复小波域混合概率图模型的超声医学图像分割

夏平; 施宇; 雷帮军; 龚国强; 胡蓉; 师冬霞

doi:10.16383/j.aas.c180132

复小波域混合概率图模型的超声医学图像分割

doi: 10.16383/j.aas.c180132

夏平^{1, 2,},
施宇^{1, 2,},
雷帮军^{1, 2, ,},
龚国强^{1, 2,},
胡蓉^{1, 2,},
师冬霞^{1, 2,}

1.
三峡大学水电工程智能视觉监测湖北省重点实验室宜昌 443002
2.
三峡大学计算机与信息学院宜昌 443002

基金项目:

国家重点研发计划 2016YFB0800403

国家自然科学基金(联合基金)项目 U1401252

湖北省重点实验室开放基金项目 2018SDSJ07

详细信息

作者简介:
夏平  三峡大学计算机与信息学院教授.主要研究方向为计算机视觉, 智能信息处理, 概率图模型及其应用.E-mail: pxia@ctgu.edu.cn

施宇  三峡大学计算机与信息学院硕士研究生.主要研究方向为信号与信息处理, 医学图像的目标检测与分割.E-mail: rwxrfs@163.com

龚国强  三峡大学计算机与信息学院副教授.主要研究方向为无线通信, 数字信号处理. E-mail: gonggq_shh@163.com

胡蓉  三峡大学计算机与信息学院硕士研究生.主要研究方向为深度学习, 医学图像的目标检测和分割.E-mail: zhrrongfyqs@163.com

师冬霞  三峡大学计算机与信息学院硕士研究生.主要研究方向为信号与信息处理, 医学图像的目标检测与分割.E-mail: longbinyuankang@163.com

通讯作者:
雷帮军三峡大学计算机与信息学院教授, IEEE高级会员.主要研究方向为图像处理, 三维计算机视觉及智能视频处理.本文通信作者.E-mail: Bangjun.Lei@ieee.org

计量
- 文章访问数: 960
- HTML全文浏览量: 282
- PDF下载量: 230
- 被引次数: 0
出版历程
- 收稿日期: 2018-03-08
- 录用日期: 2018-10-26
- 刊出日期: 2021-01-29

Ultrasound Medical Image Segmentation Based on Hybrid Probabilistic Graphical Model in Complex-wavelet Domain

XIA Ping^{1, 2
,},
SHI Yu^{1, 2
,},
LEI Bang-Jun^{1, 2
, ,},
GONG Guo-Qiang^{1, 2
,},
HU Rong^{1, 2
,},
SHI Dong-Xia^{1, 2
,}

1.
Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering, Three Gorges University, Yichang 443002
2.
College of Computer and Information Technology, Three Gorges University, Yichang 443002

Funds:

National Key Research and Development Program of China 2016YFB0800403

National Natural Science Foundation of China (Joint Fund) Project U1401252

Hubei Provincial Key Laboratory Open Fund Project 2018SDSJ07

More Information

Author Bio:
XIA Ping   Professor at the School of Computer and Information, China Three Gorges University. His research interest covers computer vision, intelligent information processing, probabilistic graph model and its application

SHI Yu   Master student at the School of Computer and Information, China Three Gorges University. Her research interest covers signal and information processing, target detection and segmentation in medical images

GONG Guo-Qiang   Associate professor at the School of Computer and Information, Three Gorges University, His research interest covers wireless communication and digital signal processing

HU Rong   Master student at the School of Computer and Information, China Three Gorges University. Her research interest covers deep learning, target detection and segmentation of medical images

SHI Dong-Xia   Master student at the College of Computer and Information Technology, China Three Gorges University. Her research interest covers signal and information processing, target detection and segmentation in medical images

Corresponding author: LEI Bang-Jun Professor at the School of Computer and Information, China Three Gorges University, IEEE senior member. His research interest covers image processing, 3-D imaging and multi-dimensional intelligent computer vision. Corresponding author of this paper

