基于灰阶超声序列图像的乳腺肿瘤计算机辅助诊断
|
摘要
超声检查是目前最常用的乳腺肿瘤早期检查手段之一。众多研究表明,配合使用计算机辅助诊断技术(CAD)可以进一步提高超声检查的准确率。乳腺肿瘤CAD系统通常使用肿瘤的形态特征和灰度纹理特征来进行肿瘤良恶性的辅助判别,然而,使用这两类特征的CAD系统尚不能达到理想的诊断效果。临床上,肿瘤的硬度(弹性)也是判别其良恶性的重要指标。本文利用超声探头加压扫描过程中的连续图像,研究如何将基于灰阶超声序列图像的乳腺肿瘤弹性特征更有效地用于乳腺肿瘤的辅助诊断。本文的研究按照计算机辅助诊断系统的常规流程展开,所完成的主要研究工作和创新点描述如下:
(1)对超声图像序列进行预处理。针对视频格式的医学超声图像序列,提出了一种同时利用空间域、灰度域和时间域的相关信息的三域滤波算法。三个域的滤波均采用高斯核函数加权,从而减小滤波结果对阈值选取的敏感度,提高算法的稳定性。针对噪声较为严重的单幅图像,又提出了一种改进的各向异性扩散斑点抑制算法。通过对现有算法中扩散系数过饱和的问题以及斑点尺度系数选择中的不足进行改进,减少了人为因素的影响,增强了各向异性扩散斑点抑制算法的稳定性。
(2)对乳腺肿瘤超声图像进行分割,以得到肿瘤边缘。首先提出了一种无需重初始化的C-V模型,大大加快了分割速度。接着针对乳腺肿瘤超声图像灰度分布的特点和C-V模型分段常量的假设,提出了手工勾画粗略边界,再划分子图进行分割的半自动分割流程,不仅提高了分割准确性,同时也进一步提高了分割效率。对于序列图像的分割,则使用每一帧图像的分割结果作为下一帧图像的初始边界,从而降低了人为影响并提高了效率。另外,通过分析现有分割评价方法的不足,又提出了一种新的评价指标,并使用现有评价指标与这个新指标对乳腺肿瘤超声图像分割结果进行了评估。
(3)从经过分割后的超声图像中提取肿瘤特征参数。本文提取的特征参数分为形态特征、灰度特征、弹性特征三类。其中,12个形态特征和3个灰度特征引自他人的研究成果。考虑到手工加压过程很难保持匀速,提出了一种针对乳腺肿瘤超声序列图像的加压深度评估算法,用以量化图像序列中每两幅图像之间的加压深度。在此基础上,本文进一步提出了一组共10个弹性特征参数,用以描述肿瘤在单位加压深度下的形变程度。其中的两个参数,形变总量和缩小放大比,创新性地使用了非刚性配准得到的形变场进行计算。
(4)根据得到的特征参数对乳腺肿瘤的良恶性进行分类判别。本文采用基于分类器的人工筛选方式挑选性能最优的特征组合。首先从弹性特征中选出性能最优的一些组合,再分别以这些组合作为基本组合,加入形态灰度特征进行测试。测试过程同时使用了支持向量分类和支持向量回归两种分析方法,并提出使用极值距离、均值距离和类间距离这三个指标,来对比特征组合之间的性能。
按照以上四个步骤,本文对临床采集的187例乳腺肿瘤(其中恶性85例,良性102例)进行了实验。实验结果表明,联合使用形态、灰度、弹性特征的辅助诊断系统,性能明显优于只使用形态、灰度特征的系统。这说明基于灰阶超声序列图像的弹性特征参数,对乳腺肿瘤的良恶性具有较好的区分能力,可为乳腺肿瘤的良恶性判别提供辅助诊断依据。
Nowadays, sonography is one of the most frequently used methods for the early detection of breast tumor. A large amount of research shows that, the accuracy of detection using the sonography can be further improved by combining the computer aided diagnosis (CAD) technology. The breast tumor CAD system usually performs the diagnosis based on the supplementary information of morphology and grayscale texture characteristics. However, the performance of the CAD system utilizing the aforementioned two characteristics is still not so satisfactory to date. Clinical research has demonstrated that the tumor elasticity is also a very important indicator to judge whether the breast tumor is benign or not. This dissertation studied the performance of a breast tumor CAD system with the particular inclusion of the tissue elasticity characteristics, which were obtained by sequential grayscale ultrasound images collected during a tissue compression process. According to the conventional processes of a CAD system, the main research work and contribution of this dissertation can be summarized as follows:
(1) Preprocessing the sequential ultrasound images. A filtering algorithm which utilized the correlation information in space, grayscale and time domains simultaneously was proposed for the video-format sequential ultrasound images. In order to improve the stability of the algorithm, the Gaussian weighting kernel was adapted in all the three domains to reduce the sensitivity of the filtering results to the selected threshold. Furthermore, an improved anisotropic diffusion speckle reduce algorithm was proposed to deal with the single images with severely high noise. Through mitigating the over-saturation problem of the diffusion coefficients in the original algorithm and the deficiency in choosing the speckle scale coefficients, the impact of human factor effect was reduced, and the stability of the new algorithm was enhanced.
(2) Segmenting the ultrasound images of breast tumor to get the tumor boundary. This dissertation proposed an improved C-V model, which could avoid the step of re-initialization, thus the speed of segmentation being accelerated greatly. Furthermore, based on the grayscale distribution characteristics of the breast tumor ultrasound images and the hypothesis of a piecewise constant in the C-V model, a semiautomatic segmentation flow was presented, in which the rough contour was sketched first, and then a subimage was obtained to apply the refined segmentation algorithm. This flow improved not only the accuracy, but also the efficiency of the segmentation algorithm. For the sequential images, using the segmentation result of each frame as the initial boundary of the next frame, can reduce the impact of human factors and enhance the segmentation efficiency. In addition, through analyzing the deficiency of the existing evaluation methods for the medical image segmentation, a new evaluation method was proposed, and then the segmentation results of breast tumor ultrasound images were evaluated by using both the existing methods and our new method.
(3) Extracting the characteristic parameters of the breast tumor from the segmentation results. Three classes of parameters, include morphology, grayscale and elasticity characteristics, were extracted in this study, in which 12 morphological characteristics and 3 grayscale characteristics were proposed by others. Considering that the freehand compression process was very difficult to keep a constant speed, an evaluation algorithm was proposed to quantify the compression depth between two consecutive images in the image sequence. On this basis, 10 elasticity parameters were proposed to describe the extent of deformation under per unit compression depth. Among the elasticity parameters, two characteristic parameters named total deformation and shrink-magnify ratio were calculated by the method of nonrigid registration deformation field in a novel way.
(4) Using the characteristic parameters that were extracted in the previous step to aid the classification of breast tumor. This dissertation selected the best combination of parameters by a manual process. Some best combinations of the elasticity parameters were selected first as the basic combinations and then morphological and grayscale parameters were added in to test the overall performance. In the testing process, both the support vector classification and the support vector regression were employed to analyze the data, and three indicators named extreme distance, mean distance and inter-class distance were proposed to compare the performance of different characteristic parameter combinations.
Based on the above four steps, 187 pathologically proven cases including 85 malignant tumors and 102 benign ones were tested in this study. The experiment result showed that the performance of the CAD system which used the morphology, grayscale and elasticity characteristics combinatively. was much better than the system which only used the morphology and grayscale characteristics. Therefore, it was concluded that the elasticity characteristics based on the sequential grayscale ultrasound images performed well in the classification of breast tumors, and it could be used as supplementary information for the diagnosis of breast tumors.
