胰腺超声内镜计算机辅助诊断系统研究
|
摘要
胰腺癌是严重危及人类健康的重大疾患,其早期发现、早期诊断、是长期困扰医学界的难题。目前的诊断方法中,超声内镜检查术对胰腺癌具有较大的诊断价值,但基于超声内镜图像的诊断受医生经验和主观因素影响大,而经穿刺的细胞学检查有一定创伤性。本文研究并初步开发了胰腺超声内镜计算机辅助诊断系统,旨在创建各种客观、量化的诊断指标以及正确的描述解释超声内镜图像的方法,提高胰腺癌超声内镜早期诊断的准确性。
本文的研究内容主要由四部分构成：胰腺超声内镜的纹理特征提取、特征选择、分类评价系统和软件系统开发,并对各部分存在的一些问题进行研究和改进。
在纹理特征提取部分,将各类文献中广泛使用的用于纹理分割与纹理分类的特征引入胰腺超声内镜图像分类,提取9大类74种纹理特征,并取得了较好的分类结果。之后对传统分形特征进行研究与改进。对Lee提出的基于M带小波变换的分形特征进行改进,引入多重分形维数并进行特征筛选,提出了基于M带小波变换的多重分形特征。基于本研究分形特征矢量的分类,在运行时间和分类准确率上均优于基于传统分形特征的分类。
在特征选择部分,针对特征选择中传统可分性判据对线性不可分数据集评价能力差的特点,提出了基于核空间距离测度的可分性判据。在核空间中计算两类样本点之间的距离,并以距离的大小评价子集的分类性能。本文的方法体现了基于核方法的优越性,尤其提高了在小样本与线性不可分数据集上的特征选择能力,同时由于核空间距离测度随核参数单调变化,便于消除核参数的影响,相比Wang提出的核散布矩阵测度,大幅度降低了运行时间,同时保留了核方法的优越性。
根据医生在临床上对分类评价的需求,提出了基于广义隶属度函数的模糊模式识别方法实现胰腺超声内镜分类评价系统。通过特征模糊化提高鲁棒性,使用训练样本构造合理的目标函数和惩罚项,通过多参数优化的方法得到模式广义隶属度函数的参数,并通过评价函数对样本进行分类评价。
在以上算法研究的基础上,编程实现计算机辅助诊断软件系统开发。使用标准C++语言在Visual Studio环境下实现本文提出的特征提取与分类算法。使用MFC、GDI+、ODBC等技术实现浏览,计算机辅助诊断,放大,测量和数据库连接等多种功能模式,方便医生临床使用。
Pancreatic cancer is a major disease which seriously threatens human health. The early detection and diagnosis are problems which have long plagued the medical profession. In current diagnostic methods, the endoscopic ultrasonography(EUS) have greater diagnostic value over pancreatic cancer. However, the diagnosis based on EUS images is affected considerably by the doctors' experience and subjective factors, and the cytology examination is invasive. In this paper, we focus on the research and basic development of the computer aided diagnosis(CAD) system of pancreatic EUS images, in order to create a variety of objective, quantitative diagnostic indices and an appropriate method to describe and understand the EUS images, and finally, increasing the accuracy of early diagnosis of pancreatic cancer through EUS.
The proposed methods are composed of four parts:textural feature extraction of the pancreatic EUS images, feature selection, classification and evaluation system and the software development. Study and improvement on each part have been done for specific problems.
As for the textural feature extraction, textural features, which have been widely used in different papers for textural segmentation and classification, are introduced into the area of pancreatic EUS image classification. 74 texture features of 9 categories are extracted, and good classification results are achieved using these features. Further work has been done on the study and improvement of tradition fractal features. By modifying the M-band wavelet transform fractal feature based on the fractal dimension(Lee,2003), the multi-fractal dimension was presented with the feature selection to obtain the multi-fractal feature vector of M-band wavelet transform. Experimental results showed that the classification based on the proposed fractal feature outperformed those based on the traditional fractal feature in both executing time and classifying accuracy.
In the part of feature selection, the kernel distance measure is proposed as a new type of class separability, considering the poor performance of traditional class separability on linearly non-separable data set. The distance of samples from two classes is measured in the kernel space, and used to evaluate the separability of subsets. The proposed method embodies the advantages of kernel-based methods, especially on small sample set and linearly non-separable data set. Meanwhile, the kernel distance measure changes with the kernel parameter monotonously, so that it is 4 easy to eliminate the influence of kernel parameter. Compared with kernel scatter matrix measure(Wang,2008), the proposed method is much faster in running time and retains the advantages of kernel-based methods as well.
