基于双模态乳腺超声图像的良恶性分类及其关键技术研究
|
摘要
乳腺癌是当今一种在全世界女性当中发病率最高的恶性肿瘤疾病。早期检查是预防乳腺癌的一个非常重要的手段。由于性价比高、无放射性、副作用小等优点，超声检查被广泛应用于乳腺癌的早期诊断中。为了提高医生对乳腺超声检查的客观性和诊断效率，计算机辅助诊断系统应运而生。目前基于乳腺超声图像的计算机辅助诊断普遍采用单帧B超图像对目标的几何特征、边界特征及纹理等特征进行提取和分类。但是，由于人体体位移动、生理变化、超声声像复杂多样、良恶性肿块在超声声像上存在不同程度的交叉和重叠，单帧的特征分析必然影响诊断的准确率。此外，单一模态的图像往往不能提供临床诊断中所需要的足够信息，因此需要将不同模态的图像信息进行融合从而进行全面和综合的分析。
为了克服单帧图像和单一模态特征的片面性，本文提出利用B型超声图像中的静态特征和彩色多普勒超声图像序列中的动态特征相结合的方式对肿块的良恶性进行综合分析。其中对图像进行有效的分割、配准和描述图像序列中的运动信息是静态图像和动态图像序列特征提取的核心问题。近年来，这些技术经历了深入和广泛的研究，但是在对于乳腺超声图像的处理方面仍存在一些尚未解决的关键问题。本文针对不同模态图像的特点，对乳腺超声图像分割、乳腺超声图像配准和彩色多普勒超声图像序列的特征提取等核心问题展开了相关的研究。
本文所完成的工作和主要创新点如下：
(1)对基于细胞自动机原理的乳腺超声图像分割方法进行研究。乳腺超声图像中的高噪声、复杂结构、模糊边界等因素是影响图像分割效果的主要原因。为解决上述问题，本文根据细胞自动机的能量传播机制，采用能量下降策略反映图像中像素点之间的空间信息，并提出种子点比较函数和局部纹理特征比较函数分别对图像的全局信息差异和局部信息差异进行建模。在此基础上，本文采用Von Neumann邻域系统和Moore邻域系统相结合的方式作为细胞自动机的演化环境，并将自适应邻域准则应用到Moore邻域系统中用来进一步地抑制噪声的干扰。该分割算法有助于识别图像中的模糊边界，对噪声具有鲁棒性，能够在较为简单的初始条件下准确地对乳腺超声图像进行分割。
(2)对基于光流场的全自动乳腺超声图像配准方法进行研究。为了克服乳腺超声图像高噪声、目标结构复杂等因素的干扰，本文将惯性原理应用到配准过程中，并产生一个能够使像素点在短时间内的运动过程中保持一个原有运动倾向的惯性力，从而克服运动过程中所受噪声点的干扰。在此基础上，本文根据牛顿第二定律思想，在每次迭代过程中利用惯性力逐步地改变合外力的大小和方向，进而融入到光流场的计算方程中对每个像素点的加速度重新进行估计。此外，本文还采用牛顿第三定律的思想对算法的收敛速度进行提高。文中算法有助于在克服噪声干扰的同时保留图像的细节，并能够快速和准确地对乳腺超声图像进行配准。
(3)对基于B超图像和彩色多普勒超声图像序列的乳腺肿块分类方法进行研究。本文首先采用颜色矩、颜色信息熵等不同的统计方法对血流的形态学信息进行建模。为提取血流动力学特征，本文首先对每个图像序列下的不同的血流信号位置进行了配准。然后结合医学背景知识，采用图像分格法模拟临床诊断中的取样容积，并根据彩色多普勒成像原理，从每个窗口内产生一个离散多普勒波形信号，进而对一系列重要的血流动力学特征进行建模。此外，本文提出一个“速度聚合向量”方法自动地寻找局部血流动力学特征提取的感兴趣区域。最后，将这些特征输入到支持向量机中进行肿瘤良恶性的划分。本文提取的特征提取策略有助于提高乳腺超声计算机辅助诊断的精度，同时降低误诊率和漏诊率。
Breast cancer is one of the most common cancers and affects women’s healthseriously. Early detection is an effective way to control the disease. Breastultrasound imaging has become one of the most prevalent and popular approachesfor breast cancer diagnosis due to the fact that it is radiation-free, non-invasive,painless, cost-effective and portable. In order to improve the effectiveness andaccuracy, computer-aided diagnostic (CAD) techniques are more and more appliedto clinical practice. Existing classification methods usually extract the geometricfeatures, boundary features and texture features from a single frame captured fromB-Mode ultrasound video. However, due to body position changes, physiologicalchanges, complexity and diversity of ultrasound imaging, cross and overlap withbenign and malignant tumors, analyzing the image with the features extracted fromthe single frame will affect the diagnostic accuracy inevitably. In addition, singlemode image can not provide enough clinic information; therefore, it is necessary tofuse the image with different model to achieve a comprehensive and synthesizedanalysis.
To overcome the one-sidedness of single mode image, this dissertationproposed to integrate the features of B-Mode ultrasound image and color Dopplerultrasound image sequence to analyze the benign and malignant breast tumorsynthetically. Wherein, image segmentation, image registration and describing thedynamic information of image sequence are the key problems of feature extractionfrom static image and dynamic image sequence which have been well studied.However, there are still problems in processing of breast ultrasound images.According to the different image characteristic, this dissertation proposed severalmethods according to a series of conventional processes including imagesegmentation, image registration, feature extraction and classification to solve theproblems above to the breast ultrasound images.
The main research work and contribution of this dissertation are:
(1) A novel breast ultrasound (BUS) image segmentation algorithm based oncellular automata is studied. Due to high noise, complicate structure and blurryboundary, breast ultrasound image segmentation is a difficult task. To overcome the problems, an energy decrease strategy is used for modeling the spatial relationinformation of pixels according to the energy transition principle of cellularautomata. Then, a seed information comparison function and a texture informationcomparison function are proposed for modeling the global image informationdifference and local image information difference. In addition, two neighborhoodsystems (von Neumann and Moore neighborhood systems) are integrated as theevolution environment, and a similarity-based criterion is used for suppressing noiseand reducing computation complexity. The proposed method is helpful to handleBUS image with blurry boundaries and low contrast well, segment BUS imageaccurately and effectively within a simple initial condition.
(2) A fully automatic non-rigid image registration algorithm based on opticalflow principle is studied for registration of BUS images. To overcome the affectionof speckle noise, complicate structure of BUS image, this dissertation proposed toapply the inertia principle to the image registration, and an “inertia force” derivedfrom the local motion trend of pixels in a Moore neighborhood system is producedand integrated into optical flow equation by the Newton’s second law to estimate theacceleration direction, which is helpful to handle the speckle noise and preserve thegeometric continuity of image. In addition, the proposed method integrated the ideaof Newton’s second law to accelerate the convergence speed. The proposed methodis helpful to register ultrasound images efficiently, robust to noise, quickly andautomatically.
(3) A breast tumor classification method based on B-Mode ultrasound imageand color Doppler image sequence is studied. First, the color moment and colorentropy methods are utilized for modeling the vascularity features. For extractinghemodynamic features, an image registration method is utilized for mapping theposition of corresponding blood signals in different phases. Then the color Dopplerimage is divided into non-overlapping lattices. From each lattice, a discrete Dopplerwaveform is constructed from the registration results and several importanthemodynamic features are extracted. Furthermore, a velocity coherence vectormethod is proposed to design to the region of interest for extracting the localhemodynamic features. Finally, these features are employed to discriminate benignmasses from malignant masses by using the support vector machine classifier. Theproposed method is helpful to improve the true-positive and decrease the false-positive diagnostic rate, which is useful for reducing the unnecessary biopsyand death rate.
