基于像素聚类的超声图像分割

doi:10.11772/j.issn.1001-9081.2017.02.0569

计算机应用 ›› 2017, Vol. 37 ›› Issue (2): 569-573.DOI: 10.11772/j.issn.1001-9081.2017.02.0569

• 计算机视觉与虚拟现实 • 上一篇下一篇

基于像素聚类的超声图像分割

黄志标^1,2, 姚宇¹

1. 中国科学院成都计算机应用研究所, 成都 610041;
2. 中国科学院大学计算机与控制学院, 北京 100049

收稿日期:2016-08-18 修回日期:2016-09-12 出版日期:2017-02-10 发布日期:2017-02-11
通讯作者: 黄志标,huangzb007@gmail.com
作者简介:黄志标(1992-),男,湖南衡阳人,硕士研究生,CCF会员,主要研究方向:图像处理、图像检索;姚宇(1980-),男,四川宜宾人,副研究员,博士,主要研究方向:图形图像处理、模式识别。
基金资助:
中科院西部之光人才培养计划项目-四川省科技支撑计划项目（2012SZ0133）。

Ultrasound image segmentation based on pixel clustering

HUANG Zhibiao^1,2, YAO Yu¹

1. Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu Sichuan 610041, China;
2. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2016-08-18 Revised:2016-09-12 Online:2017-02-10 Published:2017-02-11
Supported by:
This work is supported by the Chinese Academy of Sciences "Light of the West China" Program and the Science and Technology Support Program of Sichuan Province (2012SZ0133).

摘要/Abstract

摘要： B型心脏超声图像分割是计算心功能参数前重要的一步。针对超声图像的低分辨率影响分割精度及基于模型的分割算法需要大样本训练集的问题，结合B型心脏超声图像的先验知识，提出了一种基于像素聚类进行图像分割的算法。首先，通过各向异性扩散处理图像；然后，使用一维K-均值对像素进行聚类；最后，根据聚类结果和先验知识将像素值修改为最佳类中心像素值。理论分析表明该算法可以使图像的峰值信噪比（PSNR）达到最大值。实验结果表明：所提算法比大津算法等更准确，PSNR较大津算法提高11.5%；即使在单张图像上也可以进行分割，且适应于分割任意形状的超声图像，有利于更准确地计算各种心功能参数。

关键词: 图像分割, 超声图像, K-均值, 各向异性扩散, 峰值信噪比

Abstract: B-mode cardiac ultrasound image segmentation is a fundamental step before cardiac functional parameters estimation. Aiming at the problem that the accuracy of segmentation is low because of the low resolution of ultrasound image, and the model based image segmentation algorithms need a large number of training sets, an image segmentation algorithm based on pixel clustering was proposed combined with prior knowledge of B-mode cardiac ultrasound images. Firstly, anisotropic diffusion was used to preprocess the image. Secondly, one-dimensional K-means was used to cluster the pixels. Finally, every pixel value of the image was assigned to the pixel value of its best cluster center according to cluster results and prior knowledge. The theoretical analysis shows that the proposed algorithm can get the maximum Peak Signal-to-Noise Ratio (PSNR) of ultrasound image; the experimental results show that the proposed algorithm performs better than Otsu algorithm, and its PSNR is increased by 11.5% compared with Otsu algorithm. The proposed algorithm can still work even for a single ultrasound image and can be suitble for ultrasound image segmentation of any shapes, so it is conducive to estimate cardiac functional parameters more accurately.

Key words: image segmentation, ultrasound image, K-means, anisotropic diffusion, Peak Signal-to-Noise Ratio (PSNR)

中图分类号:

黄志标, 姚宇. 基于像素聚类的超声图像分割[J]. 计算机应用, 2017, 37(2): 569-573.

HUANG Zhibiao, YAO Yu. Ultrasound image segmentation based on pixel clustering[J]. Journal of Computer Applications, 2017, 37(2): 569-573.