According to the clinical requirements of classification and evaluation system, the fuzzy pattern recognition based on generalized membership function is proposed to realize the classification and evaluation system of pancreatic EUS images. The features are made fuzzy to increase the robustness. The training samples are used to construct a reasonable objective function and item of punishment. The unknown parameters of generalized membership function is estimated through optimization, and finally the classification and evaluation is implemented by the evaluation function.
Based on the above research on algorithm, the Computer Aided Diagnosis Software System is developed. The proposed feature extraction and classification algorithm is programmed using standard C++ language in the environment of Visual Studio. The different function mode of browsing, CAD, zooming, measuring and database connecting is realized through the technology of MFC, GDI+, ODBC, etc, to facilitate-medical clinical use.
本文的研究内容主要由四部分构成：胰腺超声内镜的纹理特征提取、特征选择、分类评价系统和软件系统开发,并对各部分存在的一些问题进行研究和改进。
在纹理特征提取部分,将各类文献中广泛使用的用于纹理分割与纹理分类的特征引入胰腺超声内镜图像分类,提取9大类74种纹理特征,并取得了较好的分类结果。之后对传统分形特征进行研究与改进。对Lee提出的基于M带小波变换的分形特征进行改进,引入多重分形维数并进行特征筛选,提出了基于M带小波变换的多重分形特征。基于本研究分形特征矢量的分类,在运行时间和分类准确率上均优于基于传统分形特征的分类。
在特征选择部分,针对特征选择中传统可分性判据对线性不可分数据集评价能力差的特点,提出了基于核空间距离测度的可分性判据。在核空间中计算两类样本点之间的距离,并以距离的大小评价子集的分类性能。本文的方法体现了基于核方法的优越性,尤其提高了在小样本与线性不可分数据集上的特征选择能力,同时由于核空间距离测度随核参数单调变化,便于消除核参数的影响,相比Wang提出的核散布矩阵测度,大幅度降低了运行时间,同时保留了核方法的优越性。
根据医生在临床上对分类评价的需求,提出了基于广义隶属度函数的模糊模式识别方法实现胰腺超声内镜分类评价系统。通过特征模糊化提高鲁棒性,使用训练样本构造合理的目标函数和惩罚项,通过多参数优化的方法得到模式广义隶属度函数的参数,并通过评价函数对样本进行分类评价。
在以上算法研究的基础上,编程实现计算机辅助诊断软件系统开发。使用标准C++语言在Visual Studio环境下实现本文提出的特征提取与分类算法。使用MFC、GDI+、ODBC等技术实现浏览,计算机辅助诊断,放大,测量和数据库连接等多种功能模式,方便医生临床使用。
Pancreatic cancer is a major disease which seriously threatens human health. The early detection and diagnosis are problems which have long plagued the medical profession. In current diagnostic methods, the endoscopic ultrasonography(EUS) have greater diagnostic value over pancreatic cancer. However, the diagnosis based on EUS images is affected considerably by the doctors' experience and subjective factors, and the cytology examination is invasive. In this paper, we focus on the research and basic development of the computer aided diagnosis(CAD) system of pancreatic EUS images, in order to create a variety of objective, quantitative diagnostic indices and an appropriate method to describe and understand the EUS images, and finally, increasing the accuracy of early diagnosis of pancreatic cancer through EUS.
The proposed methods are composed of four parts:textural feature extraction of the pancreatic EUS images, feature selection, classification and evaluation system and the software development. Study and improvement on each part have been done for specific problems.
As for the textural feature extraction, textural features, which have been widely used in different papers for textural segmentation and classification, are introduced into the area of pancreatic EUS image classification. 74 texture features of 9 categories are extracted, and good classification results are achieved using these features. Further work has been done on the study and improvement of tradition fractal features. By modifying the M-band wavelet transform fractal feature based on the fractal dimension(Lee,2003), the multi-fractal dimension was presented with the feature selection to obtain the multi-fractal feature vector of M-band wavelet transform. Experimental results showed that the classification based on the proposed fractal feature outperformed those based on the traditional fractal feature in both executing time and classifying accuracy.