(1)对超声图像序列进行预处理。针对视频格式的医学超声图像序列,提出了一种同时利用空间域、灰度域和时间域的相关信息的三域滤波算法。三个域的滤波均采用高斯核函数加权,从而减小滤波结果对阈值选取的敏感度,提高算法的稳定性。针对噪声较为严重的单幅图像,又提出了一种改进的各向异性扩散斑点抑制算法。通过对现有算法中扩散系数过饱和的问题以及斑点尺度系数选择中的不足进行改进,减少了人为因素的影响,增强了各向异性扩散斑点抑制算法的稳定性。
(2)对乳腺肿瘤超声图像进行分割,以得到肿瘤边缘。首先提出了一种无需重初始化的C-V模型,大大加快了分割速度。接着针对乳腺肿瘤超声图像灰度分布的特点和C-V模型分段常量的假设,提出了手工勾画粗略边界,再划分子图进行分割的半自动分割流程,不仅提高了分割准确性,同时也进一步提高了分割效率。对于序列图像的分割,则使用每一帧图像的分割结果作为下一帧图像的初始边界,从而降低了人为影响并提高了效率。另外,通过分析现有分割评价方法的不足,又提出了一种新的评价指标,并使用现有评价指标与这个新指标对乳腺肿瘤超声图像分割结果进行了评估。
(3)从经过分割后的超声图像中提取肿瘤特征参数。本文提取的特征参数分为形态特征、灰度特征、弹性特征三类。其中,12个形态特征和3个灰度特征引自他人的研究成果。考虑到手工加压过程很难保持匀速,提出了一种针对乳腺肿瘤超声序列图像的加压深度评估算法,用以量化图像序列中每两幅图像之间的加压深度。在此基础上,本文进一步提出了一组共10个弹性特征参数,用以描述肿瘤在单位加压深度下的形变程度。其中的两个参数,形变总量和缩小放大比,创新性地使用了非刚性配准得到的形变场进行计算。
(4)根据得到的特征参数对乳腺肿瘤的良恶性进行分类判别。本文采用基于分类器的人工筛选方式挑选性能最优的特征组合。首先从弹性特征中选出性能最优的一些组合,再分别以这些组合作为基本组合,加入形态灰度特征进行测试。测试过程同时使用了支持向量分类和支持向量回归两种分析方法,并提出使用极值距离、均值距离和类间距离这三个指标,来对比特征组合之间的性能。
按照以上四个步骤,本文对临床采集的187例乳腺肿瘤(其中恶性85例,良性102例)进行了实验。实验结果表明,联合使用形态、灰度、弹性特征的辅助诊断系统,性能明显优于只使用形态、灰度特征的系统。这说明基于灰阶超声序列图像的弹性特征参数,对乳腺肿瘤的良恶性具有较好的区分能力,可为乳腺肿瘤的良恶性判别提供辅助诊断依据。
Nowadays, sonography is one of the most frequently used methods for the early detection of breast tumor. A large amount of research shows that, the accuracy of detection using the sonography can be further improved by combining the computer aided diagnosis (CAD) technology. The breast tumor CAD system usually performs the diagnosis based on the supplementary information of morphology and grayscale texture characteristics. However, the performance of the CAD system utilizing the aforementioned two characteristics is still not so satisfactory to date. Clinical research has demonstrated that the tumor elasticity is also a very important indicator to judge whether the breast tumor is benign or not. This dissertation studied the performance of a breast tumor CAD system with the particular inclusion of the tissue elasticity characteristics, which were obtained by sequential grayscale ultrasound images collected during a tissue compression process. According to the conventional processes of a CAD system, the main research work and contribution of this dissertation can be summarized as follows:
(1) Preprocessing the sequential ultrasound images. A filtering algorithm which utilized the correlation information in space, grayscale and time domains simultaneously was proposed for the video-format sequential ultrasound images. In order to improve the stability of the algorithm, the Gaussian weighting kernel was adapted in all the three domains to reduce the sensitivity of the filtering results to the selected threshold. Furthermore, an improved anisotropic diffusion speckle reduce algorithm was proposed to deal with the single images with severely high noise. Through mitigating the over-saturation problem of the diffusion coefficients in the original algorithm and the deficiency in choosing the speckle scale coefficients, the impact of human factor effect was reduced, and the stability of the new algorithm was enhanced.
(2) Segmenting the ultrasound images of breast tumor to get the tumor boundary. This dissertation proposed an improved C-V model, which could avoid the step of re-initialization, thus the speed of segmentation being accelerated greatly. Furthermore, based on the grayscale distribution characteristics of the breast tumor ultrasound images and the hypothesis of a piecewise constant in the C-V model, a semiautomatic segmentation flow was presented, in which the rough contour was sketched first, and then a subimage was obtained to apply the refined segmentation algorithm. This flow improved not only the accuracy, but also the efficiency of the segmentation algorithm. For the sequential images, using the segmentation result of each frame as the initial boundary of the next frame, can reduce the impact of human factors and enhance the segmentation efficiency. In addition, through analyzing the deficiency of the existing evaluation methods for the medical image segmentation, a new evaluation method was proposed, and then the segmentation results of breast tumor ultrasound images were evaluated by using both the existing methods and our new method.
(3) Extracting the characteristic parameters of the breast tumor from the segmentation results. Three classes of parameters, include morphology, grayscale and elasticity characteristics, were extracted in this study, in which 12 morphological characteristics and 3 grayscale characteristics were proposed by others. Considering that the freehand compression process was very difficult to keep a constant speed, an evaluation algorithm was proposed to quantify the compression depth between two consecutive images in the image sequence. On this basis, 10 elasticity parameters were proposed to describe the extent of deformation under per unit compression depth. Among the elasticity parameters, two characteristic parameters named total deformation and shrink-magnify ratio were calculated by the method of nonrigid registration deformation field in a novel way.
(4) Using the characteristic parameters that were extracted in the previous step to aid the classification of breast tumor. This dissertation selected the best combination of parameters by a manual process. Some best combinations of the elasticity parameters were selected first as the basic combinations and then morphological and grayscale parameters were added in to test the overall performance. In the testing process, both the support vector classification and the support vector regression were employed to analyze the data, and three indicators named extreme distance, mean distance and inter-class distance were proposed to compare the performance of different characteristic parameter combinations.
Based on the above four steps, 187 pathologically proven cases including 85 malignant tumors and 102 benign ones were tested in this study. The experiment result showed that the performance of the CAD system which used the morphology, grayscale and elasticity characteristics combinatively. was much better than the system which only used the morphology and grayscale characteristics. Therefore, it was concluded that the elasticity characteristics based on the sequential grayscale ultrasound images performed well in the classification of breast tumors, and it could be used as supplementary information for the diagnosis of breast tumors.
引文
鲍润贤.2002.中华影像医学乳腺卷[M].北京:人民卫生出版社,3-12.
蔡丰,张涛.2000.乳腺癌的影像学诊断和治疗进展[J].中华超声影像学杂志,9(11):704-705.
陈可欣,何敏,董淑芬,等.2002.天津市女性乳腺癌发病率死亡率和生存率分析[J].中华肿瘤杂志,24(6):573-575.
丛新丽,李树祝.2003.乳腺癌的影像诊断现状与进展[J].医学影像学杂志,13(8):602-605.
丁丽央,沈高飞.1998.乳腺癌危险因素病例对照研究[J].中国慢性病预防与控制,6(6):283-285.
杜勇,任长征,龙艳.1997.乳腺肿块99mTc-MIBI显像规律与其组织病理学关系的初步探讨[J].中华核医学杂志,17(1):43-45.
冯霞,罗葆明,欧冰,等.2007.超声弹性成像评分标准对乳腺良恶性病变诊断价值的探讨[J].中国临床医学影像杂志,18(1):44-45.
富丽娜,王怡,王涌.2007.超声弹性成像与常规超声联合应用在乳腺病灶良恶性鉴别上的价值[J].超声影像学,13(2):124-126.
高天欣,张永红,白净.2002.乳癌检测新方法[J].世界医疗器械,8(5):46-48.
龚焕梅,任炜,王丽君,等.2003.乳腺良恶性肿瘤的钼靶x线鉴别诊断[J].实用放射学杂志,19(9):834-836.
顾志伟,吴秀清,荆浩,等.2007.一种基于特征选择的医学图像检索方法[J].中国生物医学工程学报,26(1):30-34.
侯格贤,毕笃彦,吴成柯.2000.图象分割质量评价方法研究[J].中国图象图形学报,5(1):39-43.
