基于乳腺X线图像的乳腺癌检测方法研究
|
摘要
摘要：乳腺癌的早期检测和诊断是挽救患者生命的最有效途径。目前乳腺X线图像是乳腺癌检查最主要的影像方法,但是早期具有隐匿性的乳腺癌影像特征一般不够明显,受医生主观方面的影响,极易出现误诊和漏诊的情况。随着计算机技术的不断发展,乳腺癌计算机辅助检测已经成为医学图像处理领域的一项研究热点,有效的计算机辅助检测方法可以辅助医生更好的分析乳腺X线图像,从而提高乳腺癌诊断的准确率。微钙化点、肿块、结构扭曲是乳腺癌在X线图像上的主要表现,对这些病灶的检测是计算机辅助检测领域的一项研究难点。本文在前人研究基础上,通过结合机器学习、计算机视觉等领域的思想,构建乳腺癌的计算机辅助检测系统。本文取得的创新性研究成果总结如下：
(1)深入研究了乳腺X线图像乳腺区域分割方法和预处理中图像去噪,实现了基于最佳阈值的乳腺区域分割方法和基于自适应中值滤波的乳腺X线图像平滑方法。最佳阈值分割方法通过计算最佳阈值,快速有效的剔除乳腺X线图像中的标签、背景,分割出乳腺区域,从而确定了后续处理过程的研究区域；自适应中值滤波方法在进行滤波处理时为滤波器提供负反馈,在滤除噪声的同时能较好的保留图像细节信息,为乳腺X线图像后续处理提供了前提条件。
(2)针对乳腺X线图像微钙化点检测中微钙化点分割不够完整的问题,提出一种基于多分辨率区域生长和图像差值的微钙化点分割方法。通过改进传统区域生长的生长规则,在每一个目标区域得到一个最佳阈值,使每个目标区域均得到较好的分割效果,有效的保持了微钙化点的完整形状和分布信息,为后续的微钙化点检测提供了支持。
(3)深入分析了相关向量机及其最新进展——自适应核学习相关向量机的理论及推导过程,利用自适应核学习相关向量机的核参数自动优化设置和模型更稀疏的特性,探索性地将其应用于乳腺X线图像中肿块的检测,提出了一种基于自适应核学习相关向量机的乳腺x线图像肿块检测方法。实验结果表明该方法较支持向量机、相关向量机方法具有更好的检测性能和鲁棒性。
(4)针对乳腺X线图像结构扭曲检测假阳性率偏高的问题,提出了一种新的乳腺x线图像结构扭曲检测方法——相似度收敛指数(Similarity Convergence Index,SCI)方法。首先利用马氏距离比计算出毛刺的相似度,然后通过计算相似度加权的收敛指数增强放射状毛刺,最后提取出收敛指数的局部最大值作为候选点,并对这些候选点进行分类,检测出结构扭曲。实验结果表明该方法可有效的减弱非毛刺结构对检测的影响,大幅度降低结构扭曲检测的假阳性率,同时对于不同类型的乳腺X线图像具有较强的鲁棒性。
ABSTRACT:Early detection and diagnosis of breast cancer is the most effective way to save lives of patients. Mammogram is the most preferred method for breast cancer census at Present. However, the ambiguous characteristics of the early cancers and the subjective impact of the doctors will all probably induce the error and miss on diagnosing. With the rapid develop of computers, computer-aided detection of breast cancer has become one of the hot research points among medical image processing field. The effective computer-aided detection method can help doctors realize and analyze the mammograms better, and further improve the accuracy of diagnosis. Micro-calcifications(MCs), mass and architectural distortion(AD) are major signs of breast cancer, while the detection of these lesions is a difficult and challenge problem of the computer-aided detection system. The paper is established based on the previous research, and through incorporating the ideas of machine learning and computer vision, to construct the computer-aided detection analysis system. The main contributions and innovation are as follows:
(1) Breast region segmentation and image denoising in mammogram preprocessing are explored. A breast region segmentation method based on optimal threshold and an image smoothing method based on adaptive median filtering are realized. The optimal threshold is computed to remove labels and background from mammogram to segment breast region, which can obtain research region for subsequent processing. Adaptive median filtering provides negative feedback for filters, which is capable of smoothing noise as well as retaining the details in the image, providing support to subsequent processing.
(2) In view of the problem that micro-calcifications are segmented incompletely in micro-calcification detection, a method of micro-calcification segmentation based on multi-resolution region growth and mage difference is proposed. In the method, an optimal threshold is obtained in each target region, in which the segmentation is effective. The shape and distribution of micro-calcifications can be obtained accurately, providing support to the subsequent micro-calcification processing.
(3) The basic theories of relevance vector machine (RVM) and its development---adaptive kernel learning based relevance vector machine (aRVM) are analyzed. Using the capable of aRVM automatically learning the parameters of the kernel, the use of aRVM for detection of mass in mammograms is explored, and a detection method for mass based on aRVM is proposed. The experimental results show that for mass detection, the aRVM method has better detection performance and robustness than method of SVM and RVM.
(4) For the problem of high false positive rate in the detection of architectural distortion (AD) in mammograms, a method to detect AD based on speculation similarity convergence index (SCI) is proposed. In the method, the spiculation similarity based on Mahalanobis distance is presented and applied to compute SCI to enhance radiating spiculations. Then local maximum values of SCI are extracted as AD candidates, and lastly these candidates are classified into AD and normal tissues. The experimental results show that the proposed method can effectively weaken the effect of non-spiculations on AD detection, which can reduce false positive rate significantly and be applied to mammograms of various breast types.