为了克服单帧图像和单一模态特征的片面性，本文提出利用B型超声图像中的静态特征和彩色多普勒超声图像序列中的动态特征相结合的方式对肿块的良恶性进行综合分析。其中对图像进行有效的分割、配准和描述图像序列中的运动信息是静态图像和动态图像序列特征提取的核心问题。近年来，这些技术经历了深入和广泛的研究，但是在对于乳腺超声图像的处理方面仍存在一些尚未解决的关键问题。本文针对不同模态图像的特点，对乳腺超声图像分割、乳腺超声图像配准和彩色多普勒超声图像序列的特征提取等核心问题展开了相关的研究。
本文所完成的工作和主要创新点如下：
(1)对基于细胞自动机原理的乳腺超声图像分割方法进行研究。乳腺超声图像中的高噪声、复杂结构、模糊边界等因素是影响图像分割效果的主要原因。为解决上述问题，本文根据细胞自动机的能量传播机制，采用能量下降策略反映图像中像素点之间的空间信息，并提出种子点比较函数和局部纹理特征比较函数分别对图像的全局信息差异和局部信息差异进行建模。在此基础上，本文采用Von Neumann邻域系统和Moore邻域系统相结合的方式作为细胞自动机的演化环境，并将自适应邻域准则应用到Moore邻域系统中用来进一步地抑制噪声的干扰。该分割算法有助于识别图像中的模糊边界，对噪声具有鲁棒性，能够在较为简单的初始条件下准确地对乳腺超声图像进行分割。
(2)对基于光流场的全自动乳腺超声图像配准方法进行研究。为了克服乳腺超声图像高噪声、目标结构复杂等因素的干扰，本文将惯性原理应用到配准过程中，并产生一个能够使像素点在短时间内的运动过程中保持一个原有运动倾向的惯性力，从而克服运动过程中所受噪声点的干扰。在此基础上，本文根据牛顿第二定律思想，在每次迭代过程中利用惯性力逐步地改变合外力的大小和方向，进而融入到光流场的计算方程中对每个像素点的加速度重新进行估计。此外，本文还采用牛顿第三定律的思想对算法的收敛速度进行提高。文中算法有助于在克服噪声干扰的同时保留图像的细节，并能够快速和准确地对乳腺超声图像进行配准。
(3)对基于B超图像和彩色多普勒超声图像序列的乳腺肿块分类方法进行研究。本文首先采用颜色矩、颜色信息熵等不同的统计方法对血流的形态学信息进行建模。为提取血流动力学特征，本文首先对每个图像序列下的不同的血流信号位置进行了配准。然后结合医学背景知识，采用图像分格法模拟临床诊断中的取样容积，并根据彩色多普勒成像原理，从每个窗口内产生一个离散多普勒波形信号，进而对一系列重要的血流动力学特征进行建模。此外，本文提出一个“速度聚合向量”方法自动地寻找局部血流动力学特征提取的感兴趣区域。最后，将这些特征输入到支持向量机中进行肿瘤良恶性的划分。本文提取的特征提取策略有助于提高乳腺超声计算机辅助诊断的精度，同时降低误诊率和漏诊率。
Breast cancer is one of the most common cancers and affects women’s healthseriously. Early detection is an effective way to control the disease. Breastultrasound imaging has become one of the most prevalent and popular approachesfor breast cancer diagnosis due to the fact that it is radiation-free, non-invasive,painless, cost-effective and portable. In order to improve the effectiveness andaccuracy, computer-aided diagnostic (CAD) techniques are more and more appliedto clinical practice. Existing classification methods usually extract the geometricfeatures, boundary features and texture features from a single frame captured fromB-Mode ultrasound video. However, due to body position changes, physiologicalchanges, complexity and diversity of ultrasound imaging, cross and overlap withbenign and malignant tumors, analyzing the image with the features extracted fromthe single frame will affect the diagnostic accuracy inevitably. In addition, singlemode image can not provide enough clinic information; therefore, it is necessary tofuse the image with different model to achieve a comprehensive and synthesizedanalysis.
To overcome the one-sidedness of single mode image, this dissertationproposed to integrate the features of B-Mode ultrasound image and color Dopplerultrasound image sequence to analyze the benign and malignant breast tumorsynthetically. Wherein, image segmentation, image registration and describing thedynamic information of image sequence are the key problems of feature extractionfrom static image and dynamic image sequence which have been well studied.However, there are still problems in processing of breast ultrasound images.According to the different image characteristic, this dissertation proposed severalmethods according to a series of conventional processes including imagesegmentation, image registration, feature extraction and classification to solve theproblems above to the breast ultrasound images.
The main research work and contribution of this dissertation are:
(1) A novel breast ultrasound (BUS) image segmentation algorithm based oncellular automata is studied. Due to high noise, complicate structure and blurryboundary, breast ultrasound image segmentation is a difficult task. To overcome the problems, an energy decrease strategy is used for modeling the spatial relationinformation of pixels according to the energy transition principle of cellularautomata. Then, a seed information comparison function and a texture informationcomparison function are proposed for modeling the global image informationdifference and local image information difference. In addition, two neighborhoodsystems (von Neumann and Moore neighborhood systems) are integrated as theevolution environment, and a similarity-based criterion is used for suppressing noiseand reducing computation complexity. The proposed method is helpful to handleBUS image with blurry boundaries and low contrast well, segment BUS imageaccurately and effectively within a simple initial condition.
(2) A fully automatic non-rigid image registration algorithm based on opticalflow principle is studied for registration of BUS images. To overcome the affectionof speckle noise, complicate structure of BUS image, this dissertation proposed toapply the inertia principle to the image registration, and an “inertia force” derivedfrom the local motion trend of pixels in a Moore neighborhood system is producedand integrated into optical flow equation by the Newton’s second law to estimate theacceleration direction, which is helpful to handle the speckle noise and preserve thegeometric continuity of image. In addition, the proposed method integrated the ideaof Newton’s second law to accelerate the convergence speed. The proposed methodis helpful to register ultrasound images efficiently, robust to noise, quickly andautomatically.
(3) A breast tumor classification method based on B-Mode ultrasound imageand color Doppler image sequence is studied. First, the color moment and colorentropy methods are utilized for modeling the vascularity features. For extractinghemodynamic features, an image registration method is utilized for mapping theposition of corresponding blood signals in different phases. Then the color Dopplerimage is divided into non-overlapping lattices. From each lattice, a discrete Dopplerwaveform is constructed from the registration results and several importanthemodynamic features are extracted. Furthermore, a velocity coherence vectormethod is proposed to design to the region of interest for extracting the localhemodynamic features. Finally, these features are employed to discriminate benignmasses from malignant masses by using the support vector machine classifier. Theproposed method is helpful to improve the true-positive and decrease the false-positive diagnostic rate, which is useful for reducing the unnecessary biopsyand death rate.
引文
[1] R. Siegel, D. Naishadham, A. Jernal. Cancer Statistics2012, CA: A CancerJournal for Clinicians.2012,62(1):10-29
[2] A. C. Society. Breast Cancer Facts&Figures-2002. Atlanta GA: AmericanCancer Society.2002
[3] S. Bothoral,B. B. Meunier, S. Muller. A fuzzy logic based approach forsemilogical analysis of microcalcification in mammographic images.Intemational Journal of Intelligent System,1997,12(11):819-848.
[4]刘刚，邵志敏．乳腺癌基础研究新进展．中国肿瘤，2002,(1)：31－35.
[5]孙强.乳腺癌的早期诊断.实用医学杂志.2007,23(1):1-3.
[6] K. Kaul, F. M. Daguilh. Early Detection of Breast Cancer: Is MammographyEnough. Hospital Physician.2002,9:49-55
[7] K. Kaul, F. M. Daguilh. Early Detection of Breast Cancer: Is MammographyEnough. Hospital Physician.2002,9:49-55
[8] H. D, Cheng, X. Shi, R. Min, et al: Approaches for automated detection andclassification of masses in mammograms. Pattern Recognition39(4):646–668,2006
[9] A. T. Stavros, D. Thickman, C. L. Rapp, et al. Solid breast nodules: use ofsonography to distinguish between benign and malignant lesions. Radiology.1995;196(1):123-134
[10] H. Madjar. Contrast ultrasound in breast tumor characterization: presentsituation and future tracks. European Radiology.2001,11(3),41-46.
[11]林铤,黄幼珍,陈汉荣,黄三菊.彩色多普勒超声鉴别诊断乳腺良、恶性肿瘤.中国超声诊断杂志.2004,5(5):340-343
[12]祝艳秋，杨光，徐文林，吴佳玲．彩色多普勒超声探查胸外侧动脉血流动力学参数对乳腺癌诊断价值的研究．中国医学影像技术，2007，23(10)：1481－1483.