黄福珍,苏剑波,席裕庚.2003.基于几何活动轮廓模型的人脸轮廓提取方法[J].中国图象图形学报,8(5):546-550.
黄建芳,杨斌.2001.超声诊断乳腺肿块的临床价值及钼靶对照分析[J].中国医学影像技术,17(7):662-663.
蒋越峰.2001.乳腺X线图象计算机辅助诊断算法研究[D]:[硕士].杭州:浙江大学,4-7.
康骅.2007.乳腺癌的影像学诊断[EB/OL].北京:首都医科大学宣武医院普通外科,[2007-04-26].http://www.54doctor.net/userl/477/archives/2007/8272.html.
李坤成,孙泽民.2003.乳腺影像诊断学[M].北京:人民卫生出版社.
林其忠,余建国,陈亚青,等.2006a.乳腺肿瘤超声图像识别模式分类方法的比较研究[J].上海医学影像,15(2):102-104.
林其忠,余建国,赵暖,等.2006b.乳腺肿瘤超声图像的特征分析[J].仪器仪表学报,27(6):744-746.
刘向东.2004.支持向量机若干关键问题及其应用的研究[D]:[博士].南京:南京大学.
罗葆明,欧冰,冯霞,等.2005.乳腺疾病实时组织弹性成像与病理对照的初步探讨[J].中国超声医学杂志,21(9):662-664.
罗葆明,欧冰,冯霞,等.2006.乳腺肿块的超声弹性成像、多普勒超声及X线钼靶检查[J].中国医学影像技术,22(12):1823-1826.
罗惠韬,章毓晋.1997.一个图象分割评价实例及讨论[J].数据采集与处理,12(1):18-22.
罗建文,白净.2003.超声弹性成像仿真的有限元分析[J].北京生物医学工程,22(2):99-103.
罗建文,白净,汪伟,等.2006.超声弹性成像实验系统的研制[J].仪器仪表学报,27(5):541-546.
罗建文,白净.2007.采用径向压缩的超声弹性成像逆问题求解[J].北京生物医学工程,26(2):124-128.
欧冰.2006.乳腺肿块彩色超声弹性成像、二维灰阶超声、彩色多普勒超声及钼靶X-线的对比研究[D]:[硕士].广州:中山大学,1-5.
彭玉兰.2004.乳腺高频超声图谱[M].北京:人民卫生出版社.
任新平,詹维伟.2007.超声弹性成像在乳腺疾病中的应用[J].诊断学理论与实践,6(2):166-168.
沈嘉琳,汪源源,王涌,等.2005.基于灰度阈值分割和动态规划的超声图像乳腺肿瘤边缘提取[J].航天医学与医学工程,18(4):281-286.
沈嘉琳.2006.乳腺肿瘤的超声图像分析及良恶性判别[D]:[硕士].上海:复旦大学.
孙华文,钟翠云.1996.计算机近红外光扫描与钼靶摄片诊断乳腺肿瘤的对比研究[J].中华外科杂志,34(10):638.
孙军,陈峰,郑凯尔.2001.ROC曲线分析在放射学中的应用[J].中华放射学杂志,35(8): 574-577.
汪天富,郑昌琼.1998.用神经网络进行超声医学图像分割[J].生物医学工程学杂志,15(4):397-399.
王威琪.1994.医学超声中的斑纹噪声[J].上海生物医学工程,2:2-3.
王怡,秦茜淼,陈为民,等.2003.188枚良恶性乳腺肿块声像图识别[J].上海医学影像杂志,12(1):30-34.
王怡,王涌,张希敏.2005a.组织弹性成像鉴别乳腺良恶性肿块的价值评估[J].中国医学影像技术,21(11):1704-1706.
王怡,王涌,张希敏.2005b.实时组织弹性成像技术在鉴别诊断乳腺良恶性肿块中的价值评估[J].中华超声影像学杂志,14(12):911-913.
汪源源,沈嘉琳,王涌,等.2006.基于形态特征判别超声图像中乳腺肿瘤的良恶性[J].光学精密工程,14(2):333-340.
卫娜,杨继庆,罗建,等.2004.超声技术在医学领域的应用与发展[J].医疗卫生装备,8:30-31.
吴松松,陈亚青.2006.乳腺癌超声诊断进展[J].中国医学影像技术,22(4):623-626.
谢则平,王晓芳.2000.近红外光无创伤诊断乳腺癌的临床研究[J].癌症,19(2):185.
邢占峰,吕扬生.2003a.模糊多尺度边缘检测在医学超声图像边缘检测中的应用[J].北京生物医学工程,22(3):161-163.
邢占峰.2003b.超声医学图像处理中若干问题的研究[D]:[博士].天津:天津大学,2-7.
徐智章.2001.血管内超声造影技术[J].中国医学影像技术,17(9):811-812.
杨盈,汪天富,彭玉兰,等.2005.基于形态和灰度特征的乳腺肿瘤B超图像识别[J].中国医学影像技术,21(11):1758-1760.
余成波.2003.数字图像处理及MATLAB实现[M].重庆:重庆大学出版社.
于起峰,孙祥一.2002.用曲线大窗口平滑散斑条纹图的方法研究[J].力学学报,34(3):458-462.
张济忠.1997.分形[M].北京:清华大学出版社,55-60.
张晋熙,姜玉新.2000.浅表器官组织超声诊断学[M].北京:科学技术文献出版社,124.
章毓晋.2001.图像分割[M].北京:科学出版社.
郑莹,李德禄,向泳梅,等.2001.上海市区乳腺癌流行现状及趋势分析[J].外科理论与实践,6(4):219-221.
朱磊,徐佩霞,何佳.2005.基于自适应邻域概念的实时视频预处理算法[J].中国科学 技术大学学报,35(2): 154-160.
子荫,白木.2002. 早期乳腺癌诊疗新技术[J].抗癌,1:37.
American College of Radiology (ACR). 2003. Breast Imaging Reporting and Data System (BIRADS). 4th ed [S]. Reston, VA: American College of Radiology.
Aubert G, Kornprobst P. 2001. Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations [M]. Applied Mathematical Sciences, vol 147, Springer-Verlag.
Bai J, Ding CX, Fan Y. 1999. A multi-scale algorithm for ultrasonic strain reconstruction under moderate compression [J]. Ultrasonics, 37(7): 511-519.
Bai J, Ding CX, Luo JW, et al. 2002. Estimation and reduction of decorrelation effect due to tissue lateral displacement in elastography [J]. IEEE Trans Ultrason Ferroelectr Freq Control, 49(5): 541-549.
Baker JA, Kornguth PJ, Soo MS, et al. 1999. Sonography of solid breast lesions: observer variability of lesion description and assessment [J]. Am J Roentgenol, 172(6): 1621-1625.
Bamber D. 1975. The area above the ordinal dominance graph and the area below the receiver operating characteristic graph [J]. J Math Psychol, 12:387-415.
Bassa P, Kim EE, Inoue T, et al. 1996. Evaluation of Preoperative chemotherapy using PET with fluorine-18-fluorodeoxyglucose in breast cancer [J]. J Nucl Med, 37(6): 931-938.
Bennett EP, McMilan L. 2005. Video enhancement using per-pixel virtual exposures [J]. ACM Trans Graphics, 24(3): 845-852.
Black MJ, Sapiro G, David H, et al. 1998. Robust anisotropic diffusion [J]. IEEE Trans Image Processing, 7(3): 421-431.
Bradley JE, Brian B. 2002. Computer-aided detection and diagnosis at the start of the third millennium [J]. J Digit Imaging, 15(2): 59-68.
Buadu LD, Murakami J, Murayama S, et al. 1997. Colour Doppler Sonography of breast masses: a multiparameter analysis [J]. Clin Radiol, 52(12): 917-923.
Canny J. 1986. A computational approach to edge detection [J], IEEE Trans Pattern Anal Machine Intell, 8(6): 679-698.
Caruso G, Ienzi R, Cirino A, et al. 2002. Breast lesion characterization with contrast-enhanced US. Work in progress [J]. Radiol Med (Torino), 104(5-6): 443-450.
