基于纹理相似栈的超声图像分割方法

doi:10.19678/j.issn.1000-3428.0049272

计算机工程 ›› 2019, Vol. 45 ›› Issue (2): 240-244. doi: 10.19678/j.issn.1000-3428.0049272

基于纹理相似栈的超声图像分割方法

谢行雨,王玲

西南石油大学计算机科学学院,成都 610500

收稿日期:2017-11-13 出版日期:2019-02-15 发布日期:2019-02-15
作者简介:谢行雨(1988—),男,硕士研究生,主研方向为图像处理;王玲,教授。
基金资助:
国家自然科学基金(41674141)。

Ultrasonic Image Segmentation Method Based on Similar Texture Stacks

XIE Xingyu,WANG Ling

School of Computer Science,Southwest Petroleum University,Chengdu 610500,China

Received:2017-11-13 Online:2019-02-15 Published:2019-02-15

摘要/Abstract

摘要：

超声图像高噪声、低对比度的特点使其含噪图像的纹理信息较难提取。为此,提出一种基于自适应相似栈的聚类分割方法。对超声图像进行自适应去噪获得估计图像,结合超声图像和估计图像建立基于非局部搜索的相似栈列,应用相似栈列对超声图像纹理特征值进行修正,并使用K-means聚类将超声图像划分为互不重叠的区域。实验结果表明,该方法分割结果与人工分割结果的重合度达到93.28%,在差异较大的样本下重合度标准差为2.07%,从而验证其可对超声图像实现稳定有效的分割。

关键词: 图像分割, 纹理特征, 超声图像, 小波变换, 特征提取, 特征聚类

Abstract:

The properties of high noise and low contrast in ultrasound images make the noisy texture information difficult to extract.To solve this problem,this paper proposes a new clustering segmentation method based on adaptive similar stacks.The estimated image is formed by adaptive denoising of the ultrasonic image.The original image and the estimated image are used to build the similar stacks based on nonlocal search.Then,the similar stacks are utilized to correct the texture feature vectors of the ultrasound image.The K-means clustering is used to divide the ultrasound images into non-overlapping regions.Experimental results show that the coincidence degree between the results of manual segmentation and the results of this algorithm is 93.28%,and the standard deviation of that is 2.07% under the scenario of large samples,which prove that the proposed method can efficiently and steadily segment the ultrasonic image.

Key words: image segmentation, texture feature, ultrasonic image, wavelet transform, feature extraction, feature clustering

中图分类号:

TP751.1

谢行雨,王玲. 基于纹理相似栈的超声图像分割方法[J]. 计算机工程, 2019, 45(2): 240-244.

XIE Xingyu,WANG Ling. Ultrasonic Image Segmentation Method Based on Similar Texture Stacks[J]. Computer Engineering, 2019, 45(2): 240-244.

http://www.ecice06.com/CN/Y2019/V45/I2/240

参考文献

［1］VALSECCHI A,DAMAS S,SANTAMARIA J.Evolutionary Intensity-based medical image registration:a review［J］.Current Medical Imaging Reviews,2013,9(4):283-297.
［2］WANG Peng,ECABERT O,OSTERMEIER M,et al.Image-based co-registration of angiography and intravascular ultrasound images［J］.IEEE Transactions on Medical Imaging,2013,32(12):2238-2249.
［3］PLUIM J P,MAINTZ J B,VIERGEVER M A.Mutualinformation-based registration of medical images:a survey［J］.IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
［4］SZABO T L.Diagnostic ultrasound imaging:inside out［M］.Pittsburgh,USA:Academic Press,2004.
［5］NOBLE J A,BOUKERROUI D.Ultrasound image segmentation:a survey［J］.IEEE Transactions on Medical Imaging,2006,25(8):987-1010.
［6］PEREYRA M.Segmentation of skin lesions in 2-D and 3-D ultrasound images using a spatially coherent generalized Rayleigh mixture model［J］.IEEE Transactions on Medical Imaging,2012,31(8):1509-1520.
［7］NIMA T,AYATOLLAHI A.An efficient neural network based method for medical image segmentation［J］.Computers in Biology and Medicine,2014,44(1):76-87.
［8］GUPTA D.A hybrid segmentation method based on Gaussian kernel fuzzy clustering and region based active contour model for ultrasound medical images［J］.Biomedical Signal Processing and Control,2015,16(1):98-112.
［9］盛蕴霞,霍冠英,刘静.基于超像素聚类的侧扫声呐图像分割算法［J］.计算机工程,2018,44(6):219-225,232.
［10］谢行雨,王玲.基于散斑纹理评估的超声分割方法［J］.通信技术,2017,50(5):917-922.
［11］KYRIACOU E.Wavelet image extension for analysis and classification of infracted myocardial tissue［J］.IEEE Transactions on Biomedical Engineering,1997,44(9):856-866.
［12］CHEN D R.Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks［J］.Ultrasound in Medicine and Biology,2002,28(10):1301-1310.
［13］LI S,SHAWE-TAYLOR J.Comparison and fusion of multiresolution features for texture classification［J］.Pattern Recognition Letters,2005,26(5):633-638.
［14］HUANG K,AVIYENTE S.Information-theoretic wavelet packet subband selection for texture classification［J］.Signal Processing,2006,86(7):1410-1420.
［15］STOITSIS J.Texture characterization of carotid atherosclerotic plaque from B-mode ultrasound using Gabor filters［C］//Proceedings of 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Washington D.C.,USA:IEEE Press,2009:3-6.
［16］TSIAPARASN N.Comparison of multiresolution features for texture classification of carotid atherosclerosis from B-mode ultrasound［J］.IEEE Transactions on Information Technology in Biomedicine,2010,26(1):633-638.
［17］CHRISTODOULOU C I.AM-FM representations for the characterization of carotid plaque ultrasound images［C］//Proceedings of the 4th European Conference of the International Federation for Medical and Biological Engineering.Berlin,Germany:Springer,2009:546-549.
［18］刘怡光,吴鹏飞,曹丽萍,等.一种新的前列腺超声图像分割技术:CN104504720B［P］.［2017-10-24］.
［19］WAGNER R F.Statistics of speckle in ultrasound B-scans［J］.IEEE Transactions on Sonics and Ultrasonics,1983,30(3):156-163.
［20］DABOV K.Image denoising by sparse 3D transform-domain collaborative filtering［J］.IEEE Transactions on Image Processing,2007,16(8):2080-2095.

