|
|
Mammographic mass segmentation algorithm based on automatic random walks |
CAO Ying, HAO Xin, ZHU Xiao-en, XIA Shun-ren |
Key Laboratory of Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou 310027, China |
|
|
Abstract A mammographic mass segmentation algorithm based on automatic random walks algorithm was presented in order to overcome the interference of the weak edge and surrounding tissues on mass segmentation in mammograms. Twodimensional maximum entropy threshold, region growing algorithm and morphological method were used to automatically get a series of labels. Then the evaluation method of average edge gradient was used to select the effective labels for random walks segmentation, and the initial segmentation results were obtained; the spiculation pattern was also detected based on such segmentation results. The complete segmentation contour for mass was achieved. 227 images containing mass were randomly selected for segmentation. Then feature extraction and classification were implemented based on the segmentation results. Experimental results show that the algorithm overcomes the application limitation of semi-automatic random walks algorithm, and improves the accuracy of segmentation. The algorithm achieves higher classification accuracy compared with other segmentation algorithms for mass.
|
Published: 01 October 2011
|
|
基于自动随机游走的乳腺肿块分割算法
针对乳腺X线影像肿块分割易受弱边缘和周围组织干扰的问题,提出一种基于自动随机游走的乳腺肿块分割算法.利用二维最大熵阈值法、区域生长及形态学方法自动确定一系列标记点,采用平均边缘梯度评价法选择有效标记点进行随机游走分割以获得初步分割结果,并在此分割基础上进行星芒状结构检测,获得完整的肿块分割边缘.随机选取227例肿块图像进行分割,对分割结果进行特征提取和分类.实验结果表明,该算法克服了半自动随机游走的应用局限性,提高了乳腺肿块的分割精度;与其他分割算法相比,该算法在后续的分类中具有更高的分类精度.
|
|
[1] ETTLIN C. Global breast cancer mortality statistics [J]. CA: A Cancer Journal for Clinicians, 1999, 49(3): 138-144. [2] MILLER A B. Mammography: reviewing the evidence. epidemiology aspect [J]. Canadian Family Physician, 1993, 39: 85-90. [3] SMART C R, HENDRICK R E, RUTLEDGE III J H, et al. Benefit of mammography screening in women ages 40 to 49 years: current evidence from randomized controlled trials [J]. Cancer, 1995, 75(7): 1619-1626. [4] 郝欣,曹颖,夏顺仁.基于医学图像内容检索的计算机辅助乳腺X线影像诊断技术[J].中国生物医学工程学报,2009,28(6): 922-930. HAO Xin, CAO Ying, XIA Shunren. Computeraided diagnosis technique on mammograms using contentbased medical image retrieval [J]. Chinese Journal of Biomedical Engineering, 2009, 28(6): 922-930. [5] TANG J S, RANGAYYAN R M, XU J, et al. Computeraided detection and diagnosis of breast cancer with mammography: recent advances [J]. IEEE Transactions on Information on Technology in Biomedicine, 2009, 13(2): 236-251. [6] 沈晔,夏顺仁,李敏丹. 基于内容的医学图像检索中的相关反馈技术[J].中国生物医学工程学报, 2009,28(1): 128-136. SHEN Ye,XIA Shunren, LI Mindan. A survey on relevance feedback techniques in content based medical image retrieval [J]. Chinese Journal of Biomedical Engineering, 2009, 28(1): 128-136. [7] CHENG H D, SHI X J, MIN R, et al. Approaches for automated detection and classification of masses in mammograms [J]. Pattern Recognition, 2006, 39(4): 646-668. [8] BRZAKOVIC D, LUO X M, BRZAKOVIC P. An approach to automated detection of tumors in mammograms [J]. IEEE Transaction on Medical Imaging, 1990, 9(3): 233-241. [9] LI L, QIAN W, CLARKE L P, et al. Improving mass detection by adaptive and multiscale processing in digitized mammograms [J]. Proceedings of SPIE, 1999, 3661: 490-498. [10] LANKTON S, TANNENBAUM A R. Localizing regionbased active contours [J]. IEEE Transactions on Image Processing, 2008, 17(11): 2029-2039. [11] GRADY L. Random walks for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(11): 1768-1783. [12] GRADY L, SCHIWIETZ T, AHARON S, et al. Random walks for interactive organ segmentation in two and three dimensions: Implementation and validation [J]. Medical Image Computing and Computerassisted Intervention, 2005, 3750: 773-780. [13] JIANG L, SONE E M, XU X Y, et al. Automated detection of breast mass spiculation levels and evaluation of scheme performance [J]. Academic Radiology, 2008, 15(12): 1534-1544. [14] 李刚.数字图像的模糊增强方法[D].武汉:武汉理工大学,2005: 19-26. LI Gang. Digital image processing methods based on fuzzy enhancement [D]. Wuhan: Wuhan University of Technology, 2005: 19-26. [15] 李宏言,盛利元,陈良款,等.基于二维最大熵原理和改进遗传算法的图像阈值分割[J].计算机与现代化, 2007(2): 34-37. LI Hongyan, SHEN Liyuan, CHEN Liangkuan, et al. Image thresholding segmentation based on 2D maximum entropy principle and improved genetic algorithm [J]. Computer and Modernization, 2007(2): 34-37. [16] YUAN Y, GIGER M L, LI H, et al. A dualstage method for lesion segmentation on digital mammograms [J]. Medical Physics, 2007, 34(11): 4180-4193. [17] SAMPAT M P, BOVIK A C, WHITMAN G J, et al. A modelbased framework for the detection of spiculated masses on mammography [J]. Medical Physics, 2008, 35(5): 2110-2123. [18] DOYLE P, SNELL L. Random walks and electric networks [M]. Washington, D.C.: Mathematical Association of America, 1984: 16-50. [19] CAO Y, HAO X, ZHU X E, et al. An adaptive region growing algorithm for breast mass in mammograms [J]. Frontiers of Electrical and Electronic Engineering in China, 2010, 5(2): 128-136. [20] 胡永升.现代乳腺影像诊断学[M].北京:科学出版社,2001: 45-58. [21] HARALICK R M, SHANMUGAM K, DINSTEIN I H. Textural features for image classification [J]. IEEE Transaction on Systems, Man and Cybernetics, 1973, 3(6): 610-622. [22] MAVROFORAKIS M E, GEORGIOU H V, DIMITROPOULOS N, et al. Mammographic masses characterization based on localized texture and |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|