基于乳腺X线图像的计算机辅助诊断方法研究
|
摘要
乳腺钼靶X线摄影术是目前普查和诊断乳腺癌最有效的方法，对乳腺癌的及早发现、及早治疗，并提高治愈率和降低死亡率具有重要的意义。为了克服人工阅片效率低、而且容易造成误检和漏检等问题，基于乳腺X线图像的计算机辅助诊断技术被广泛应用于乳腺癌的普查和早期诊断之中。本文主要研究基于乳腺X线图像的乳腺肿块计算机辅助检测技术，以提高检测的准确性和效率为目标，并建立了一个完整的计算机辅助诊断系统。本文的主要研究工作和贡献主要体现在以下几个方面：
为了抑制噪声对图像质量的影响，本文提出了一种基于非下采样Contourlet变换和对称反高斯模型的乳腺X线图像去噪方法。该方法使用贝叶斯最大后验估计，将去噪问题简化为一个求阈值的过程。为此，本文提出了一种阈值求取策略，使得到的阈值不仅自适应于不同的方向和尺度，而且还考虑到了不同尺度的NSCT系数所包含的噪声的差异。实验结果表明：该算法在去除噪声的同时，能很好地保留图像边缘和细节特征。
为了消除背景等区域对肿块检测的影响，本文提出了一种基于小波的自适应阈值乳房轮廓提取方法。该方法首先对乳腺X线图像进行二维小波变换，以克服因灰度分布不平稳而造成的噪声敏感，然后对选定的低频图像直方图进行一维小波变换，去除直方图波形的起伏现象，以取得局部最小值，进而获得分割阈值，将乳房区域和背景区域进行分离。实验结果表明，该方法的分割结果与手工圈画的金标准有很好的一致性，比迭代阈值法、基于标记控制的分水岭算法以及基于水平集的算法分割结果更接近于乳房区域的真实轮廓。
为了减少冗余信息，提高系统的处理速度和准确性，本文根据肿瘤生长特性，提出了一种改进的基于自适应阈值的感兴趣区域提取方法。该方法利用同心层规则和形态学特征，实现了对可疑肿块区域的自动检测，并由此确定感兴趣区域。实验结果表明，本文提出的算法比基于固定阈值间隔的同心层方法和基于MCA的自适应阈值间隔法有更高的灵敏度和更低的假阳性率。
为了从感兴趣区域中提取出肿块轮廓，以便对肿块的良恶性做进一步分析，本文提出了一种基于等周算法和梯度向量流活动轮廓模型的肿块轮廓提取方法。为了增强感兴趣区域的对比度，该方法首先使用最小二乘平面拟合法对背景趋势进行去除。然后，为了克服梯度向量流活动轮廓模型对初始位置敏感的缺点，采用基于图论的等周算法对肿块轮廓进行初始分割。最后，将分割结果作为初始位置，对肿块轮廓进一步精细化。实验结果表明，本文的方法运行时间和分割精度都要优于归一化割(Ncut)方法和改进的水平集方法。
Mammography is considered as the most reliable and effective method for earlyscreening and diagnosis of the breast cancer. It plays important roles in early diagnosis andtreatment for improving the cure rates and reducing the mortality rates of breast cancer.However, inspecting of the mammograms by radiologists is not only inefficient but alsosubject to cause misdiagnosis and missed diagnosis of the breast cancer. For tackling sucha problem, this thesis devotes itself in developing techniques for automatic detection of thebreast cancer from the mammographic images and constructing a computer-aideddiagnosis system. The main work and contributions of this thesis are as follows:
In order to suppress the noise and extract the mass correctly, a novel mammographicimage denoising method is proposed based on the non-subsampled contourlet transform(NSCT) and the symmetric normal inverse Gaussian (SNIG) model. In the framework ofBayesian maximum a posteriori estimation, the problem of denoising is reduced to aproblem of threshold derivation. A novel strategy is then proposed to determine thethreshold that is not only adaptive to different directions and scales, but also able to takeinto considerations the scale-to-scale difference in the contribution of the NSCTcoefficients to the noise. Experimental results show that the proposed method can not onlyreduce the noise but also well preserve edges and fine details in the mammographicimages.
In order to reduce the effect of the background on the mass detection procedure, anovel adaptive thresholding method based on wavelet transform is proposed to segment thebreast region from the mammograms. First, a two dimensional wavelet transform isperformed with respect to the mammogram to alleviate the noise susceptibility caused bynonstationary distributions of intensities in the mammographic images. Then a onedimensional transform is performed with respect to the selected low frequency image for reducing the fluctuations, after which the local minima in the histogram curve is found anda threshold is then determined for extracting the breast region from the background.Experimental results indicate that the breast contours extracted by our method are well inconsistence with the corresponding ground truth.
In order to reduce the redundant information in the mammographic images andimprove the speed and accuracy of the mass detection system, a ROI (region of interest)extraction method is proposed based on the adaptive threshold value interval and accordingto the hypothesis that mass growth can produce concentric layers. Using the concentriclayer rules and morphological features, suspicious mass regions areas are automaticallydetected and the ROIs are then determined. Experimental results show that our method canachieve higher sensitivity and lower false positive rate.
In order to extract the contour of the mass from the extracted ROI, a novel masssegmentation method is proposed based on graph theoretic isoperimetric algorithm and thegradient vector flow (GVF) snake model. In this method, the isoperimetric algorithm isemployed to perform a rough segmentation of the mass and provide the initial position forthe GVF snake model, while the GVF snake model is used to obtain more accurate contourof the mass. Experimental results show that our method is more accurate and can beimplemented faster than other methods.
为了抑制噪声对图像质量的影响，本文提出了一种基于非下采样Contourlet变换和对称反高斯模型的乳腺X线图像去噪方法。该方法使用贝叶斯最大后验估计，将去噪问题简化为一个求阈值的过程。为此，本文提出了一种阈值求取策略，使得到的阈值不仅自适应于不同的方向和尺度，而且还考虑到了不同尺度的NSCT系数所包含的噪声的差异。实验结果表明：该算法在去除噪声的同时，能很好地保留图像边缘和细节特征。
为了消除背景等区域对肿块检测的影响，本文提出了一种基于小波的自适应阈值乳房轮廓提取方法。该方法首先对乳腺X线图像进行二维小波变换，以克服因灰度分布不平稳而造成的噪声敏感，然后对选定的低频图像直方图进行一维小波变换，去除直方图波形的起伏现象，以取得局部最小值，进而获得分割阈值，将乳房区域和背景区域进行分离。实验结果表明，该方法的分割结果与手工圈画的金标准有很好的一致性，比迭代阈值法、基于标记控制的分水岭算法以及基于水平集的算法分割结果更接近于乳房区域的真实轮廓。
为了减少冗余信息，提高系统的处理速度和准确性，本文根据肿瘤生长特性，提出了一种改进的基于自适应阈值的感兴趣区域提取方法。该方法利用同心层规则和形态学特征，实现了对可疑肿块区域的自动检测，并由此确定感兴趣区域。实验结果表明，本文提出的算法比基于固定阈值间隔的同心层方法和基于MCA的自适应阈值间隔法有更高的灵敏度和更低的假阳性率。
为了从感兴趣区域中提取出肿块轮廓，以便对肿块的良恶性做进一步分析，本文提出了一种基于等周算法和梯度向量流活动轮廓模型的肿块轮廓提取方法。为了增强感兴趣区域的对比度，该方法首先使用最小二乘平面拟合法对背景趋势进行去除。然后，为了克服梯度向量流活动轮廓模型对初始位置敏感的缺点，采用基于图论的等周算法对肿块轮廓进行初始分割。最后，将分割结果作为初始位置，对肿块轮廓进一步精细化。实验结果表明，本文的方法运行时间和分割精度都要优于归一化割(Ncut)方法和改进的水平集方法。
Mammography is considered as the most reliable and effective method for earlyscreening and diagnosis of the breast cancer. It plays important roles in early diagnosis andtreatment for improving the cure rates and reducing the mortality rates of breast cancer.However, inspecting of the mammograms by radiologists is not only inefficient but alsosubject to cause misdiagnosis and missed diagnosis of the breast cancer. For tackling sucha problem, this thesis devotes itself in developing techniques for automatic detection of thebreast cancer from the mammographic images and constructing a computer-aideddiagnosis system. The main work and contributions of this thesis are as follows:
In order to suppress the noise and extract the mass correctly, a novel mammographicimage denoising method is proposed based on the non-subsampled contourlet transform(NSCT) and the symmetric normal inverse Gaussian (SNIG) model. In the framework ofBayesian maximum a posteriori estimation, the problem of denoising is reduced to aproblem of threshold derivation. A novel strategy is then proposed to determine thethreshold that is not only adaptive to different directions and scales, but also able to takeinto considerations the scale-to-scale difference in the contribution of the NSCTcoefficients to the noise. Experimental results show that the proposed method can not onlyreduce the noise but also well preserve edges and fine details in the mammographicimages.
