Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA

WANG Xing-ce; WEN Lei; WU Zhong-ke; ZHOU Ming-quan; TIAN Yun; LIU Xin-yu

doi:10.3788/OPE.20142202.0497

您当前的位置：

首页 >

文章列表页 >

Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA

Information Sciences | 更新时间：2020-08-13

- Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA
- Optics and Precision Engineering Vol. 22, Issue 2, Pages: 497-507(2014)
- 作者机构：
  
  1. 北京师范大学信息科学与技术学院北京,100875
  2. 中国科学院计算技术研究所前瞻研究实验室北京,100190
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142202.0497
  CLC： TP391
- Received：14 June 2013，
  
  Published：20 February 2014
- 稿件说明：
移动端阅览
王醒策,文蕾,武仲科等. 面向时飞磁共振血管造影术的脑血管统计分割混合模型[J]. 光学精密工程, 2014,22(2): 497-507

WANG Xing-ce, WEN Lei, WU Zhong-ke etc. Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 497-507
王醒策,文蕾,武仲科等. 面向时飞磁共振血管造影术的脑血管统计分割混合模型[J]. 光学精密工程, 2014,22(2): 497-507 DOI： 10.3788/OPE.20142202.0497.

WANG Xing-ce, WEN Lei, WU Zhong-ke etc. Finite mixture model of stochastic cerebrovascular segmentation based on TOF MRA[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 497-507 DOI： 10.3788/OPE.20142202.0497.

摘要

由于人体脑血管结构复杂

空间比例小

三维分割和重构十分困难

本文面向时飞磁共振血管造影(TOF MRA)数据提出了一种新的瑞利高斯有限混合模型来实现脑血管的自动提取和分割。首先

对已有的混合模型进行了分析;然后

采用最大强度投影法(MIP)预处理脑部数据后采用高斯分布拟合血管类

采用瑞利分布和高斯分布拟合非血管类。提出的模型构造简单

参数向量较少;在血管与非血管的混合区域

模型与灰度直方图具有较好的拟合性。模型在传统期望最大化(EM)算法中加入随机扰动项构造随机期望最大化(SEM)算法来实现混合模型的参数估计

降低了算法对初值的依赖

同时提高了鲁棒性。实验证明

与已有双高斯模型相比

血管点数增加了27%

可细分到三级血管且细节的连通性更好。本模型可更准确地拟合数据的灰度分布曲线

有效地分割脑血管主分支及周围较细小分支

泛化性较好并可应用于相似系统中。

Abstract

As the brain vessel of human has complex topological structure and smaller space proportion

it is hard to be segmented and reconstructed in three dimensions. Therefore

this paper proposes an automatic statistical intensity based approach for extracting the 3D cerebrovascular system from time-of-flight (TOF) Magnetic Resonance Angiography (MRA) data. First

the Finite Mixture Model (FMM) is analyzed

and it is used to fit the intensity histogram of the brain image sequence preprocessed by the Maximum Intensity Projection(MIP). Then

the Gaussian distribution is used to fit the vessel

and the Gaussian distribution and Rayleigh distribution are used to fit other low intensity tissues. Since the model is easy to realize and has a short parameter vector

it decreases the parameter drift problem and can fit the intensity histogram well

especially in the cross region between the cerebrovascular and other tissues. Moreover

the stochastic disturbance is added in the traditional Expectation Maximization(EM) to construct Stochastic Estimation Maximization (SEM) algorithm to estimate the parameter vector

by which the method shows low initial value dependence and a high robust. As compared with the experiments

this model can segment more 27% cerebrovascular voxels than two Gaussian models do and it can segment in three level for the small cerebrovascular branches with a better connectivity. The model can fit a gray distribition curve of the data accurately

segment the main branch of brain vessel and slight vessel branch and can be used in other similar systems.

关键词

Keywords

references

心脑血管疾病.百度百科[OL].[2013-03-20]http://baike.baidu.com/view/783095.htm.

Cardiovascular and cerebrovascular diseases, Baidu Encyclopedia[OL].[2013-03-20]. http://baike.baidu.com/view/783095.htm.(in chinese)

LESAGE D, ANGELINI E D, BLOCH I, et al.. A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes[J]. Medical Image Analysis, 2009, 13(6): 819-845.

KIRBAS C, QUEK F. A review of vessel extraction techniques and algorithms[J]. ACM Computing Surveys (CSUR), 2004, 36(2): 81-121.

田沄, 周明全, 武仲科. 心脑血管三维分割研究进展[J]. 计算机辅助设计与图形学学报, 2012, 24(7): 839-851.

TIAN Y,ZHOU M Q, WU ZH K. On 3D cardia-cerebrovascular segmentation [J]. Journal of Computer-Aided Design & Computer Graphics,2012,24(7):1-13.(in chinese)

IBANEZ L, SCHROEDER W, NG L, et al.. The ITK software guide[J]. NLM Insight Toolkit Publications,http://www.itk.org/.

HARTIGAN J A. Clustering Algorithms[M]. John Wiley & Sons, Inc., 1975.

DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm [J]. Journal of the Royal Statistical Society:Series B (Methodological), 1977,39(1):1-38.

RUAN S, JAGGI C, XUE J, et al.. Brain tissue classification of magnetic resonance images using partial volume modeling[J]. IEEE Transactions on Medical Imaging, 2000, 19(12): 1179-1187.

PRASTAWA M, GILMORE J H, LIN W, et al.. Automatic segmentation of MR images of the developing newborn brain [J]. Medical Image Analysis, 2005, 9(5): 457-466.

ADELINOR,SILVA F D. A Dirichlet process mixture model for brain MRI tissue classification [J]. Medical Image Analysis, 2007, 11(2): 169-182.

徐丰, 王醒策, 周明全, 等. SEM 混合模型脑血管分割算法[J]. 计算机辅助设计与图形学学报, 2010,22(11):1905-1911.

XU F,WANG X C,ZHOU M Q, et al.. Segmentation algorithm of brain vessel image based on SEM statistical mixture model[J]. Journal of Computer-Aided Design & Computer Graphics, 2010,22(11):1905-1911.(in chinese)

TIAN Y, DUAN F, ZHOU M, et al.. Active contour model combining region and edge information [J]. Machine Vision and Applications, 2013, 24(1): 47-61.

DIAS J G, WEDEL M. An empirical comparison of EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods [J]. Statistics and Computing, 2004, 14(4): 323-332..

GAO X, UCHIYAMA Y, ZHOU X, et al.. A fast and fully automatic method for cerebrovascular segmentation on time-of-flight (TOF) MRA image [J]. Journal of Digital Imaging, 2011, 24(4): 609-625.

CHAPMAN B E, STAPELTON J O, PARKER D L. Intracranial vessel segmentation from time-of-flight MRA using pre-processing of the MIP Z-buffer: accuracy of the ZBS algorithm [J]. Medical Image Analysis, 2004, 8(2): 113-126..

ADEL M, MOUSSAOUI A, RASIGNI M, et al.. Statistical-based tracking technique for linear structures detection: Application to vessel segmentation in medical images[J]. Signal Processing Letters, IEEE, 2010, 17(6): 555-558.

HUDA S, YEARWOOD J, TOGNERI R. A stochastic version of expectation maximization algorithm for better estimation of hidden Markov model [J]. Pattern Recognition Letters, 2009, 30(14): 1301-1309.

LINGURARU M G, PURA J A, PAMULAPATI V, et al.. Statistical 4D graphs for multi-organ abdominal segmentation from multiphase CT[J]. Medical Image Analysis, 2012, 16(4): 904-914.

ROY S, CARASS A, BAZIN P L, et al.. Consistent segmentation using a Rician classifier [J]. Medical Image Analysis, 2012, 16(2): 524-535.

WILSON D L, NOBLE J A. An adaptive segmentation algorithm for time-of-flight MRA data [J]. IEEE Transactions on Medical Imaging, 1999, 18(10): 938-945.

HASSOUNA M S, FARAG A A, HUSHEK S, et al.. Statistical-based approach for extracting 3D blood vessels from tof-myra data [C].Medical Image Computing and Computer-Assisted Intervention-MICCAI 2003,Springer Berlin Heidelberg, 2003: 680-687.

HASSOUNA M S, FARAG A A, HUSHEK S, et al.. Cerebrovascular segmentation from TOF using stochastic models [J]. Medical Image Analysis, 2006, 10(1): 2-18.

HAO J, LI M. A supervised bayesian method for cerebrovascular segmentation [J]. WSEAS Trans. Signal Process, 2007, 3(12): 487-495.

WU Z K, SEAH H S, ZHOU M Q. Skeleton based parametric solid models: Ball B-Spline curves [C].2007 10th IEEE International Conference on Computer-Aided Design and Computer Graphics, 2007:421-424.

Views

356

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