基于多尺度模糊聚类与DGVF模型分割颈动脉超声造影图像

doi:10.3969/j.issn.1007-2861.2014.01.016

上海大学学报(自然科学版) ›› 2014, Vol. 20 ›› Issue (5): 633-644.doi: 10.3969/j.issn.1007-2861.2014.01.016

基于多尺度模糊聚类与DGVF模型分割颈动脉超声造影图像

张麒1, 黄春春1, 韩红2, 李超伦2, 王文平2

1. 上海大学通信与信息工程学院, 上海 200444; 2. 复旦大学附属中山医院超声诊断科, 上海 200032

收稿日期:2013-11-22 出版日期:2014-10-30 发布日期:2014-10-30
通讯作者: 张麒(1983—), 男, 博士, 研究方向为医学图像处理. E-mail:zhangq@shu.edu.cn
基金资助:
上海市自然科学基金青年资助项目(12ZR1444100); 上海市教委人才计划“晨光计划”资助项目(11CG45); 上海市教委科研创新基金资助项目(12YZ026)

CEUS Image Segmentation of Carotid Arteries Using Multi-scale Fuzzy Clustering and DGVF Model

ZHANG Qi1, HUANG Chun-chun1, HAN Hong2, LI Chao-lun2, WANG Wen-ping2

1. School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China; 2. Department of Ultrasound, Zhongshan Hospital, Fudan University, Shanghai 200032, China

Received:2013-11-22 Online:2014-10-30 Published:2014-10-30

摘要/Abstract

摘要： 超声造影(contrast-enhanced ultrasound, CEUS) 图像在血管疾病诊断与治疗中有很高的应用价值, 其中通过提取颈动脉CEUS 图像中的血管边界对血管形态及弹性等属性进行测量具有重要意义. 由医生手工勾勒血管轮廓耗时耗力, 且重复性差、主观性强, 而传统计算机分割方法因受到图像中斑点噪声的干扰而存在鲁棒性差和初始化难两大问题. 首先, 结合多尺度模糊聚类方法与粒子群优化算法提取血管的粗略轮廓, 以此作为方向梯度矢量流(directional gradient vector flow, DGVF) 模型的初始轮廓; 然后, 对轮廓进行形变收敛至最终结果. 通过分割来自14例患者的48张颈动脉CEUS 图像的实验, 结果表明所提出的方法优于传统方法, 能自动、精确地提取颈动脉CEUS 图像中的血管边界.

关键词: 超声造影, 多尺度分析, 方向梯度矢量流模型, 模糊C均值聚类, 血管轮廓

Abstract: Contrast-enhanced ultrasound (CEUS) is of great value for the diagnosis and treatment of vascular diseases. Extraction of carotid arterial contours is important for the measurement of morphological and elastic properties of arteries. Since manually tracing of arterial contours is time-consuming, subjective, and unrepeatable, computer-aided methods are required. However, speckle noise in the CEUS images causes poor robustness and difficult initialization in traditional computer-aided image segmentation methods. This paper integrates multi-scale fuzzy C-means clustering with particle swarm optimization to extract coarse boundaries of carotid arteries. Then boundaries are used as initial contours of the directional gradient vector flow (DGVF) model, and deform them until convergence to get final refined contours. Experimental results on 48 CEUS images from 14 patients show that the proposed method is superior to the traditional method, and can automatically and accurately extract boundaries of carotid arteries in CEUS images.

Key words: contrast-enhanced ultrasound (CEUS), directional gradient vector flow (DGVF) model, fuzzy C-means (FCM) clustering, multi-scale analysis, vascular contours

中图分类号:

TP 391.4

张麒1, 黄春春1, 韩红2, 李超伦2, 王文平2. 基于多尺度模糊聚类与DGVF模型分割颈动脉超声造影图像[J]. 上海大学学报(自然科学版), 2014, 20(5): 633-644.

ZHANG Qi1, HUANG Chun-chun1, HAN Hong2, LI Chao-lun2, WANG Wen-ping2. CEUS Image Segmentation of Carotid Arteries Using Multi-scale Fuzzy Clustering and DGVF Model[J]. Journal of Shanghai University（Natural Science Edition）, 2014, 20(5): 633-644.

参考文献

[1] 主海文, 刘友军, 曾衍钧. 血管图像分割技术的研究进展[J]. 北京生物医学工程, 2005, 24(2): 155-159.

[2] 邢锦, 何文. 超声造影在颈动脉粥样硬化斑块诊断中的应用[J]. 临床超声医学杂志, 2010, 12(2): 111-116.

[3] 钱华明, 姜波, 钱明, 等. 结合时域信息区域生长算法及其在动脉超声造影图像分割中的应用[J]. 计算机辅助设计与图形学学报, 2011, 23(3): 442-447.

[4] Molinari F, Liboni W, Pavanelli E, et al. Accurate and automatic carotid plaque characterization in contrast enhanced 2D ultrasound images [C]//IEEE EMBS. 2007: 335-338.

[5] Hoogi A, Adam D, Hoffman A, et al. Carotid plaque vulnerability quantification of neovascularization on contrast enhanced ultrasound with histopathologic correlation [J]. American

Journal of Roentgenology, 2011, 196(2): 431-436.

[6] Tauber C, Batatia H, Morin G, et al. Robust B-spline snakes for ultrasound image segmentation [J]. Computers in Cardiology, 2004, 31(1): 325-328.

[7] Tang J, Acton S T. Vessel boundary tracking for intravital microscopy via multiscale gradient vector flow snakes [J]. IEEE Transactions on Biomedical Engineering, 2004, 51(2): 316-324.

[8] Tauber C, Batatia H, Ayache A. Quasi-automatic initialization for parametric active contours [J]. Pattern Recognition Letters, 2010, 31(1): 83-93.

[9] Wang H S, Fei B W. A modified fuzzy C-means classification method using multiscale diffusion filtering scheme [J]. Medical Image Analysis, 2009, 13(2): 193-202.
[10] Yang X F, Fei B W. A MR brain classification method based on multi-scale and multi-block fuzzy C-means [C]//5th International Conference on Bioinformatics and Biomedical Engineering. 2011: 1-4.

[11] Yu J Y, Acton S T. Speckle reducing anisotropic diffusion [J]. IEEE Transactions on Image Processing, 2002, 11(11): 1260-1270.

[12] YuJ H,WangYY. Two dimensional fuzzy clustering for ultrasound image segmentation [C]//1st International Conference on Bioinformatics and Biomedical Engineering. 2007: 599-603.

[13] Chen S C, Zhang D Q. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure [J]. IEEE Transactions on Systems, Man, and Cybernetics, 2004, 34(4): 1907-1916.

[14] Zhang Y, Huang D, Ji M, et al. Image segmentation using PSO and PCM with Mahalanobis distance [J]. Expert Systems with Applications, 2011, 38(7): 9036-9040.

[15] 周驰, 高海兵, 高亮, 等. 粒子群优化算法[J]. 计算机应用研究, 2003, 20(12): 7-11.

[16] Tang J. A multi-direction GVF snake for the segmentation of skin cancer images [J]. Pattern Recognition, 2009, 42(6): 1172-1179.

[17] Sadri A R, Zekri M. Segmentation of dermoscopy images using wavelet networks [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(4): 1134-1141.

基于多尺度模糊聚类与DGVF模型分割颈动脉超声造影图像

CEUS Image Segmentation of Carotid Arteries Using Multi-scale Fuzzy Clustering and DGVF Model

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 2

编辑推荐

Metrics

本文评价

[1]	李婧, 于丽英. 基于直觉模糊集的模糊C均值聚类改进算法[J]. 上海大学学报(自然科学版), 2018, 24(4): 634-641.
[2]	杨青1, 徐凯宇1,2, 冯江涛1,2. 两种立方体构型的微泡超声造影剂的温度场[J]. 上海大学学报(自然科学版), 2016, 22(5): 616-623.