-
摘要: 乳腺超声(Breast ultrasound, BUS)图像具有较低的信噪比、 较低的对比度以及较模糊的边缘, 其分割是一项富有挑战性的工作. 本文提出了一种多域协同分割模型, 该模型通过结合空域与频域先验, 并引入协同分割的思想来实现对乳腺超声序列的分割. 模型在空域中得到肿瘤的姿态、 位置和强度信息, 在频域中通过使用相位一致性与零交叉检测得到肿瘤的边缘信息, 最后利用协同分割的思想构建起全局能量项, 有效地利用了图像序列信息.实验结果表明, 与传统的乳腺超声图像分割方法相比, 本文提出的分割模型能够很好地处理低对比度低回声图像以及单帧分割模型不能有效分割的图像, 分割结果具有更高的准确性.Abstract: Because of low signal-noise ratio, low contrast and blurry boundaries, breast ultrasound (BUS) image segmentation is quite challenging. In this paper, a multiple-domain knowledge based co-segmentation model is proposed for BUS segmentation. It combines spatial and frequency domain prior knowledge and introduces the idea of co-segmentation to segment BUS sequence. First, tumor poses, position and intensity distribution are modeled to constrain the segmentation in the spatial domain, and then the phase feature and zero-crossing feature in the frequency domain. Finally, the BUS sequence segmentation is formulated as a co-segmentation problem. Experimental results show that the proposed method can handle low contrast and hypoechoic BUS images well and segment BUS accurately.
-
图 4 4 含较多与肿瘤区域相似的正常组织的超声序列分割结果
Fig. 4 Segmentation results of normal breast ultrasound sequence similar to tumor regions
图 5 低对比度、边界模糊的超声序列的分割结果
Fig. 5 Segmentation results of breast ultrasound sequence with low contrast and blurry boundaries
图 6 单帧不易分割的超声序列的分割结果
Fig. 6 Segmentation results of breast ultrasound sequence hard to segment for single frame
图 7 单帧不易分割的超声序列的分割结果
Fig. 7 Segmentation results of breast ultrasound sequence hard to segment for single frame
表 1 4类方法在所有乳腺超声图像上的整体分割结果
Table 1 Segmentation results of four methods on all breast ultrasound images
下载: 导出CSV
-
[1] Cheng H D, Shan J, Ju W, Guo Y H, Zhang L. Automated breast cancer detection and classification using ultrasound images: a survey. Pattern Recognition, 2010, 43(1): 299-317 doi: 10.1016/j.patcog.2009.05.012 [2] Cheng H D, Shi X J, Min R, Hu L M, Cai X P, Du H N. Approaches for automated detection and classification of masses in mammograms. Pattern Recognition, 2006, 39(4): 646-668 doi: 10.1016/j.patcog.2005.07.006 [3] Chen D R, Chang R F, Huang Y L. Breast cancer diagnosis using self-organizing map for sonography. Ultrasound in Medicine & Biology, 2000, 26(3): 405-411 http://cn.bing.com/academic/profile?id=2085695360&encoded=0&v=paper_preview&mkt=zh-cn [4] Xian M, Zhang Y T, Cheng H D. Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domains. Pattern Recognition, 2015, 48(2): 485-497 doi: 10.1016/j.patcog.2014.07.026 [5] Shan J, Wang Y X, Cheng H D. Completely automatic segmentation for breast ultrasound using multiple-domain features. In: Proceedings of the 17th IEEE International Conference on Image Processing (ICIP). Hong Kong, China: IEEE, 2010. 1713-1716 [6] Drukker K, Giger M L, Horsch K, Kupinski M A, Vyborny C J, Mendelson E B. Computerized lesion detection on breast ultrasound. Medical Physics, 2002, 29(7): 1438-1446 doi: 10.1118/1.1485995 [7] Boukerroui D, Baskurt A, Noble J A, Basset O. Segmentation of ultrasound images-multiresolution 2D and 3D algorithm based on global and local statistics. Pattern Recognition Letters, 2003, 24(4-5): 779-790 doi: 10.1016/S0167-8655(02)00181-2 [8] Chen D R, Chang R F, Wu W J, Moon W K, Wu W L. 3-D breast ultrasound segmentation using active contour model. Ultrasound in Medicine & Biology, 2003, 29(7): 1017-1026 http://cn.bing.com/academic/profile?id=2033144186&encoded=0&v=paper_preview&mkt=zh-cn [9] Chen D R, Chang R F, Kuo W J, Chen M C, Huang Y L. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. Ultrasound in Medicine & Biology, 2002, 28(10): 1301-1310 http://cn.bing.com/academic/profile?id=2163287977&encoded=0&v=paper_preview&mkt=zh-cn [10] 刘博, 黄剑华, 唐降龙, 刘家锋, 张英涛. 结合全局概率密度差异与局部灰度拟合的超声图像分割. 自动化学报, 2010, 36(7): 951-959 doi: 10.3724/SP.J.1004.2010.00951Liu Bo, Huang Jian-Hua, Tang Xiang-Long, Liu Jia-Feng, Zhang Ying-Tao. Combing global probability density difference and local gray level fitting for ultrasound image segmentation. Acta Automatica Sinica, 2010, 36(7): 951-959 doi: 10.3724/SP.J.1004.2010.00951 [11] 钱生, 陈宗海, 林名强, 张陈斌. 基于条件随机场和图像分割的显著性检测. 自动化学报, 2015, 41(4): 711-724 http://www.aas.net.cn/CN/abstract/abstract18647.shtmlQian Sheng, Chen Zong-Hai, Lin Ming-Qiang, Zhang Chen-Bin. Saliency detection based on conditional random field and image segmentation. Acta Automatica Sinica, 2015, 41(4): 711-724 http://www.aas.net.cn/CN/abstract/abstract18647.shtml [12] 唐利明, 田学全, 黄大荣, 王晓峰. 结合FCMS与变分水平集的图像分割模型. 