摘要

摘要: 针对存在大量不规则斑点噪声、目标边缘弱化的超声医学图像分割中较难识别目标的问题, 提出了一种复小波域中混合概率图模型的超声医学图像分割算法.采用具有近似平移不变性和良好方向选择性的双树复小波变换(Dual tree-complex wavelet transform, DT-CWT)提取超声医学图像6个方向的高频特征信息; 其次, 为关联目标的弱特征信息并抑制统计独立的高频噪声, 构建了复小波域混合概率图模型; 尺度间"父—子"节点间标记采用贝叶斯网络进行建模, 尺度内邻域间标记采用马尔科夫随机场(Markov random field, MRF)无向图建模, 对复小波域中同尺度的特征系数采用高斯混合模型建模, 尺度内同标记的观测特征采用高斯模型建模; 最后, 用迭代条件模式(Iterated conditional mode, ICM)实现MRF中误分割率最小的能量函数最优解, 获取标记场, 实现超声医学图像分割.实验结果从视觉效果和定量分析两方面验证表明, 本文算法能有效地提取超声图像的弱目标信息, 较好地定位目标区域, 具有较高的分割精度和鲁棒性.
- 医学图像分割 /
- 复小波分析 /
- 混合概率图模型 /
- 马尔科夫随机场 /
- 迭代条件模式
Abstract: For ultrasound medical image with a lot of irregular speckle noise and the weakened object edge, it is difficult to identify the object in image segmentation. An ultrasound medical image segmentation algorithm based on hybrid probabilistic graphical model in complex-wavelet domain is proposed. First, dual tree-complex wavelet transform (DT-CWT) has approximate shift invariance and nice directional selectivity, so using DT-CWT to extract the high frequency characteristic information. Then, hybrid probabilistic graphical model in complex-wavelet domain is constructed, for associating the weak characteristic information of object and suppressing statistical independent of high-frequency noise. The labels of the father-child nodes in the inter-scale is modeled by Bayesian network. The mark within the intra-scale of the neighborhood is modeled by Markov random field (MRF) undirected graph model. The characteristic coefficients of the same scale in the complex-wavelet domain is modeled by Gaussian hybrid model. Using Gaussian model describes the observational characteristics with a same mark in the intra-scale. Finally, the optimal solution of the energy function with the smallest error segmentation rate in the MRF is obtained by using iterated conditional mode (ICM) to get the tag field, and complete the ultrasound medical image segmentation. From two aspects of visual effect and quantitative analysis, the proposed algorithm can extract the weak object information of ultrasound image effectively, which can better locate the target region, and has higher segmentation accuracy and robustness.
- Ultrasound medical image segmentation /
- complex wavelet analysis /
- hybrid probabilistic graphical model /
- Markov random field (MRF) /
- iterated conditional mode (ICM)
Recommended by Associate Editor ZHANG Dao-Qiang
注释:

1) 本文责任编委张道强

HTML全文

图 1 DT-CWT变换及其子带方向

Fig. 1 DT-CWT and the sub-band direction

下载: 全尺寸图片幻灯片

图 2 DT-CWT域系数向量结构

Fig. 2 Coefficient vector structure of DT-CWT domain

下载: 全尺寸图片幻灯片

图 3 DT-CWT域标记场贝叶斯网络模型

Fig. 3 Marking field Bayesian network model in DT-CWT domain

下载: 全尺寸图片幻灯片

图 4 DT-CWT域标记场的2阶邻域系统

Fig. 4 The second order neighborhood system in DT-CW

下载: 全尺寸图片幻灯片

图 5 医学图像的DT-CWT分解及其高频系统统计

Fig. 5 Medical image of DT-CWT and Statistical characteristics of the coefficient

下载: 全尺寸图片幻灯片

图 6 超声医学图像4种算法分割结果比较

Fig. 6 Comparison of segmentation results of four algorithms for ultrasonic medical images

下载: 全尺寸图片幻灯片

图 7 医学超声图像4种算法定量评价指标比较

Fig. 7 Comparison of quantitative evaluation indexes of four algorithms for medical ultrasound images

下载: 全尺寸图片幻灯片

参考文献(26)