In order to reduce the effect of the background on the mass detection procedure, anovel adaptive thresholding method based on wavelet transform is proposed to segment thebreast region from the mammograms. First, a two dimensional wavelet transform isperformed with respect to the mammogram to alleviate the noise susceptibility caused bynonstationary distributions of intensities in the mammographic images. Then a onedimensional transform is performed with respect to the selected low frequency image for reducing the fluctuations, after which the local minima in the histogram curve is found anda threshold is then determined for extracting the breast region from the background.Experimental results indicate that the breast contours extracted by our method are well inconsistence with the corresponding ground truth.
In order to reduce the redundant information in the mammographic images andimprove the speed and accuracy of the mass detection system, a ROI (region of interest)extraction method is proposed based on the adaptive threshold value interval and accordingto the hypothesis that mass growth can produce concentric layers. Using the concentriclayer rules and morphological features, suspicious mass regions areas are automaticallydetected and the ROIs are then determined. Experimental results show that our method canachieve higher sensitivity and lower false positive rate.
In order to extract the contour of the mass from the extracted ROI, a novel masssegmentation method is proposed based on graph theoretic isoperimetric algorithm and thegradient vector flow (GVF) snake model. In this method, the isoperimetric algorithm isemployed to perform a rough segmentation of the mass and provide the initial position forthe GVF snake model, while the GVF snake model is used to obtain more accurate contourof the mass. Experimental results show that our method is more accurate and can beimplemented faster than other methods.
引文
[1] Jemal A, Siegel R, Ward E, et al. Cancer statistics,2008[J]. CA: a cancer journal forclinicians,2008,58(2):71-96.
[2] Sample J T. Computer Assisted Screening of Digital Mammogram Images. Louisiana:Louisiana state university,2003.
[3]孙强.乳腺癌的早期诊断[J].实用医学杂志,2007,23(1):1-3.
[4]李树玲.中国常见恶性肿瘤诊治规范,第八分册·乳腺癌[J].1989.
[5] Vyborny C J, Giger M L. Computer vision and artificial intelligence in mammography[J]. AJR. American journal of roentgenology,1994,162(3):699-708.
[6] Brem R F, Hoffmeister J W, Zisman G, et al. A computer-aided detection system for theevaluation of breast cancer by mammographic appearance and lesion size[J].American Journal of Roentgenology,2005,184(3):893-896.
[7] Dean J C, Ilvento C C. Improved cancer detection using computer-aided detection withdiagnostic and screening mammography: prospective study of104cancers[J].American Journal of Roentgenology,2006,187(1):20-28.
[8] Gur D, Sumkin J H, Rockette H E, et al. Changes in breast cancer detection andmammography recall rates after the introduction of a computer-aided detectionsystem[J]. Journal of the National Cancer Institute,2004,96(3):185-190.
[9] Birdwell R L, Bandodkar P, Ikeda D M. Computer-aided detection with screeningmammography in a university hospital setting1[J]. Radiology,2005,236(2):451-457.
[10] Cupples T E, Cunningham J E, Reynolds J C. Impact of computer-aided detection in aregional screening mammography program[J]. American Journal of Roentgenology,2005,185(4):944-950.
[11] Morton M J, Whaley D H, Brandt K R, et al. Screening Mammograms: Interpretationwith Computer-aided Detection—Prospective Evaluation [J]. Radiology,2006,239(2):375-383.
[12] Fischer U, Hermann K P, Baum F. Digital mammography: current state and futureaspects[J]. European radiology,2006,16(1):38-44.
[13]钱民,徐向民.乳腺X线计算机辅助检测系统研究进展[J].放射学实践,2009,24(1):100-103.
[14] Lechner M, Nelson M, Elvecrog E. Comparison of two commercially availablecomputer-aided detection (CAD) systems[J]. Applied Radiology,2002,31(4):31-37.
[15]东软医疗乳腺CAD产品通过SFDA认证依靠自主创新再次打破垄断格局.中国医疗器械信息，2008,14(3):80-80
[16]曹厚德.我国自主研发的三项计算机辅助诊断(CAD)软件先后通过国家认证[J].中国医疗器械杂志,2008,32(4):309-309.
[17] Bick U, Giger M L, Schmidt R A, et al. Automated segmentation of digitizedmammograms[J]. Academic Radiology,1995,2(1):1-9.
[18] Ojala T, N ppi J, Nevalainen O. Accurate segmentation of the breast region fromdigitized mammograms[J]. Computerized Medical Imaging and Graphics,2001,25(1):47-59.
[19] Wirth M A, Stapinski A. Segmentation of the breast region in mammograms usingsnakes[C]//Computer and Robot Vision,2004. Proceedings. First CanadianConference on. IEEE,2004:385-392.
[20] Méndez A J, Tahoces P G, Lado M J, et al. Automatic detection of breast border andnipple in digital mammograms[J]. Computer methods and programs in biomedicine,1996,49(3):253-262.
[21] Zhou C, Chan H P, Petrick N, et al. Computerized image analysis: estimation of breastdensity on mammograms[J]. Medical physics,2001,28(6):1056-1069.
[22] Raba D, Oliver A, Martí J, et al. Breast segmentation with pectoral musclesuppression on digital mammograms[M]//Pattern Recognition and Image Analysis.Springer Berlin Heidelberg,2005:471-478.
[23] Gauch J M. Image segmentation and analysis via multiscale gradient watershedhierarchies[J]. Image Processing, IEEE Transactions on,1999,8(1):69-79.
[24] Goodsitt M M, Chan H P, Liu B, et al. Classification of compressed breast shapes forthe design of equalization filters in x-ray mammography[J]. Medical Physics,1998,25(6):937-948.
[25] Saha P K, Udupa J K, Conant E F, et al. Breast tissue density quantification viadigitized mammograms[J]. Medical Imaging, IEEE Transactions on,2001,20(8):792-803.
[26] Rickard H E, Tourassi G D, Elmaghraby A S. Self-organizing maps for maskingmammography images[C]//Information Technology Applications in Biomedicine,2003.4th International IEEE EMBS Special Topic Conference on. IEEE,2003:302-305.
[27] Rickard H E, Tourassi G D, Eltonsy N, et al. Breast segmentation in screeningmammograms using multiscale analysis and self-organizing maps[C]//Engineering inMedicine and Biology Society,2004. IEMBS'04.26th Annual InternationalConference of the IEEE. IEEE,2004,1:1786-1789.