[13] H. D. Cheng, J. Shan, W. Ju, Y. Guo, L. Zhang. Automated breast cancerdetection and classification using ultrasound images: A survey. PatternRecognition,2010.43(1):299-317
[14] C. M. Chen, Y. H. Chou, K. C. Han, et al. Breast lesions on sonograms:computer-aided diagnosis with nearly setting-independent features andartificial neural networks. Radiology.2003,226:504-514
[15] S. Joo, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solid breastnodules on ultrasound with digital image processing and artificial neuralnetwork. Proceedings of the26th Annual International Conference of the IEEEEMBS.2004
[16] S. Joo, Y. S. Yang, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solidbreast nodules: use of an artificial neural network based on multiplesonographic features. IEEE Trans. Med. Imag.2004,23:1292-1300
[17] K. Horsch, M. L. Giger, L. A. Venta, C. J. Vyborny. Automatic segmentationof breast lesions on ultrasound. Medical Physics,2001,28(8):1652-1659
[18] K. Drukker, M. L. Giger, C. J. Vyborny, et al. Computerized lesion andclassification detection on breast ultrasound. Academic Radiology.2004,11(5):526-535
[19] J. Shan, H. D. Cheng, Y. Wang. A completely automatic segmentation methodfor breast ultrasound images using region growing.11th Joint Conference onInformation Science.2008
[20] Y. J. Yu, S. T. Acton. Speckle reducing anisotropic diffusion. IEEE Trans.Image Processing.2002,11(11):1260-1270
[21] J. Massich, F. Meriaudeau, E. Perez, et al. Lesion segmentation in breastsonography. Digital Mammography, Lecture Notes in Computer Science.2010,LNCS6136:39-45
[22] H. P. Ng. S. H. Ong, K. W. C. Foong, et al. Medical image segmentation usingK-means clustering and improved watershed algorithm.2006IEEE SouthwestSymposium on Image Analysis and interpretation.2006,61-65
[23] Y. L. Huang, D. R. Chen. Watershed segmentation for breast tumor in2-Dsonography. Ultrasound in Medicine and Biology.2004,30(5):625-632
[24] S. H. Lewis. Detection of breast tumor candidates using marker-controlledwatershed segmentation and morphological analysis.2012IEEE SouthwestSymposium on Image Analysis and interpretation.2012,22-24
[25] A. Ahemd, O. Othman, R. Hamid, et al. Segmentation of breast ultrasoundimages using neural networks. Engineering Applications of Neural Networks:IFIP Advances in Information and Communication Technology.2011,363,260-269
[26] C. M. Chen, Y. H. Chou, C. S. K. Chen. Cell-Competition: a new segmentationalgorithm for multiple objects with irregular boundaries in ultrasound images.Ultrasound in Medicine and Biology.2005,31(2):1647-1664
[27] J. Z. Chen, C. M. Chen, Y. H. Chou, et al. Cell-based two-region competitionalgorithm with a MAP framework for boundary delineation of a series of2Dultrasound images. Ultrasound in Medicine and Biology.2007,33(10):1640-1650
[28] E. A. Ashton, K. J. Parker. Multiple resolution Bayesian segmentation ofultrasound images. Ultrasonic Imaging.1995,17:291-304
[29] D. Boukerroui, O. Basset, N. Gu, A. Baskurt. Multiresolution texture basedadaptive clustering algorithm for breast lesion segmentation. European Journalof Ultrasound,1998,8(2):135-144
[30] D. Boukerroui, O. Basset, A. Baskurt, G. Gimenez. A multiparametric andmultiresolution segmentation algorithm of3D ultrasonic data. IEEE Trans.Ultrason. Ferroelectrics Freq.Contr.2001,48(1):64-77
[31] D. Boukerroui, A. Baskurt, J. A. Noble, O. Basset. Segmentation of ultrasoundimages-multiresolution2D and3D algorithm based on global and localstatistics. Pattern Recognition Letter.2003,24(4):779-790
[32] G. Xiao, M. Brady, J. A. Noble, Y. Zhang. Segmentation of ultrasound B-modeimages with intensity inhomogeneity correction. IEEE Trans. Med. Imag.2002,21(1):48-57
[33] L. A. Christopher, E. J. Delp, C. R. Meyer, P. L. Carson.3-D Bayesianultrasound breast image segmentation using the EM/MPM algorithm.Proceedings of the2002IEEE International Symposium on BiomedicalImaging.2002
[34] M. Kass, A. Witkin, D. Terzopoulos. Snakes: active contour models.International Journal of Computer Vision,1988,1(4):321-331.
[35] D. R. Chen, R. F. Chang, W. J. Wu, W. K. Moon, W. L. Wu.3-D Breastultrasound segmentation using active contour model. Ultrasound in Medicineand Biology,2003,29(7):1017-1026
[36] R. F. Chang, W. J. Wu, W. K. Moon, W. M. Chen, W. Lee, D. R. Chen.Segmentation of breast tumor in three-dimensional ultrasound images usingthree-dimensional discrete active contour model. Ultrasound in Medicine andBiology.2003,29(11):1571-1581
[37] A. Madabhushi, D. N. Metaxas. Combining low-,high-level and empiricaldomain knowledge for automated segmentation of ultrasonic breast lesions.IEEE Trans. Med. Imag.2003,22(2):155-169
[38] A. K. Jurnaat, W. E. Zarina, W. A. Rahman, A. Ibrahim, R. Mahmud.Segmentation of masses from breast ultrasound images using parametric activecontour algorithm. International Conference on Mathematics EducationResearch2010.2010,8:640-647
[39] R. F. Chang, W. J. Wu, W. K. Moon, D. R. Chen. Automatic ultrasoundsegmentation and morphology based diagnosis of solid breast tumors. BreastCancer Research and Treatment,2005,89(2):179-185
[40] W. K. Moon, R. F. Chang, C. J. Chen, D. R. Chen, W. L. Chen. Solid breastmasses: classification with computer-aided analysis of continuous US images.Radiology,2005,236:458-464
[41] J. Perona, J. Malik. Scale-scape and edge-detection using anisotropic diffusion.IEEE Trans. Pattern Anal. Machine Intell.1990,12(7):629-639
[42] R. N. Czerwinski, D. L. Jones, W. D. O. B. Jr. Detection of lines andboundaries in speckle images–application to medical ultrasound. IEEE Trans.Med. Imag.1999,18(2):126-136
[43] B. Liu, H. D. Cheng, J. H. Huang, J. W. Tian, J. F. Liu, X. L. Tang. Automatedsegmentation of ultrasonic breast lesions using statistical texture classificationand active contour based on probability distance. Ultrasound Med. Biol.200935(8):1309-1324
[44] B. Liu, H. D. Cheng, J. H. Huang, J. W. Tian, X. L. Tang, J. F. Liu. Probabilitydensity difference-based active contour for ultrasound image segmentation.Pattern Recognition.201043:2028-2042
[45] C. K. Yeh, Y. S. Chen, W. C. Fan, Y. Y. Liao. A disk expansion segmentationmethod for ultrasonic breast lesions. Pattern Recognition,2009,42(5):596-606
[46] P. Abolmaesumi, M. R. Sirouspour. An interacting multiple model probabilisticdata association filter for cavity boundary extraction from ultrasound images.IEEE Trans.Med.Imag.2004,23(6):772-784
[47] H. M. Wu, H. H. Lu. Iterative sliced inverse regression for segmentation ofultrasound and MR images. Pattern Recognition.2007,40(12):3492-3502
[48] J. Yu, Y. Wang, P. Cheng, H. Xu. Two-dimensional fuzzy clustering forultrasound image segmentation.1st International Conference on Bioinformaticsand Biomedical Engineering.2007
[49]余锦华.超声图像处理新方法及其在产前诊断中的应用.复旦大学博士论文，2007
[50]刘海华，陈心浩，高智勇，谢长生.基于形态学操作和模糊聚类技术的超声图像分割.电子学报，2007，35(7):1306-1312
[51] J. A. Noble, D. Boukerroui. Ultrasound image segmentation: a survey. IEEETrans. Med. Imag.2006,25(8):987-1010
[52] B. Zitova, J. Flusser. Image registration methods, a survey. Image VisionComputing.2003,21,977-1000
[53] D. L. Hill, P. G. Batchelor, M. Holden, and D.J. Hawkes,"Medical imageregistration," Phys. Med. Biol.2001,46(3):1-45
[54] D. L. Collins, T. M. Peters, A. C. Evans. An Automated3D Non-LinearDeformation Procedure for Determination of Gross Morphoetric Variability inHuman Brain. Visualization in Biomedical Computing, Bellingham, WA,1994,2359:180-190
[55] R. P. Woods, S. R. Cherry, J. C. Mazziotta. Rapid Automated Algorithm forAligning and Reslicing PET Images. J. Comput. Assist. Tomogr.1992,16(4):620-633
[56] R. P. Woods, J. C. Mazziotta, S. R. Cherry. MRI-PET Registration withAutomated Algorithm. J. Comput. Assist. Tomogr.1993,17(4):536-546
[57] R. P. Woods, S. T. Grafton, C. J. Holmes, S. R. Cherry, J. C. Mazziotta.Automated Image Registration. I:General Methods and Intrasubject,Intramodality Validation. J. Comput. Assist. Tomogr.1998,22:141-154
[58] K. Rohr, H. S. Stiehl, H. S. R. Sprengel. Landmark-based elastic registrationusing approximating thin-plate splines, IEEE Trans. on Med. Imaging.1999,20(6):526-543
[59] D. Reuckert, L. I. Sonoda, C. Hayes. Nonrigid registration using free-Formdeformation: application to breast MRI images. IEEE Trans. on MedicalImaging.1999,18(8):712-721
[60] J. Kybic, M. Unser. Fast parametric elastic image registration, IEEE Trans onImage Processing.2003,12(11): l427-1442
[61]杨明星，庄天戈.一种非刚性医学图像的点配准方法.上海交通大学学报.2004，35(5)：775-778
[62] C. Broit. Optimal Registration of Deformed Images. Doctoral Dissertation.1981
[63] Y. Jin, Y. Shi, N. Jahanshad, et al.3D elastic registration improvesHARDI-derived fiber alignment and automated tract clustering.2011IEEEInternational Symposium on Biomedical Imaging.