[1]	Smistad E, Falch T L, Bozorgi M, et al. Medical image segmentation on GPUs —— a comprehensive review. Medical Image Analysis, 2015, 20(1): 1-18 doi: 10.1016/j.media.2014.10.012
[2]	Khadidos A, Sanchez V, Li C T. Weighted level set evolution based on local edge features for medical image segmentation. IEEE Transactions on Image Processing, 2017, 26(4): 1979-1991 doi: 10.1109/TIP.2017.2666042
[3]	Chittajallu D R, Paragios N, Kakadiaris I A. An explicit shape-constrained MRF-based contour evolution method for 2-D medical image segmentation. IEEE Journal of Biomedical and Health Informatics, 2014, 18(1): 120-129 doi: 10.1109/JBHI.2013.2257820
[4]	许新征, 丁世飞, 史忠植, 等.图像分割的新理论和新方法.电子学报, 2010, 38(2): 76-82 Xu Xin-Zheng, Ding Shi-Fei, Shi Zhong-Zhi, et al. New Theories and methods of image segmentation. Acta Electronica Sinica, 2010, 38(2): 76-82
[5]	Yuan Y, Chao M, Lo Y C. Automatic skin lesion segmentation using deep fully convolutional networks with Jaccard distance. IEEE Transactions on Medical Imaging, 2017, 36(9): 1876-1886 doi: 10.1109/TMI.2017.2695227
[6]	Namburu A, Samayamantula S K, Edara S R. Generalised rough intuitionistic fuzzy C-means for magnetic resonance brain image segmentation. IET Image Processing, 2017, 11(9): 777-785 doi: 10.1049/iet-ipr.2016.0891
[7]	Yang X, Gao X, Tao D, et al. An efficient MRF embedded level set method for image segmentation. IEEE Transactions on Image Processing, 2014, 24(1): 9-21
[8]	Zheng Y, Jeon B, Xu D, et al. Image segmentation by generalized hierarchical fuzzy C-means algorithm. Journal of Intelligent and Fuzzy Systems, 2015, 28(2): 961-973 doi: 10.3233/IFS-141378
[9]	Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2015: 234-241
[10]	AlZubi S, Islam N, Abbod M. Multiresolution analysis using wavelet, ridgelet, and curvelet transforms for medical image segmentation. Journal of Biomedical Imaging, 2011, 2011: 1-18
[11]	唐利明, 田学全, 黄大荣, 等.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 doi: 10.3724/SP.J.1004.2014.01233 Tang Li-Ming, Tian Xue-Quan, Huang Da-Rong, et al. Image segmentation model combined with fcms and variational level set. Acta Automatica Sinica, 2014, 40(6): 1233-1248 doi: 10.3724/SP.J.1004.2014.01233
[12]	Yang X, Gao X, Tao D, et al. An efficient MRF embedded level set method for image segmentation. IEEE Transaction on Image Processing, 2015, 24(1): 9-21 doi: 10.1109/TIP.2014.2372615
[13]	江贵平, 秦文健, 周寿军, 等.医学图像分割及其发展现状.计算机学报, 2015, 38(6): 1222-1242 Jiang Gui-Ping, Qin Wen-Jian, Zhou Shou-Jun, et al. State-of-the-art in medical image segmentation. Chinese Journal of Computers, 2015, 38(6): 1222-1242
[14]	Li B N, Chui C K, Chang S, et al. Integrating spatial fuzzy clustering with level set methods for automated medical image segmentation. Computers in Biology and Medicine, 2011, 41(1): 1-10 doi: 10.1016/j.compbiomed.2010.10.007
[15]	李宣平, 王雪.模糊聚类协作区域主动轮廓模型医学图像分割.仪器仪表学报, 2013, 34(4): 860-865 doi: 10.3969/j.issn.0254-3087.2013.04.022 Li Xuan-Ping, Wang Xue. Active contour model-based medical image segmentation method collaborative with fuzzy C-means. Chinese Journal of Scientific Instrument, 2013, 34(4): 860-865 doi: 10.3969/j.issn.0254-3087.2013.04.022
[16]	Liu G Y, Qin Q Q, Mei T C, et al. Supervised image segmentation based on tree-structured MRF model in wavelet domain. IEEE Geoscience and Remote Sensing Letters, 2009, 6(4): 850-854 doi: 10.1109/LGRS.2009.2026719
[17]	Selesnick I W, Baraniuk R G, Kingsbury N C. The dual-tree complex wavelet transform. IEEE Signal Processing Magazine, 2005, 22(6): 123-151 doi: 10.1109/MSP.2005.1550194
[18]	刘宇.基于水平集方法和模糊模型的医学图像分割算法研究[博士学位论文].吉林大学, 中国, 2016. Liu Yu. Medical image segmentation based on level set methods and fuzzy models[Ph. D. dissertation]. Jilin University, China, 2016.
[19]	Khare M, Srivastava R K, Khare A. Moving object segmentation in Daubechies complex wavelet domain. Signal, Image and Video Processing, 2015, 9(3): 635-650 doi: 10.1007/s11760-013-0496-4
[20]	夏平, 任强, 吴涛, 雷帮军.融合多尺度统计信息模糊C均值聚类与Markov随机场的小波域声纳图像分割.兵工学报, 2017, 38(5): 940-948 doi: 10.3969/j.issn.1000-1093.2017.05.014 Xia Ping, Ren Qiang, Wu Tao, Lei Bang-Jun. Sonar image segmentation fusion of multi-scale statistical information FCM clustering and MRF model in wavelet domain. Acta Armamentarii, 2017, 38(5): 940-948 doi: 10.3969/j.issn.1000-1093.2017.05.014
[21]	Geman S, Geman D. Stochastic relaxation, gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis And Machine Intelligence, 1984, PAMI-6(6): 721-741 doi: 10.1109/TPAMI.1984.4767596
[22]	Rahman S M M, Ahmad M O, Swamy M N S. Statistics of 2-D DT-CWT coefficients for a Gaussian distributed signal. IEEE Transactions on Circuits and Systems, 2008, 55(7): 2013-2025 doi: 10.1109/TCSI.2008.918198
[23]	Monteiro F C, Campilho A C. Performance evaluation of image segmentation. Computer Science, 2006, 4141: 248-259
[24]	Meila M. Comparing clusterings —— an information based distance. Journal of Multivariate Analysis, 2007, 98(5): 873-895 doi: 10.1016/j.jmva.2006.11.013
[25]	Martin D, Fowlkes C, Tal D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the International Conference on Computer Vision. British Columbia. Vancouver, Canada: IEEE, 2001: 416-423
[26]	Freixenet J, Munoz X, Raba D, et al. Yet another survey on image segmentation: region and boundary information integration. In: Proceedings of the European Conference on Computer Vision. Berlin/Heidelberg: Springer, 2002: 408-422