In the part of feature selection, the kernel distance measure is proposed as a new type of class separability, considering the poor performance of traditional class separability on linearly non-separable data set. The distance of samples from two classes is measured in the kernel space, and used to evaluate the separability of subsets. The proposed method embodies the advantages of kernel-based methods, especially on small sample set and linearly non-separable data set. Meanwhile, the kernel distance measure changes with the kernel parameter monotonously, so that it is 4 easy to eliminate the influence of kernel parameter. Compared with kernel scatter matrix measure(Wang,2008), the proposed method is much faster in running time and retains the advantages of kernel-based methods as well.
According to the clinical requirements of classification and evaluation system, the fuzzy pattern recognition based on generalized membership function is proposed to realize the classification and evaluation system of pancreatic EUS images. The features are made fuzzy to increase the robustness. The training samples are used to construct a reasonable objective function and item of punishment. The unknown parameters of generalized membership function is estimated through optimization, and finally the classification and evaluation is implemented by the evaluation function.
Based on the above research on algorithm, the Computer Aided Diagnosis Software System is developed. The proposed feature extraction and classification algorithm is programmed using standard C++ language in the environment of Visual Studio. The different function mode of browsing, CAD, zooming, measuring and database connecting is realized through the technology of MFC, GDI+, ODBC, etc, to facilitate-medical clinical use.
引文
[1]陆星华,李益农,消化内镜学[M],第2版,北京：科学出版社,2004：pp 577
[2]汪毅,胰腺癌早期诊断的现状与进展[J],癌症进展杂志2006年7月第4卷第4期,pp.327-332
[3]金震东,李兆申,消化超声内镜学[M],北京：科学出版社,2006
[4]张定国,超声内镜对胰腺疾病的诊断价值[J],国际内科学杂志2007年3月第34卷第3期,pp.159-162
[5]K. Ogawa, M. Fukushima, K. Kubota, and N. Hisa, Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural network[J], IEEE Trans. Nucl. Sci., vol.45, pp.3069-3074, Dec.1998.
[6]C. M. Wu, Y. C. Chen, and K. S. Hsieh, Texture features for classification of ultrasonic liver images[J], IEEE Trans. Med. Imag., vol.11, pp.141-152, June 1992.
[7]A. Mojsilovic', M. Popovic', S. Markovic', and M. Krstic', Characterization of visually similar diffuse diseases from B-scan liver images using nonseparable wavelet transform[J], IEEE Trans. Med Imag., vol.17, pp.541-549, Aug.1998.
[8]Wen-Li Lee, Yung-Chang Chen, and Kai-Sheng Hsieh, Ultrasonic Liver Tissues Classification by Fractal Feature Vector Based on M-Band Wavelet Transform[J], IEEE Trans. Med. Imag., vol.22, pp.382-392, Mar.2003.
[9]Du-Yih Tsai and Yongbum Lee, Fuzzy-reasoning-based-diagnosis scheme for automated classification of heart disease from ultrasonic images[C],2001 IEEE International Fuzzy System Conference
[10]Du-Yih Tsai and Shinji Watanabe, A Method for Optimization of Fuzzy Reasoning by Genetic Algorithms and Its Application to Discrimination of Myocardial Heart Disease[J], IEEE Trans. Nucl. Sci., VOL.46, pp.2239-2246, NO.6, DECEMBER 1999
[11]D.R. Chen, R.F. Chang and Y.L. Huang. Breast cancer diagnosis using self-organizing map for sonography[J]. Ultrasound Med Biol.,2000,3:405-411.
[12]W.J. Kuo, R.F. Chang and W.K. Moon et al. Computer-aided diagnosis of breast tumors with different us systems[J]. Acad. Radiol.,2002,9:793-799
[13]R.F. Chang, C.J. Chen and M.F. Ho. Breast ultrasound image classification using fractal analysis[C].2004 Proceedings of the Fourth IEEE Symposium on Bioinformatics and Bioengineering
[14]Hsin-Chia Yang et al, Breast Ultrasound Computer-Aided Diagnosis Using Both Acoustic and Image Features[C],2007 IEEE Ultrasonics Symposium
[15]Seok Min Han, Hak Jong Lee and Jin Young Choi, Prostate Cancer Detection using Texture and Clinical Features in Ultrasound Image[C], Proceedings of the 2007 International Conference on Information Acquisition
[16]J. E. Wilhjelm, L. M. Gronholdt, B. Wiebe, S. K. Jespersen, L. K. Hansen, and H. Sillesen, Quantitative analysis of ultrasound B-mode images of carotid atherosclerotic plaque:Correlation with visual classification and histological examination[J], IEEE Trans. Med. Imag.,vol.17, pp.910-922, Dec.1998.