Caselles V, Catte F, Coll T, et al. 1993. A geometric model for active contours in image processing [J]. Numerische Mathematik, 66(1): 1-31.
Caselles V, Kimmel R, Sapiro G. 1997. Geodesic active contours [J]. Int J Computer Vision, 22(1):61-79.
Chan TF, Vese LA. 2001. Active contours without edges [J]. IEEE Trans Image Proc, 10(2): 266-277.
Chang CC, Lin CJ. 2001. LIBSVM: a library for support vector machines [EB/OL]. [2007-12-20]. Software available at http://www.csie.ntu.edu.tw/～cjlin/libsvm.
Chang RF, Wu WJ, Moon WK, et al. 2005. Automatic ultrasound segmentation and morphology based diagnosis of solid breast rumors [J]. Breast Cancer Res Treat, 89(2): 179-185.
Chao TC, Lo YF, Chen SC, et al. 1999. Prospective sonographic study of 3093 breast tumors [J]. J Ultrasound Med, 18(5): 363-370.
Chen CJ, Chang RF, Moon WK, et al. 2006. 2-D ultrasound strain images for breast cancer diagnosis using nonrigid subregion registration [J]. Ultrasound Med Biol, 32(6): 837-846.
Chen CM, Chou YH, Han KC, et al. 2003. Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks [J]. Radiology, 226(2): 504-514.
Chen DR, Chang RF, Kuo WJ,et al. 2002. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks [J]. Ultrasound Med Biol, 28(10): 1301-1310.
Chen KM, Qin QM, Mao R. 1995. Evaluation of ultrasound in the differentiation of benign and malignant breast masses [J]. China J. Radiol, 29(3): 154-157.
Cherkassky V, Mulier F. 1998. Learning from data: concept, theory and method [M]. NY: John Wiley & Sons.
Cho KR, Seo BK, Lee JY, et al. 2005. A comparative study of 2D and 3D ultrasonography for evaluation of solid breast masses [J]. Eur J Radiol, 54(3): 365-370.
Chou YH, Tiu CM, Hung GS, et al. 2001. Stepwise Logistic Regression Analysis of Tumor Contour Features for Breast Ultrasound Diagnosis [J]. Ultrasound Med Biol, 27(11): 1493-1498.
Cole-Beuglet C, Kurtz AB, Rubin CS, et al. 1980. Ultrasound mammography. Radiol Clin North Am, 18(1): 133-143.
Doi K. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential [J]. Comput Med Imaging Graph, 31(4-5): 198-211.
Donoho D. 1995. De-noising by soft-thresholding [J]. IEEE Trans Information Theory, 41(3): 613-627.
Doyley MM, Srinivasan S, Pendergrass SA, et al. 2005. Comparative evaluation of strain-based and model-based modulus elastography [J]. Ultrasound Med Biol, 31(6): 787-802.
Drukker K, Giger ML, Vyborny CJ, et al. 2004. Computerized detection and classification of cancer on breast ultrasound [J]. Acad Radiol, 11(5): 526-535.
Durand F, Dorsey J. 2002. Fast bilateral filtering for the display of high dynamic range images [J]. ACM Trans Graphics, 21(3):257-266.
Freund Y, Schapire R. 1997. A decision-theoretic generalization of on-line learning and an application to boosting [J]. J Comput Syst Sci, 55(1): 119-139.
Gander W, Golub GH, Strebel R. 1994. Least-squares fitting of circles and ellipses [J]. BIT, 34: 558-578.
Garra BS, Krasner BH, Horii SC, et al. 1993. Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis [J]. Ultrason Imaging, 15(4): 267-285.
Garra BS, Cespedes I, Ophir J, et al. 1997. Elastography of the breast: Initial clinical results [J]. Radiology, 202(1): 79-86.
Gaser C, Volz HP, Kiebel S, et al. 1999. Detecting structural changes in whole brain based on nonlinear deformations-Application to schizophrenia research [J]. Neurolmage, 10:107-133.
Getty DJ, Pickett RM, D'Orsi CJ. 2001. Stereoscopic digital mammography: improving detection and diagnosis of breast cancer [J]. International Congress Series, 1230:535-544.
Giuseppetti GM, Martegani A, Di Cioccio B, et al. 2005. Elastosonography in the diagnosis of the nodular breast lesions: Preliminary report [J]. Radiol Med (Torino), 110(1-2): 69-76.
Hall TJ, Zhu YN, Spalding CS. 2003. In vivo real-time freehand palpation imaging [J]. Ultrasound Med Biol, 29(3): 427-435.
Han LH, Noble J A, Burcher M. 2003. A novel ultrasound indentation system for measuring biomechanical properties of in vivo soft tissue [J]. Ultrasound Med Biol, 29(6): 813-823.
Hsu CW, Chang CC, Lin CJ. 2007. A practical guide to support vector classification [EB/OL].
Taiwan: Department of Computer Science, National Taiwan University, [2007-12-20]. http://www.csie.ntu.edu.tw/～cjlin/libsvm/index.html.
Huang YL, Chen DR. 2004. Watershed segmentation for breast tumor in 2-D sonography [J]. Ultrasound Med Biol, 30(5): 625-632.
Huttenlocher DJ, Klanderman GA, Rucklidge WJ. 1993. Comparing images using the Hausdorff distance [J]. IEEE Trans Pattern Anal Machine Intell, 15(9): 850-863.
Itoh A, Ueno E, Tohno E, et al. 2006. Breast disease: clinical application of US elastography for diagnosis [J]. Radiology, 239(2): 341-350.
Jackson VP. 1990. The role of US in breast imaging [J], Radiology, 177(2): 305-311.
Joo S, Yang YS, Moon WK, et al. 2004. Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features [J]. IEEE Trans Med Imaging, 23(10): 1292-1300.
Kass M, Witkin AP, Terzopoulos D. 1988. Snakes: Active contour models [J]. Int J Computer Vision, 1(4): p321-331.
Key TJ, Verkasalo PK, Banks E. 2001. Epidemiology of Breast Cancer [J]. Lancet Oncology, 2: 133-140.
Khalkhali I, Cutrone J, Mena I, et al. 1995. Technetium-99m-Sestamibi scintimammography of breast lesions: clinical and Pathological follow-up [J]. J Nucl Med, 36(10): 1784-1789.
Kher A, Mitra S. 1993. Optimum morphological filtering to remove speckle noise form SAR images [C]. Proc SPIE Image Algebra and Morphological Image Processing IV, 2030:97-108.
Krouskop TA, Wheeler TM, Kallel F, et al. 1998. Elastic moduli of breast and prostate tissues under compression [J]. Ultrason Imaging, 20(4): 260-274.
Kuo WJ, Chang RF, Moon WK, et al. 2002. Computer-aided Diagnosis of Breast Tumors with Different US Systems [J]. Acad Radiol, 9(7): 793-799.
Ibanez L, Schroeder W. 2005. The ITK software guide second edition updated for ITK version 2.4 [EB/OL]. [2007-9-23]. http://www.itk.org.
Lee JS. 1981. Speckle analysis and smoothing of Synthetic Aperture Radar images [J]. Computer graphics and images processing, 17(1): 24 -32.
Lefebvre F, Meunier M, Thibault F, et al. 2000. Computerized ultrasound B-scan characterization of breast nodules [J]. Ultrasound Med Biol, 26(9): 1421-1428.
Li CM, Xu CY, Gui CF, et al. 2005. Level set evolution without re-initialization: a new variational formulation [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR), 1: 430-436.
Loupas T, Mcdicken WN, Allan PL. 1989. An adaptive weighted median filter for speckle suppression in medical ultrasound image [J]. IEEE Trans Circuits Syst, 36(1): 129-135.
Luo JW, Bai J, He P, et al. 2004. Axial strain calculation using a low-pass digital differentiator in ultrasound elastography [J]. IEEE Trans Ultrason Ferroelectr Freq Control, 51(9): 1119-1127.
Macsweeney JE, Cosgrove DO, Arenson J. 1996. Color Doppler energy (power) mode ultrasound [J], clin Radiol, 51(6): 387-390.