[28] Eltonsy N H, Tourassi G D, Elmaghraby A S. A concentric morphology model for thedetection of masses in mammography[J]. Medical Imaging, IEEE Transactions on,2007,26(6):880-889.
[29] Karnan M, Thangavel K. Automatic detection of the breast border and nipple positionon digital mammograms using genetic algorithm for asymmetry approach to detectionof microcalcifications[J]. Computer methods and programs in biomedicine,2007,87(1):12-20.
[30] Dengler J, Behrens S, Desaga J F. Segmentation of microcalcifications inmammograms[J]. Medical Imaging, IEEE Transactions on,1993,12(4):634-642.
[31] Cheng H D, Lui Y M, Freimanis R I. A new approach to microcalcification detectionin digital mammograms[C]//Nuclear Science Symposium,1996. Conference Record.,1996IEEE. IEEE,1996,2:1094-1098.
[32] Bhangale T, Desai U B, Sharma U. An unsupervised scheme for detection ofmicrocalcifications on mammograms[C]//Image Processing,2000. Proceedings.2000International Conference on. IEEE,2000,1:184-187.
[33] Li H, Liu K J R, Lo S C B. Fractal modeling and segmentation for the enhancement ofmicrocalcifications in digital mammograms[J]. Medical Imaging, IEEE Transactionson,1997,16(6):785-798.
[34] Smith,C.M., Nelson, S.R., Tuovilla, S.M.Morphological and related image processingtechniques for the detection of microcalcifications in mammography images. IEEESouthwest Symposium on Image Analysis and Interpretation, Tucson, USA,1998:29-34.
[35] Wang R, Wan B, Ma Z, et al. Computer-aided detection of microcalcifications indigital mammograms using a synthetic technique[C]//Second InternationalConference on Image and Graphics. International Society for Optics and Photonics,2002:639-644.
[36] Nesbitt D, Aghdasi F, Ward R, et al. Detection of microcalcifications in digitizedmammogram film images using wavelet enhancement and local adaptive falsepositive suppression[C]//Communications, Computers, and Signal Processing,1995.Proceedings., IEEE Pacific Rim Conference on. IEEE,1995:594-597.
[37] El-Naqa I, Yang Y, Wernick M N, et al. A support vector machine approach fordetection of microcalcifications[J]. Medical Imaging, IEEE Transactions on,2002,21(12):1552-1563.
[38] Xu W, Xia S, Duan H. A novel computer-aided diagnosis system of themammograms[M]//Intelligent Computing in Signal Processing and PatternRecognition. Springer Berlin Heidelberg,2006:639-644.
[39] Yoshida H, Zhang W, Cai W, et al. Optimizing wavelet transform based on supervisedlearning for detection of microcalcifications in digital mammograms[C]//ImageProcessing,1995. Proceedings., International Conference on. IEEE,1995,3:152-155.
[40] Strickland R, Hahn H I. Wavelet transforms for detecting microcalcifications inmammograms[J]. Medical Imaging, IEEE Transactions on,1996,15(2):218-229.
[41]万柏坤,王瑞平,朱欣,等. SVM算法及其在乳腺X片微钙化点自动检测中的应用[J].电子学报,2004,32(4):587-590.
[42]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[J].中国图象图形学报,2007,11(12):1839-1843.
[43]龚浩,王玉慧.基于小波变换和图论方法识别乳腺微钙化点簇[J].光学技术,2007,33(5):769-771.
[44]王磊,朱淼良,邓丽萍,等.一种基于二维粒子的自动检测乳腺钼靶片上微钙化点簇的方法[J].计算机研究与发展,2009(9):1438-1445.
[45]胡正平,刘敏华.基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测[J].电路与系统学报,2011,16(001):85-91.
[46] Petrick N, Chan H P, Sahiner B, et al. An adaptive density-weighted contrastenhancement filter for mammographic breast mass detection[J]. Medical Imaging,IEEE Transactions on,1996,15(1):59-67.
[47] Wei J, Chan H P, Sahiner B, et al. Dual system approach to computer-aided detectionof breast masses on mammograms[J]. Medical physics,2006,33(11):4157-4168.
[48] Petrick N, Chan H P, Sahiner B, et al. Combined adaptive enhancement andregion-growing segmentation of breast masses on digitized mammograms[J]. MedicalPhysics,1999,26(8):1642-1654.
[49] Wei J, Sahiner B, Hadjiiski L M, et al. Computer-aided detection of breast masses onfull field digital mammograms[J]. Medical physics,2005,32(9):2827-2838.
[50] Zheng L, Chan A K. An artificial intelligent algorithm for tumor detection in screeningmammogram[J]. Medical Imaging, IEEE Transactions on,2001,20(7):559-567.
[51] Sampat M P, Bovik A C. Detection of spiculated lesions inmammograms[C]//Engineering in Medicine and Biology Society,2003. Proceedingsof the25th Annual International Conference of the IEEE. IEEE,2003,1:810-813.
[52] Timp S, Karssemeijer N. A new2D segmentation method based on dynamicprogramming applied to computer aided detection in mammography[J]. MedicalPhysics,2004,31(5):958-971.
[53] Domínguez A R, Nandi A K. Improved dynamic-programming-based algorithms forsegmentation of masses in mammograms[J]. Medical physics,2007,34(11):4256-4269.
[54] Kupinski M A, Giger M L. Automated seeded lesion segmentation on digitalmammograms[J]. Medical Imaging, IEEE Transactions on,1998,17(4):510-517.
[55] Hatanaka Y, Hara T, Fujita H, et al. Development of an automated method fordetecting mammographic masses with a partial loss of region[J]. Medical Imaging,IEEE Transactions on,2001,20(12):1209-1214.
[56]徐伟栋,刘伟,厉力华,等.基于特性模型与神经网络的乳腺图像肿块自动检测技术[J].电子与信息学报,2009,31(7):1653-1658.
[57]金人超,孟波,宋恩民,等.从乳腺X线图像中检测肿块的基于内容的图像检索[J].小型微型计算机系统,2008,29(2):324-328.
[58]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[J].仪器仪表学报,2010(006):1418-1423.
[59]王颖,李洁,高新波.基于MCA的乳腺X线图像中肿块的自适应检测方法[J].电子学报,2011,39(3):525-530.
[60]黄琳琳,胡健.一种基于二叉树决策分类的乳腺肿块自动检测方法[J].信号处理,2012,28(3):329-334.
[61] Haralick R M, Shanmugam K, Dinstein I H. Textural features for imageclassification[J]. Systems, Man and Cybernetics, IEEE Transactions on,1973(6):610-621.
[62] Kegelmeyer Jr W P. Evaluation of stellate lesion detection in a standard mammogramdata set[J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(06):1477-1492.
[63] Sahiner B, Chan H P, Petrick N, et al. Computerized characterization of masses onmammograms: The rubber band straightening transform and texture analysis[J].Medical Physics,1998,25(4):516-526.
[64] Sahiner B, Chan H P, Petrick N, et al. Improvement of mammographic masscharacterization using spiculation measures and morphological features[J]. MedicalPhysics,2001,28(7):1455-1465.
[65] Shi J, Sahiner B, Chan H P, et al. Characterization of mammographic masses based onlevel set segmentation with new image features and patient information[J]. Medicalphysics,2007,35(1):280-290.
[66] Huo Z, Giger M L, Wolverton D E, et al. Computerized analysis of mammographicparenchymal patterns for breast cancer risk assessment: feature selection[J]. MedicalPhysics,2000,27(1):4-12.