(1)深入研究了乳腺X线图像乳腺区域分割方法和预处理中图像去噪,实现了基于最佳阈值的乳腺区域分割方法和基于自适应中值滤波的乳腺X线图像平滑方法。最佳阈值分割方法通过计算最佳阈值,快速有效的剔除乳腺X线图像中的标签、背景,分割出乳腺区域,从而确定了后续处理过程的研究区域；自适应中值滤波方法在进行滤波处理时为滤波器提供负反馈,在滤除噪声的同时能较好的保留图像细节信息,为乳腺X线图像后续处理提供了前提条件。
(2)针对乳腺X线图像微钙化点检测中微钙化点分割不够完整的问题,提出一种基于多分辨率区域生长和图像差值的微钙化点分割方法。通过改进传统区域生长的生长规则,在每一个目标区域得到一个最佳阈值,使每个目标区域均得到较好的分割效果,有效的保持了微钙化点的完整形状和分布信息,为后续的微钙化点检测提供了支持。
(3)深入分析了相关向量机及其最新进展——自适应核学习相关向量机的理论及推导过程,利用自适应核学习相关向量机的核参数自动优化设置和模型更稀疏的特性,探索性地将其应用于乳腺X线图像中肿块的检测,提出了一种基于自适应核学习相关向量机的乳腺x线图像肿块检测方法。实验结果表明该方法较支持向量机、相关向量机方法具有更好的检测性能和鲁棒性。
(4)针对乳腺X线图像结构扭曲检测假阳性率偏高的问题,提出了一种新的乳腺x线图像结构扭曲检测方法——相似度收敛指数(Similarity Convergence Index,SCI)方法。首先利用马氏距离比计算出毛刺的相似度,然后通过计算相似度加权的收敛指数增强放射状毛刺,最后提取出收敛指数的局部最大值作为候选点,并对这些候选点进行分类,检测出结构扭曲。实验结果表明该方法可有效的减弱非毛刺结构对检测的影响,大幅度降低结构扭曲检测的假阳性率,同时对于不同类型的乳腺X线图像具有较强的鲁棒性。
ABSTRACT:Early detection and diagnosis of breast cancer is the most effective way to save lives of patients. Mammogram is the most preferred method for breast cancer census at Present. However, the ambiguous characteristics of the early cancers and the subjective impact of the doctors will all probably induce the error and miss on diagnosing. With the rapid develop of computers, computer-aided detection of breast cancer has become one of the hot research points among medical image processing field. The effective computer-aided detection method can help doctors realize and analyze the mammograms better, and further improve the accuracy of diagnosis. Micro-calcifications(MCs), mass and architectural distortion(AD) are major signs of breast cancer, while the detection of these lesions is a difficult and challenge problem of the computer-aided detection system. The paper is established based on the previous research, and through incorporating the ideas of machine learning and computer vision, to construct the computer-aided detection analysis system. The main contributions and innovation are as follows:
(1) Breast region segmentation and image denoising in mammogram preprocessing are explored. A breast region segmentation method based on optimal threshold and an image smoothing method based on adaptive median filtering are realized. The optimal threshold is computed to remove labels and background from mammogram to segment breast region, which can obtain research region for subsequent processing. Adaptive median filtering provides negative feedback for filters, which is capable of smoothing noise as well as retaining the details in the image, providing support to subsequent processing.
(2) In view of the problem that micro-calcifications are segmented incompletely in micro-calcification detection, a method of micro-calcification segmentation based on multi-resolution region growth and mage difference is proposed. In the method, an optimal threshold is obtained in each target region, in which the segmentation is effective. The shape and distribution of micro-calcifications can be obtained accurately, providing support to the subsequent micro-calcification processing.
(3) The basic theories of relevance vector machine (RVM) and its development---adaptive kernel learning based relevance vector machine (aRVM) are analyzed. Using the capable of aRVM automatically learning the parameters of the kernel, the use of aRVM for detection of mass in mammograms is explored, and a detection method for mass based on aRVM is proposed. The experimental results show that for mass detection, the aRVM method has better detection performance and robustness than method of SVM and RVM.
(4) For the problem of high false positive rate in the detection of architectural distortion (AD) in mammograms, a method to detect AD based on speculation similarity convergence index (SCI) is proposed. In the method, the spiculation similarity based on Mahalanobis distance is presented and applied to compute SCI to enhance radiating spiculations. Then local maximum values of SCI are extracted as AD candidates, and lastly these candidates are classified into AD and normal tissues. The experimental results show that the proposed method can effectively weaken the effect of non-spiculations on AD detection, which can reduce false positive rate significantly and be applied to mammograms of various breast types.
引文
[1]章鲁,陈瑛,顾顺德,等.医学图像处理与分析.上海.上海科学技术出版社.2006.1-2
[2]NCI Cancer Fact Sheets. http://www.cancer.gov/cancertopics/types/breast.2008
[3]WHO Cancer Fact Sheets. http://www.who.int/mediacentre/factsheets/fs297/en/index.html.2009
[4]M. Althuis, J. Dozier, W. Anderson, et al. Global trends in breast cancer incidence and mortality 1973-1997. Int. J. Epidemiol.2005.34(2).405-412
[5]International Agency for Research on Cancer. World cancer report. International Agency for Research on Cancer.2008
[6]J. V. Lacey, A. R. Kreimer, S. S. Buys, et al. Breast cancer epidemiology according to recognized breast cancer risk factors in the prostate, lung, colorectal and ovarian (PLCO) cancer screening trial cohort. Bmc Cancer.2009.9(84)
[7]B. O. Anderson, C. H. Yip, R. A. Smith, et al. Guideline implementation for breast healthcare in low-income and middle-income countries overview of the breast health global initiative global summit. Cancer.2008.113(8).2221-2243
[8]M. P. Coleman, M. Quaresma, F. Berrino, et al. Cancer survival in five continents:a worldwide population-based study. Lancet Oncology.2008.9(8).730-756
[9]World Health Organization. Breast cancer:prevention and control. http://www.who.int/cancer/detection/breastcancer/en/index.html.2009
[10]World Health Organization. Cancer control:knowledge into action:WHO guide for effective programmes:early detection. World Health Organization.2007
[11]曾繁余.乳腺癌早期筛查方法及其应用.华夏医学.2012.25(4).644-647
[12]王荣福.乳腺癌影像诊断技术应用进展.中国医学影像技术.2009.(5).905-907
[13]赵年,秦燕,袁方均.早期乳腺癌影像学诊断现状及进展.湖北医药学院学报.2011.(5).445-447
[14]H. P. Chan, K. Doi, S. Galhotra, et al. Image feature analysis and computer-aided diagnosis in digital radiography I Automated detection of microcalcifications in mammography. Medical Physics.1987.14(4).538-548
[15]M. L. Giger, K. Doi and H. Macmahon. Image feature analysis and computer-aided diagnosis in digital radiography.3. Automated detection of nodules in peripheral lung fields. Medical Physics.1988.15(2).158-166
[16]E. D. Pisano, C. Gatsonis, E. Hendrick. Diagnostic performance of digital versus film mammography for breast-cancer screening. The New England Journal of Medicine.2005. 353(17).1773-1783
[17]J. Elmore, M.Wells, M.Carol, et al. Variability in radiologists' interpretation of mammograms. The New England Journal of Medieine.1994.331.1493-1499
[18]M. L. Giger, H. P. Chan, J. Boone. Anniversary Paper:History and status of CAD and quantitative image analysis:The role of Medical Physics and AAPM. Medical Physics.2008. 35(12).5799-5820
[19]R. F. Brem, J. Baum, M. Leehner, et al. Improvement insensitivity of screening mammography with computer-aided detection:a multi-institutional trial. American Journal of Roentgenology 2003.181.687-693
[20]邵婉仪.乳腺X线摄影投照体位和压迫技术的应用及质量控制.实用医技杂志.2006.13(22).4079-4080
[21]D. J. Dronkers, J. H. C. L. Hendriks, R. Holland, et al. The practice of mammography: pathology, technique, interpretation, adjunct modalities. Stuttgart, Germany. Georg Thieme Verlag.2002
[22]曹志坚.乳腺癌钼靶X线表现特征(118例分析).放射学实践.2009.24(1).39-42
[23]American College of Radiology. Breast imaging reporting and date system (BI-RADS).3rd ed. American College of Radiology.1998
[24]L. Tabar and P B. Dean. Teaching atlas of mammography. Fortschr Geb Rontgenstrahlen Nuklearmed Erganzungsbd.1983.116.1-222
[25]顾雅佳,周康荣,陈彤咸,等.乳腺癌的X线表现及病理基础.中华放射学杂志.2003.37(5).439-444
[26]H. Jing, Y. Yang, R. M. Nishikawa. Detection of clustered micro-calcifications using spatial point process modeling. Physics in medicine and biology.2011.56(1).1-17
[27]K. J. McLoughlin, P. J. Bones, and N. Karssemeijer. Noise equalization for detection of microcalcification clusters in direct digital mammogramimages. IEEE Trans Med Imag.2004. 23(3).313-320
[28]M. G. Linguraru, K. Marias, R. English, et al. A biologically inspired algorithm for microcalcification cluster detection. Med Image Anal.2006.10(6).850-862
[29]B.Caputo, E. L. Torre, S. Bouattour, et al. A new kernel method for microcalcification detection: Spin glass-Markov random fields. Stud Health Technol Inf.2002.90.30-34
[30]P. Casaseca-de-la-Higuera, J. I. Arribas, E. Munoz-Moreno, et al. A comparative study on microcalcification detection methods with posterior probability estimation based on Gaussian mixture models. Proc 27th Annu. Int Conf Eng Med Biol Soc.2005.1.49-54
[31]R. Nakayama, Y. Uchiyama, K. Yamamoto, et al. Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms. IEEE Trans Biomed Eng.2006.53(2).273-283
[32]E. Regentova, L. Zhang, J. Zheng, et al. Microcalcification detection based on wavelet domain hidden Markov tree model:Study for inclusion to computer aided diagnostic prompting system. Med Phys.2007.34(6).2206-2219
[33]J. Jiang, B. Yao, and A. M. Wason. A genetic algorithm design for microcalcification detection and classification in digital mammograms. Comput Med Imag Graph.2007.31(1).49-61
[34]Y. Peng, B. Yao, and J. Jiang, "Knowledge-discovery incorporated evolutionary search for microcalcification detection in breast cancer diagnosis," Artif. Intell. Med., vol.37, no.1, pp. 43-53,2006
[35]I. El Naqa, Y. Yang, M. N. Wernick, N. P. Galatsanos, and R. M. Nishikawa, "A support vector machine approach for detection of microcalcifications," IEEE Trans.Med. Imag., vol.21, no.12, pp.1552-1563, Dec.2002
[36]S. Singh, V. Kumar, H. K. Verma, and D. Singh, "SVM based system for classification of microcalcifications in digital mammograms," in Proc 28th Annu Int Conf Eng Med Biol Soc. 2006.1.4747-4750
[37]L. Wei, Y. Yang, R. M. Nishikawa, et al. Relevance vector machine for automatic detection of clustered microcalcifications. IEEE Trans Med Imag.2005.24(10).1278-1285
[38]董妍,高新波,王颖.一种基于Top-hat的乳腺图像中钙化点的检测方法.中国图象图形学 报.2006.11(12).1839-1843
[39]万柏坤,王瑞平,朱欣.SVM算法及其在乳腺X片微钙化点自动检测中的应用.电子学报.2004.32(4).587-590
[40]高洁,宋立新.基于微钙化点检测的乳腺X光片计算机辅助诊断系统.哈尔滨理工大学学报.2006.11(4).18-21
[41]文浩,马金盛,王玉慧,等.基于形态学灰度重构的乳腺微钙化点提取.CT理论与应用研究.2006.15(2).33-37
[42]W.P.Kegelmeyer, J.M.Pruneda, P.D.Bourland, et al. Computer-aided mammographic screening for speculated lesions. Radiology.1994.191(2).331-337
[43]S. Liu, C. F. Babbs, and E. J. Delp. Multiresolution detection of spiculated lesions in digital mammograms," IEEE Trans. Image Process, vol.10, no.6, pp.874-884, Jun.2001
[44]M. P. Sampat, A. C. Bovik. Detection of spiculated lesions in mam-mograms. Proc 25th Annu Int Conf IEEE Eng Med Biol Soc.2003.1.810-813
[45]R. Campanini, D. Dongiovanni, E. Iampieri, et al. A novel featureless approach to mass detection in digital mammograms based on support vector machines. Phys Med Biol.2004. 49(6).961-975
[46]G. Kom, A. Tiedeu, and M. Kom. Automated detection of masses in mammograms by local adaptive thresholding. Comput Biol Med.2007.37(1).37-48
[47]N. H. Eltonsy, G. D. Tourassi, and A. S. Elmaghraby. A concentric morphologymodel for the detection ofinasses inmammography. IEEE Trans Med Imag.2007.26(6).880-889
[48]H. P. Chan, D.Wei, M. A. Helvie, et al. Computer-aided classification of mammographic masses and normal tissue:Linear discriminant analysis in texture feature space. Phys Med Biol. 1995.40(5).857-876
[49]B. Sahiner, H. P. Chan, N. Petrick, et al. Classification of mass and normal breast tissue:A convolution neural network classifier with spatial domain and texture images. IEEE Trans Med Imag.1996.15(5).598-610
[50]N. R. Mudigonda, R. M. Rangayyan, and J. E. L. Desautels. Gradient and texture analysis for the classification of mammographic masses. IEEE Trans Med Imag.2008.19(10).1032-1043
[51]J. Wei, B. Sahiner, L. Hadjiiski, et al. Computer aided detection of breast masses on full field digital mammograms. Med Phys.2005.32(9).2827-2837
[52]S. Timp, C. Varela, N. Karssemeijer, and et al. Temporal change analysis for characterization of mass lesions in mammography. IEEE Trans Med. Imag.2007.26(7).945-953
[53]G. D. Tourassi, R. Vargas-Voracek. Computer-assisted detection of mammographic masses:A template matching scheme based on mutual information. Med Phys.2003.30(8).2123-2130
[54]S. M. Lai, X. Li, and W. F. Biscof. On techniques for detecting circumscribed masses in mammograms. IEEE Trans Med Imag.1989.18(4).377-386
[55]F. Moayedi, R. Boostani, Z. Azimifar, et al. A support vector based fuzzy neural network approach for mass classification in mammography. Proc 15th Int Conf Digit Signal Process. 2007.1(4).240-243
[56]张一飞,于戈,张智祺,等.基于多尺度的乳腺图像中星形肿块检测方法.哈尔滨工程大学学报.2006.27.194-197
[57]虞红伟,厉力华,徐伟栋,等.一种基于水平集的多尺度乳腺肿块分割方法.仪器仪表学报.2010.31(6).1418-1423
[58]彭芳青,厉力华,徐伟栋,等,基于Multi-Agent的乳腺钼靶图像肿块分类方法.传感技术 学报.2010.23(2).153-157
[59]Ayres FJ, Rangayyan RM. Characterization of architectural distortion in mammograms. Proc of the 25th Annual Int Conf of the IEEE Engineering in Medicine and Biology Society. Cancun, Mexico.2003.886-889
[60]Ayres FJ, Rangayyan RM. Detection of architectural distortion in mammograms using phase portraits. Proceedings SPIE International Symposium on Medical Imaging:Image Processing. San Diego.2004.5370.587-597
[61]Tourassi GD, Delong DM, Floyd Jr CE. A study on the computerized fractal analysis of architectural distortion in screening mammograms. Phys Med Biol.2006.51.1299-1312
[62]Q Guo, J Shao, V Ruiz. Investigation of support vector machine for the detection of architectural distortion in mammographic images. Journal of Physics Conference Series.2005. 15.88-94
[63]龚著琳,陈瑛,章鲁.用支持向量机检测乳腺X线影像中的结构扭曲.上海交通大学学报.2009.26(4).503-507
[64]Baeg S, Kehtarnavaz N, Dougherty E. Morphological Texture Based Classification of Abnormalities in Mammograms. Proceedings of SPIE's International Symposium on Medical Imaging. San Diego.1999.20-26
[65]Baeg S, Kehtamavaz N. Texture Based Classification of Mass Abnormalities in Mammograms. CBMS 2000 Proceedings 13th IEEE Symposium Computer-Based Medical Systems. Houston. 2000.163-168
[66]Mudigonda NR, Rangayyan RM, Desautels JEL. Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE Trans Medical Imaging.2001.20(12). 1215-1227
[67]Mudigonda NR, Rangayyan RM. Texture flow-field analysis for the detection of architectural distortion in mammograms. Proc of Biovisionvision. Bangalore, India.2001.76-81
[68]Michael Heath, Kevin Bowyer, Daniel Kopans, et al. Digital Database for Screening Mammography. http://marathon.csee.usf.edu/Mammography/Database.html.2007
[69]John Suckling. The Mammographic Image Analysis Society Digital Mammogram Database. http://peipa.essex.ac.uk/info/mias.html.2012
[70]Bornefalk H, Hermansson A B. On the comparison of FROC curves in mammography CAD systems. Medical Physics.2005.32(2).412-417
[71]张兆礼,赵春晖,梅晓丹.现代图像处理技术及Matlab实现.北京.人民邮电出版社.2001.
[72]Go C-S, Lim S, Kim S. Themodeling and the optimization of a grating optical low-pass filter. Applied PhysicsB:Lasers and Optics.2001.73(7).721-725
[73]HeinleinP, DrexlJ, Schneider W. Integrated Wavelets for Enhancement of in Mieroealeification Digital MammograPhy. IEEE Transaction on Medieal Imaging.2003.22(3).402-413
[74]Wirth M, Fraschini M, Lyon J. Contrast Enhancement of Microcalcifications in Mammograms Using Morphological Enhancement and Non-flat Structuring Elements. Proc of the 17th IEEE Symposium on Computer-based Medical Systems.2004
[75]孙蕾,温有奎.图像增强算法与评价方法研究.计算机工程.2007.33(8).168-172.
[76]R. Adams, L. Bischof. Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence.1994.16(6).641-647
[77]A. Mehnert, P. Jackway. An improved seeded region growing algorithm. Pattern Recognition Letters.1997. (18).1065-1071
[78]F. Y. Shih, Cheng Shouxian. Automatic seeded region growing for color image segmentation. Image and Vision Computing.2005.23(10).877-886
[79]Chang Y L, Li X B. Adaptive image region growing. IEEE Transactions on Image Processing. 1994.3(6).450-454
[80]Campanini R, Dongiovanni E, Iampieri E. A novel featureless approach to mass detection in digital mammograms based on support vector machines. Physics Medicine Biology.2002.49(6) 961-975
[81]Mavroforakis M E, Georgiou H V, Dimitropoulos N, et al. Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artificial Intelligence.2006.37(2).145-162
[82]王颖,高新波,李洁,等.基于PSVM的主动学习肿块检测方法.计算机研究与发展.2012.49(3).572-578.
[83]D. G. Tzikas, A. C. Likas, and N. P. Galatsanos, Sparse Bayesian modeling with adaptive kernel learning. IEEE Trans Neural Networks.2009.20(6).926-936
[84]M. M. Dundar, D. A. Landgrebe. Toward an optimal supervised classier for the analysis of hyperspectral data. IEEE Trans Geosci Remote Sens.2004.42(1).271-277
[85]B. Demir, S. Erturk. Hyperspectral Image Classification Using Relevance Vector Machines. IEEE Geoscience and Remote Sensing Letters.2007.4(4).586-590
[86]陆爱国,王珏,刘红卫.基于改进的SVM学习算法及其在信用评分中的应用.系统工程理论与实践.2012.32(3).515-521
[87]Tipping ME. Sparse Bayesian Learning and the Relevance Vector Machine. Journal of Machine Learning Research.2001.1(2001).211-244
[88]朱旭锋,马彩文,刘波.基于特征级融合和支持向量机的飞机识别.光电子·激光.2011.22(11).1710-1713
[89]K. R. Muller, S. Mika, G. Ratsch, et al. An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw.2001.12(2).181-201
[90]M. E. Tipping, A. Faul. Fast marginal likelihood maximization for sparse Bayesian models. Proceedings of 9th International Workshop on Artificial Intelligence and Statistics. Key West, USA.2003
[91]Li H, Wang Y, Liu K J R, et al. Computerized radiographic mass detection. II. Decision support by featured database visualization and modular neural networks. IEEE Transactions on Medical Imaging.2001.20(4).302-313
[92]杨德坤,侯德文,步亚东.灰度共生矩阵在纹理特征提取中的发展.信息系统工程.2012.(1).134-136
[93]周明全,耿国华,韦娜.基于内容图像检索技术.第2版.北京.清华大学出版社.2007
[94]唐坚刚,刘丛.基于小波分解和游程长度矩阵的医学图像检索.计算机工程与设计.2010.31(8).1771-1774
[95]American College of Radiology. About BI-RADS. http://www.birads.at/info.html.2012
[96]J A Baker, E L Rosen, J Y Lo, et al. Computer-aided detection (CAD) in screening mammography:Sensitivity of commercial CAD systems for detecting architectural distortion. American Journal of Roentgenology.2003.181(4).1083-1088
[97]R M Rangayyan, F J Ayres. Gabor filters and phase portraits for the detection of architectural distortion in mammograms. Medical and Biological Engineering and Computing.2006.44(10). 883-894
[98]Sampat M P, Whitman G J, Markey M K, et al. Evidence based detection of spiculated masses and architectural distortions. Proceedings of the SPIE Medical Imaging:Image Processing. 2005.5747.26-37
[99]Shantanu Banik, R M Rangayyan, J E Leo Desautels. Detection of Architectural Distortion in Prior Mammograms. IEEE Transactions on Medical Imaging.2011.30(2).279-294
[100]Ayres F J, Rangayyan R M. Reduction of false positives in the detection of architectural distortion in mammograms by using a geometrically constrained phase portrait model. International Journal of Computer Assisted Radiology and Surgery.2007.1(6).361-369
[101]S. K. Biswas, D. P. Mukherjee. Recognizing architectural distortion in mammogram:a multiscale texture modeling approach with GMM. IEEE Transactions on Biomedical Engineering.2011.58(7).2023-2030
[102]Herman G T, Huang Lianjie, Li Youming. Basic methods of tomography and inverse problems IOP publishing limited and individual contributor. Beijing. Petroleum Industry Press.1997
[103]Pratt W. Digital Image Processing:PIKS Scientific Inside.4th ed. New York. Wiley.2007
[104]李军宏,潘泉,陈玉春,等.基于Radon变换的矩不变量及其应用.西北工业大学学报.2004.22(3).392-396
[105]Kwok SM, Chandrasekhar R, Attikiouzel Y. Automatic pectoral muscle segmentation on mammograms by straight line estimation and cliff detection. Proceedings of 7th Australian and New Zealand Intelligent Information Systems Conference. Perth, Australia. ARCME-UWA, 2001.67-72
[106]S.E. Grigorescu, N. Petkov, P. Kruizinga. Comparison of texture features based on Gabor filters. IEEE Transactions on Image Processing.2002.11(10).1160-1167
[107]te Brake GM, Karssemeijer N, Hendriks JH. An automatic method to discriminate malignant masses from normal tissue in digital mammograms. Physics in Medicine and Biology.2000. 45(10).2843-2857
[2]NCI Cancer Fact Sheets. http://www.cancer.gov/cancertopics/types/breast.2008
[3]WHO Cancer Fact Sheets. http://www.who.int/mediacentre/factsheets/fs297/en/index.html.2009
[4]M. Althuis, J. Dozier, W. Anderson, et al. Global trends in breast cancer incidence and mortality 1973-1997. Int. J. Epidemiol.2005.34(2).405-412
[5]International Agency for Research on Cancer. World cancer report. International Agency for Research on Cancer.2008
[6]J. V. Lacey, A. R. Kreimer, S. S. Buys, et al. Breast cancer epidemiology according to recognized breast cancer risk factors in the prostate, lung, colorectal and ovarian (PLCO) cancer screening trial cohort. Bmc Cancer.2009.9(84)
[7]B. O. Anderson, C. H. Yip, R. A. Smith, et al. Guideline implementation for breast healthcare in low-income and middle-income countries overview of the breast health global initiative global summit. Cancer.2008.113(8).2221-2243
[8]M. P. Coleman, M. Quaresma, F. Berrino, et al. Cancer survival in five continents:a worldwide population-based study. Lancet Oncology.2008.9(8).730-756
[9]World Health Organization. Breast cancer:prevention and control. http://www.who.int/cancer/detection/breastcancer/en/index.html.2009
[10]World Health Organization. Cancer control:knowledge into action:WHO guide for effective programmes:early detection. World Health Organization.2007
[11]曾繁余.乳腺癌早期筛查方法及其应用.华夏医学.2012.25(4).644-647
[12]王荣福.乳腺癌影像诊断技术应用进展.中国医学影像技术.2009.(5).905-907
[13]赵年,秦燕,袁方均.早期乳腺癌影像学诊断现状及进展.湖北医药学院学报.2011.(5).445-447
[14]H. P. Chan, K. Doi, S. Galhotra, et al. Image feature analysis and computer-aided diagnosis in digital radiography I Automated detection of microcalcifications in mammography. Medical Physics.1987.14(4).538-548
[15]M. L. Giger, K. Doi and H. Macmahon. Image feature analysis and computer-aided diagnosis in digital radiography.3. Automated detection of nodules in peripheral lung fields. Medical Physics.1988.15(2).158-166
[16]E. D. Pisano, C. Gatsonis, E. Hendrick. Diagnostic performance of digital versus film mammography for breast-cancer screening. The New England Journal of Medicine.2005. 353(17).1773-1783
[17]J. Elmore, M.Wells, M.Carol, et al. Variability in radiologists' interpretation of mammograms. The New England Journal of Medieine.1994.331.1493-1499
[18]M. L. Giger, H. P. Chan, J. Boone. Anniversary Paper:History and status of CAD and quantitative image analysis:The role of Medical Physics and AAPM. Medical Physics.2008. 35(12).5799-5820
[19]R. F. Brem, J. Baum, M. Leehner, et al. Improvement insensitivity of screening mammography with computer-aided detection:a multi-institutional trial. American Journal of Roentgenology 2003.181.687-693
[20]邵婉仪.乳腺X线摄影投照体位和压迫技术的应用及质量控制.实用医技杂志.2006.13(22).4079-4080
[21]D. J. Dronkers, J. H. C. L. Hendriks, R. Holland, et al. The practice of mammography: pathology, technique, interpretation, adjunct modalities. Stuttgart, Germany. Georg Thieme Verlag.2002
[22]曹志坚.乳腺癌钼靶X线表现特征(118例分析).放射学实践.2009.24(1).39-42
[23]American College of Radiology. Breast imaging reporting and date system (BI-RADS).3rd ed. American College of Radiology.1998
[24]L. Tabar and P B. Dean. Teaching atlas of mammography. Fortschr Geb Rontgenstrahlen Nuklearmed Erganzungsbd.1983.116.1-222
[25]顾雅佳,周康荣,陈彤咸,等.乳腺癌的X线表现及病理基础.中华放射学杂志.2003.37(5).439-444
[26]H. Jing, Y. Yang, R. M. Nishikawa. Detection of clustered micro-calcifications using spatial point process modeling. Physics in medicine and biology.2011.56(1).1-17
[27]K. J. McLoughlin, P. J. Bones, and N. Karssemeijer. Noise equalization for detection of microcalcification clusters in direct digital mammogramimages. IEEE Trans Med Imag.2004. 23(3).313-320
[28]M. G. Linguraru, K. Marias, R. English, et al. A biologically inspired algorithm for microcalcification cluster detection. Med Image Anal.2006.10(6).850-862
[29]B.Caputo, E. L. Torre, S. Bouattour, et al. A new kernel method for microcalcification detection: Spin glass-Markov random fields. Stud Health Technol Inf.2002.90.30-34
[30]P. Casaseca-de-la-Higuera, J. I. Arribas, E. Munoz-Moreno, et al. A comparative study on microcalcification detection methods with posterior probability estimation based on Gaussian mixture models. Proc 27th Annu. Int Conf Eng Med Biol Soc.2005.1.49-54
[31]R. Nakayama, Y. Uchiyama, K. Yamamoto, et al. Computer-aided diagnosis scheme using a filter bank for detection of microcalcification clusters in mammograms. IEEE Trans Biomed Eng.2006.53(2).273-283
[32]E. Regentova, L. Zhang, J. Zheng, et al. Microcalcification detection based on wavelet domain hidden Markov tree model:Study for inclusion to computer aided diagnostic prompting system. Med Phys.2007.34(6).2206-2219
[33]J. Jiang, B. Yao, and A. M. Wason. A genetic algorithm design for microcalcification detection and classification in digital mammograms. Comput Med Imag Graph.2007.31(1).49-61
[34]Y. Peng, B. Yao, and J. Jiang, "Knowledge-discovery incorporated evolutionary search for microcalcification detection in breast cancer diagnosis," Artif. Intell. Med., vol.37, no.1, pp. 43-53,2006
[35]I. El Naqa, Y. Yang, M. N. Wernick, N. P. Galatsanos, and R. M. Nishikawa, "A support vector machine approach for detection of microcalcifications," IEEE Trans.Med. Imag., vol.21, no.12, pp.1552-1563, Dec.2002
[36]S. Singh, V. Kumar, H. K. Verma, and D. Singh, "SVM based system for classification of microcalcifications in digital mammograms," in Proc 28th Annu Int Conf Eng Med Biol Soc. 2006.1.4747-4750
[37]L. Wei, Y. Yang, R. M. Nishikawa, et al. Relevance vector machine for automatic detection of clustered microcalcifications. IEEE Trans Med Imag.2005.24(10).1278-1285
[38]董妍,高新波,王颖.一种基于Top-hat的乳腺图像中钙化点的检测方法.中国图象图形学 报.2006.11(12).1839-1843
[39]万柏坤,王瑞平,朱欣.SVM算法及其在乳腺X片微钙化点自动检测中的应用.电子学报.2004.32(4).587-590
[40]高洁,宋立新.基于微钙化点检测的乳腺X光片计算机辅助诊断系统.哈尔滨理工大学学报.2006.11(4).18-21
[41]文浩,马金盛,王玉慧,等.基于形态学灰度重构的乳腺微钙化点提取.CT理论与应用研究.2006.15(2).33-37
[42]W.P.Kegelmeyer, J.M.Pruneda, P.D.Bourland, et al. Computer-aided mammographic screening for speculated lesions. Radiology.1994.191(2).331-337
[43]S. Liu, C. F. Babbs, and E. J. Delp. Multiresolution detection of spiculated lesions in digital mammograms," IEEE Trans. Image Process, vol.10, no.6, pp.874-884, Jun.2001
[44]M. P. Sampat, A. C. Bovik. Detection of spiculated lesions in mam-mograms. Proc 25th Annu Int Conf IEEE Eng Med Biol Soc.2003.1.810-813
[45]R. Campanini, D. Dongiovanni, E. Iampieri, et al. A novel featureless approach to mass detection in digital mammograms based on support vector machines. Phys Med Biol.2004. 49(6).961-975
[46]G. Kom, A. Tiedeu, and M. Kom. Automated detection of masses in mammograms by local adaptive thresholding. Comput Biol Med.2007.37(1).37-48
[47]N. H. Eltonsy, G. D. Tourassi, and A. S. Elmaghraby. A concentric morphologymodel for the detection ofinasses inmammography. IEEE Trans Med Imag.2007.26(6).880-889
[48]H. P. Chan, D.Wei, M. A. Helvie, et al. Computer-aided classification of mammographic masses and normal tissue:Linear discriminant analysis in texture feature space. Phys Med Biol. 1995.40(5).857-876
[49]B. Sahiner, H. P. Chan, N. Petrick, et al. Classification of mass and normal breast tissue:A convolution neural network classifier with spatial domain and texture images. IEEE Trans Med Imag.1996.15(5).598-610
[50]N. R. Mudigonda, R. M. Rangayyan, and J. E. L. Desautels. Gradient and texture analysis for the classification of mammographic masses. IEEE Trans Med Imag.2008.19(10).1032-1043
[51]J. Wei, B. Sahiner, L. Hadjiiski, et al. Computer aided detection of breast masses on full field digital mammograms. Med Phys.2005.32(9).2827-2837
[52]S. Timp, C. Varela, N. Karssemeijer, and et al. Temporal change analysis for characterization of mass lesions in mammography. IEEE Trans Med. Imag.2007.26(7).945-953
[53]G. D. Tourassi, R. Vargas-Voracek. Computer-assisted detection of mammographic masses:A template matching scheme based on mutual information. Med Phys.2003.30(8).2123-2130
[54]S. M. Lai, X. Li, and W. F. Biscof. On techniques for detecting circumscribed masses in mammograms. IEEE Trans Med Imag.1989.18(4).377-386
[55]F. Moayedi, R. Boostani, Z. Azimifar, et al. A support vector based fuzzy neural network approach for mass classification in mammography. Proc 15th Int Conf Digit Signal Process. 2007.1(4).240-243
[56]张一飞,于戈,张智祺,等.基于多尺度的乳腺图像中星形肿块检测方法.哈尔滨工程大学学报.2006.27.194-197
[57]虞红伟,厉力华,徐伟栋,等.一种基于水平集的多尺度乳腺肿块分割方法.仪器仪表学报.2010.31(6).1418-1423
[58]彭芳青,厉力华,徐伟栋,等,基于Multi-Agent的乳腺钼靶图像肿块分类方法.传感技术 学报.2010.23(2).153-157
[59]Ayres FJ, Rangayyan RM. Characterization of architectural distortion in mammograms. Proc of the 25th Annual Int Conf of the IEEE Engineering in Medicine and Biology Society. Cancun, Mexico.2003.886-889
[60]Ayres FJ, Rangayyan RM. Detection of architectural distortion in mammograms using phase portraits. Proceedings SPIE International Symposium on Medical Imaging:Image Processing. San Diego.2004.5370.587-597
[61]Tourassi GD, Delong DM, Floyd Jr CE. A study on the computerized fractal analysis of architectural distortion in screening mammograms. Phys Med Biol.2006.51.1299-1312
[62]Q Guo, J Shao, V Ruiz. Investigation of support vector machine for the detection of architectural distortion in mammographic images. Journal of Physics Conference Series.2005. 15.88-94
[63]龚著琳,陈瑛,章鲁.用支持向量机检测乳腺X线影像中的结构扭曲.上海交通大学学报.2009.26(4).503-507
[64]Baeg S, Kehtarnavaz N, Dougherty E. Morphological Texture Based Classification of Abnormalities in Mammograms. Proceedings of SPIE's International Symposium on Medical Imaging. San Diego.1999.20-26
[65]Baeg S, Kehtamavaz N. Texture Based Classification of Mass Abnormalities in Mammograms. CBMS 2000 Proceedings 13th IEEE Symposium Computer-Based Medical Systems. Houston. 2000.163-168
[66]Mudigonda NR, Rangayyan RM, Desautels JEL. Detection of breast masses in mammograms by density slicing and texture flow-field analysis. IEEE Trans Medical Imaging.2001.20(12). 1215-1227
[67]Mudigonda NR, Rangayyan RM. Texture flow-field analysis for the detection of architectural distortion in mammograms. Proc of Biovisionvision. Bangalore, India.2001.76-81
[68]Michael Heath, Kevin Bowyer, Daniel Kopans, et al. Digital Database for Screening Mammography. http://marathon.csee.usf.edu/Mammography/Database.html.2007
[69]John Suckling. The Mammographic Image Analysis Society Digital Mammogram Database. http://peipa.essex.ac.uk/info/mias.html.2012
[70]Bornefalk H, Hermansson A B. On the comparison of FROC curves in mammography CAD systems. Medical Physics.2005.32(2).412-417
[71]张兆礼,赵春晖,梅晓丹.现代图像处理技术及Matlab实现.北京.人民邮电出版社.2001.