[64] A. R. Mejia-Rodriguez, E. R. Arce-Santana, Scalco E, et al. Conf Proc IEEEEng Med Biol Soc.2011,8049-8052
[65] J. Chappelow, B. N. Bloch, N. Rofsky, et al. Elastic registration of multimodalprostate MRI and histology via multiattribute combined mutual information.Med. Phys.2011,38(4):2005-2018
[66] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Log-unbiased elastic imageregistration with spatial constraint for3D CT lung images. In Proc. of MedicalImage Understanding and Analysis.2010,147.
[67] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Elastic Registration of chest CTimages with log un-biased deformations and rigidity constraint. Proc. IEEEInternational Symposium on Biomedical Imaging (ISBI).2011,1235-1238
[68] G. E. Christensen, R. D. Rabbitt, M. Miller. Deformable Templates Using LargeDeformation Kinematics. IEEE Trans on Image Processing.1996,5(10):1435-1447
[69] G. Christensen, S. Joshi, M. Miller. Volumetric Transformation of BrainAnatomy. IEEE Trans on Medical Imaging.1997,16:864-877
[70] H. Lester, S. R. Arridge, K. M. Jansons, et al. Non-linear registration with thevariable viscosity fluid algorithm. In: Proceedings of16th InternationalConference on Information Processing in Medical Imaging,1999.238-251
[71] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Non-rigid chest image registrationwith preservation of topology and rigid structures.
[72] J. P. Thirion. Image matching as a diffusion process: an analogy withMaxwell’s demons. Med. Image Anal.1998,2,243-60
[73] P. Rogelj, S. Lovacic. Symmetric image registration. SPIE-Medical Imaging2003: Image Processing.2003,5032:334-343
[74] X. J. Gu, H. Pan, Y. Liang, et al. Implementation and evaluation of variousdemons deformable image registration algorithms on a GPU. Physics inMedicine and Biology.2010,55:207-219
[75] J. H. Woo, B. W. Hong, C. H. Hu, et al. Non-Rigid Ultrasound ImageRegistration Based on Intensity and Local Phase Information. J Sign ProcessSyst.2009,54:33-43
[76] P. Foroughi，P. Abolmaesumi. A modified HAMMER algorithm for deformableregistration of ultrasound images. International Congress Series.2005:236-241
[77]陈佃苹，彭玉华.一种基于特征向量的超声图像配准方法.计算机工程与应用.2010,46(14)：205-208.
[78]董海艳,王惠南,李虹.基于血管内超声图像序列的相角配准与边缘检测.中国图像图形学报.2007,12(6):1048-1054
[79] B. Cohen, I. Dinstein. New maximum likelihood motion estimation schemes fornoisy ultrasound images. Pattern Recognition.2002,35:455-463
[80] D. Boukerroui, J.A. Noble, M. Brady. Velocity Estimation in UltrasoundImages: a Block Matching Approach. In Proc. IPMI.2003,586-598
[81] A. Singh. Image-flow computation: An estimation-theoretic framework and aunified perspective. CVGIP: Image understanding.1992,65(2):152–177.
[82] Z. Wang, G. Slabaugh, G. Unal, et al. Registration of ultrasound images usingan information-theoretic feature detector.
[83] G. Hermosillo, C. ChefdHotel, O. Faugeras. Variational Methods forMultimodal Image Matching. International Journal of Computer Vision.2002,50(3):329-343.
[84]邵斌，唐娉，曾庆业，张送根，姚克纯.基于PC的实时超声全景成像系统中的图像配准.计算机工程与应用.2010,43(28):206-209
[85] M. J. Ledesma-Carbayo, J. Kybic, M. Desco, et al. Spatio-temporal nonrigidregistration for ultrasound cardiac motion estimation. IEEE Trans MedImaging.200524(9):1113-26
[86] A. V. Alvarenga, W. C. A. Pereira, A. F. C. Infantosi, C. M. D. Azevedo.Classification of breast tumors on ultrasound images using morphometricparameters. IEEE International Workshop on Intelligent SignalProcessing05’.2005.
[87] O. S. Soliman, A. E. Hassanien. A computer aided diagnosis system for breastcancer using support vector machine. Lecture Notes in Computer Science.2012,7413:106-115.
[88] P. Filipezuk, M. Kowal, A. Obuchowicz. Fuzzy Clustering and AdaptiveThresholding Based Segmentation Method for Breast Cancer Diagnosis.Computer Recognition systems, Advances in Intelligent and Soft Computing.2011,95:613-622
[89] S. F. Huang, R. F. Chang, D. R. Chen, W. K. Moon. Characterization ofspeculation on ultrasound lesions. IEEE Trans. Med. Imag.2004,23(1):111-121
[90] D. R. Chen, R. F. Chang, Y. L. Huang. Breast cancer diagnosis usingself-organizing map for sonography. Ultrasound in Medicine and Biology.2000,26(3):405-411
[91] Y. L. Huang, D. R. Chen. Support vector machines in sonography applicationto decision making in the diagnosis of breast cancer. Clinical Imaging.2005,29:179-184
[92] Y. L. Huang, Y. G. Liu. Diagnosis of solid breast tumors with sonographictexture analysis.16th IPPR Conference on Computer Vision, Graphics andImage Processing.2003
[93] W. J. Kuo, R. F. Chang, D. R. Chen, C. C. Lee. Data mining with decision treesfor diagnosis of breast tumor in medical ultrasonic images. Breast CancerResearch and Treatment.2001,66:51-57
[94] R. Sivaramakrishna, K. A. Powell, M. L. Lieber, et al. Texture analysis oflesions in breast ultrasound images. Computerized Medical Imaging andGraphics.2002,26(5):303-307.
[95] N. Piliouras, I. Kalatzis, N. Dimitropoulos, D. Cavouras. Development of thecubic least squares mapping linear-kernel support vector machine classifier forimproving the characterization of breast lesions on ultrasound. ComputerizedMedical Imaging and Graphics.2004,28(5):247-255
[96] B. Liu, H. D. Cheng, J. H. Huang, X. L. Tang, J. F. Liu. Fully automatic andsegmentation-robust classification of breast tumors based on local textureanalysis. Pattern Recognition.2010,43(1):280-298
[97] K. Horsch, M. L. Giger. Computerized diagnosis of breast lesions on ultrasound.Medical Physics,2002,29(2):157-164
[98]V. D. Heiden, R. P. W. Duin, D. Ridder, et al. Classification, parameterestimation and state estimation: An engineering approach using Matlab.Oxford: Wiley.2004
[99] B. Sahnier, H. Chan, M. A. Roubidoux, et al. Malignant and benign breastmasses on3D volumetric images: effect of computer-aided diagnosis onradiologist accuracy. Radiology.2007,242(3):716-724.
[100]R. F. Chang, S. F. Huang, W. K. Moon, Y. H. Lee, D. R. Chen. Solid breastmasses: neural network analysis of vascular features at three-dimensionalpower Doppler US for benign or malignant classification. Radiology.2007,243(1):56-62.
[101] D. R. Chen, R. F. Chang, W. M. Chen, W. K. Moon. Computer-AidedDiagnosis for3-Dimensional Breast Ultrasonography. Arch Surg.2003,138(3):296-302.