Madabhushi A, Metaxas DN. 2003. Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions [J], IEEE Trans Med Imaging, 22(2): 155-169.
Malladi R, Sethian JA, Vemuri BC. 1995. Shape modeling with front propagation - A level set approach [J]. IEEE Trans Pattern Anal Machine Intell, 17(2): 158-175.
Mallat S, Zhong S. 1992. Characterization of signals from multiscale edges [J]. IEEE Trans Pattern Anal Machine Intell, 14(7): 710-732.
Metz CE. 1986. ROC methodology in radiologic imaging [J]. Invest Radiol, 21(9): 720-733.
Meyberg-Solomayer GC, Kraemer B, Bergmann A, et al. 2004. Does 3-D sonography bring any advantage to noninvasive breast diagnostics?[J]. Ultrasound Med Biol, 30(5): 583-589.
Michailovich OV, Tannenbaum A. 2006. Despeckling of medical ultrasound images [J]. IEEE Trans UFFC, 53(1): 64-78.
Moon WK, Chang RF, Chen CJ, et al. 2005. Solid breast masses: classification with computer-aided analysis of continuous US images obtained with probe compression [J]. Radiology, 236(2): 458-464.
Mumford D, Shah J. 1989. Optimal approximation by piecewise smooth functions and associated variational problem [J]. Commun Pure Appl Math, 42(5): 577-685.
Ophir J, Cespedes I, Ponnekanti H, et al. 1991. Elastography: a quantitative method for imaging the elasticity of biological tissues [J]. Ultrason Imaging, 13(2): 111-134.
Ophir J, Cespedes I, Garra B, et al. 1996. Elastography: Ultrasonic imaging of tissue strain and elastic modulus in vivo [J]. Eur J Ultrasound, 3:49-70.
Osher S, Sethian JA. 1988. Fronts Propagating with Curvature Dependent Speed: Algorithms Based on the Hamilton-Jacobi Formulation [J]. J Comput Phys, 79(1): 12-49.
Otsu N. 1979. A threshold selection method from gray-level histograms [J]. IEEE Trans on Systems Man and Cybernetics, 9(1): 62-66.
Paranjape RB, Rangayyan RM, Morrow WM. 1994a. Adaptive neighborhood mean and median filtering [J]. J Electron Imag, 3(4): 360-367.
Paranjape RB, Rabie TF, Rangayyan RM. 1994b. Image restoration by adaptive neighborhood noise subtraction [J], Applied Optics, 33(14): 1861-1869.
Parker JR. 1997. Algorithms for image processing and computer vision [M]. New York, John Wiley & Sons, Inc., 23-29.
Perona P, Malik J. 1990. Scale-space and edge detection using anisotropic diffusion [J]. IEEE Trans Pattern Anal Machine Intell, 12(7): 629-639.
Pham DL, Prince JL. 1999. An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities [J]. Pattern Recognition Letters, 20(1): 57-68.
Rahbar G, Sie AC, Hansen GC, et al. 1999. Benign versus malignant solid breast masses: US differentiation [J]. Radiology, 213(3): 889-894.
Rao M, Chen Q, Shi H, et al. 2007. Normal and shear strain estimation using beam steering on linear-array transducers [J], Ultrasound Med Biol, 33(1): 57-66.
Sahiner B, Petrick N, Chan HP, et al. 2001. Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization [J]. IEEE Trans Med Imaging, 20(12): 1275-1284.
Shen WC, Chang RF, Moon WK, et al. 2007. Breast ultrasound computer-aided diagnosis using BI-RADS features [J]. Acad Radiol, 14(8): 928-939.
Shiina T, Yamakawa M. 2004. Recent progress of ultrasound elasticity imaging technology [C]. Proceeding of 7th Congress of the Asian Federation of Societies for Ultrasound in Medicine and Biology (AFSUMB 2004), 59-63.
Sinha U, Kangarloo H. 2002. Principal component analysis for content-based image retrieval [J]. Radiographics, 22(5): 1271-1289.
Sivaramakrishna R, Powell KA, Lieber ML, et al. 2002. Texture analysis of lesions in breast ultrasound images [J]. Comput Med Imaging Graph, 26(5): 303-307.
Song YW, Upda SS. 1996. A new morphological approach for reducing speckle noise in ultrasonic images [C]. IEEE 39th Midwest symposium on Circuits and Systems, 3:1397-1400.
Srinivasan S, Krouskop T, Ophir J. 2004. A quantitative comparison of modulus images obtained using nanoindentation with strain elastograms [J]. Ultrasound Med Biol, 30(7): 899-918.
Stavros AT, Thickman D, Rapp CL, et al. 1995. Solid breast nodules: use of sonography to distinguish between benign and malignant lesions [J]. Radiology, 196(1):123-134.
Steinberg BD, Sullivan DC, Carlson DL. 1998. Disparity mapping applied to sonography of the breast [J]. Radiology, 207(2): 545-550.
Steinberg BD, Carlson DL, Zuckerman JA, et al. 2000. .Discrimination between cancers and benign breast lesions by ultrasound disparity mapping [C]. Proceedings of SPIE2000, 3982: 172-179.
Steinberg BD, Carlson DL, Birnbaum JA. 2001. Sonographic discrimination between benign and malignant breast lesions with use of disparity processing [J]. Acad Radiol, 8(8): 705-712.
Svensson WE, Amiras D. 2006. Ultrasound elasticity imaging [J]. Breast Cancer Online, e00: 1-7.
Thirion JP. 1996. Non-rigid matching using demons [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR), 245 -251.
Tominaga S, Kuroishi T. 1995. Epidemiology of Breast Cancer in Japan [J]. Cancer Letters, 90: 75-79.
Udupa JK, Smarasekera S, Barrett WA. 1992. Edge detection via dynamical programming [J]. SPIE Proc Medical Imaging, 1808:33-39.
Vapnik VN. 1995. The nature of statistical learning theory [M]. NY: Springer-Verlag. Vincent L, Soille P. 1991. Watersheds in digital spaces: An efficient algorithm based on immersion simulations [J] . IEEE Trans Pattern Anal Machine Intell, 13(6): 583-598.
Yamakawa M, Shiina T. 2001. Strain estimation using the extended combined autocorrelation method [J]. Jpn J Appl Phys, 40:3872-3876.
Yang MS. 1993. A survey of fuzzy clustering [J]. Math Comput Modeling, 18(11): 1-16.
Yu YJ, Scott TA. 2002. Speckle reducing anisotropic diffusion [J]. IEEE Trans Image Process, 11(11):1260-1270.
Zhang YJ. 1996. A survey on evaluation methods for image segmentation [J]. Pattern Recognition, 29(8): 1335-1346.
Zhao HK, Chan T, Merriman B, et al. 1996. A variational level set approach to multiphase motion [J]. J Comput Phys, 127(1): 179-195.
Zhu YN, Hall TJ. 2002. A modified block matching method for real-time freehand strain imaging [J]. Ultrason. Imaging, 24(3): 161-176.
Zong XL, Laine AF, Geiser EA. 1998. Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing [J], IEEE trans Med Imaging, 17(4): 532-540.
蔡丰,张涛.2000.乳腺癌的影像学诊断和治疗进展[J].中华超声影像学杂志,9(11):704-705.
陈可欣,何敏,董淑芬,等.2002.天津市女性乳腺癌发病率死亡率和生存率分析[J].中华肿瘤杂志,24(6):573-575.
丛新丽,李树祝.2003.乳腺癌的影像诊断现状与进展[J].医学影像学杂志,13(8):602-605.
丁丽央,沈高飞.1998.乳腺癌危险因素病例对照研究[J].中国慢性病预防与控制,6(6):283-285.
杜勇,任长征,龙艳.1997.乳腺肿块99mTc-MIBI显像规律与其组织病理学关系的初步探讨[J].中华核医学杂志,17(1):43-45.
冯霞,罗葆明,欧冰,等.2007.超声弹性成像评分标准对乳腺良恶性病变诊断价值的探讨[J].中国临床医学影像杂志,18(1):44-45.