参考文献

[1] 中华医学会麻醉学分会.围手术期经食管超声心动图监测操作的专家共识[EB/OL].(2015-02-11)[2016-05-27]. http://www.csaol.cn/a/xuehuigongzuo/linchuangzhinan/2015/0907/2555.html. (Anesthesiology Branch of Chinese Medical Association. The expert consensus on the operation of the perioperative period of esophageal echocardiography[EB/OL]. (2015-02-11)[2016-05-27]. http://www.csaol.cn/a/xuehuigongzuo/linchuangzhinan/2015/0907/2555.html.).
[2] CARNEIRO G, NASCIMENTO J C, FREITAS A. The segmentation of the left ventricle of the heart from ultrasound data using deep learning architectures and derivative-based search methods[J]. IEEE Transactions on Image Processing, 2012, 21(3):968-982.
[3] MARSOUSI M, ALIREZAIE J, AHMADIAN A, et al. Segmenting echocardiography images using B-spline snake and active ellipse model[C]//Proceedings of the 2010 IEEE Annual International Conference on Engineering in Medicine and Biology Society. Piscataway, NJ:IEEE, 2010:3125-3128.
[4] MAZAHERI S, SULAIMAN P S B, WIRZA R, et al. Echocardiography image segmentation:a survey[C]//Proceedings of the 2013 International Conference on Advanced Computer Science Applications and Technologies. Piscataway, NJ:IEEE, 2013:327-332.
[5] 兰红,闵乐泉.多阈值优化交互式分割算法及其在医学图像中的应用[J].计算机应用,2013,33(5):1435-1438.(LAN H, MIN L Q. Interactive segmentation algorithm optimized by multi-threshold with application in medical images[J]. Journal of Computer Applications, 2013, 33(5):1435-1438.).
[6] 杨明川,吕学斌,周群彪.不完全K-means聚类与分类优化结合的图像分割算法[J].计算机应用,2012,32(1):248-251.(YANG M C, LYU X B, ZHOU Q B. Image segmentation algorithm based on incomplete K-means clustering and category optimization[J]. Journal of Computer Applications, 2012, 32(1):248-251.).
[7] TATIRAJU S, MEHTA A. Image segmentation using k-means clustering, EM and normalized cuts[EB/OL].[2016-05-20].http://www.ics.uci.edu/~dramanan/teaching/ics273a_winter08/projects/avim_report.pdf.
[8] PATEL B C, SINHA G R. An adaptive k-means clustering algorithm for breast image segmentation[J]. International Journal of Computer Applications, 2010, 10(4):35-38.
[9] 祖克举,周昌雄,张尤赛.基于各向异性扩散活动轮廓模型的左心室MRI分割[J].计算机测量与控制,2007,15(3):339-341.(ZU K J, ZHOU C X, ZHANG Y S. Left ventricle MRI segmentation based on anisotropic diffusion snake model[J]. Computer Measurement & Control, 2007, 15(3):339-341.).
[10] 曾文权,何拥军,崔晓坤.基于各向异性滤波和空间FCM的MRI图像分割方法[J].计算机应用研究,2014,31(1):316-320.(ZENG W Q, HE Y J, CUI X K. MRI image segmentation method based on anisotropic diffusion and spatial FCM[J]. Application Research of Computers, 2014, 31(1):316-320.).
[11] PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7):629-639.
[12] WANG H, SONG M. Ckmeans.1d.dp:optimal k-means clustering in one dimension by dynamic programming[J]. The R Journal, 2011, 3(2):29-33.
[13] BUADES A, COLL B, MOREL J M. A review of image denoising algorithms, with a new one[J]. Multiscale Modeling & Simulation, 2005, 4(2):490-530.
[14] TSIOTSIOS C, PETROU M. On the choice of the parameters for anisotropic diffusion in image processing[J]. Pattern Recognition, 2013, 46(5):1369-1381.
[15] PETROU M, PETROU C. Image processing:the fundamentals[M]. 2nd ed. Hoboken, NJ:John Wiley and Sons, 2010:549-550.

基于像素聚类的超声图像分割

Ultrasound image segmentation based on pixel clustering

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	石雪松, 李宪华, 孙青, 宋韬. 基于人工蜂群与模糊C均值的自适应小波变换的噪声图像分割[J]. 计算机应用, 2021, 41(8): 2312-2317.
[2]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[3]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[4]	黄梨, 卢龙. 基于长距离依赖编码与深度残差U-Net的缺血性卒中病灶分割[J]. 计算机应用, 2021, 41(6): 1820-1827.
[5]	罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183.
[6]	董阳, 潘海为, 崔倩娜, 边晓菲, 滕腾, 王邦菊. 面向多模态磁共振脑瘤图像的小样本分割方法[J]. 计算机应用, 2021, 41(4): 1049-1054.
[7]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[8]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[9]	原泉, 王艳, 李玉先. 距离保持水平集演化模型的快速实现算法[J]. 计算机应用, 2020, 40(9): 2743-2747.
[10]	高海军, 曾祥银, 潘大志, 郑伯川. 基于U-Net改进模型的直肠肿瘤分割方法[J]. 计算机应用, 2020, 40(8): 2392-2397.
[11]	吴崇数, 林霖, 薛蕴菁, 时鹏. 基于自监督学习的病理图像层次分割[J]. 计算机应用, 2020, 40(6): 1856-1862.
[12]	张一飞, 李新福, 田学东. 基于图像分割的立体匹配算法[J]. 计算机应用, 2020, 40(5): 1415-1420.
[13]	曾招鑫, 刘俊. 基于深度学习的秀丽隐杆线虫显微图像分割方法[J]. 计算机应用, 2020, 40(5): 1453-1459.
[14]	魏小娜, 邢嘉祺, 王振宇, 王颖珊, 石洁, 赵地, 汪红志. 基于改进U-Net的关节滑膜磁共振图像的分割[J]. 计算机应用, 2020, 40(11): 3340-3345.
[15]	冯涛, 陈斌, 张跃飞. 基于改进的Mask R-CNN的染色体图像分割框架[J]. 计算机应用, 2020, 40(11): 3332-3339.