[17]C. I. Christodoulou*, C. S. Pattichis et al, Texture-Based Classification of Atherosclerotic Carotid Plaques[J], IEEE Trans. Med. Imag., vol.22, NO.7, pp. 902-912, JULY 2003
[18]Marek R. Ogiela, Ryszard Tadeusiewicz, Syntactic pattern recognition for X-ray diagnosis of pancreatic cancer[J], IEEE ENGINEERING IN MEDICINE AND BIOLOGY, pp.94-104, November/December 2000
[19]R. M. Haralick, K. Shanmugam, and I. Dinstein, Texture features for image classification[J], IEEE Trans. Syst., Man, Cybern, vol. SMC-3, pp.610-621, Nov. 1973.
[20]J. S. Weszka, C. R. Dyer, and A. Rosenfield, A comparative study of texture measures for terrain classification[J], IEEE Trans. Syst., Man, Cybern., vol. SMC-6, Apr.1976.
[21]M. Amadasun and R. King, Textural features corresponding to textural properties[J], IEEE Trans. Syst., Man, Cybern., vol.19, pp.1264,269-1274,285, Sept./Oct.1989
[22]K. I. Laws, Rapid texture identification[C], Proc. SPIE, vol.238, pp.376-380, 1980.
[23]G. O. Lendaris and G L. Stanley. Diffraction pattern sampling for automatic pattern recognition[C]. Proc IEEE, vol.58, pp.198-216,1970.
[24]TIEN C. HSIA, A Note on Invariant Moments in Image Processing[J], IEEE Trans Syst. Man Cybern, vol. SMC-I1, NO.12, DECEMBER 1981
[25]林其忠,余建国等.乳腺肿瘤超声图像的特征分析[J],仪器仪表学报,2006,27(6),pp.744-746
[26]边肇祺,张学工等.模式识别[M].北京：清华大学出版社,2000
[27]Andrew R. Webb.统计模式识别(第二版)[M].北京：电子工业出版社,2004
[28]B. B. Mandelbrot, The Fractal Geometry of Nature[M]. San Francisco, CA: Freeman,1982.
[29]李杰,刘金国,分形维数及其在图象块分类中的应用[J],长春大学学报,200111(2),pp.7-9.
[30]C. C. Chen, J. S. Daponte, and M. D. Fox, Fractal feature analysis and classification in medical imaging[J], IEEE Trans. Med. Imag., vol.6, pp.133-142, June 1989.
[31]A. P. Pentland, Fractal based description of natural scenes[J], IEEE Trans. Pattern. Anal. Mach. Intell., vol. PAMI-6, no.6, pp.661-674, Jun.1984.
[32]S. Peleg, J. Naor, R. Hartley, and D. Avnir, Multiple resolution texture analysis and classification[J], IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-6, no.6, pp. 518-523, Jun.1984.
[33]Y. Xia, D. Feng and R. Zhao, Morphology-Based multifractal estimation for texture segmentation [J], IEEE Trans. Image Processing, vol.15, pp.614-623, Mar. 2006.
[34]N. Sarkar and B. B. Chaudhuri, An efficient differential box-counting approach to compute fractal dimension of image[J], IEEE Trans Syst. Man Cybern., vol.24, no.1, pp.115-120, Jan.1994.
[35]B. B. Chaudhuri and N. Sarkar, Texture segmentation using fractal dimension[J], IEEE Trans. Pattern Anal. Mach. Intell., vol.17, no.1, pp.72-77, Jan.1995.
[36]Gu Zuhan, Lee Sh. Optical implementation of the Hotelling trace criterion for image classification [J]. Opt Eng,1984,23:727-731.
[37]Devijver PA, Kittler J. Pattern recognition:a statistical approach [M]. New Jersey: Prentice Hall,1982.
[38]M.Pardo and G. Sberveglieri, Learning from data:a tutorial with emphasis on modern pattern recognition methods[J], IEEE Sensors Journal, vol.2, pp.203-217, June 2003
[39]Simon Haykini,神经网络原理[M],北京：机械工业出版社,2004,pp 229-252
[40]Y. Freund, Boosting a weak learning algorithm by majority[J], Inform. Comput., vol.121 no.2, pp.256-285,1998
[41]Y. Freund and R. E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting[J], J. Comput. Syst. Sci., vol.55, no.1, pp.
