM/KDD2001, San Francisco, CA, USA,2001: 94-101
[45]姚敏.数字图像处理[M].北京：机械工业出版社,2006
[46]章毓晋.图像工程(上册)——图像分析和处理[M].北京：清华大学出版社,1999
[47]章毓晋.图像工程(下册)——图像理解与计算机视觉[M].北京：清华大学出版社,1999
[48]Rafael C. Gonzalez, Richard E. Woods著.数字图像处理(MATLAB版)[M].阮秋琦,阮宇智等译.北京：电子工业出版社,2009
[49]MATLAB官方网站.Documentation [EB/OL]. http://www.mathworks.com/,2009
[50]Anany Levitin著.算法设计与分析基础[M].潘彦译.北京：清华大学出版社,2004
[2]Pratt, W.K. Digital Image Processing [M].3rd. New York:John Wiley & Sons,2001
[3]Jahne, B. Digital Image Processing:Concepts, Algorithms, and Scientific Applications [M]. New York:Springer-Verlag,1997
[4]Sid-Ahmed, M. A. Image Processing:Theory, Algorithms, and Architectures [M]. New York:McGraw-Hill,1995
[5]Andrews H. C. Computer Techniques in Image Processing [M]. New York:Academic Press,1970
[6]Gonzalez, R. C., Fittes, B. A. Gray-Level Transformations for Interactive Image Enhancement [J]. Machanism and Machine Theory, Vol.12,1997:111-122
[7]Chen, Y.-S., Yu, Y.-T. Thinking Approach for Noisy Digital Patterns [J]. Pattern Recog., vol.29, no.11,1996:1847-1862
[8]Chu, C.-C, Aggarwal, J. K. The Intergration of Image Segmentation Maps Using Regions and Edge Information [J]. IEEE Trans. Pattern Anal. Machine Intell., vol.15, no. 12,1993:1241-1252
[9]Marchand-Maillet, S. and Sharaiha, Y. M. Binary Digital Image Processing:A Ddiscrete Approach [M]. NY:Academic Press,2000
[10]Serra, J. Image Analysis and Mathematical Morphology [M]. New York:Academic Press, 1982
[11]Baccar, M., Gee, L. A., Abidi, M. A., and Gonzalez, R. C. Segmentation of Range Images Via Data Fusion and Morphological Watersheds [J]. Pattern Recog., Vol.29, no.10, 1671-1685
[12]Beucher, S., and Meyer, F. The Morphological Approach of Segmentation:The Watershed Transformation, Mathematical Morphology in Image Processing [C]. E. Dougherty(ed), Marcel Dekker, New York,1992
[13]Blweau, A. and Leno, L. J. Watershed-Based Segmentation and Region Merging [J]. Computer Vision and Image Understanding, vol.77, no.3,2000:317-370
[14]Marr, D., Hildreth, E. Theory of Edge Detection [C]. Proc. R. Soc. Lnd., vol. B207,1980: 187-217
[15]Canny, J. A. Computation Approach for Edge Detection [J]. IEEE Trans. Pattern Anal Machine Intell., vol.8, no.6,1986:679-698
[16]Clark, J. J. Authentication Edges Produced by Zero-crossing Crossing Algorithms [J]. IEEE Trans. Pattern Anal. Machine Intell., vol.12, no.8,1989:830-831
[17]Gunn, S. R. Edge Detection Error in the Discrete Laplacian of a Gaussian [C]. Proc. of 1998 Int 1 Conference on Image Processing, vol.Ⅱ,1998:515-519
[18]程广斌.应用于数字化诊断的若干医学图像分析方法研究[D].博士论文.南方医科大学,2008
[19]史英杰.医学图像辅助诊断系统中图像分割技术的研究[D].硕士论文.华中科技大学,2007
[20]程琼.基于二维CT图像的三维重建及其应用[D].硕士论文.同济大学,2006