自动化学报, 2014, 40(6): 1233-1248 http://www.aas.net.cn/CN/abstract/abstract18394.shtmlTang Li-Ming, Tian Xue-Quan, Huang Da-Rong, Wang Xiao-Feng. Image segmentation model combined with FCMS and variational level set. Acta Automatica Sinica, 2014, 40(6): 1233-1248 http://www.aas.net.cn/CN/abstract/abstract18394.shtml [13] 龙建武, 申铉京, 臧慧, 陈海鹏. 高斯尺度空间下估计背景的自适应阈值分割算法. 自动化学报, 2014, 40(8): 1773-1782 http://www.aas.net.cn/CN/abstract/abstract18444.shtmlLong Jian-Wu, Shen Xuan-Jing, Zang Hui, Chen Hai-Peng. An adaptive thresholding algorithm by background estimation in Gaussian scale space. Acta Automatica Sinica, 2014, 40(8): 1773-1782 http://www.aas.net.cn/CN/abstract/abstract18444.shtml [14] Rother C, Minka T, Blake A, Kolmogorov V. Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: IEEE, 2006. 993-1000 http://cn.bing.com/academic/profile?id=2157244733&encoded=0&v=paper_preview&mkt=zh-cn [15] Yu H K, Xian M, Qi X J. Unsupervised co-segmentation based on a new global GMM constraint in MRF. In: Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP). Paris, France: IEEE, 2014. 4412-4416 [16] Joulin A, Bach F, Ponce J. Multi-class cosegmentation. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, RI, USA: IEEE, 2012. 542-549 [17] Kim G, Xing E P, Li F F, Kanade T. Distributed cosegmentation via submodular optimization on anisotropic diffusion. In: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011. 169-176 https://www.computer.org/csdl/proceedings/iccv/2011/1101/00/index.html [18] Meng F M, Li H L, Liu G H, Ngan K N. Object co-segmentation based on shortest path algorithm and saliency model. IEEE Transactions on Multimedia, 2012, 14(5): 1429-1441 doi: 10.1109/TMM.2012.2197741 [19] Shao H Y, Zhang Y T, Xian M, Cheng H D, Xu F, Ding J R. A saliency model for automated tumor detection in breast ultrasound images. In: Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP). Quebec, Canada: IEEE, 2015. 1424-1428 [20] Morrone M C, Ross J, Burr D C, Owens R. Mach bands are phase dependent. Nature, 1986, 324(6094): 250-253 doi: 10.1038/324250a0 [21] Mallat S. Zero-crossings of a wavelet transform. IEEE Transactions on Information Theory, 1991, 37(4): 1019-1033 doi: 10.1109/18.86995 [22] Xian M, Huang J H, Zhang Y T, Tang X L. Multiple-domain knowledge based MRF model for tumor segmentation in breast ultrasound images. In: Proceedings of the 19th IEEE International Conference on Image Processing (ICIP). Orlando, FL, USA: IEEE, 2012. 2021-2024 [23] Kovesi P. Image features from phase congruency. Videre: Journal of Computer Vision Research, 1999, 1(3): 1-26 http://cn.bing.com/academic/profile?id=1962010357&encoded=0&v=paper_preview&mkt=zh-cn [24] Vicente S, Kolmogorov V, Rother C. Cosegmentation revisited: models and optimization. Computer Vision (ECCV 2010). Berlin Heidelberg: Springer, 2010. 465-479 http://cn.bing.com/academic/profile?id=1635155787&encoded=0&v=paper_preview&mkt=zh-cn [25] Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV). Vancouver, BC, Canada: IEEE, 2001. 105-112 http://www.oalib.com/references/16889765 [26] Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137 doi: 10.1109/TPAMI.2004.60 [27] Kolmogorov V, Zabin R. What energy functions can be minimized via graph cuts? IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 147-159 doi: 10.1109/TPAMI.2004.1262177 [28] Shan J, Cheng H D, Wang Y X. Completely automated segmentation approach for breast ultrasound images using multiple-domain features. Ultrasound in Medicine & Biology, 2012, 38(2): 262-275 http://cn.bing.com/academic/profile?id=2122264932&encoded=0&v=paper_preview&mkt=zh-cn [29] Huang Q H, Yang F B, Liu L Z, Li X L. Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis. Information Sciences, 2015, 314: 293-310 doi: 10.1016/j.ins.2014.08.021 [30] 陈雨羲, 刘奇, 黄韫栀, 张劲, 何凌, 邓丽华. 基于相位信息的乳腺超声图像水平集分割. 中国医学影像技术, 2015, 31(3): 463-466 http://www.cnki.com.cn/Article/CJFDTOTAL-ZYXX201503056.htmChen Yu-Xi, Liu Qi, Huang Yun-Zhi, Zhang Jing, He Ling, Deng Li-Hua. Level set segmentation based on phase information of the breast ultrasound image. Chinese Journal of Medical Imaging Technology, 2015, 31(3): 463-466 http://www.cnki.com.cn/Article/CJFDTOTAL-ZYXX201503056.htm [31] Xian M, Cheng H D, Zhang Y T. A fully automatic breast ultrasound image segmentation approach based on neutro-connectedness. In: Proceedings of the 22nd International Conference on Pattern Recognition (ICPR). Stockholm, Sweden: IEEE, 2014. 2495-2500 -
图(8) / 表(2)
计量
- 文章访问数: 1996
- HTML全文浏览量: 176
- PDF下载量: 812
- 被引次数: 0