[1]	马娜, 温廷新, 贾旭, 李晓会. 复杂光照条件下自适应的车脸重识别模型[J]. 计算机工程, 2023, 49(8): 275-282, 290.
[2]	戴浩磊, 黄永慧, 周郭许. 基于超图正则化非负张量链分解的聚类分析[J]. 计算机工程, 2023, 49(6): 81-89.
[3]	宋羽凯, 谢江. 基于多任务学习的轻量级语音情感识别模型[J]. 计算机工程, 2023, 49(5): 122-128.
[4]	许凤, 杨兴耀, 于炯, 李梓杨, 李晨瑜, 张君. 小波卷积增强的对比学习推荐算法[J]. 计算机工程, 2023, 49(5): 105-111,121.
[5]	关日鹏, 况立群, 焦世超, 熊风光, 韩燮. 多模态特征融合与词嵌入驱动的三维检索方法[J]. 计算机工程, 2023, 49(4): 101-107,113.
[6]	李培育, 张雅丽. 基于改进SRGAN模型的人脸图像超分辨率重建[J]. 计算机工程, 2023, 49(4): 199-205.
[7]	耿磊, 傅洪亮, 陶华伟, 卢远, 郭歆莹, 赵力. 基于动态卷积递归神经网络的语音情感识别[J]. 计算机工程, 2023, 49(4): 125-130,137.
[8]	孙欣悦, 李庆忠. 基于小波变换的水下显著性目标快速检测算法[J]. 计算机工程, 2023, 49(4): 249-255.
[9]	何悦, 陈广胜, 景维鹏, 徐泽堃. 基于深度多相似性哈希方法的遥感图像检索[J]. 计算机工程, 2023, 49(2): 206-212.
[10]	范润泽, 刘宇红, 张荣芬, 李景玉. 基于多尺度注意力机制的道路场景语义分割模型[J]. 计算机工程, 2023, 49(2): 288-295.
[11]	高庆吉, 李天昊, 邢志伟, 刘佩佩. 基于区块特征融合的点云语义分割方法[J]. 计算机工程, 2022, 48(9): 37-44,54.
[12]	闫静, 张雪英, 李凤莲, 陈桂军, 黄丽霞. 结合栈式监督AE与可变加权ELM的回归预测模型[J]. 计算机工程, 2022, 48(8): 62-69,76.
[13]	林志洁, 郑秋岚, 梁涌, 邢卫. 基于内卷U-Net的医学图像分割模型[J]. 计算机工程, 2022, 48(8): 180-186.
[14]	乔彩彩, 吴成茂, 李昌兴, 王佳烨. 结合隶属度与像素交替引导滤波的鲁棒模糊聚类算法[J]. 计算机工程, 2022, 48(8): 224-233.
[15]	李柯泉, 陈燕, 刘佳晨, 牟向伟. 基于深度学习的目标检测算法综述[J]. 计算机工程, 2022, 48(7): 1-12.

选择文件类型/文献管理软件名称

选择包含的内容

基于纹理相似栈的超声图像分割方法

Ultrasonic Image Segmentation Method Based on Similar Texture Stacks

PDF

可视化

被引次数

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

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于纹理相似栈的超声图像分割方法

Ultrasonic Image Segmentation Method Based on Similar Texture Stacks

PDF

可视化

被引次数

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

本文评价