[102] B. Sahiner, H. P. Chan, M. A. Roubidoux, et al. Malignant and benign breastmasses on3D US volumetric images: effect of computer-aided diagnosis onradiologist accuracy. Radiology.2007,242(3):716-724
[103] S. F. Huang, R. F. Chang, W. K. Moon, Y. H. Lee, D. R. Chen. Analysis oftumor vascularity using three-dimensional power Doppler ultrasound images.IEEE Trans. Med. Imag.2008,27(3):320-330
[104] R. F. Chang, S. F. Huang, W. K. Moon, Y. H. Lee, D. R. Chen. Solid breastmasses: neural network analysis of vascular features at three-dimensionalPower Doppler US of benign and malignant classification. Radiology.2007,243(1):56-62.
[105] Y. H. Hsiao, Y. L. Huang, S. J. Kuo, W. M. Liang, et al. Characterization ofbenign and malignant solid breast masses in harmonic3D power Dopplerimaging. European Journal of Radiology.2009,71(1),89-95
[106] S. T. Chen, Y. H. Hsiao, Y. L. Huang, et al. Comparative analysis of logisticregression, support vector machine and artificial neural network for thedifferential diagnosis of benign and malignant solid breast tumors by the use ofthree-dimensional power Doppler imaging. Korean J Radiol.2009,10(5):464-471
[107]W. M. Chen, R. F. Chang, S. J. Kuo, et al.3-D ultrasound texture classificationusing run difference matrix. Ultrasound Med Biol.2005,31(6):763-770.
[108] X. F. Diao, X. Y. Zhang, T. F. Wang, et al. Highly Sensitive Computer AidedDiagnosis System for Breast Tumor Based on Color Doppler Flow Images. J.Med. Syst.2011,35:801-809
[109] G. Rizzatto, R. Chersevani, G. Ralleigh. Contrast media in ultrasonographybasic principles and clinical applications: breast. Med. Radiol. Diagn. Imaging.2005,48(5),301–303
[110] J. Quartieri, N. E. Mastorakis, G. lannone, et al. Cellular Automata Applicationto Traffic Noise Control. Proceedings of the12th WSEAS InternationalConference on automatic control, modelling and simulation.2010,299-304
[111] K. Mirzaei, H. Motameni, Rasul Enayatifar. New method for edge detectionand de noising via fuzzy cellular automata. International Journal of PhysicalSciences,2011,6(13),3175-3180
[112] P. J. Selvapeter, W. Hordijk. Cellular automata for image noise filtering.Nature&Biologically Inspired Computing.2009,193-197
[113]陈炎雄,郝志峰,温尚清,杨晓伟.基于二维细胞自动机和中值运算的图像滤波方法.计算机辅助工程.2006,15(3)
[114] A. Popovici, D. Popovici. Cellular automata in image processing. FifteenthInternational Symposium on Mathematical Theory of Networks and Systems.2002
[115]惠周利,王鹏.细胞自动机在图像边缘检测中的应用.中国科技信息.2008,18:38-39
[116] G. Sahoo, T. Kumar, B. L. Raina, C. M. Bhatia. Text extraction andenhancement of binary images using cellular automata.
[117] C. Y. Wang, L. Cheng. Feature extraction of geographical image with statustransfer of cellular automata. Proceedings of the International Symposium onIntelligent Information Systems and Applications.2009,307-309
[118] V. Vezhnevets, V. Konouchine.“Grow cut”—interactive multi-label N-Dimage segmentation by cellular automata. Proceedings of Graphicon.2005,150-156
[119] J. Weszka，C. Dyer，A. Rosenfeld. A comparative study of texture measuresfor terrain classifications. IEEE Transactions on Systems, Man andCybernetics.1976,6(4):269-285
[120]D. Harwood, T. Ojala, M. Pietikinen, S. Kelman, L. Davis. Textureclassification by center-symmetric auto-correlation, using kullbackdiscrimination of distributions. Pattern Recognition Letters,1995,16(1):1-10
[121]P. A. Dondes, A. Rosenfeld. Pixel classification based on gray level and local“business”. IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(1):79-84
[122]H. Wang, L. Dong, J. O’Daniel, R. Mohan, et al. Validation of an accelerated‘demons’ algorithm for deformable image registration in radiation therapy.Phys. Med. Biol.2005,50:2887-2905
[123]X. B. Lin, T. S. Qiu, F. Nicolier, S. Ruan. An improved method of “demons”non-rigid image registration. ICSP2008Proceedings.1091-1094
[124]D. Yang, H. Li, D. A. Low, et al. A fast inverse consistent deformable imageregistration method based on symmetric optical flow computation. Phys. Med.Biol.2008,53:6135-6145
[125]L. Paninski. Estimation of entropy and mutual information. NeuralComputation.2003,15,1191-1253
[126]K. Jeongtae, A. F. Jeffrey. Image registration using robust correlation. IEEETransactions on medical imaging.2004,23(11),1430-1443.
[127]M. Roser, A. Geiger. Video-based raindrop detection for improved imageregistration.2009IEEE12th International Conference on Computer VisionWorkshops.2009,570-577
[128]B. D. Steinberg, D. L. Carlson, J. A. Birnbaum. Sonographic discriminationbetween benign and malignant breast lesions with use of disparity processing.Acad Radiol.2001,8(8):705-712
[129]W. K. Moon, R. F. Chang, C. J. Cheng, et al. Solid breast masses:classification with computer-aided analysis of continuous US images obtainedwith probe compression. Radiology.2005,236(2):458-464
[130]P. S. S. Rodrigues, G. A. Giraldi, R. F. Chang et al. Object tracking in imagesequence combining hausdorff distance, non-extensive entropy in level setformulation. Topics in Biomedical Engineering. International Book Series.2007,477-515
[131]贺礼，周康源，冯欢清，李传富，杨振森.乳腺超声图像序列的弹性特征病变分析.中国科学技术大学学报.2010,40(11):1108-1111
[132]E. Jessee, E. Wiebe. Visual perception and the hsv color system: Exploringcolor in the communications technology classroom. Technol. Teacher.2008,7-11.
[133]M. Strieke, M. Orengo. Similarity of color images. In: Proceedings of SPIEStorage and Retrieval for Image and Video Databas.1995,24(20):381-392.
[134]J. D. Sun, et al. Image retrieval based on color distribution entropy. Patternrecognition letters.2006,27(10),1122-1126.
[135]E. D. Ubeyli, I. Guler. Feature extraction from color Doppler ultrasoundsignals for automated diagnosis systems. Comp. Biol. Med.2005,35(9):735-764.
[136]S. Tascioglu, O. Ureten, Z. telatar. Impact of noise power uncertainty on theperformance of wideband spectrum segmentation. Radio engineering.2010,19(4):561-566
[137]K. H. Kang, Y. I. Yoon, J. S. Choi, et al. Additive texture informationextraction using color conherence vector. Proceedings of the7th WSEASInternational Conference on Multimedia Systems&Signal Processing.2007,15-17
[138]R. Gordon, R. M. Rangayyan. Feature enhancement of film mammogramsusing fixed and adaptive neighborhoods. Appl Opt.1984,23(4),560-564.
[139]A. Zollanvari, U. M. Braga-Neto, E. R. Dougherty. On the joint samplingdistribution between the actual classification error and the resubstitution andleave-one-out error estimators for linear classifiers. IEEE Transactions onInformation Theory.2010,56(2):784-804
[2] A. C. Society. Breast Cancer Facts&Figures-2002. Atlanta GA: AmericanCancer Society.2002
[3] S. Bothoral,B. B. Meunier, S. Muller. A fuzzy logic based approach forsemilogical analysis of microcalcification in mammographic images.Intemational Journal of Intelligent System,1997,12(11):819-848.
[4]刘刚，邵志敏．乳腺癌基础研究新进展．中国肿瘤，2002,(1)：31－35.
[5]孙强.乳腺癌的早期诊断.实用医学杂志.2007,23(1):1-3.
[6] K. Kaul, F. M. Daguilh. Early Detection of Breast Cancer: Is MammographyEnough. Hospital Physician.2002,9:49-55
[7] K. Kaul, F. M. Daguilh. Early Detection of Breast Cancer: Is MammographyEnough. Hospital Physician.2002,9:49-55
[8] H. D, Cheng, X. Shi, R. Min, et al: Approaches for automated detection andclassification of masses in mammograms. Pattern Recognition39(4):646–668,2006
[9] A. T. Stavros, D. Thickman, C. L. Rapp, et al. Solid breast nodules: use ofsonography to distinguish between benign and malignant lesions. Radiology.1995;196(1):123-134
[10] H. Madjar. Contrast ultrasound in breast tumor characterization: presentsituation and future tracks. European Radiology.2001,11(3),41-46.