富丽娜,王怡,王涌.2007.超声弹性成像与常规超声联合应用在乳腺病灶良恶性鉴别上的价值[J].超声影像学,13(2):124-126.
高天欣,张永红,白净.2002.乳癌检测新方法[J].世界医疗器械,8(5):46-48.
龚焕梅,任炜,王丽君,等.2003.乳腺良恶性肿瘤的钼靶x线鉴别诊断[J].实用放射学杂志,19(9):834-836.
顾志伟,吴秀清,荆浩,等.2007.一种基于特征选择的医学图像检索方法[J].中国生物医学工程学报,26(1):30-34.
侯格贤,毕笃彦,吴成柯.2000.图象分割质量评价方法研究[J].中国图象图形学报,5(1):39-43.
黄福珍,苏剑波,席裕庚.2003.基于几何活动轮廓模型的人脸轮廓提取方法[J].中国图象图形学报,8(5):546-550.
黄建芳,杨斌.2001.超声诊断乳腺肿块的临床价值及钼靶对照分析[J].中国医学影像技术,17(7):662-663.
蒋越峰.2001.乳腺X线图象计算机辅助诊断算法研究[D]:[硕士].杭州:浙江大学,4-7.
康骅.2007.乳腺癌的影像学诊断[EB/OL].北京:首都医科大学宣武医院普通外科,[2007-04-26].http://www.54doctor.net/userl/477/archives/2007/8272.html.
李坤成,孙泽民.2003.乳腺影像诊断学[M].北京:人民卫生出版社.
林其忠,余建国,陈亚青,等.2006a.乳腺肿瘤超声图像识别模式分类方法的比较研究[J].上海医学影像,15(2):102-104.
林其忠,余建国,赵暖,等.2006b.乳腺肿瘤超声图像的特征分析[J].仪器仪表学报,27(6):744-746.
刘向东.2004.支持向量机若干关键问题及其应用的研究[D]:[博士].南京:南京大学.
罗葆明,欧冰,冯霞,等.2005.乳腺疾病实时组织弹性成像与病理对照的初步探讨[J].中国超声医学杂志,21(9):662-664.
罗葆明,欧冰,冯霞,等.2006.乳腺肿块的超声弹性成像、多普勒超声及X线钼靶检查[J].中国医学影像技术,22(12):1823-1826.
罗惠韬,章毓晋.1997.一个图象分割评价实例及讨论[J].数据采集与处理,12(1):18-22.
罗建文,白净.2003.超声弹性成像仿真的有限元分析[J].北京生物医学工程,22(2):99-103.
罗建文,白净,汪伟,等.2006.超声弹性成像实验系统的研制[J].仪器仪表学报,27(5):541-546.
罗建文,白净.2007.采用径向压缩的超声弹性成像逆问题求解[J].北京生物医学工程,26(2):124-128.
欧冰.2006.乳腺肿块彩色超声弹性成像、二维灰阶超声、彩色多普勒超声及钼靶X-线的对比研究[D]:[硕士].广州:中山大学,1-5.
彭玉兰.2004.乳腺高频超声图谱[M].北京:人民卫生出版社.
任新平,詹维伟.2007.超声弹性成像在乳腺疾病中的应用[J].诊断学理论与实践,6(2):166-168.
沈嘉琳,汪源源,王涌,等.2005.基于灰度阈值分割和动态规划的超声图像乳腺肿瘤边缘提取[J].航天医学与医学工程,18(4):281-286.
沈嘉琳.2006.乳腺肿瘤的超声图像分析及良恶性判别[D]:[硕士].上海:复旦大学.
孙华文,钟翠云.1996.计算机近红外光扫描与钼靶摄片诊断乳腺肿瘤的对比研究[J].中华外科杂志,34(10):638.
孙军,陈峰,郑凯尔.2001.ROC曲线分析在放射学中的应用[J].中华放射学杂志,35(8): 574-577.
汪天富,郑昌琼.1998.用神经网络进行超声医学图像分割[J].生物医学工程学杂志,15(4):397-399.
王威琪.1994.医学超声中的斑纹噪声[J].上海生物医学工程,2:2-3.
王怡,秦茜淼,陈为民,等.2003.188枚良恶性乳腺肿块声像图识别[J].上海医学影像杂志,12(1):30-34.
王怡,王涌,张希敏.2005a.组织弹性成像鉴别乳腺良恶性肿块的价值评估[J].中国医学影像技术,21(11):1704-1706.
王怡,王涌,张希敏.2005b.实时组织弹性成像技术在鉴别诊断乳腺良恶性肿块中的价值评估[J].中华超声影像学杂志,14(12):911-913.
汪源源,沈嘉琳,王涌,等.2006.基于形态特征判别超声图像中乳腺肿瘤的良恶性[J].光学精密工程,14(2):333-340.
卫娜,杨继庆,罗建,等.2004.超声技术在医学领域的应用与发展[J].医疗卫生装备,8:30-31.
吴松松,陈亚青.2006.乳腺癌超声诊断进展[J].中国医学影像技术,22(4):623-626.
谢则平,王晓芳.2000.近红外光无创伤诊断乳腺癌的临床研究[J].癌症,19(2):185.
邢占峰,吕扬生.2003a.模糊多尺度边缘检测在医学超声图像边缘检测中的应用[J].北京生物医学工程,22(3):161-163.
邢占峰.2003b.超声医学图像处理中若干问题的研究[D]:[博士].天津:天津大学,2-7.
徐智章.2001.血管内超声造影技术[J].中国医学影像技术,17(9):811-812.
杨盈,汪天富,彭玉兰,等.2005.基于形态和灰度特征的乳腺肿瘤B超图像识别[J].中国医学影像技术,21(11):1758-1760.
余成波.2003.数字图像处理及MATLAB实现[M].重庆:重庆大学出版社.
于起峰,孙祥一.2002.用曲线大窗口平滑散斑条纹图的方法研究[J].力学学报,34(3):458-462.
张济忠.1997.分形[M].北京:清华大学出版社,55-60.
张晋熙,姜玉新.2000.浅表器官组织超声诊断学[M].北京:科学技术文献出版社,124.
章毓晋.2001.图像分割[M].北京:科学出版社.
郑莹,李德禄,向泳梅,等.2001.上海市区乳腺癌流行现状及趋势分析[J].外科理论与实践,6(4):219-221.
朱磊,徐佩霞,何佳.2005.基于自适应邻域概念的实时视频预处理算法[J].中国科学 技术大学学报,35(2): 154-160.
子荫,白木.2002. 早期乳腺癌诊疗新技术[J].抗癌,1:37.
American College of Radiology (ACR). 2003. Breast Imaging Reporting and Data System (BIRADS). 4th ed [S]. Reston, VA: American College of Radiology.
Aubert G, Kornprobst P. 2001. Mathematical Problems in Image Processing: Partial Differential Equations and the Calculus of Variations [M]. Applied Mathematical Sciences, vol 147, Springer-Verlag.
Bai J, Ding CX, Fan Y. 1999. A multi-scale algorithm for ultrasonic strain reconstruction under moderate compression [J]. Ultrasonics, 37(7): 511-519.
Bai J, Ding CX, Luo JW, et al. 2002. Estimation and reduction of decorrelation effect due to tissue lateral displacement in elastography [J]. IEEE Trans Ultrason Ferroelectr Freq Control, 49(5): 541-549.
Baker JA, Kornguth PJ, Soo MS, et al. 1999. Sonography of solid breast lesions: observer variability of lesion description and assessment [J]. Am J Roentgenol, 172(6): 1621-1625.
Bamber D. 1975. The area above the ordinal dominance graph and the area below the receiver operating characteristic graph [J]. J Math Psychol, 12:387-415.
Bassa P, Kim EE, Inoue T, et al. 1996. Evaluation of Preoperative chemotherapy using PET with fluorine-18-fluorodeoxyglucose in breast cancer [J]. J Nucl Med, 37(6): 931-938.
Bennett EP, McMilan L. 2005. Video enhancement using per-pixel virtual exposures [J]. ACM Trans Graphics, 24(3): 845-852.