119-139,1997
[42]Vezhnevets A, Vezhnevets V. Modest AdaBoost-teaching AdaBoost to generalize better [EB/OL]. http://graphics.cs.msu.ru/en/publications/text/gc2005vv.pdf
[43]GML AdaBoost Matlab Toolbox[CP] http://research.graphicon.ru/machine-learning/gml-adaboost-matlab-toolbox.html
[44]Hocke M, Schulze E, Gottschalk P, et al. Contrast-enhanced endoscopic ultrasound in discrimination between focal pancreatitis and pancreatic cancer[J]. World J Gastroenterol,2006,12(2):246-250.
[45]Wang L. Feature Selection with Kernel Class Separability [J]. IEEE Trans Pattern Anal Mach. Intell., 2008,30(9):1534-1546
[46]Liu H, Yu L. Toward Integrating Feature Selection Algorithms for Classification and Clustering[J]. IEEE Trans. Knowledge and Data Eng,2005,17(4):491-502
[47]Narendra PM, Fukunaga K. A Branch and Bound Algorithm for Feature Subset Selection[J].IEEE Trans. Computer,1977,26(9):917-922
[48]Liu H, Motoda H. Featue Selection for Knowledge Discovery and Data Mining [M]. Boston:Kluwer Academic,1998
[49]Busetti F. Simulated annealing overview [EB/OL]. www.geocities.com/francorbusetti/saweb.pdf
[50]C.H. Wu, Y.N. Sun. Segmentation of kidney from ultrasound B-mode images with texture-based classification[J]. Computer Methods and Programs in Biomedicine. Dec.,2006,84(2-3):114-123.
[51]Muller KR, Mika S, Ratsch G, et al. An Introduction to Kernel-Based Learning Algorithms[J]. IEEE Trans.. Neural Networks,2001,12(2):181-201
[52]Weston J, Mukherjee S, Chapelle O, et al. Feature Selection for SVMs[C]. Advances in Nerual Information Processing Systems 13—Proc. Ann. Conf. Neural Information Processing Systems(NIPS'00), T.K. Leen, T.G. Dietterich, and V. Tresp, eds., pp.668-674, MIT Press,2000
[53]蔡哲元,余建国,张敏敏,金震东,胰腺内镜超声图像纹理特征提取与分类研究[J],《生物医学工程学进展》,2008,29(3)：141-145
[54]C.H.Chen, Statistical Pattern Recognition[M], Hayden(Sparton Books), New York,1973
[55]陈水利,李敬功等,模糊集理论及其应用[M].北京：科学出版社,2005
[56]彭复员,余西等,基于分形特征的水下图像模糊分类[J],仪器仪表学报,200526(8),pp.654-656
[2]汪毅,胰腺癌早期诊断的现状与进展[J],癌症进展杂志2006年7月第4卷第4期,pp.327-332
[3]金震东,李兆申,消化超声内镜学[M],北京：科学出版社,2006
[4]张定国,超声内镜对胰腺疾病的诊断价值[J],国际内科学杂志2007年3月第34卷第3期,pp.159-162
[5]K. Ogawa, M. Fukushima, K. Kubota, and N. Hisa, Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural network[J], IEEE Trans. Nucl. Sci., vol.45, pp.3069-3074, Dec.1998.
[6]C. M. Wu, Y. C. Chen, and K. S. Hsieh, Texture features for classification of ultrasonic liver images[J], IEEE Trans. Med. Imag., vol.11, pp.141-152, June 1992.
[7]A. Mojsilovic', M. Popovic', S. Markovic', and M. Krstic', Characterization of visually similar diffuse diseases from B-scan liver images using nonseparable wavelet transform[J], IEEE Trans. Med Imag., vol.17, pp.541-549, Aug.1998.
[8]Wen-Li Lee, Yung-Chang Chen, and Kai-Sheng Hsieh, Ultrasonic Liver Tissues Classification by Fractal Feature Vector Based on M-Band Wavelet Transform[J], IEEE Trans. Med. Imag., vol.22, pp.382-392, Mar.2003.