[11]林铤,黄幼珍,陈汉荣,黄三菊.彩色多普勒超声鉴别诊断乳腺良、恶性肿瘤.中国超声诊断杂志.2004,5(5):340-343
[12]祝艳秋，杨光，徐文林，吴佳玲．彩色多普勒超声探查胸外侧动脉血流动力学参数对乳腺癌诊断价值的研究．中国医学影像技术，2007，23(10)：1481－1483.
[13] H. D. Cheng, J. Shan, W. Ju, Y. Guo, L. Zhang. Automated breast cancerdetection and classification using ultrasound images: A survey. PatternRecognition,2010.43(1):299-317
[14] C. M. Chen, Y. H. Chou, K. C. Han, et al. Breast lesions on sonograms:computer-aided diagnosis with nearly setting-independent features andartificial neural networks. Radiology.2003,226:504-514
[15] S. Joo, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solid breastnodules on ultrasound with digital image processing and artificial neuralnetwork. Proceedings of the26th Annual International Conference of the IEEEEMBS.2004
[16] S. Joo, Y. S. Yang, W. K. Moon, H. C. Kim. Computer-aided diagnosis of solidbreast nodules: use of an artificial neural network based on multiplesonographic features. IEEE Trans. Med. Imag.2004,23:1292-1300
[17] K. Horsch, M. L. Giger, L. A. Venta, C. J. Vyborny. Automatic segmentationof breast lesions on ultrasound. Medical Physics,2001,28(8):1652-1659
[18] K. Drukker, M. L. Giger, C. J. Vyborny, et al. Computerized lesion andclassification detection on breast ultrasound. Academic Radiology.2004,11(5):526-535
[19] J. Shan, H. D. Cheng, Y. Wang. A completely automatic segmentation methodfor breast ultrasound images using region growing.11th Joint Conference onInformation Science.2008
[20] Y. J. Yu, S. T. Acton. Speckle reducing anisotropic diffusion. IEEE Trans.Image Processing.2002,11(11):1260-1270
[21] J. Massich, F. Meriaudeau, E. Perez, et al. Lesion segmentation in breastsonography. Digital Mammography, Lecture Notes in Computer Science.2010,LNCS6136:39-45
[22] H. P. Ng. S. H. Ong, K. W. C. Foong, et al. Medical image segmentation usingK-means clustering and improved watershed algorithm.2006IEEE SouthwestSymposium on Image Analysis and interpretation.2006,61-65
[23] Y. L. Huang, D. R. Chen. Watershed segmentation for breast tumor in2-Dsonography. Ultrasound in Medicine and Biology.2004,30(5):625-632
[24] S. H. Lewis. Detection of breast tumor candidates using marker-controlledwatershed segmentation and morphological analysis.2012IEEE SouthwestSymposium on Image Analysis and interpretation.2012,22-24
[25] A. Ahemd, O. Othman, R. Hamid, et al. Segmentation of breast ultrasoundimages using neural networks. Engineering Applications of Neural Networks:IFIP Advances in Information and Communication Technology.2011,363,260-269
[26] C. M. Chen, Y. H. Chou, C. S. K. Chen. Cell-Competition: a new segmentationalgorithm for multiple objects with irregular boundaries in ultrasound images.Ultrasound in Medicine and Biology.2005,31(2):1647-1664
[27] J. Z. Chen, C. M. Chen, Y. H. Chou, et al. Cell-based two-region competitionalgorithm with a MAP framework for boundary delineation of a series of2Dultrasound images. Ultrasound in Medicine and Biology.2007,33(10):1640-1650
[28] E. A. Ashton, K. J. Parker. Multiple resolution Bayesian segmentation ofultrasound images. Ultrasonic Imaging.1995,17:291-304
[29] D. Boukerroui, O. Basset, N. Gu, A. Baskurt. Multiresolution texture basedadaptive clustering algorithm for breast lesion segmentation. European Journalof Ultrasound,1998,8(2):135-144
[30] D. Boukerroui, O. Basset, A. Baskurt, G. Gimenez. A multiparametric andmultiresolution segmentation algorithm of3D ultrasonic data. IEEE Trans.Ultrason. Ferroelectrics Freq.Contr.2001,48(1):64-77
[31] D. Boukerroui, A. Baskurt, J. A. Noble, O. Basset. Segmentation of ultrasoundimages-multiresolution2D and3D algorithm based on global and localstatistics. Pattern Recognition Letter.2003,24(4):779-790
[32] G. Xiao, M. Brady, J. A. Noble, Y. Zhang. Segmentation of ultrasound B-modeimages with intensity inhomogeneity correction. IEEE Trans. Med. Imag.2002,21(1):48-57
[33] L. A. Christopher, E. J. Delp, C. R. Meyer, P. L. Carson.3-D Bayesianultrasound breast image segmentation using the EM/MPM algorithm.Proceedings of the2002IEEE International Symposium on BiomedicalImaging.2002
[34] M. Kass, A. Witkin, D. Terzopoulos. Snakes: active contour models.International Journal of Computer Vision,1988,1(4):321-331.
[35] D. R. Chen, R. F. Chang, W. J. Wu, W. K. Moon, W. L. Wu.3-D Breastultrasound segmentation using active contour model. Ultrasound in Medicineand Biology,2003,29(7):1017-1026
[36] R. F. Chang, W. J. Wu, W. K. Moon, W. M. Chen, W. Lee, D. R. Chen.Segmentation of breast tumor in three-dimensional ultrasound images usingthree-dimensional discrete active contour model. Ultrasound in Medicine andBiology.2003,29(11):1571-1581
[37] A. Madabhushi, D. N. Metaxas. Combining low-,high-level and empiricaldomain knowledge for automated segmentation of ultrasonic breast lesions.IEEE Trans. Med. Imag.2003,22(2):155-169
[38] A. K. Jurnaat, W. E. Zarina, W. A. Rahman, A. Ibrahim, R. Mahmud.Segmentation of masses from breast ultrasound images using parametric activecontour algorithm. International Conference on Mathematics EducationResearch2010.2010,8:640-647
[39] R. F. Chang, W. J. Wu, W. K. Moon, D. R. Chen. Automatic ultrasoundsegmentation and morphology based diagnosis of solid breast tumors. BreastCancer Research and Treatment,2005,89(2):179-185
[40] W. K. Moon, R. F. Chang, C. J. Chen, D. R. Chen, W. L. Chen. Solid breastmasses: classification with computer-aided analysis of continuous US images.Radiology,2005,236:458-464
[41] J. Perona, J. Malik. Scale-scape and edge-detection using anisotropic diffusion.IEEE Trans. Pattern Anal. Machine Intell.1990,12(7):629-639
[42] R. N. Czerwinski, D. L. Jones, W. D. O. B. Jr. Detection of lines andboundaries in speckle images–application to medical ultrasound. IEEE Trans.Med. Imag.1999,18(2):126-136
[43] B. Liu, H. D. Cheng, J. H. Huang, J. W. Tian, J. F. Liu, X. L. Tang. Automatedsegmentation of ultrasonic breast lesions using statistical texture classificationand active contour based on probability distance. Ultrasound Med. Biol.200935(8):1309-1324
[44] B. Liu, H. D. Cheng, J. H. Huang, J. W. Tian, X. L. Tang, J. F. Liu. Probabilitydensity difference-based active contour for ultrasound image segmentation.Pattern Recognition.201043:2028-2042
[45] C. K. Yeh, Y. S. Chen, W. C. Fan, Y. Y. Liao. A disk expansion segmentationmethod for ultrasonic breast lesions. Pattern Recognition,2009,42(5):596-606
[46] P. Abolmaesumi, M. R. Sirouspour. An interacting multiple model probabilisticdata association filter for cavity boundary extraction from ultrasound images.IEEE Trans.Med.Imag.2004,23(6):772-784
[47] H. M. Wu, H. H. Lu. Iterative sliced inverse regression for segmentation ofultrasound and MR images. Pattern Recognition.2007,40(12):3492-3502
[48] J. Yu, Y. Wang, P. Cheng, H. Xu. Two-dimensional fuzzy clustering forultrasound image segmentation.1st International Conference on Bioinformaticsand Biomedical Engineering.2007
[49]余锦华.超声图像处理新方法及其在产前诊断中的应用.复旦大学博士论文，2007
[50]刘海华，陈心浩，高智勇，谢长生.基于形态学操作和模糊聚类技术的超声图像分割.电子学报，2007，35(7):1306-1312
[51] J. A. Noble, D. Boukerroui. Ultrasound image segmentation: a survey. IEEETrans. Med. Imag.2006,25(8):987-1010
[52] B. Zitova, J. Flusser. Image registration methods, a survey. Image VisionComputing.2003,21,977-1000
[53] D. L. Hill, P. G. Batchelor, M. Holden, and D.J. Hawkes,"Medical imageregistration," Phys. Med. Biol.2001,46(3):1-45
[54] D. L. Collins, T. M. Peters, A. C. Evans. An Automated3D Non-LinearDeformation Procedure for Determination of Gross Morphoetric Variability inHuman Brain. Visualization in Biomedical Computing, Bellingham, WA,1994,2359:180-190
[55] R. P. Woods, S. R. Cherry, J. C. Mazziotta. Rapid Automated Algorithm forAligning and Reslicing PET Images. J. Comput. Assist. Tomogr.1992,16(4):620-633
[56] R. P. Woods, J. C. Mazziotta, S. R. Cherry. MRI-PET Registration withAutomated Algorithm. J. Comput. Assist. Tomogr.1993,17(4):536-546
[57] R. P. Woods, S. T. Grafton, C. J. Holmes, S. R. Cherry, J. C. Mazziotta.Automated Image Registration. I:General Methods and Intrasubject,Intramodality Validation. J. Comput. Assist. Tomogr.1998,22:141-154
[58] K. Rohr, H. S. Stiehl, H. S. R. Sprengel. Landmark-based elastic registrationusing approximating thin-plate splines, IEEE Trans. on Med. Imaging.1999,20(6):526-543
[59] D. Reuckert, L. I. Sonoda, C. Hayes. Nonrigid registration using free-Formdeformation: application to breast MRI images. IEEE Trans. on MedicalImaging.1999,18(8):712-721
[60] J. Kybic, M. Unser. Fast parametric elastic image registration, IEEE Trans onImage Processing.2003,12(11): l427-1442
[61]杨明星，庄天戈.一种非刚性医学图像的点配准方法.上海交通大学学报.2004，35(5)：775-778
[62] C. Broit. Optimal Registration of Deformed Images. Doctoral Dissertation.1981
[63] Y. Jin, Y. Shi, N. Jahanshad, et al.3D elastic registration improvesHARDI-derived fiber alignment and automated tract clustering.2011IEEEInternational Symposium on Biomedical Imaging.