[67] Sahiner B, Chan H P, Wei D, et al. Image feature selection by a genetic algorithm:Application to classification of mass and normal breast tissue[J]. Medical Physics,1996,23(10):1671-1684.
[68] Zwiggelaar R. Separating Background Texture, Image Structure inMammograms[C]//BMVC.1999:1-10.
[69] Zhou Z H, Wu J, Tang W. Ensembling neural networks: many could be better thanall[J]. Artificial intelligence,2002,137(1):239-263.
[70] Chan H P, Wei D, Helvie M A, et al. Computer-aided classification of mammographicmasses and normal tissue: linear discriminant analysis in texture feature space[J].Physics in medicine and biology,1995,40(5):857.
[71]高妮.支持向量机及其在乳腺癌辅助诊断系统中的应用研究[D].西安:西北大学,2009.
[72] Wei L, Yang Y, Nishikawa R M, et al. A study on several machine-learning methodsfor classification of malignant and benign clustered microcalcifications[J]. MedicalImaging, IEEE Transactions on,2005,24(3):371-380.
[73]李晓峰,沈毅.基于支持向量机的超声乳腺肿瘤图像计算机辅助诊断系统[J].光电子.激光,2008,19(1):115-119.
[74] Peng Y, Huang Q, Jiang P, et al. Cost-sensitive ensemble of support vector machinesfor effective detection of microcalcification in breast cancer diagnosis[M]//FuzzySystems and Knowledge Discovery. Springer Berlin Heidelberg,2005:483-493.
[75] Cheng H D, Cui M. Mass lesion detection with a fuzzy neural network[J]. Patternrecognition,2004,37(6):1189-1200.
[76]钟明霞,孔颖.基于KL变换和神经网络分类的微钙化点检测新方法[J].计算机与现代化,2008(9):101-105.
[77] Rymon R, Zheng B, Chang Y H, et al. Incorporation of a set enumeration trees-basedclassifier into a hybrid computer-assisted diagnosis scheme for mass detection[J].Academic radiology,1998,5(3):181-187.
[78] Zheng B, Mello-Thoms C, Wang X H, et al. Interactive computer-aided diagnosis ofbreast masses: computerized selection of visually similar image sets from a referencelibrary[J]. Academic radiology,2007,14(8):917-927.
[79] Te Brake G M, Karssemeijer N. Segmentation of suspicious densities in digitalmammograms[J]. Medical Physics,2001,28(2):259-266.
[80] Tourassi G D, Vargas-Voracek R, Catarious Jr D M, et al. Computer-assisted detectionof mammographic masses: A template matching scheme based on mutualinformation[J]. Medical Physics,2003,30(8):2123-2130.
[81] Gur D, Stalder J S, Hardesty L A, et al. Computer-aided Detection Performance inMammographic Examination of Masses: Assessment1[J]. Radiology,2004,233(2):418-423.
[82] Li L, Zheng Y, Zhang L, et al. False-positive reduction in CAD mass detection using acompetitive classification strategy[J]. Medical physics,2001,28(2):250-258.
[83] Paquerault S, Petrick N, Chan H P, et al. Improvement of computerized mass detectionon mammograms: Fusion of two-view information[J]. Medical Physics,2002,29(2):238-247.
[84] Van Engeland S, Timp S, Karssemeijer N. Finding corresponding regions of interest inmediolateral oblique and craniocaudal mammographic views[J]. Medical physics,2006,33(9):3203-3212.
[85] Zheng B, Leader J K, Abrams G S, et al. Multiview-based computer-aided detectionscheme for breast masses[J]. Medical physics,2006,33(9):3135-3143.
[86] Chang Y H, Good W F, Sumkin J H, et al. Computerized localization of breast lesionsfrom two views: An experimental comparison of two methods[J]. Investigativeradiology,1999,34(9):585.
[87] Pu J, Zheng B, Leader J K, et al. An ellipse-fitting based method for efficientregistration of breast masses on two mammographic views[J]. Medical physics,2008,35(2):487-494.
[88] Miller P, Astley S M. Detection of breast asymmetry using anatomicalfeatures[C]//IS&T/SPIE's Symposium on Electronic Imaging: Science andTechnology. International Society for Optics and Photonics,1993:433-442.
[89] Miller P, Astley S. Automated detection of breast asymmetry using anatomicalfeatures[J]. State of the Art in Digital Mammographic Image Analysis, Series inMachine Perception and Artificial Intelligence,1994,9:247-261.
[90] Mendez A J, Tahoces P G, Lado M J, et al. Computer-aided diagnosis: Automaticdetection of malignant masses in digitized mammograms[J]. Medical Physics,1998,25(6):957-964.
[91] Ferrari R J, Rangayyan R M, Desautels J E L, et al. Analysis of asymmetry inmammograms via directional filtering with Gabor wavelets[J]. Medical Imaging,IEEE Transactions on,2001,20(9):953-964.
[92] R.M.Rangayyan,R.J.Ferrari,Detection of asymmetry between left and rightmammograms.in E.Pisano.Proceedings of the Seventh International Workshop onDigital Mammography.Springer,2004,651-658
[93]徐胜舟,宋恩民,许向阳.基于改进Demons算法的乳腺X线摄片非刚性配准[J].中国图象图形学报,2009,14(12):2566-2571.
[94] Wu Y T, Wei J, Hadjiiski L M, et al. Bilateral analysis based false positive reductionfor computer-aided mass detection[J]. Medical physics,2007,34(8):3334-3344.
[95] Burnside E S, Sickles E A, Sohlich R E, et al. Differential value of comparison withprevious examinations in diagnostic versus screening mammography[J]. AmericanJournal of Roentgenology,2002,179(5):1173-1177.
[96] Zheng B, Good W F, Armfield D R, et al. Performance change of mammographicCAD schemes optimized with most-recent and prior image databases[J]. Academicradiology,2003,10(3):283-288.
[97] Hadjiiski L, Sahiner B, Chan H P, et al. Analysis of temporal changes ofmammographic features: computer-aided classification of malignant and benignbreast masses[J]. Medical Physics,2001,28(11):2309-2317.
[98] Hadjiiski L, Sahiner B, Helvie M A, et al. Breast Masses: Computer-aided Diagnosiswith Serial Mammograms1[J]. Radiology,2006,240(2):343-356.
[99] Hadjiiski L, Chan H P, Sahiner B, et al. Automated registration of breast lesions intemporal pairs of mammograms for interval change analysis—Local affinetransformation for improved localization[J]. Medical physics,2001,28(6):1070-1079.
[100] Timp S, van Engeland S, Karssemeijer N. A regional registration method to findcorresponding mass lesions in temporal mammogram pairs[J]. Medical physics,2005,32(8):2629-2638.
[101] Sanjay-Gopal S, Chan H P, Wilson T, et al. A regional registration technique forautomated interval change analysis of breast lesions on mammograms[J]. MedicalPhysics,1999,26(12):2669-2679.
[102] Donoho D L, Johnstone J M. Ideal spatial adaptation by wavelet shrinkage[J].Biometrika,1994,81(3):425-455.
[103] Candès E J. Harmonic analysis of neural networks[J]. Applied and ComputationalHarmonic Analysis,1999,6(2):197-218.
[104] Candes E J, Donoho D L. Curvelets: A surprisingly effective nonadaptiverepresentation for objects with edges[R]. Stanford Univ Ca Dept of Statistics,2000.
[105] Meyer F G, Coifman R R. Brushlets: a tool for directional image analysis and imagecompression[J]. Applied and computational harmonic analysis,1997,4(2):147-187.
[106] Do M N, Vetterli M. The contourlet transform: an efficient directionalmultiresolution image representation[J]. Image Processing, IEEE Transactions on,2005,14(12):2091-2106.