[9]Du-Yih Tsai and Yongbum Lee, Fuzzy-reasoning-based-diagnosis scheme for automated classification of heart disease from ultrasonic images[C],2001 IEEE International Fuzzy System Conference
[10]Du-Yih Tsai and Shinji Watanabe, A Method for Optimization of Fuzzy Reasoning by Genetic Algorithms and Its Application to Discrimination of Myocardial Heart Disease[J], IEEE Trans. Nucl. Sci., VOL.46, pp.2239-2246, NO.6, DECEMBER 1999
[11]D.R. Chen, R.F. Chang and Y.L. Huang. Breast cancer diagnosis using self-organizing map for sonography[J]. Ultrasound Med Biol.,2000,3:405-411.
[12]W.J. Kuo, R.F. Chang and W.K. Moon et al. Computer-aided diagnosis of breast tumors with different us systems[J]. Acad. Radiol.,2002,9:793-799
[13]R.F. Chang, C.J. Chen and M.F. Ho. Breast ultrasound image classification using fractal analysis[C].2004 Proceedings of the Fourth IEEE Symposium on Bioinformatics and Bioengineering
[14]Hsin-Chia Yang et al, Breast Ultrasound Computer-Aided Diagnosis Using Both Acoustic and Image Features[C],2007 IEEE Ultrasonics Symposium
[15]Seok Min Han, Hak Jong Lee and Jin Young Choi, Prostate Cancer Detection using Texture and Clinical Features in Ultrasound Image[C], Proceedings of the 2007 International Conference on Information Acquisition
[16]J. E. Wilhjelm, L. M. Gronholdt, B. Wiebe, S. K. Jespersen, L. K. Hansen, and H. Sillesen, Quantitative analysis of ultrasound B-mode images of carotid atherosclerotic plaque:Correlation with visual classification and histological examination[J], IEEE Trans. Med. Imag.,vol.17, pp.910-922, Dec.1998.
[17]C. I. Christodoulou*, C. S. Pattichis et al, Texture-Based Classification of Atherosclerotic Carotid Plaques[J], IEEE Trans. Med. Imag., vol.22, NO.7, pp. 902-912, JULY 2003
[18]Marek R. Ogiela, Ryszard Tadeusiewicz, Syntactic pattern recognition for X-ray diagnosis of pancreatic cancer[J], IEEE ENGINEERING IN MEDICINE AND BIOLOGY, pp.94-104, November/December 2000
[19]R. M. Haralick, K. Shanmugam, and I. Dinstein, Texture features for image classification[J], IEEE Trans. Syst., Man, Cybern, vol. SMC-3, pp.610-621, Nov. 1973.
[20]J. S. Weszka, C. R. Dyer, and A. Rosenfield, A comparative study of texture measures for terrain classification[J], IEEE Trans. Syst., Man, Cybern., vol. SMC-6, Apr.1976.
[21]M. Amadasun and R. King, Textural features corresponding to textural properties[J], IEEE Trans. Syst., Man, Cybern., vol.19, pp.1264,269-1274,285, Sept./Oct.1989
[22]K. I. Laws, Rapid texture identification[C], Proc. SPIE, vol.238, pp.376-380, 1980.
[23]G. O. Lendaris and G L. Stanley. Diffraction pattern sampling for automatic pattern recognition[C]. Proc IEEE, vol.58, pp.198-216,1970.
[24]TIEN C. HSIA, A Note on Invariant Moments in Image Processing[J], IEEE Trans Syst. Man Cybern, vol. SMC-I1, NO.12, DECEMBER 1981
[25]林其忠,余建国等.乳腺肿瘤超声图像的特征分析[J],仪器仪表学报,2006,27(6),pp.744-746
[26]边肇祺,张学工等.模式识别[M].北京：清华大学出版社,2000
[27]Andrew R. Webb.统计模式识别(第二版)[M].北京：电子工业出版社,2004
[28]B. B. Mandelbrot, The Fractal Geometry of Nature[M]. San Francisco, CA: Freeman,1982.
[29]李杰,刘金国,分形维数及其在图象块分类中的应用[J],长春大学学报,200111(2),pp.7-9.
[30]C. C. Chen, J. S. Daponte, and M. D. Fox, Fractal feature analysis and classification in medical imaging[J], IEEE Trans. Med. Imag., vol.6, pp.133-142, June 1989.
[31]A. P. Pentland, Fractal based description of natural scenes[J], IEEE Trans. Pattern. Anal. Mach. Intell., vol. PAMI-6, no.6, pp.661-674, Jun.1984.