[21]何培培.脑部CT图像处理研究[D].硕士论文.长沙理工大学,2008
[22]袁丽婷.基于Matlab的医学图像增强与边缘检测算法的实验研究[D].硕士论文.第四军医大学,2007
[23]刘慧.医学图像处理中的分割与检索关键技术研究[D].博士论文.山东大学,2008
[24]沈阳.基于形态学的图像边缘检测技术研究[D].硕士论文.电子科技大学,2008
[25]卢官明.一种计算图像形态梯度的多尺度算法[J].中国图像图形学报,2001,6(3)：214-218
[26]汪军峰,郭佑民等.图像分割在医学图像中的研究方法及应用[J].中国医学影像技术,2005,21(10)：1627-1630
[27]Lehmann, T. M., Gonner, C., Spitzer, K. Survey:Interpolation Methods in Medical Image Processing[J]. IEEE Trans Medical Imaging, vol.18, no.11,1999:1049-1076
[28]张太发,程东旭,石瑞银.基于Log算子的一种新的边界轮廓线提取方法[J].计算机工程与应用,2008,44(22)：183-185
[29]刘晨,张东.边缘检测算子研究及其在医学图像中的应用[J].计算机技术与发展,2006,16(8)：128-131
[30]Haralick, R. M., and Lee, J. S. J. Context Dependent Edge Detection and Evaluation [J]. Patter Recog.,vol.23, no.1-2,1990:1-20
[31]王宇,陈殿仁,沈美丽等.基于形态学梯度重构和标记提取的分水岭图像分割[J].中国图象图形学报,2008,13(11)：2176-2180
[32]吴雷磊,王卫星.一种改进的分水岭图像分割算法[J].通讯和计算机,2007,4(6)：48-52
[33]吴昊,刘正熙,罗以宁等.改进多尺度分水岭算法在医学图像分割中的应用研究[J].计算机应用,2006,26(8)：1975-1976
[34]王蜀,李永宁,陈楷民等.基于数学形态学的医学图像分割[J].计算机应用,2005, 25(10)：2381-2383
[35]刘喜英,吴淑泉,徐向民.基于改进分水岭算法的医学图像分割的研究[J].微电子技术,2003,31(4)：39-42
[36]夏平,刘馨琼,向学军,等.复合形态滤波和改进型分水岭算法的图像分割[J].三峡大学学报,2008,30(5)：60-64
[37]Goutsias, J, Vincent, L., Bloomberg, D. S. (eds). Mathematical Morphology and Its Applications to Image and Signal Processing[M]. Kluwer Academic Publishers, Boston, Mass,2000
[38]Haddon, J. F., and Boyce, J. F. Image Segmentation by Unifying Region and Boundary Information[J]. IEEE Trans. Pattern Anal. Machine Intell., vol,12, no.10,1990:929-948
[39]曹加恒,舒风笛,张凯,彭敏,叶可.基于多媒体数据库的数据挖掘系统原型[J].武汉大学学报(自然科学版),2000,46(5)：567-570
[40]Fayyad U, Smyth P. Image database exploration:Progress and challenges [C]. Proceedings of 1993 Knowledge Discovery in Databases Workshop, Washington, DC, 1993:14-27
[41]Zaiane O.R., Han J., Li Z.N., and et al. Multimedia Miner:A system prototype for multimedia data mining [C]. Proceesings of 1998 ACM-SIGMOD Conference on Management of Data(SIGMOD'98), Seattle, WA, June 1998,581-583
[42]David Hand, Heikki Mannila, Padhraic Smyth.数据挖掘原理[M].张银奎,寥丽,宋俊等译.机械工业出版社,中信出版社,2003
[43]Zaiane O.R. Resource and Knowledge Discovery from the Internetand Multimedia Repositories [D]. Doctoral Dissertation. Simon Fraser University, Canada,1999
[44]Antonie M. L., Zaiane O. R., Coman A. Application of Data Mining Techniques for Medical Image Classification [C]. MDM/KDD2001, San Francisco, CA, USA,2001: 94-101
[45]姚敏.数字图像处理[M].北京：机械工业出版社,2006
[46]章毓晋.图像工程(上册)——图像分析和处理[M].北京：清华大学出版社,1999
[47]章毓晋.图像工程(下册)——图像理解与计算机视觉[M].北京：清华大学出版社,1999
[48]Rafael C. Gonzalez, Richard E. Woods著.数字图像处理(MATLAB版)[M].阮秋琦,阮宇智等译.北京：电子工业出版社,2009
[49]MATLAB官方网站.Documentation [EB/OL]. http://www.mathworks.com/,2009
[50]Anany Levitin著.算法设计与分析基础[M].潘彦译.北京：清华大学出版社,2004