Black MJ, Sapiro G, David H, et al. 1998. Robust anisotropic diffusion [J]. IEEE Trans Image Processing, 7(3): 421-431.
Bradley JE, Brian B. 2002. Computer-aided detection and diagnosis at the start of the third millennium [J]. J Digit Imaging, 15(2): 59-68.
Buadu LD, Murakami J, Murayama S, et al. 1997. Colour Doppler Sonography of breast masses: a multiparameter analysis [J]. Clin Radiol, 52(12): 917-923.
Canny J. 1986. A computational approach to edge detection [J], IEEE Trans Pattern Anal Machine Intell, 8(6): 679-698.
Caruso G, Ienzi R, Cirino A, et al. 2002. Breast lesion characterization with contrast-enhanced US. Work in progress [J]. Radiol Med (Torino), 104(5-6): 443-450.
Caselles V, Catte F, Coll T, et al. 1993. A geometric model for active contours in image processing [J]. Numerische Mathematik, 66(1): 1-31.
Caselles V, Kimmel R, Sapiro G. 1997. Geodesic active contours [J]. Int J Computer Vision, 22(1):61-79.
Chan TF, Vese LA. 2001. Active contours without edges [J]. IEEE Trans Image Proc, 10(2): 266-277.
Chang CC, Lin CJ. 2001. LIBSVM: a library for support vector machines [EB/OL]. [2007-12-20]. Software available at http://www.csie.ntu.edu.tw/～cjlin/libsvm.
Chang RF, Wu WJ, Moon WK, et al. 2005. Automatic ultrasound segmentation and morphology based diagnosis of solid breast rumors [J]. Breast Cancer Res Treat, 89(2): 179-185.
Chao TC, Lo YF, Chen SC, et al. 1999. Prospective sonographic study of 3093 breast tumors [J]. J Ultrasound Med, 18(5): 363-370.
Chen CJ, Chang RF, Moon WK, et al. 2006. 2-D ultrasound strain images for breast cancer diagnosis using nonrigid subregion registration [J]. Ultrasound Med Biol, 32(6): 837-846.
Chen CM, Chou YH, Han KC, et al. 2003. Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks [J]. Radiology, 226(2): 504-514.
Chen DR, Chang RF, Kuo WJ,et al. 2002. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks [J]. Ultrasound Med Biol, 28(10): 1301-1310.
Chen KM, Qin QM, Mao R. 1995. Evaluation of ultrasound in the differentiation of benign and malignant breast masses [J]. China J. Radiol, 29(3): 154-157.
Cherkassky V, Mulier F. 1998. Learning from data: concept, theory and method [M]. NY: John Wiley & Sons.
Cho KR, Seo BK, Lee JY, et al. 2005. A comparative study of 2D and 3D ultrasonography for evaluation of solid breast masses [J]. Eur J Radiol, 54(3): 365-370.
Chou YH, Tiu CM, Hung GS, et al. 2001. Stepwise Logistic Regression Analysis of Tumor Contour Features for Breast Ultrasound Diagnosis [J]. Ultrasound Med Biol, 27(11): 1493-1498.
Cole-Beuglet C, Kurtz AB, Rubin CS, et al. 1980. Ultrasound mammography. Radiol Clin North Am, 18(1): 133-143.
Doi K. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential [J]. Comput Med Imaging Graph, 31(4-5): 198-211.
Donoho D. 1995. De-noising by soft-thresholding [J]. IEEE Trans Information Theory, 41(3): 613-627.
Doyley MM, Srinivasan S, Pendergrass SA, et al. 2005. Comparative evaluation of strain-based and model-based modulus elastography [J]. Ultrasound Med Biol, 31(6): 787-802.
Drukker K, Giger ML, Vyborny CJ, et al. 2004. Computerized detection and classification of cancer on breast ultrasound [J]. Acad Radiol, 11(5): 526-535.
Durand F, Dorsey J. 2002. Fast bilateral filtering for the display of high dynamic range images [J]. ACM Trans Graphics, 21(3):257-266.
Freund Y, Schapire R. 1997. A decision-theoretic generalization of on-line learning and an application to boosting [J]. J Comput Syst Sci, 55(1): 119-139.
Gander W, Golub GH, Strebel R. 1994. Least-squares fitting of circles and ellipses [J]. BIT, 34: 558-578.
Garra BS, Krasner BH, Horii SC, et al. 1993. Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis [J]. Ultrason Imaging, 15(4): 267-285.
Garra BS, Cespedes I, Ophir J, et al. 1997. Elastography of the breast: Initial clinical results [J]. Radiology, 202(1): 79-86.
Gaser C, Volz HP, Kiebel S, et al. 1999. Detecting structural changes in whole brain based on nonlinear deformations-Application to schizophrenia research [J]. Neurolmage, 10:107-133.
Getty DJ, Pickett RM, D'Orsi CJ. 2001. Stereoscopic digital mammography: improving detection and diagnosis of breast cancer [J]. International Congress Series, 1230:535-544.
Giuseppetti GM, Martegani A, Di Cioccio B, et al. 2005. Elastosonography in the diagnosis of the nodular breast lesions: Preliminary report [J]. Radiol Med (Torino), 110(1-2): 69-76.
Hall TJ, Zhu YN, Spalding CS. 2003. In vivo real-time freehand palpation imaging [J]. Ultrasound Med Biol, 29(3): 427-435.
Han LH, Noble J A, Burcher M. 2003. A novel ultrasound indentation system for measuring biomechanical properties of in vivo soft tissue [J]. Ultrasound Med Biol, 29(6): 813-823.
Hsu CW, Chang CC, Lin CJ. 2007. A practical guide to support vector classification [EB/OL].
Taiwan: Department of Computer Science, National Taiwan University, [2007-12-20]. http://www.csie.ntu.edu.tw/～cjlin/libsvm/index.html.
Huang YL, Chen DR. 2004. Watershed segmentation for breast tumor in 2-D sonography [J]. Ultrasound Med Biol, 30(5): 625-632.
Huttenlocher DJ, Klanderman GA, Rucklidge WJ. 1993. Comparing images using the Hausdorff distance [J]. IEEE Trans Pattern Anal Machine Intell, 15(9): 850-863.
Itoh A, Ueno E, Tohno E, et al. 2006. Breast disease: clinical application of US elastography for diagnosis [J]. Radiology, 239(2): 341-350.
Jackson VP. 1990. The role of US in breast imaging [J], Radiology, 177(2): 305-311.
Joo S, Yang YS, Moon WK, et al. 2004. Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features [J]. IEEE Trans Med Imaging, 23(10): 1292-1300.
Kass M, Witkin AP, Terzopoulos D. 1988. Snakes: Active contour models [J]. Int J Computer Vision, 1(4): p321-331.
Key TJ, Verkasalo PK, Banks E. 2001. Epidemiology of Breast Cancer [J]. Lancet Oncology, 2: 133-140.
Khalkhali I, Cutrone J, Mena I, et al. 1995. Technetium-99m-Sestamibi scintimammography of breast lesions: clinical and Pathological follow-up [J]. J Nucl Med, 36(10): 1784-1789.
Kher A, Mitra S. 1993. Optimum morphological filtering to remove speckle noise form SAR images [C]. Proc SPIE Image Algebra and Morphological Image Processing IV, 2030:97-108.
Krouskop TA, Wheeler TM, Kallel F, et al. 1998. Elastic moduli of breast and prostate tissues under compression [J]. Ultrason Imaging, 20(4): 260-274.
Kuo WJ, Chang RF, Moon WK, et al. 2002. Computer-aided Diagnosis of Breast Tumors with Different US Systems [J]. Acad Radiol, 9(7): 793-799.
Ibanez L, Schroeder W. 2005. The ITK software guide second edition updated for ITK version 2.4 [EB/OL]. [2007-9-23]. http://www.itk.org.
Lee JS. 1981. Speckle analysis and smoothing of Synthetic Aperture Radar images [J]. Computer graphics and images processing, 17(1): 24 -32.