[32]S. Peleg, J. Naor, R. Hartley, and D. Avnir, Multiple resolution texture analysis and classification[J], IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-6, no.6, pp. 518-523, Jun.1984.
[33]Y. Xia, D. Feng and R. Zhao, Morphology-Based multifractal estimation for texture segmentation [J], IEEE Trans. Image Processing, vol.15, pp.614-623, Mar. 2006.
[34]N. Sarkar and B. B. Chaudhuri, An efficient differential box-counting approach to compute fractal dimension of image[J], IEEE Trans Syst. Man Cybern., vol.24, no.1, pp.115-120, Jan.1994.
[35]B. B. Chaudhuri and N. Sarkar, Texture segmentation using fractal dimension[J], IEEE Trans. Pattern Anal. Mach. Intell., vol.17, no.1, pp.72-77, Jan.1995.
[36]Gu Zuhan, Lee Sh. Optical implementation of the Hotelling trace criterion for image classification [J]. Opt Eng,1984,23:727-731.
[37]Devijver PA, Kittler J. Pattern recognition:a statistical approach [M]. New Jersey: Prentice Hall,1982.
[38]M.Pardo and G. Sberveglieri, Learning from data:a tutorial with emphasis on modern pattern recognition methods[J], IEEE Sensors Journal, vol.2, pp.203-217, June 2003
[39]Simon Haykini,神经网络原理[M],北京：机械工业出版社,2004,pp 229-252
[40]Y. Freund, Boosting a weak learning algorithm by majority[J], Inform. Comput., vol.121 no.2, pp.256-285,1998
[41]Y. Freund and R. E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting[J], J. Comput. Syst. Sci., vol.55, no.1, pp.
119-139,1997
[42]Vezhnevets A, Vezhnevets V. Modest AdaBoost-teaching AdaBoost to generalize better [EB/OL]. http://graphics.cs.msu.ru/en/publications/text/gc2005vv.pdf
[43]GML AdaBoost Matlab Toolbox[CP] http://research.graphicon.ru/machine-learning/gml-adaboost-matlab-toolbox.html
[44]Hocke M, Schulze E, Gottschalk P, et al. Contrast-enhanced endoscopic ultrasound in discrimination between focal pancreatitis and pancreatic cancer[J]. World J Gastroenterol,2006,12(2):246-250.
[45]Wang L. Feature Selection with Kernel Class Separability [J]. IEEE Trans Pattern Anal Mach. Intell., 2008,30(9):1534-1546
[46]Liu H, Yu L. Toward Integrating Feature Selection Algorithms for Classification and Clustering[J]. IEEE Trans. Knowledge and Data Eng,2005,17(4):491-502
[47]Narendra PM, Fukunaga K. A Branch and Bound Algorithm for Feature Subset Selection[J].IEEE Trans. Computer,1977,26(9):917-922
[48]Liu H, Motoda H. Featue Selection for Knowledge Discovery and Data Mining [M]. Boston:Kluwer Academic,1998
[49]Busetti F. Simulated annealing overview [EB/OL]. www.geocities.com/francorbusetti/saweb.pdf
[50]C.H. Wu, Y.N. Sun. Segmentation of kidney from ultrasound B-mode images with texture-based classification[J]. Computer Methods and Programs in Biomedicine. Dec.,2006,84(2-3):114-123.
[51]Muller KR, Mika S, Ratsch G, et al. An Introduction to Kernel-Based Learning Algorithms[J]. IEEE Trans.. Neural Networks,2001,12(2):181-201
[52]Weston J, Mukherjee S, Chapelle O, et al. Feature Selection for SVMs[C]. Advances in Nerual Information Processing Systems 13—Proc. Ann. Conf. Neural Information Processing Systems(NIPS'00), T.K. Leen, T.G. Dietterich, and V. Tresp, eds., pp.668-674, MIT Press,2000
[53]蔡哲元,余建国,张敏敏,金震东,胰腺内镜超声图像纹理特征提取与分类研究[J],《生物医学工程学进展》,2008,29(3)：141-145
[54]C.H.Chen, Statistical Pattern Recognition[M], Hayden(Sparton Books), New York,1973
[55]陈水利,李敬功等,模糊集理论及其应用[M].北京：科学出版社,2005
[56]彭复员,余西等,基于分形特征的水下图像模糊分类[J],仪器仪表学报,200526(8),pp.654-656