[64] A. R. Mejia-Rodriguez, E. R. Arce-Santana, Scalco E, et al. Conf Proc IEEEEng Med Biol Soc.2011,8049-8052
[65] J. Chappelow, B. N. Bloch, N. Rofsky, et al. Elastic registration of multimodalprostate MRI and histology via multiattribute combined mutual information.Med. Phys.2011,38(4):2005-2018
[66] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Log-unbiased elastic imageregistration with spatial constraint for3D CT lung images. In Proc. of MedicalImage Understanding and Analysis.2010,147.
[67] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Elastic Registration of chest CTimages with log un-biased deformations and rigidity constraint. Proc. IEEEInternational Symposium on Biomedical Imaging (ISBI).2011,1235-1238
[68] G. E. Christensen, R. D. Rabbitt, M. Miller. Deformable Templates Using LargeDeformation Kinematics. IEEE Trans on Image Processing.1996,5(10):1435-1447
[69] G. Christensen, S. Joshi, M. Miller. Volumetric Transformation of BrainAnatomy. IEEE Trans on Medical Imaging.1997,16:864-877
[70] H. Lester, S. R. Arridge, K. M. Jansons, et al. Non-linear registration with thevariable viscosity fluid algorithm. In: Proceedings of16th InternationalConference on Information Processing in Medical Imaging,1999.238-251
[71] H. Y. Baluwala, K. A. Saddi, J. A. Schnabel. Non-rigid chest image registrationwith preservation of topology and rigid structures.
[72] J. P. Thirion. Image matching as a diffusion process: an analogy withMaxwell’s demons. Med. Image Anal.1998,2,243-60
[73] P. Rogelj, S. Lovacic. Symmetric image registration. SPIE-Medical Imaging2003: Image Processing.2003,5032:334-343
[74] X. J. Gu, H. Pan, Y. Liang, et al. Implementation and evaluation of variousdemons deformable image registration algorithms on a GPU. Physics inMedicine and Biology.2010,55:207-219
[75] J. H. Woo, B. W. Hong, C. H. Hu, et al. Non-Rigid Ultrasound ImageRegistration Based on Intensity and Local Phase Information. J Sign ProcessSyst.2009,54:33-43
[76] P. Foroughi，P. Abolmaesumi. A modified HAMMER algorithm for deformableregistration of ultrasound images. International Congress Series.2005:236-241
[77]陈佃苹，彭玉华.一种基于特征向量的超声图像配准方法.计算机工程与应用.2010,46(14)：205-208.
[78]董海艳,王惠南,李虹.基于血管内超声图像序列的相角配准与边缘检测.中国图像图形学报.2007,12(6):1048-1054
[79] B. Cohen, I. Dinstein. New maximum likelihood motion estimation schemes fornoisy ultrasound images. Pattern Recognition.2002,35:455-463
[80] D. Boukerroui, J.A. Noble, M. Brady. Velocity Estimation in UltrasoundImages: a Block Matching Approach. In Proc. IPMI.2003,586-598
[81] A. Singh. Image-flow computation: An estimation-theoretic framework and aunified perspective. CVGIP: Image understanding.1992,65(2):152–177.
[82] Z. Wang, G. Slabaugh, G. Unal, et al. Registration of ultrasound images usingan information-theoretic feature detector.
[83] G. Hermosillo, C. ChefdHotel, O. Faugeras. Variational Methods forMultimodal Image Matching. International Journal of Computer Vision.2002,50(3):329-343.
[84]邵斌，唐娉，曾庆业，张送根，姚克纯.基于PC的实时超声全景成像系统中的图像配准.计算机工程与应用.2010,43(28):206-209
[85] M. J. Ledesma-Carbayo, J. Kybic, M. Desco, et al. Spatio-temporal nonrigidregistration for ultrasound cardiac motion estimation. IEEE Trans MedImaging.200524(9):1113-26
[86] A. V. Alvarenga, W. C. A. Pereira, A. F. C. Infantosi, C. M. D. Azevedo.Classification of breast tumors on ultrasound images using morphometricparameters. IEEE International Workshop on Intelligent SignalProcessing05’.2005.
[87] O. S. Soliman, A. E. Hassanien. A computer aided diagnosis system for breastcancer using support vector machine. Lecture Notes in Computer Science.2012,7413:106-115.
[88] P. Filipezuk, M. Kowal, A. Obuchowicz. Fuzzy Clustering and AdaptiveThresholding Based Segmentation Method for Breast Cancer Diagnosis.Computer Recognition systems, Advances in Intelligent and Soft Computing.2011,95:613-622
[89] S. F. Huang, R. F. Chang, D. R. Chen, W. K. Moon. Characterization ofspeculation on ultrasound lesions. IEEE Trans. Med. Imag.2004,23(1):111-121
[90] D. R. Chen, R. F. Chang, Y. L. Huang. Breast cancer diagnosis usingself-organizing map for sonography. Ultrasound in Medicine and Biology.2000,26(3):405-411
[91] Y. L. Huang, D. R. Chen. Support vector machines in sonography applicationto decision making in the diagnosis of breast cancer. Clinical Imaging.2005,29:179-184
[92] Y. L. Huang, Y. G. Liu. Diagnosis of solid breast tumors with sonographictexture analysis.16th IPPR Conference on Computer Vision, Graphics andImage Processing.2003
[93] W. J. Kuo, R. F. Chang, D. R. Chen, C. C. Lee. Data mining with decision treesfor diagnosis of breast tumor in medical ultrasonic images. Breast CancerResearch and Treatment.2001,66:51-57
[94] R. Sivaramakrishna, K. A. Powell, M. L. Lieber, et al. Texture analysis oflesions in breast ultrasound images. Computerized Medical Imaging andGraphics.2002,26(5):303-307.
[95] N. Piliouras, I. Kalatzis, N. Dimitropoulos, D. Cavouras. Development of thecubic least squares mapping linear-kernel support vector machine classifier forimproving the characterization of breast lesions on ultrasound. ComputerizedMedical Imaging and Graphics.2004,28(5):247-255
[96] B. Liu, H. D. Cheng, J. H. Huang, X. L. Tang, J. F. Liu. Fully automatic andsegmentation-robust classification of breast tumors based on local textureanalysis. Pattern Recognition.2010,43(1):280-298
[97] K. Horsch, M. L. Giger. Computerized diagnosis of breast lesions on ultrasound.Medical Physics,2002,29(2):157-164
[98]V. D. Heiden, R. P. W. Duin, D. Ridder, et al. Classification, parameterestimation and state estimation: An engineering approach using Matlab.Oxford: Wiley.2004
[99] B. Sahnier, H. Chan, M. A. Roubidoux, et al. Malignant and benign breastmasses on3D volumetric images: effect of computer-aided diagnosis onradiologist accuracy. Radiology.2007,242(3):716-724.
[100]R. F. Chang, S. F. Huang, W. K. Moon, Y. H. Lee, D. R. Chen. Solid breastmasses: neural network analysis of vascular features at three-dimensionalpower Doppler US for benign or malignant classification. Radiology.2007,243(1):56-62.
[101] D. R. Chen, R. F. Chang, W. M. Chen, W. K. Moon. Computer-AidedDiagnosis for3-Dimensional Breast Ultrasonography. Arch Surg.2003,138(3):296-302.
[102] B. Sahiner, H. P. Chan, M. A. Roubidoux, et al. Malignant and benign breastmasses on3D US volumetric images: effect of computer-aided diagnosis onradiologist accuracy. Radiology.2007,242(3):716-724
[103] S. F. Huang, R. F. Chang, W. K. Moon, Y. H. Lee, D. R. Chen. Analysis oftumor vascularity using three-dimensional power Doppler ultrasound images.IEEE Trans. Med. Imag.2008,27(3):320-330
[104] R. F. Chang, S. F. Huang, W. K. Moon, Y. H. Lee, D. R. Chen. Solid breastmasses: neural network analysis of vascular features at three-dimensionalPower Doppler US of benign and malignant classification. Radiology.2007,243(1):56-62.
[105] Y. H. Hsiao, Y. L. Huang, S. J. Kuo, W. M. Liang, et al. Characterization ofbenign and malignant solid breast masses in harmonic3D power Dopplerimaging. European Journal of Radiology.2009,71(1),89-95
[106] S. T. Chen, Y. H. Hsiao, Y. L. Huang, et al. Comparative analysis of logisticregression, support vector machine and artificial neural network for thedifferential diagnosis of benign and malignant solid breast tumors by the use ofthree-dimensional power Doppler imaging. Korean J Radiol.2009,10(5):464-471
[107]W. M. Chen, R. F. Chang, S. J. Kuo, et al.3-D ultrasound texture classificationusing run difference matrix. Ultrasound Med Biol.2005,31(6):763-770.
[108] X. F. Diao, X. Y. Zhang, T. F. Wang, et al. Highly Sensitive Computer AidedDiagnosis System for Breast Tumor Based on Color Doppler Flow Images. J.Med. Syst.2011,35:801-809
[109] G. Rizzatto, R. Chersevani, G. Ralleigh. Contrast media in ultrasonographybasic principles and clinical applications: breast. Med. Radiol. Diagn. Imaging.2005,48(5),301–303
[110] J. Quartieri, N. E. Mastorakis, G. lannone, et al. Cellular Automata Applicationto Traffic Noise Control. Proceedings of the12th WSEAS InternationalConference on automatic control, modelling and simulation.2010,299-304
[111] K. Mirzaei, H. Motameni, Rasul Enayatifar. New method for edge detectionand de noising via fuzzy cellular automata. International Journal of PhysicalSciences,2011,6(13),3175-3180
[112] P. J. Selvapeter, W. Hordijk. Cellular automata for image noise filtering.Nature&Biologically Inspired Computing.2009,193-197
[113]陈炎雄,郝志峰,温尚清,杨晓伟.基于二维细胞自动机和中值运算的图像滤波方法.计算机辅助工程.2006,15(3)
[114] A. Popovici, D. Popovici. Cellular automata in image processing. FifteenthInternational Symposium on Mathematical Theory of Networks and Systems.2002
[115]惠周利,王鹏.细胞自动机在图像边缘检测中的应用.中国科技信息.2008,18:38-39
[116] G. Sahoo, T. Kumar, B. L. Raina, C. M. Bhatia. Text extraction andenhancement of binary images using cellular automata.
[117] C. Y. Wang, L. Cheng. Feature extraction of geographical image with statustransfer of cellular automata. Proceedings of the International Symposium onIntelligent Information Systems and Applications.2009,307-309
[118] V. Vezhnevets, V. Konouchine.“Grow cut”—interactive multi-label N-Dimage segmentation by cellular automata. Proceedings of Graphicon.2005,150-156
[119] J. Weszka，C. Dyer，A. Rosenfeld. A comparative study of texture measuresfor terrain classifications. IEEE Transactions on Systems, Man andCybernetics.1976,6(4):269-285
[120]D. Harwood, T. Ojala, M. Pietikinen, S. Kelman, L. Davis. Textureclassification by center-symmetric auto-correlation, using kullbackdiscrimination of distributions. Pattern Recognition Letters,1995,16(1):1-10
[121]P. A. Dondes, A. Rosenfeld. Pixel classification based on gray level and local“business”. IEEE Transactions on Pattern Analysis and Machine Intelligence.1982,4(1):79-84
[122]H. Wang, L. Dong, J. O’Daniel, R. Mohan, et al. Validation of an accelerated‘demons’ algorithm for deformable image registration in radiation therapy.Phys. Med. Biol.2005,50:2887-2905
[123]X. B. Lin, T. S. Qiu, F. Nicolier, S. Ruan. An improved method of “demons”non-rigid image registration. ICSP2008Proceedings.1091-1094
[124]D. Yang, H. Li, D. A. Low, et al. A fast inverse consistent deformable imageregistration method based on symmetric optical flow computation. Phys. Med.Biol.2008,53:6135-6145
[125]L. Paninski. Estimation of entropy and mutual information. NeuralComputation.2003,15,1191-1253
[126]K. Jeongtae, A. F. Jeffrey. Image registration using robust correlation. IEEETransactions on medical imaging.2004,23(11),1430-1443.
[127]M. Roser, A. Geiger. Video-based raindrop detection for improved imageregistration.2009IEEE12th International Conference on Computer VisionWorkshops.2009,570-577
[128]B. D. Steinberg, D. L. Carlson, J. A. Birnbaum. Sonographic discriminationbetween benign and malignant breast lesions with use of disparity processing.Acad Radiol.2001,8(8):705-712
[129]W. K. Moon, R. F. Chang, C. J. Cheng, et al. Solid breast masses:classification with computer-aided analysis of continuous US images obtainedwith probe compression. Radiology.2005,236(2):458-464
[130]P. S. S. Rodrigues, G. A. Giraldi, R. F. Chang et al. Object tracking in imagesequence combining hausdorff distance, non-extensive entropy in level setformulation. Topics in Biomedical Engineering. International Book Series.2007,477-515
[131]贺礼，周康源，冯欢清，李传富，杨振森.乳腺超声图像序列的弹性特征病变分析.中国科学技术大学学报.2010,40(11):1108-1111
[132]E. Jessee, E. Wiebe. Visual perception and the hsv color system: Exploringcolor in the communications technology classroom. Technol. Teacher.2008,7-11.
[133]M. Strieke, M. Orengo. Similarity of color images. In: Proceedings of SPIEStorage and Retrieval for Image and Video Databas.1995,24(20):381-392.
[134]J. D. Sun, et al. Image retrieval based on color distribution entropy. Patternrecognition letters.2006,27(10),1122-1126.
[135]E. D. Ubeyli, I. Guler. Feature extraction from color Doppler ultrasoundsignals for automated diagnosis systems. Comp. Biol. Med.2005,35(9):735-764.
[136]S. Tascioglu, O. Ureten, Z. telatar. Impact of noise power uncertainty on theperformance of wideband spectrum segmentation. Radio engineering.2010,19(4):561-566
[137]K. H. Kang, Y. I. Yoon, J. S. Choi, et al. Additive texture informationextraction using color conherence vector. Proceedings of the7th WSEASInternational Conference on Multimedia Systems&Signal Processing.2007,15-17
[138]R. Gordon, R. M. Rangayyan. Feature enhancement of film mammogramsusing fixed and adaptive neighborhoods. Appl Opt.1984,23(4),560-564.
[139]A. Zollanvari, U. M. Braga-Neto, E. R. Dougherty. On the joint samplingdistribution between the actual classification error and the resubstitution andleave-one-out error estimators for linear classifiers. IEEE Transactions onInformation Theory.2010,56(2):784-804