施引文献

资源附件(0)

访问统计

图(7)

计量

文章访问数: 960
HTML全文浏览量: 282
PDF下载量: 230
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

复小波域混合概率图模型的超声医学图像分割

doi: 10.16383/j.aas.c180132

通讯作者:
雷帮军三峡大学计算机与信息学院教授, IEEE高级会员.主要研究方向为图像处理, 三维计算机视觉及智能视频处理.本文通信作者.E-mail: Bangjun.Lei@ieee.org

计量

Ultrasound Medical Image Segmentation Based on Hybrid Probabilistic Graphical Model in Complex-wavelet Domain

Corresponding author: LEI Bang-Jun Professor at the School of Computer and Information, China Three Gorges University, IEEE senior member. His research interest covers image processing, 3-D imaging and multi-dimensional intelligent computer vision. Corresponding author of this paper

计量

目录

留言板

复小波域混合概率图模型的超声医学图像分割

doi: 10.16383/j.aas.c180132

通讯作者: 雷帮军 三峡大学计算机与信息学院教授, IEEE高级会员.主要研究方向为图像处理, 三维计算机视觉及智能视频处理.本文通信作者.E-mail: Bangjun.Lei@ieee.org

计量

出版历程

Ultrasound Medical Image Segmentation Based on Hybrid Probabilistic Graphical Model in Complex-wavelet Domain

Corresponding author: LEI Bang-Jun Professor at the School of Computer and Information, China Three Gorges University, IEEE senior member. His research interest covers image processing, 3-D imaging and multi-dimensional intelligent computer vision. Corresponding author of this paper

计量

出版历程

目录

通讯作者:
雷帮军三峡大学计算机与信息学院教授, IEEE高级会员.主要研究方向为图像处理, 三维计算机视觉及智能视频处理.本文通信作者.E-mail: Bangjun.Lei@ieee.org