[72]Go C-S, Lim S, Kim S. Themodeling and the optimization of a grating optical low-pass filter. Applied PhysicsB:Lasers and Optics.2001.73(7).721-725
[73]HeinleinP, DrexlJ, Schneider W. Integrated Wavelets for Enhancement of in Mieroealeification Digital MammograPhy. IEEE Transaction on Medieal Imaging.2003.22(3).402-413
[74]Wirth M, Fraschini M, Lyon J. Contrast Enhancement of Microcalcifications in Mammograms Using Morphological Enhancement and Non-flat Structuring Elements. Proc of the 17th IEEE Symposium on Computer-based Medical Systems.2004
[75]孙蕾,温有奎.图像增强算法与评价方法研究.计算机工程.2007.33(8).168-172.
[76]R. Adams, L. Bischof. Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligence.1994.16(6).641-647
[77]A. Mehnert, P. Jackway. An improved seeded region growing algorithm. Pattern Recognition Letters.1997. (18).1065-1071
[78]F. Y. Shih, Cheng Shouxian. Automatic seeded region growing for color image segmentation. Image and Vision Computing.2005.23(10).877-886
[79]Chang Y L, Li X B. Adaptive image region growing. IEEE Transactions on Image Processing. 1994.3(6).450-454
[80]Campanini R, Dongiovanni E, Iampieri E. A novel featureless approach to mass detection in digital mammograms based on support vector machines. Physics Medicine Biology.2002.49(6) 961-975
[81]Mavroforakis M E, Georgiou H V, Dimitropoulos N, et al. Mammographic masses characterization based on localized texture and dataset fractal analysis using linear, neural and support vector machine classifiers. Artificial Intelligence.2006.37(2).145-162
[82]王颖,高新波,李洁,等.基于PSVM的主动学习肿块检测方法.计算机研究与发展.2012.49(3).572-578.
[83]D. G. Tzikas, A. C. Likas, and N. P. Galatsanos, Sparse Bayesian modeling with adaptive kernel learning. IEEE Trans Neural Networks.2009.20(6).926-936
[84]M. M. Dundar, D. A. Landgrebe. Toward an optimal supervised classier for the analysis of hyperspectral data. IEEE Trans Geosci Remote Sens.2004.42(1).271-277
[85]B. Demir, S. Erturk. Hyperspectral Image Classification Using Relevance Vector Machines. IEEE Geoscience and Remote Sensing Letters.2007.4(4).586-590
[86]陆爱国,王珏,刘红卫.基于改进的SVM学习算法及其在信用评分中的应用.系统工程理论与实践.2012.32(3).515-521
[87]Tipping ME. Sparse Bayesian Learning and the Relevance Vector Machine. Journal of Machine Learning Research.2001.1(2001).211-244
[88]朱旭锋,马彩文,刘波.基于特征级融合和支持向量机的飞机识别.光电子·激光.2011.22(11).1710-1713
[89]K. R. Muller, S. Mika, G. Ratsch, et al. An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw.2001.12(2).181-201
[90]M. E. Tipping, A. Faul. Fast marginal likelihood maximization for sparse Bayesian models. Proceedings of 9th International Workshop on Artificial Intelligence and Statistics. Key West, USA.2003
[91]Li H, Wang Y, Liu K J R, et al. Computerized radiographic mass detection. II. Decision support by featured database visualization and modular neural networks. IEEE Transactions on Medical Imaging.2001.20(4).302-313
[92]杨德坤,侯德文,步亚东.灰度共生矩阵在纹理特征提取中的发展.信息系统工程.2012.(1).134-136
[93]周明全,耿国华,韦娜.基于内容图像检索技术.第2版.北京.清华大学出版社.2007
[94]唐坚刚,刘丛.基于小波分解和游程长度矩阵的医学图像检索.计算机工程与设计.2010.31(8).1771-1774
[95]American College of Radiology. About BI-RADS. http://www.birads.at/info.html.2012
[96]J A Baker, E L Rosen, J Y Lo, et al. Computer-aided detection (CAD) in screening mammography:Sensitivity of commercial CAD systems for detecting architectural distortion. American Journal of Roentgenology.2003.181(4).1083-1088
[97]R M Rangayyan, F J Ayres. Gabor filters and phase portraits for the detection of architectural distortion in mammograms. Medical and Biological Engineering and Computing.2006.44(10). 883-894
[98]Sampat M P, Whitman G J, Markey M K, et al. Evidence based detection of spiculated masses and architectural distortions. Proceedings of the SPIE Medical Imaging:Image Processing. 2005.5747.26-37
[99]Shantanu Banik, R M Rangayyan, J E Leo Desautels. Detection of Architectural Distortion in Prior Mammograms. IEEE Transactions on Medical Imaging.2011.30(2).279-294
[100]Ayres F J, Rangayyan R M. Reduction of false positives in the detection of architectural distortion in mammograms by using a geometrically constrained phase portrait model. International Journal of Computer Assisted Radiology and Surgery.2007.1(6).361-369
[101]S. K. Biswas, D. P. Mukherjee. Recognizing architectural distortion in mammogram:a multiscale texture modeling approach with GMM. IEEE Transactions on Biomedical Engineering.2011.58(7).2023-2030
[102]Herman G T, Huang Lianjie, Li Youming. Basic methods of tomography and inverse problems IOP publishing limited and individual contributor. Beijing. Petroleum Industry Press.1997
[103]Pratt W. Digital Image Processing:PIKS Scientific Inside.4th ed. New York. Wiley.2007
[104]李军宏,潘泉,陈玉春,等.基于Radon变换的矩不变量及其应用.西北工业大学学报.2004.22(3).392-396
[105]Kwok SM, Chandrasekhar R, Attikiouzel Y. Automatic pectoral muscle segmentation on mammograms by straight line estimation and cliff detection. Proceedings of 7th Australian and New Zealand Intelligent Information Systems Conference. Perth, Australia. ARCME-UWA, 2001.67-72
[106]S.E. Grigorescu, N. Petkov, P. Kruizinga. Comparison of texture features based on Gabor filters. IEEE Transactions on Image Processing.2002.11(10).1160-1167
[107]te Brake GM, Karssemeijer N, Hendriks JH. An automatic method to discriminate malignant masses from normal tissue in digital mammograms. Physics in Medicine and Biology.2000. 45(10).2843-2857