[107] Da Cunha A L, Zhou J, Do M N. The nonsubsampled contourlet transform: theory,design, and applications[J]. Image Processing, IEEE Transactions on,2006,15(10):3089-3101.
[108] Zhou Y, Wang J. Image denoising based on the symmetric normal inverse Gaussianmodel and non-subsampled contourlet transform[J]. Image Processing, IET,2012,6(8):1136-1147.
[109] Buades A, Coll B, Morel J M. A non-local algorithm for imagedenoising[C]//Computer Vision and Pattern Recognition,2005. CVPR2005. IEEEComputer Society Conference on. IEEE,2005,2:60-65.
[110]李均利,侯艳芹,魏平,等.一种基于模糊均差和小波变换的医学图像去噪方法[J].中国生物医学工程学报,2007,26(3):342-348.
[111] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from errorvisibility to structural similarity[J]. Image Processing, IEEE Transactions on,2004,13(4):600-612.
[112] Ridler T W, Calvard S. Picture thresholding using an iterative selection method[J].IEEE transactions on Systems, Man and Cybernetics,1978,8(8):630-632.
[113] Otsu N. A threshold selection method from gray-level histograms[J]. Automatica,1975,11(285-296):23-27.
[114] Zhang X P, Desai M D. Segmentation of bright targets using wavelets and adaptivethresholding[J]. Image Processing, IEEE Transactions on,2001,10(7):1020-1030.
[115] Iijima T. Basic theory on normalization of a pattern (in case of typicalone-dimensional pattern)[J]. Bulletin of Electrical Laboratory,1962,26:368-388.
[116] Lindeberg T. Scale-space theory: A basic tool for analyzing structures at differentscales[J]. Journal of applied statistics,1994,21(1-2):225-270.
[117] Lou S L, Lin H D, Lin K P, et al. Automatic breast region extraction from digitalmammograms for PACS and telemammography applications[J]. ComputerizedMedical Imaging and Graphics,2000,24(4):205-220.
[118]魏平,李均利,鲁东明,等.基于乳腺钼靶X线图像等值面特征的乳腺区域阈值分割算法[J].中国图象图形学报,2011,16(2):227-235.
[119] Wang Q, Song E, Jin R, et al. Segmentation of Lung Nodules in ComputedTomography Images Using Dynamic Programming and Multidirection FusionTechniques[J]. Academic radiology,2009,16(6):678-688.
[120] Song E, Jiang L, Jin R, et al. Breast mass segmentation in mammography usingplane fitting and dynamic programming[J]. Academic radiology,2009,16(7):826-835.
[121] Domínguez A R, Nandi A K. Improved dynamic-programming-based algorithms forsegmentation of masses in mammograms[J]. Medical physics,2007,34(11):4256-4269.
[122]徐胜舟.乳腺X线摄片中肿块的计算机辅助诊断方法研究[D].华中科技大学,2011.
[123] Chan T F, Vese L A. Active contours without edges[J]. Image processing, IEEEtransactions on,2001,10(2):266-277.
[124]王颖,李洁,高新波.基于MCA的乳腺X线图像中肿块的自适应检测方法[J].电子学报,2011,39(3):525-530.
[125] Zhou Y,JiaJun Wang， Mammographic Lesion Detection Based on ImprovedConcentric Morphology Model，2013International Conference on MechatronicSciences,Electric Engineering and Computer,929-933.
[126]罗希平,田捷.图像分割方法综述[J].模式识别与人工智能,1999,12(3):300-312.
[127] Kass M, Witkin A, Terzopoulos D. Snakes: Active contour models[J]. Internationaljournal of computer vision,1988,1(4):321-331.
[128] Xu C, Prince J L. Snakes, shapes, and gradient vector flow[J]. Image Processing,IEEE Transactions on,1998,7(3):359-369.
[129] Wu Z, Leahy R. An optimal graph theoretic approach to data clustering: Theory andits application to image segmentation[J]. Pattern Analysis and Machine Intelligence,IEEE Transactions on,1993,15(11):1101-1113.
[130] Sarkar S, Soundararajan P. Supervised learning of large perceptual organization:Graph spectral partitioning and learning automata[J]. Pattern Analysis and MachineIntelligence, IEEE Transactions on,2000,22(5):504-525.
[131] Shi J, Malik J. Normalized cuts and image segmentation[J]. Pattern Analysis andMachine Intelligence, IEEE Transactions on,2000,22(8):888-905.
[132] Grady L, Schwartz E L. Isoperimetric graph partitioning for image segmentation[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2006,28(3):469-475.
[133] Yuan Y, Giger M L, Li H, et al. A dual-stage method for lesion segmentation ondigital mammograms[J]. Medical physics,2007,34(11):4180-4193.
[134]姜娈.基于乳腺X线摄片的计算机辅助检测肿块方法研究[D].华中科技大学,2009.
[135]兰红,张璐.分水岭优化的Snake模型肝脏图像分割[J].中国图象图形学报,2012,17(7):873-879.
[136] Li C, Kao C Y, Gore J C, et al. Minimization of region-scalable fitting energy forimage segmentation[J]. Image Processing, IEEE Transactions on,2008,17(10):1940-1949.
[2] Sample J T. Computer Assisted Screening of Digital Mammogram Images. Louisiana:Louisiana state university,2003.
[3]孙强.乳腺癌的早期诊断[J].实用医学杂志,2007,23(1):1-3.
[4]李树玲.中国常见恶性肿瘤诊治规范,第八分册·乳腺癌[J].1989.
[5] Vyborny C J, Giger M L. Computer vision and artificial intelligence in mammography[J]. AJR. American journal of roentgenology,1994,162(3):699-708.
[6] Brem R F, Hoffmeister J W, Zisman G, et al. A computer-aided detection system for theevaluation of breast cancer by mammographic appearance and lesion size[J].American Journal of Roentgenology,2005,184(3):893-896.
[7] Dean J C, Ilvento C C. Improved cancer detection using computer-aided detection withdiagnostic and screening mammography: prospective study of104cancers[J].American Journal of Roentgenology,2006,187(1):20-28.
[8] Gur D, Sumkin J H, Rockette H E, et al. Changes in breast cancer detection andmammography recall rates after the introduction of a computer-aided detectionsystem[J]. Journal of the National Cancer Institute,2004,96(3):185-190.
[9] Birdwell R L, Bandodkar P, Ikeda D M. Computer-aided detection with screeningmammography in a university hospital setting1[J]. Radiology,2005,236(2):451-457.
[10] Cupples T E, Cunningham J E, Reynolds J C. Impact of computer-aided detection in aregional screening mammography program[J]. American Journal of Roentgenology,2005,185(4):944-950.
[11] Morton M J, Whaley D H, Brandt K R, et al. Screening Mammograms: Interpretationwith Computer-aided Detection—Prospective Evaluation [J]. Radiology,2006,239(2):375-383.
[12] Fischer U, Hermann K P, Baum F. Digital mammography: current state and futureaspects[J]. European radiology,2006,16(1):38-44.
[13]钱民,徐向民.乳腺X线计算机辅助检测系统研究进展[J].放射学实践,2009,24(1):100-103.
[14] Lechner M, Nelson M, Elvecrog E. Comparison of two commercially availablecomputer-aided detection (CAD) systems[J]. Applied Radiology,2002,31(4):31-37.
[15]东软医疗乳腺CAD产品通过SFDA认证依靠自主创新再次打破垄断格局.中国医疗器械信息，2008,14(3):80-80
[16]曹厚德.我国自主研发的三项计算机辅助诊断(CAD)软件先后通过国家认证[J].中国医疗器械杂志,2008,32(4):309-309.
[17] Bick U, Giger M L, Schmidt R A, et al. Automated segmentation of digitizedmammograms[J]. Academic Radiology,1995,2(1):1-9.
[18] Ojala T, N ppi J, Nevalainen O. Accurate segmentation of the breast region fromdigitized mammograms[J]. Computerized Medical Imaging and Graphics,2001,25(1):47-59.
[19] Wirth M A, Stapinski A. Segmentation of the breast region in mammograms usingsnakes[C]//Computer and Robot Vision,2004. Proceedings. First CanadianConference on. IEEE,2004:385-392.
[20] Méndez A J, Tahoces P G, Lado M J, et al. Automatic detection of breast border andnipple in digital mammograms[J]. Computer methods and programs in biomedicine,1996,49(3):253-262.
[21] Zhou C, Chan H P, Petrick N, et al. Computerized image analysis: estimation of breastdensity on mammograms[J]. Medical physics,2001,28(6):1056-1069.
[22] Raba D, Oliver A, Martí J, et al. Breast segmentation with pectoral musclesuppression on digital mammograms[M]//Pattern Recognition and Image Analysis.Springer Berlin Heidelberg,2005:471-478.
[23] Gauch J M. Image segmentation and analysis via multiscale gradient watershedhierarchies[J]. Image Processing, IEEE Transactions on,1999,8(1):69-79.
[24] Goodsitt M M, Chan H P, Liu B, et al. Classification of compressed breast shapes forthe design of equalization filters in x-ray mammography[J]. Medical Physics,1998,25(6):937-948.
[25] Saha P K, Udupa J K, Conant E F, et al. Breast tissue density quantification viadigitized mammograms[J]. Medical Imaging, IEEE Transactions on,2001,20(8):792-803.
[26] Rickard H E, Tourassi G D, Elmaghraby A S. Self-organizing maps for maskingmammography images[C]//Information Technology Applications in Biomedicine,2003.4th International IEEE EMBS Special Topic Conference on. IEEE,2003:302-305.
[27] Rickard H E, Tourassi G D, Eltonsy N, et al. Breast segmentation in screeningmammograms using multiscale analysis and self-organizing maps[C]//Engineering inMedicine and Biology Society,2004. IEMBS'04.26th Annual InternationalConference of the IEEE. IEEE,2004,1:1786-1789.
[28] Eltonsy N H, Tourassi G D, Elmaghraby A S. A concentric morphology model for thedetection of masses in mammography[J]. Medical Imaging, IEEE Transactions on,2007,26(6):880-889.
[29] Karnan M, Thangavel K. Automatic detection of the breast border and nipple positionon digital mammograms using genetic algorithm for asymmetry approach to detectionof microcalcifications[J]. Computer methods and programs in biomedicine,2007,87(1):12-20.
[30] Dengler J, Behrens S, Desaga J F. Segmentation of microcalcifications inmammograms[J]. Medical Imaging, IEEE Transactions on,1993,12(4):634-642.
[31] Cheng H D, Lui Y M, Freimanis R I. A new approach to microcalcification detectionin digital mammograms[C]//Nuclear Science Symposium,1996. Conference Record.,1996IEEE. IEEE,1996,2:1094-1098.
[32] Bhangale T, Desai U B, Sharma U. An unsupervised scheme for detection ofmicrocalcifications on mammograms[C]//Image Processing,2000. Proceedings.2000International Conference on. IEEE,2000,1:184-187.
[33] Li H, Liu K J R, Lo S C B. Fractal modeling and segmentation for the enhancement ofmicrocalcifications in digital mammograms[J]. Medical Imaging, IEEE Transactionson,1997,16(6):785-798.
[34] Smith,C.M., Nelson, S.R., Tuovilla, S.M.Morphological and related image processingtechniques for the detection of microcalcifications in mammography images. IEEESouthwest Symposium on Image Analysis and Interpretation, Tucson, USA,1998:29-34.
[35] Wang R, Wan B, Ma Z, et al. Computer-aided detection of microcalcifications indigital mammograms using a synthetic technique[C]//Second InternationalConference on Image and Graphics. International Society for Optics and Photonics,2002:639-644.
[36] Nesbitt D, Aghdasi F, Ward R, et al. Detection of microcalcifications in digitizedmammogram film images using wavelet enhancement and local adaptive falsepositive suppression[C]//Communications, Computers, and Signal Processing,1995.Proceedings., IEEE Pacific Rim Conference on. IEEE,1995:594-597.
[37] El-Naqa I, Yang Y, Wernick M N, et al. A support vector machine approach fordetection of microcalcifications[J]. Medical Imaging, IEEE Transactions on,2002,21(12):1552-1563.
[38] Xu W, Xia S, Duan H. A novel computer-aided diagnosis system of themammograms[M]//Intelligent Computing in Signal Processing and PatternRecognition. Springer Berlin Heidelberg,2006:639-644.
[39] Yoshida H, Zhang W, Cai W, et al. Optimizing wavelet transform based on supervisedlearning for detection of microcalcifications in digital mammograms[C]//ImageProcessing,1995. Proceedings., International Conference on. IEEE,1995,3:152-155.
[40] Strickland R, Hahn H I. Wavelet transforms for detecting microcalcifications inmammograms[J]. Medical Imaging, IEEE Transactions on,1996,15(2):218-229.
[41]万柏坤,王瑞平,朱欣,等. SVM算法及其在乳腺X片微钙化点自动检测中的应用[J].电子学报,2004,32(4):587-590.
[42]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[J].中国图象图形学报,2007,11(12):1839-1843.
[43]龚浩,王玉慧.基于小波变换和图论方法识别乳腺微钙化点簇[J].光学技术,2007,33(5):769-771.
[44]王磊,朱淼良,邓丽萍,等.一种基于二维粒子的自动检测乳腺钼靶片上微钙化点簇的方法[J].计算机研究与发展,2009(9):1438-1445.
[45]胡正平,刘敏华.基于多尺度空间滤波和l1范数最近邻分类的乳腺图像微钙化点检测[J].电路与系统学报,2011,16(001):85-91.
[46] Petrick N, Chan H P, Sahiner B, et al. An adaptive density-weighted contrastenhancement filter for mammographic breast mass detection[J]. Medical Imaging,IEEE Transactions on,1996,15(1):59-67.
[47] Wei J, Chan H P, Sahiner B, et al. Dual system approach to computer-aided detectionof breast masses on mammograms[J]. Medical physics,2006,33(11):4157-4168.
[48] Petrick N, Chan H P, Sahiner B, et al. Combined adaptive enhancement andregion-growing segmentation of breast masses on digitized mammograms[J]. MedicalPhysics,1999,26(8):1642-1654.
[49] Wei J, Sahiner B, Hadjiiski L M, et al. Computer-aided detection of breast masses onfull field digital mammograms[J]. Medical physics,2005,32(9):2827-2838.
[50] Zheng L, Chan A K. An artificial intelligent algorithm for tumor detection in screeningmammogram[J]. Medical Imaging, IEEE Transactions on,2001,20(7):559-567.
[51] Sampat M P, Bovik A C. Detection of spiculated lesions inmammograms[C]//Engineering in Medicine and Biology Society,2003. Proceedingsof the25th Annual International Conference of the IEEE. IEEE,2003,1:810-813.
[52] Timp S, Karssemeijer N. A new2D segmentation method based on dynamicprogramming applied to computer aided detection in mammography[J]. MedicalPhysics,2004,31(5):958-971.
[53] Domínguez A R, Nandi A K. Improved dynamic-programming-based algorithms forsegmentation of masses in mammograms[J]. Medical physics,2007,34(11):4256-4269.
[54] Kupinski M A, Giger M L. Automated seeded lesion segmentation on digitalmammograms[J]. Medical Imaging, IEEE Transactions on,1998,17(4):510-517.
[55] Hatanaka Y, Hara T, Fujita H, et al. Development of an automated method fordetecting mammographic masses with a partial loss of region[J]. Medical Imaging,IEEE Transactions on,2001,20(12):1209-1214.
[56]徐伟栋,刘伟,厉力华,等.基于特性模型与神经网络的乳腺图像肿块自动检测技术[J].电子与信息学报,2009,31(7):1653-1658.
[57]金人超,孟波,宋恩民,等.从乳腺X线图像中检测肿块的基于内容的图像检索[J].小型微型计算机系统,2008,29(2):324-328.
[58]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[J].仪器仪表学报,2010(006):1418-1423.
[59]王颖,李洁,高新波.基于MCA的乳腺X线图像中肿块的自适应检测方法[J].电子学报,2011,39(3):525-530.
[60]黄琳琳,胡健.一种基于二叉树决策分类的乳腺肿块自动检测方法[J].信号处理,2012,28(3):329-334.
[61] Haralick R M, Shanmugam K, Dinstein I H. Textural features for imageclassification[J]. Systems, Man and Cybernetics, IEEE Transactions on,1973(6):610-621.
[62] Kegelmeyer Jr W P. Evaluation of stellate lesion detection in a standard mammogramdata set[J]. International Journal of Pattern Recognition and Artificial Intelligence,1993,7(06):1477-1492.
[63] Sahiner B, Chan H P, Petrick N, et al. Computerized characterization of masses onmammograms: The rubber band straightening transform and texture analysis[J].Medical Physics,1998,25(4):516-526.
[64] Sahiner B, Chan H P, Petrick N, et al. Improvement of mammographic masscharacterization using spiculation measures and morphological features[J]. MedicalPhysics,2001,28(7):1455-1465.
[65] Shi J, Sahiner B, Chan H P, et al. Characterization of mammographic masses based onlevel set segmentation with new image features and patient information[J]. Medicalphysics,2007,35(1):280-290.
[66] Huo Z, Giger M L, Wolverton D E, et al. Computerized analysis of mammographicparenchymal patterns for breast cancer risk assessment: feature selection[J]. MedicalPhysics,2000,27(1):4-12.
[67] Sahiner B, Chan H P, Wei D, et al. Image feature selection by a genetic algorithm:Application to classification of mass and normal breast tissue[J]. Medical Physics,1996,23(10):1671-1684.
[68] Zwiggelaar R. Separating Background Texture, Image Structure inMammograms[C]//BMVC.1999:1-10.
[69] Zhou Z H, Wu J, Tang W. Ensembling neural networks: many could be better thanall[J]. Artificial intelligence,2002,137(1):239-263.
[70] Chan H P, Wei D, Helvie M A, et al. Computer-aided classification of mammographicmasses and normal tissue: linear discriminant analysis in texture feature space[J].Physics in medicine and biology,1995,40(5):857.
[71]高妮.支持向量机及其在乳腺癌辅助诊断系统中的应用研究[D].西安:西北大学,2009.
[72] Wei L, Yang Y, Nishikawa R M, et al. A study on several machine-learning methodsfor classification of malignant and benign clustered microcalcifications[J]. MedicalImaging, IEEE Transactions on,2005,24(3):371-380.
[73]李晓峰,沈毅.基于支持向量机的超声乳腺肿瘤图像计算机辅助诊断系统[J].光电子.激光,2008,19(1):115-119.
[74] Peng Y, Huang Q, Jiang P, et al. Cost-sensitive ensemble of support vector machinesfor effective detection of microcalcification in breast cancer diagnosis[M]//FuzzySystems and Knowledge Discovery. Springer Berlin Heidelberg,2005:483-493.
[75] Cheng H D, Cui M. Mass lesion detection with a fuzzy neural network[J]. Patternrecognition,2004,37(6):1189-1200.
[76]钟明霞,孔颖.基于KL变换和神经网络分类的微钙化点检测新方法[J].计算机与现代化,2008(9):101-105.
[77] Rymon R, Zheng B, Chang Y H, et al. Incorporation of a set enumeration trees-basedclassifier into a hybrid computer-assisted diagnosis scheme for mass detection[J].Academic radiology,1998,5(3):181-187.
[78] Zheng B, Mello-Thoms C, Wang X H, et al. Interactive computer-aided diagnosis ofbreast masses: computerized selection of visually similar image sets from a referencelibrary[J]. Academic radiology,2007,14(8):917-927.
[79] Te Brake G M, Karssemeijer N. Segmentation of suspicious densities in digitalmammograms[J]. Medical Physics,2001,28(2):259-266.
[80] Tourassi G D, Vargas-Voracek R, Catarious Jr D M, et al. Computer-assisted detectionof mammographic masses: A template matching scheme based on mutualinformation[J]. Medical Physics,2003,30(8):2123-2130.
[81] Gur D, Stalder J S, Hardesty L A, et al. Computer-aided Detection Performance inMammographic Examination of Masses: Assessment1[J]. Radiology,2004,233(2):418-423.
[82] Li L, Zheng Y, Zhang L, et al. False-positive reduction in CAD mass detection using acompetitive classification strategy[J]. Medical physics,2001,28(2):250-258.
[83] Paquerault S, Petrick N, Chan H P, et al. Improvement of computerized mass detectionon mammograms: Fusion of two-view information[J]. Medical Physics,2002,29(2):238-247.
[84] Van Engeland S, Timp S, Karssemeijer N. Finding corresponding regions of interest inmediolateral oblique and craniocaudal mammographic views[J]. Medical physics,2006,33(9):3203-3212.
[85] Zheng B, Leader J K, Abrams G S, et al. Multiview-based computer-aided detectionscheme for breast masses[J]. Medical physics,2006,33(9):3135-3143.
[86] Chang Y H, Good W F, Sumkin J H, et al. Computerized localization of breast lesionsfrom two views: An experimental comparison of two methods[J]. Investigativeradiology,1999,34(9):585.
[87] Pu J, Zheng B, Leader J K, et al. An ellipse-fitting based method for efficientregistration of breast masses on two mammographic views[J]. Medical physics,2008,35(2):487-494.
[88] Miller P, Astley S M. Detection of breast asymmetry using anatomicalfeatures[C]//IS&T/SPIE's Symposium on Electronic Imaging: Science andTechnology. International Society for Optics and Photonics,1993:433-442.
[89] Miller P, Astley S. Automated detection of breast asymmetry using anatomicalfeatures[J]. State of the Art in Digital Mammographic Image Analysis, Series inMachine Perception and Artificial Intelligence,1994,9:247-261.
[90] Mendez A J, Tahoces P G, Lado M J, et al. Computer-aided diagnosis: Automaticdetection of malignant masses in digitized mammograms[J]. Medical Physics,1998,25(6):957-964.
[91] Ferrari R J, Rangayyan R M, Desautels J E L, et al. Analysis of asymmetry inmammograms via directional filtering with Gabor wavelets[J]. Medical Imaging,IEEE Transactions on,2001,20(9):953-964.
[92] R.M.Rangayyan,R.J.Ferrari,Detection of asymmetry between left and rightmammograms.in E.Pisano.Proceedings of the Seventh International Workshop onDigital Mammography.Springer,2004,651-658
[93]徐胜舟,宋恩民,许向阳.基于改进Demons算法的乳腺X线摄片非刚性配准[J].中国图象图形学报,2009,14(12):2566-2571.
[94] Wu Y T, Wei J, Hadjiiski L M, et al. Bilateral analysis based false positive reductionfor computer-aided mass detection[J]. Medical physics,2007,34(8):3334-3344.
[95] Burnside E S, Sickles E A, Sohlich R E, et al. Differential value of comparison withprevious examinations in diagnostic versus screening mammography[J]. AmericanJournal of Roentgenology,2002,179(5):1173-1177.
[96] Zheng B, Good W F, Armfield D R, et al. Performance change of mammographicCAD schemes optimized with most-recent and prior image databases[J]. Academicradiology,2003,10(3):283-288.
[97] Hadjiiski L, Sahiner B, Chan H P, et al. Analysis of temporal changes ofmammographic features: computer-aided classification of malignant and benignbreast masses[J]. Medical Physics,2001,28(11):2309-2317.
[98] Hadjiiski L, Sahiner B, Helvie M A, et al. Breast Masses: Computer-aided Diagnosiswith Serial Mammograms1[J]. Radiology,2006,240(2):343-356.
[99] Hadjiiski L, Chan H P, Sahiner B, et al. Automated registration of breast lesions intemporal pairs of mammograms for interval change analysis—Local affinetransformation for improved localization[J]. Medical physics,2001,28(6):1070-1079.
[100] Timp S, van Engeland S, Karssemeijer N. A regional registration method to findcorresponding mass lesions in temporal mammogram pairs[J]. Medical physics,2005,32(8):2629-2638.
[101] Sanjay-Gopal S, Chan H P, Wilson T, et al. A regional registration technique forautomated interval change analysis of breast lesions on mammograms[J]. MedicalPhysics,1999,26(12):2669-2679.
[102] Donoho D L, Johnstone J M. Ideal spatial adaptation by wavelet shrinkage[J].Biometrika,1994,81(3):425-455.
[103] Candès E J. Harmonic analysis of neural networks[J]. Applied and ComputationalHarmonic Analysis,1999,6(2):197-218.
[104] Candes E J, Donoho D L. Curvelets: A surprisingly effective nonadaptiverepresentation for objects with edges[R]. Stanford Univ Ca Dept of Statistics,2000.
[105] Meyer F G, Coifman R R. Brushlets: a tool for directional image analysis and imagecompression[J]. Applied and computational harmonic analysis,1997,4(2):147-187.
[106] Do M N, Vetterli M. The contourlet transform: an efficient directionalmultiresolution image representation[J]. Image Processing, IEEE Transactions on,2005,14(12):2091-2106.
[107] Da Cunha A L, Zhou J, Do M N. The nonsubsampled contourlet transform: theory,design, and applications[J]. Image Processing, IEEE Transactions on,2006,15(10):3089-3101.
[108] Zhou Y, Wang J. Image denoising based on the symmetric normal inverse Gaussianmodel and non-subsampled contourlet transform[J]. Image Processing, IET,2012,6(8):1136-1147.
[109] Buades A, Coll B, Morel J M. A non-local algorithm for imagedenoising[C]//Computer Vision and Pattern Recognition,2005. CVPR2005. IEEEComputer Society Conference on. IEEE,2005,2:60-65.
[110]李均利,侯艳芹,魏平,等.一种基于模糊均差和小波变换的医学图像去噪方法[J].中国生物医学工程学报,2007,26(3):342-348.
[111] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from errorvisibility to structural similarity[J]. Image Processing, IEEE Transactions on,2004,13(4):600-612.
[112] Ridler T W, Calvard S. Picture thresholding using an iterative selection method[J].IEEE transactions on Systems, Man and Cybernetics,1978,8(8):630-632.
[113] Otsu N. A threshold selection method from gray-level histograms[J]. Automatica,1975,11(285-296):23-27.
[114] Zhang X P, Desai M D. Segmentation of bright targets using wavelets and adaptivethresholding[J]. Image Processing, IEEE Transactions on,2001,10(7):1020-1030.
[115] Iijima T. Basic theory on normalization of a pattern (in case of typicalone-dimensional pattern)[J]. Bulletin of Electrical Laboratory,1962,26:368-388.
[116] Lindeberg T. Scale-space theory: A basic tool for analyzing structures at differentscales[J]. Journal of applied statistics,1994,21(1-2):225-270.
[117] Lou S L, Lin H D, Lin K P, et al. Automatic breast region extraction from digitalmammograms for PACS and telemammography applications[J]. ComputerizedMedical Imaging and Graphics,2000,24(4):205-220.
[118]魏平,李均利,鲁东明,等.基于乳腺钼靶X线图像等值面特征的乳腺区域阈值分割算法[J].中国图象图形学报,2011,16(2):227-235.
[119] Wang Q, Song E, Jin R, et al. Segmentation of Lung Nodules in ComputedTomography Images Using Dynamic Programming and Multidirection FusionTechniques[J]. Academic radiology,2009,16(6):678-688.
[120] Song E, Jiang L, Jin R, et al. Breast mass segmentation in mammography usingplane fitting and dynamic programming[J]. Academic radiology,2009,16(7):826-835.
[121] Domínguez A R, Nandi A K. Improved dynamic-programming-based algorithms forsegmentation of masses in mammograms[J]. Medical physics,2007,34(11):4256-4269.
[122]徐胜舟.乳腺X线摄片中肿块的计算机辅助诊断方法研究[D].华中科技大学,2011.
[123] Chan T F, Vese L A. Active contours without edges[J]. Image processing, IEEEtransactions on,2001,10(2):266-277.
[124]王颖,李洁,高新波.基于MCA的乳腺X线图像中肿块的自适应检测方法[J].电子学报,2011,39(3):525-530.
[125] Zhou Y,JiaJun Wang， Mammographic Lesion Detection Based on ImprovedConcentric Morphology Model，2013International Conference on MechatronicSciences,Electric Engineering and Computer,929-933.
[126]罗希平,田捷.图像分割方法综述[J].模式识别与人工智能,1999,12(3):300-312.
[127] Kass M, Witkin A, Terzopoulos D. Snakes: Active contour models[J]. Internationaljournal of computer vision,1988,1(4):321-331.
[128] Xu C, Prince J L. Snakes, shapes, and gradient vector flow[J]. Image Processing,IEEE Transactions on,1998,7(3):359-369.
[129] Wu Z, Leahy R. An optimal graph theoretic approach to data clustering: Theory andits application to image segmentation[J]. Pattern Analysis and Machine Intelligence,IEEE Transactions on,1993,15(11):1101-1113.
[130] Sarkar S, Soundararajan P. Supervised learning of large perceptual organization:Graph spectral partitioning and learning automata[J]. Pattern Analysis and MachineIntelligence, IEEE Transactions on,2000,22(5):504-525.
[131] Shi J, Malik J. Normalized cuts and image segmentation[J]. Pattern Analysis andMachine Intelligence, IEEE Transactions on,2000,22(8):888-905.
[132] Grady L, Schwartz E L. Isoperimetric graph partitioning for image segmentation[J].Pattern Analysis and Machine Intelligence, IEEE Transactions on,2006,28(3):469-475.
[133] Yuan Y, Giger M L, Li H, et al. A dual-stage method for lesion segmentation ondigital mammograms[J]. Medical physics,2007,34(11):4180-4193.
[134]姜娈.基于乳腺X线摄片的计算机辅助检测肿块方法研究[D].华中科技大学,2009.
[135]兰红,张璐.分水岭优化的Snake模型肝脏图像分割[J].中国图象图形学报,2012,17(7):873-879.
[136] Li C, Kao C Y, Gore J C, et al. Minimization of region-scalable fitting energy forimage segmentation[J]. Image Processing, IEEE Transactions on,2008,17(10):1940-1949.