Lefebvre F, Meunier M, Thibault F, et al. 2000. Computerized ultrasound B-scan characterization of breast nodules [J]. Ultrasound Med Biol, 26(9): 1421-1428.
Li CM, Xu CY, Gui CF, et al. 2005. Level set evolution without re-initialization: a new variational formulation [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR), 1: 430-436.
Loupas T, Mcdicken WN, Allan PL. 1989. An adaptive weighted median filter for speckle suppression in medical ultrasound image [J]. IEEE Trans Circuits Syst, 36(1): 129-135.
Luo JW, Bai J, He P, et al. 2004. Axial strain calculation using a low-pass digital differentiator in ultrasound elastography [J]. IEEE Trans Ultrason Ferroelectr Freq Control, 51(9): 1119-1127.
Macsweeney JE, Cosgrove DO, Arenson J. 1996. Color Doppler energy (power) mode ultrasound [J], clin Radiol, 51(6): 387-390.
Madabhushi A, Metaxas DN. 2003. Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions [J], IEEE Trans Med Imaging, 22(2): 155-169.
Malladi R, Sethian JA, Vemuri BC. 1995. Shape modeling with front propagation - A level set approach [J]. IEEE Trans Pattern Anal Machine Intell, 17(2): 158-175.
Mallat S, Zhong S. 1992. Characterization of signals from multiscale edges [J]. IEEE Trans Pattern Anal Machine Intell, 14(7): 710-732.
Metz CE. 1986. ROC methodology in radiologic imaging [J]. Invest Radiol, 21(9): 720-733.
Meyberg-Solomayer GC, Kraemer B, Bergmann A, et al. 2004. Does 3-D sonography bring any advantage to noninvasive breast diagnostics?[J]. Ultrasound Med Biol, 30(5): 583-589.
Michailovich OV, Tannenbaum A. 2006. Despeckling of medical ultrasound images [J]. IEEE Trans UFFC, 53(1): 64-78.
Moon WK, Chang RF, Chen CJ, et al. 2005. Solid breast masses: classification with computer-aided analysis of continuous US images obtained with probe compression [J]. Radiology, 236(2): 458-464.
Mumford D, Shah J. 1989. Optimal approximation by piecewise smooth functions and associated variational problem [J]. Commun Pure Appl Math, 42(5): 577-685.
Ophir J, Cespedes I, Ponnekanti H, et al. 1991. Elastography: a quantitative method for imaging the elasticity of biological tissues [J]. Ultrason Imaging, 13(2): 111-134.
Ophir J, Cespedes I, Garra B, et al. 1996. Elastography: Ultrasonic imaging of tissue strain and elastic modulus in vivo [J]. Eur J Ultrasound, 3:49-70.
Osher S, Sethian JA. 1988. Fronts Propagating with Curvature Dependent Speed: Algorithms Based on the Hamilton-Jacobi Formulation [J]. J Comput Phys, 79(1): 12-49.
Otsu N. 1979. A threshold selection method from gray-level histograms [J]. IEEE Trans on Systems Man and Cybernetics, 9(1): 62-66.
Paranjape RB, Rangayyan RM, Morrow WM. 1994a. Adaptive neighborhood mean and median filtering [J]. J Electron Imag, 3(4): 360-367.
Paranjape RB, Rabie TF, Rangayyan RM. 1994b. Image restoration by adaptive neighborhood noise subtraction [J], Applied Optics, 33(14): 1861-1869.
Parker JR. 1997. Algorithms for image processing and computer vision [M]. New York, John Wiley & Sons, Inc., 23-29.
Perona P, Malik J. 1990. Scale-space and edge detection using anisotropic diffusion [J]. IEEE Trans Pattern Anal Machine Intell, 12(7): 629-639.
Pham DL, Prince JL. 1999. An adaptive fuzzy C-means algorithm for image segmentation in the presence of intensity inhomogeneities [J]. Pattern Recognition Letters, 20(1): 57-68.
Rahbar G, Sie AC, Hansen GC, et al. 1999. Benign versus malignant solid breast masses: US differentiation [J]. Radiology, 213(3): 889-894.
Rao M, Chen Q, Shi H, et al. 2007. Normal and shear strain estimation using beam steering on linear-array transducers [J], Ultrasound Med Biol, 33(1): 57-66.
Sahiner B, Petrick N, Chan HP, et al. 2001. Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization [J]. IEEE Trans Med Imaging, 20(12): 1275-1284.
Shen WC, Chang RF, Moon WK, et al. 2007. Breast ultrasound computer-aided diagnosis using BI-RADS features [J]. Acad Radiol, 14(8): 928-939.
Shiina T, Yamakawa M. 2004. Recent progress of ultrasound elasticity imaging technology [C]. Proceeding of 7th Congress of the Asian Federation of Societies for Ultrasound in Medicine and Biology (AFSUMB 2004), 59-63.
Sinha U, Kangarloo H. 2002. Principal component analysis for content-based image retrieval [J]. Radiographics, 22(5): 1271-1289.
Sivaramakrishna R, Powell KA, Lieber ML, et al. 2002. Texture analysis of lesions in breast ultrasound images [J]. Comput Med Imaging Graph, 26(5): 303-307.
Song YW, Upda SS. 1996. A new morphological approach for reducing speckle noise in ultrasonic images [C]. IEEE 39th Midwest symposium on Circuits and Systems, 3:1397-1400.
Srinivasan S, Krouskop T, Ophir J. 2004. A quantitative comparison of modulus images obtained using nanoindentation with strain elastograms [J]. Ultrasound Med Biol, 30(7): 899-918.
Stavros AT, Thickman D, Rapp CL, et al. 1995. Solid breast nodules: use of sonography to distinguish between benign and malignant lesions [J]. Radiology, 196(1):123-134.
Steinberg BD, Sullivan DC, Carlson DL. 1998. Disparity mapping applied to sonography of the breast [J]. Radiology, 207(2): 545-550.
Steinberg BD, Carlson DL, Zuckerman JA, et al. 2000. .Discrimination between cancers and benign breast lesions by ultrasound disparity mapping [C]. Proceedings of SPIE2000, 3982: 172-179.
Steinberg BD, Carlson DL, Birnbaum JA. 2001. Sonographic discrimination between benign and malignant breast lesions with use of disparity processing [J]. Acad Radiol, 8(8): 705-712.
Svensson WE, Amiras D. 2006. Ultrasound elasticity imaging [J]. Breast Cancer Online, e00: 1-7.
Thirion JP. 1996. Non-rigid matching using demons [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR), 245 -251.
Tominaga S, Kuroishi T. 1995. Epidemiology of Breast Cancer in Japan [J]. Cancer Letters, 90: 75-79.
Udupa JK, Smarasekera S, Barrett WA. 1992. Edge detection via dynamical programming [J]. SPIE Proc Medical Imaging, 1808:33-39.
Vapnik VN. 1995. The nature of statistical learning theory [M]. NY: Springer-Verlag. Vincent L, Soille P. 1991. Watersheds in digital spaces: An efficient algorithm based on immersion simulations [J] . IEEE Trans Pattern Anal Machine Intell, 13(6): 583-598.
Yamakawa M, Shiina T. 2001. Strain estimation using the extended combined autocorrelation method [J]. Jpn J Appl Phys, 40:3872-3876.
Yang MS. 1993. A survey of fuzzy clustering [J]. Math Comput Modeling, 18(11): 1-16.
Yu YJ, Scott TA. 2002. Speckle reducing anisotropic diffusion [J]. IEEE Trans Image Process, 11(11):1260-1270.
Zhang YJ. 1996. A survey on evaluation methods for image segmentation [J]. Pattern Recognition, 29(8): 1335-1346.
Zhao HK, Chan T, Merriman B, et al. 1996. A variational level set approach to multiphase motion [J]. J Comput Phys, 127(1): 179-195.
Zhu YN, Hall TJ. 2002. A modified block matching method for real-time freehand strain imaging [J]. Ultrason. Imaging, 24(3): 161-176.
Zong XL, Laine AF, Geiser EA. 1998. Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing [J], IEEE trans Med Imaging, 17(4): 532-540.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |