基于数字钼靶软X线图像的乳腺肿块分割和检测算法研究
|
摘要
乳腺X线成像是一种早期检测乳腺癌的主要手段。人们提出利用计算机技术辅助医师阅读X线图像,从而减轻医师在阅片时的负担,提高乳腺癌诊断的准确率。本论文主要介绍作者在乳腺肿块方面计算机辅助诊断技术的研究工作,包括乳腺图像预处理、种子点的肿块分割和感兴趣区域的快速搜索三部分内容。
在乳腺图像预处理方面,作者主要介绍乳腺轮廓提取算法和边缘灰度补偿算法。这两个算法的目的是获得图像中的乳腺区域,同时补偿由于乳腺边缘区域厚度变化造成的灰度变化,算法主要基于数学形态学运算尤其是分水岭变换。轮廓提取算法的结果由临床医师评价,实验结果表明本文提出的轮廓提取算法准确有效。
种子点的肿块分割算法的目的是在预先知道肿块内部的一个点的基础上,利用计算机图像处理技术获得一个肿块边界的最优近似。作者首先提出一个肿块的模型,在此基础上定义了肿块边界,利用基于数学形态学的加权区域膨胀算法和离心梯度均值确定最优的边界。我们把分割算法获得的结果与医师人工勾画的肿块区域比较,结果显示我们的算法与目前国际提出的分割算法具有相似的分割精度,但是这种算法更符合DDSM中医师定义的肿块边界,而且算法对种子点的位置具有鲁棒性。除了目前国际比较通用的评价方法,作者还提出了一种种子点阵评价,用来估计算法对种子点的鲁棒性。
感兴趣区域的快速搜索算法主要是在整个乳腺区域内搜索可疑的区域,这些区域具有与肿块区域类似的图像特征。作者主要利用多尺度下的通用邻域算子计算像素的一阶梯度,通过判断一阶梯度的方向寻找图像中的亮斑,从而获得可疑的区域。评价方法也是把分割算法获得的结果与医师标记的肿块比较,实验结果显示在保证90%的真阳性被检测出来的同时,平均每张图片会检测出5~6个假阳性。
上述三个部分的工作实现了一个完整的乳腺肿块计算机辅助诊断系统的部分功能。
Mammographic imaging is especially valuable as an early detection tool for breastcancer. People have been proposed the application of computer technology to assist theclinicians with breast cancer detection and diagnosis. The thesis summarizes theauthor's research in computer—aided diagnosis on masses on mammograms, includingmammogram preprocessing, automated seeded mass segmentation and fast detection ofregion of interest.
Breast boundary extracting algorithm and peripheral breast gray value correctingalgorithm were proposed in the mammogram preprocessing step. These two algorithmsaimed at extracting the breast—air interface on mammograms and enhancing the darkportions due to the reduction of thickness along the peripheral breast. The breastboundary extracting algorithm based mainly on morphological operations, especially thewatershed transformation and the boundaries from extracting algorithm were evaluatedby a clinician. Experimental results demonstrate the proposed boundary extractionalgorithm to be accurate and effective.
With the application of computer image processing techniques, automated seededmass segmentation gained an optimal approximation from a seeded pixel within themass region selected manually. The author first proposed a mass model and describedthe definition of mass boundary. Then the gray—value—weighted region dilatingalgorithm and centrifugal gradient index were employed to determine the optimalboundary. We compared the segmentation of our algorithm with the mass boundarymanually drawn by clinicians. Experimental results demonstrated that the performanceof the proposed algorithm was similar to the performances of those segmentationschemes proposed by other researchers. In addition, the author also proposed the seededmatrix evaluation method to estimate the seeded pixel robustness of the segmentingalgorithm.
The fast detecting algorithm of region of interest aimed at detecting possible mass
regions from the entire breast region on mammograms. The author employed themultiscale generic neighborhood operator to calculate the gradient of image pixels. Then,those possible mass regions were determined by analyzing the gradient orientations. Theevaluation method was a comparison between the performances of detecting algorithmand those of clinicians. Experimental results demonstrated that a sensitivity ofapproximately 90% was reached at an average level of five false positive per image.All three researching steps described above partially implement the function of acomplete computer—aided diagnosis system on breast mass.
在乳腺图像预处理方面,作者主要介绍乳腺轮廓提取算法和边缘灰度补偿算法。这两个算法的目的是获得图像中的乳腺区域,同时补偿由于乳腺边缘区域厚度变化造成的灰度变化,算法主要基于数学形态学运算尤其是分水岭变换。轮廓提取算法的结果由临床医师评价,实验结果表明本文提出的轮廓提取算法准确有效。
种子点的肿块分割算法的目的是在预先知道肿块内部的一个点的基础上,利用计算机图像处理技术获得一个肿块边界的最优近似。作者首先提出一个肿块的模型,在此基础上定义了肿块边界,利用基于数学形态学的加权区域膨胀算法和离心梯度均值确定最优的边界。我们把分割算法获得的结果与医师人工勾画的肿块区域比较,结果显示我们的算法与目前国际提出的分割算法具有相似的分割精度,但是这种算法更符合DDSM中医师定义的肿块边界,而且算法对种子点的位置具有鲁棒性。除了目前国际比较通用的评价方法,作者还提出了一种种子点阵评价,用来估计算法对种子点的鲁棒性。
感兴趣区域的快速搜索算法主要是在整个乳腺区域内搜索可疑的区域,这些区域具有与肿块区域类似的图像特征。作者主要利用多尺度下的通用邻域算子计算像素的一阶梯度,通过判断一阶梯度的方向寻找图像中的亮斑,从而获得可疑的区域。评价方法也是把分割算法获得的结果与医师标记的肿块比较,实验结果显示在保证90%的真阳性被检测出来的同时,平均每张图片会检测出5~6个假阳性。
上述三个部分的工作实现了一个完整的乳腺肿块计算机辅助诊断系统的部分功能。
Mammographic imaging is especially valuable as an early detection tool for breastcancer. People have been proposed the application of computer technology to assist theclinicians with breast cancer detection and diagnosis. The thesis summarizes theauthor's research in computer—aided diagnosis on masses on mammograms, includingmammogram preprocessing, automated seeded mass segmentation and fast detection ofregion of interest.
Breast boundary extracting algorithm and peripheral breast gray value correctingalgorithm were proposed in the mammogram preprocessing step. These two algorithmsaimed at extracting the breast—air interface on mammograms and enhancing the darkportions due to the reduction of thickness along the peripheral breast. The breastboundary extracting algorithm based mainly on morphological operations, especially thewatershed transformation and the boundaries from extracting algorithm were evaluatedby a clinician. Experimental results demonstrate the proposed boundary extractionalgorithm to be accurate and effective.
With the application of computer image processing techniques, automated seededmass segmentation gained an optimal approximation from a seeded pixel within themass region selected manually. The author first proposed a mass model and describedthe definition of mass boundary. Then the gray—value—weighted region dilatingalgorithm and centrifugal gradient index were employed to determine the optimalboundary. We compared the segmentation of our algorithm with the mass boundarymanually drawn by clinicians. Experimental results demonstrated that the performanceof the proposed algorithm was similar to the performances of those segmentationschemes proposed by other researchers. In addition, the author also proposed the seededmatrix evaluation method to estimate the seeded pixel robustness of the segmentingalgorithm.
The fast detecting algorithm of region of interest aimed at detecting possible mass
regions from the entire breast region on mammograms. The author employed themultiscale generic neighborhood operator to calculate the gradient of image pixels. Then,those possible mass regions were determined by analyzing the gradient orientations. Theevaluation method was a comparison between the performances of detecting algorithmand those of clinicians. Experimental results demonstrated that a sensitivity ofapproximately 90% was reached at an average level of five false positive per image.All three researching steps described above partially implement the function of acomplete computer—aided diagnosis system on breast mass.
引文
[1] American Cancer Society. Cancer Facts and Figures 2005. Atlanta: American Cancer Society;2005.
[2] 董志伟, 乔友林, 李连弟, 等. 中国癌症控制策略研究报告. 中国肿瘤, 2002, 11 (5): 250~260
[3] Giger M. Overview of computer-aided diagnosis in breast imaging. In: Proceedings of the First International Workshop on Computer-Aided Diagnosis, Chicago, U.S.A., 20-23 Sept., 1998: 167~176
[4] Giger M, Huo Z, Kupinski M, et al. Computer-aided diagnosis in mammography. In: Sonka M, Fitzpatrick M, eds. Handbook of Medical Imaging, Washington, DC: SPIE, 2000, 2: 915~986
[5] 胡永升. 现代乳腺影像诊断学. 北京: 科学出版社, 2001.2. 48~81
[6] Huo Z, Giger M.L, Vyborny C.J. Computerized analysis of multiple-mammographic views: potential usefulness of special view mammograms in computer-aided diagnosis. IEEE Trans. Med. Imag. December 2001, 20 (12):1285~1292
[7] Veldkamp.W, Karssemeijer N. Normalization of local contrast in mammograms. IEEE Trans. Med. Imag. 2000, 19:731-738
[8] McLoughlin K, Bones P, Karssemeijer N. Noise equalization for detection of microcalcification clusters in direct digital mammogram images. IEEE Trans. Med. Imag. 2004, 23(3):313-320
[9] Sari-Sarraf H., Gleason S., Hudson K. A novel approach to computer-aided diagnosis of mammographic images. In: Applications of Computer Vision, Proceedings 3rd IEEE Workshop, 2-4 Dec. 1996: 230-235
[10] Li H, Wang Y, Liu K, et al. Computerized radiographic mass detection—part II: decision support by featured database visualization and modular neural networks. IEEE Trans. Med. Imag. 2001, 20(4):302-313
[11] Shalom B, Isaac L, Richard L, et al. Can the size of microcalcifications predict malignancy of clusters at mammography? Acad. Radiol. 2002, 9:18–25
[12] Verma B, Zakos J. A computer-aided diagnosis system for digital mammograms nased on fuzzy-neural and feature extraction techniques. IEEE Transaction on Information Technology in Biomedicine, 2001, 5(1):46-54
[13] Li H, Liu K, Lo S. Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms. IEEE Trans. Med. Imag. 1997, 16(6):785-798
[14] Gavrielides M, Lo J, Vargas-Voracek R, et al. Segmentation of suspicious clustered microcalcifications in mammograms. Med. Phys. 2000, 27(1):13-22
[15] Liu S, Babbs C, Delp E. Multiresolution detection of speculated lesions in digital mammograms. IEEE Transactions on Image Processing, 2001, 10(3):874-884
[16] Li L, Zheng Y, Clark R. False-positive reduction in CAD mass detection using a competitive classification strategy. Med. Phys. 2001, 28(2):250-258
[17] Lo S, Li H, Wang Y, et al. A multiple circular path convolution neural network system for detection of mammographic masses. IEEE Trans. Med. Imag. 2002, 21(2):150-158
[18] Bishop C. Neural networks for pattern recognition. Oxford: Oxford University Press. 1995
[19] .Pao Y—H. Adaptive pattern recognition and neural networks. Addison—Wesley, 1989
[20] Obuchowski N. Receiver operating characteristic curves and their use in radiology. Radiology, 2003, 229:3–8
[21] 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. 电子学报, Apr. 2004, 32(4): 587~590
[22] Brake G, Karssemeijer N. Single and multiscale detection of masses in digital mammogram. IEEE Trans. Med. Imag. July 1999, 18(7): 628~639
[23] Karssemeijer N, Brake G. Detection of Stellate distortions in mammograms. IEEE Trans. Med. Imag. Oct. 1996, 15(5): 611~619
[24] Koenderink J, Doorn A. Generic neighborhood operators. IEEE Transactions on Pattern Analysis and Machine Intelligence, June 1992, 14(6): 597~605
[25] Bick U, Giger M.L, Schmidt R.A, et al. Automated segmentation of digitized mammograms. Acad. Radiol. 1995, 2: 1~9
[26] Mendez A.J, Tahoces P.G, Lado M.J, et al. Automatic detection of breast border and nipple in digital mammograms. Computer Methods and Programs in Biomedicine, 1996, 49:253~262
[27] Wirth M.A, Stapinski A. Segmentation of the breast region in mammograms using snakes. In: Computer and Robot Vision, 2004. Proceedings of First Canadian Conference on, 2004, 385~392
[28] Wirth M.A, Lyon J, Nikitenko D, et al. A fuzzy approach to segmenting the breast region in mammograms. In: Fuzzy Information, 2004. Processing NAFIPS '04. IEEE Annual Meeting of the, 2004, 1: 474~479
[29] Soille P. Morphological image analysis: principles and applications, 2nd ed., Germany: Springer, 2003
[30] Petrick N, Chan H.P, Wei D, et al. Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification. Med. Phys. 1996, 23(10):1685~1696
[31] Comer M.L, Liu S, Delp E.J. Statistical segmentation of mammograms. In: Doi K, Giger M.L, Nishikawa R.M, et al Eds., Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 471~474
[32] Li H.D, Kallergi M, Clarke L.P, et al. Markov random field for tumor detection in digital mammography. IEEE Trans. Med. Imag. June 1995, 14: 565~576
[33] Sameti M, Ward R.K. A fuzzy segmentation algorithm for mammogram partitioning. In: Doi K ed. Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 471~474
[34] Kupinski M.A, Giger M.L. Automated seeded lesion segmentation on digital mammograms. IEEE Trans. Med. Imag. 1998, 17(4): 510~517
[35] Ng S.L, Bischof W.F. Automated detection and classification of breast tumors. Comput. Biomed. Res. 1992, 25: 218~237
[36] Groshong B.R, Kegelmeyer W.P. Evaluation of a Hough transform method for circumscribed lesion detection. In: Doi K, Giger M.L, Nishikawa R.M, et al Eds., Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 361~366
[37] Liu S, Babbs C.F, Delp E.J. Multiresolution detection of speculated lesions in digital mammograms. IEEE Trans. Med. Imag. 2001, 10(6): 874~884
[38] Nishikawa R.M, Giger M.L, Doi K, et al. Computer—aided detection and diagnosis of masses and clustered microcalcifications from digital mammograms. In: Bowyer K.W, Astley S.M Eds., State of the Art in Digital Mammographic Image Analysis(Series in Machine Perception and Artificial Intelligence). New York: World Scientific, 1994, 9: 82~102
[2] 董志伟, 乔友林, 李连弟, 等. 中国癌症控制策略研究报告. 中国肿瘤, 2002, 11 (5): 250~260
[3] Giger M. Overview of computer-aided diagnosis in breast imaging. In: Proceedings of the First International Workshop on Computer-Aided Diagnosis, Chicago, U.S.A., 20-23 Sept., 1998: 167~176
[4] Giger M, Huo Z, Kupinski M, et al. Computer-aided diagnosis in mammography. In: Sonka M, Fitzpatrick M, eds. Handbook of Medical Imaging, Washington, DC: SPIE, 2000, 2: 915~986
[5] 胡永升. 现代乳腺影像诊断学. 北京: 科学出版社, 2001.2. 48~81
[6] Huo Z, Giger M.L, Vyborny C.J. Computerized analysis of multiple-mammographic views: potential usefulness of special view mammograms in computer-aided diagnosis. IEEE Trans. Med. Imag. December 2001, 20 (12):1285~1292
[7] Veldkamp.W, Karssemeijer N. Normalization of local contrast in mammograms. IEEE Trans. Med. Imag. 2000, 19:731-738
[8] McLoughlin K, Bones P, Karssemeijer N. Noise equalization for detection of microcalcification clusters in direct digital mammogram images. IEEE Trans. Med. Imag. 2004, 23(3):313-320
[9] Sari-Sarraf H., Gleason S., Hudson K. A novel approach to computer-aided diagnosis of mammographic images. In: Applications of Computer Vision, Proceedings 3rd IEEE Workshop, 2-4 Dec. 1996: 230-235
[10] Li H, Wang Y, Liu K, et al. Computerized radiographic mass detection—part II: decision support by featured database visualization and modular neural networks. IEEE Trans. Med. Imag. 2001, 20(4):302-313
[11] Shalom B, Isaac L, Richard L, et al. Can the size of microcalcifications predict malignancy of clusters at mammography? Acad. Radiol. 2002, 9:18–25
[12] Verma B, Zakos J. A computer-aided diagnosis system for digital mammograms nased on fuzzy-neural and feature extraction techniques. IEEE Transaction on Information Technology in Biomedicine, 2001, 5(1):46-54
[13] Li H, Liu K, Lo S. Fractal modeling and segmentation for the enhancement of microcalcifications in digital mammograms. IEEE Trans. Med. Imag. 1997, 16(6):785-798
[14] Gavrielides M, Lo J, Vargas-Voracek R, et al. Segmentation of suspicious clustered microcalcifications in mammograms. Med. Phys. 2000, 27(1):13-22
[15] Liu S, Babbs C, Delp E. Multiresolution detection of speculated lesions in digital mammograms. IEEE Transactions on Image Processing, 2001, 10(3):874-884
[16] Li L, Zheng Y, Clark R. False-positive reduction in CAD mass detection using a competitive classification strategy. Med. Phys. 2001, 28(2):250-258
[17] Lo S, Li H, Wang Y, et al. A multiple circular path convolution neural network system for detection of mammographic masses. IEEE Trans. Med. Imag. 2002, 21(2):150-158
[18] Bishop C. Neural networks for pattern recognition. Oxford: Oxford University Press. 1995
[19] .Pao Y—H. Adaptive pattern recognition and neural networks. Addison—Wesley, 1989
[20] Obuchowski N. Receiver operating characteristic curves and their use in radiology. Radiology, 2003, 229:3–8
[21] 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. 电子学报, Apr. 2004, 32(4): 587~590
[22] Brake G, Karssemeijer N. Single and multiscale detection of masses in digital mammogram. IEEE Trans. Med. Imag. July 1999, 18(7): 628~639
[23] Karssemeijer N, Brake G. Detection of Stellate distortions in mammograms. IEEE Trans. Med. Imag. Oct. 1996, 15(5): 611~619
[24] Koenderink J, Doorn A. Generic neighborhood operators. IEEE Transactions on Pattern Analysis and Machine Intelligence, June 1992, 14(6): 597~605
[25] Bick U, Giger M.L, Schmidt R.A, et al. Automated segmentation of digitized mammograms. Acad. Radiol. 1995, 2: 1~9
[26] Mendez A.J, Tahoces P.G, Lado M.J, et al. Automatic detection of breast border and nipple in digital mammograms. Computer Methods and Programs in Biomedicine, 1996, 49:253~262
[27] Wirth M.A, Stapinski A. Segmentation of the breast region in mammograms using snakes. In: Computer and Robot Vision, 2004. Proceedings of First Canadian Conference on, 2004, 385~392
[28] Wirth M.A, Lyon J, Nikitenko D, et al. A fuzzy approach to segmenting the breast region in mammograms. In: Fuzzy Information, 2004. Processing NAFIPS '04. IEEE Annual Meeting of the, 2004, 1: 474~479
[29] Soille P. Morphological image analysis: principles and applications, 2nd ed., Germany: Springer, 2003
[30] Petrick N, Chan H.P, Wei D, et al. Automated detection of breast masses on mammograms using adaptive contrast enhancement and texture classification. Med. Phys. 1996, 23(10):1685~1696
[31] Comer M.L, Liu S, Delp E.J. Statistical segmentation of mammograms. In: Doi K, Giger M.L, Nishikawa R.M, et al Eds., Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 471~474
[32] Li H.D, Kallergi M, Clarke L.P, et al. Markov random field for tumor detection in digital mammography. IEEE Trans. Med. Imag. June 1995, 14: 565~576
[33] Sameti M, Ward R.K. A fuzzy segmentation algorithm for mammogram partitioning. In: Doi K ed. Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 471~474
[34] Kupinski M.A, Giger M.L. Automated seeded lesion segmentation on digital mammograms. IEEE Trans. Med. Imag. 1998, 17(4): 510~517
[35] Ng S.L, Bischof W.F. Automated detection and classification of breast tumors. Comput. Biomed. Res. 1992, 25: 218~237
[36] Groshong B.R, Kegelmeyer W.P. Evaluation of a Hough transform method for circumscribed lesion detection. In: Doi K, Giger M.L, Nishikawa R.M, et al Eds., Digital Mammography. International Congress Series. Amsterdam, the Netherlands: Elsevier, 1996: 361~366
[37] Liu S, Babbs C.F, Delp E.J. Multiresolution detection of speculated lesions in digital mammograms. IEEE Trans. Med. Imag. 2001, 10(6): 874~884
[38] Nishikawa R.M, Giger M.L, Doi K, et al. Computer—aided detection and diagnosis of masses and clustered microcalcifications from digital mammograms. In: Bowyer K.W, Astley S.M Eds., State of the Art in Digital Mammographic Image Analysis(Series in Machine Perception and Artificial Intelligence). New York: World Scientific, 1994, 9: 82~102
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |