全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于图划分的形状统计主动轮廓模型心脏MR图像分割*

, PP. 275-281

Keywords: 主动轮廓模型,形状统计,心脏核磁共振(MR)图像分割,图划分,图论

Full-Text   Cite this paper   Add to My Lib

Abstract:

为有效分析心脏功能,高精度分割左、右心室是必要的.心脏MR图像中存在图像灰度不均,左、右心室及周围其它组织灰度接近,存在弱边缘、边缘断裂及噪声造成边缘模糊等现象,给精确分割左、右心室轮廓带来困难.本文在基于图划分的主动轮廓方法基础上,通过对训练形状进行配准及变化模式分析,定义左、右心室轮廓形状变化允许空间,提出基于图划分的形状统计主动轮廓模型来分割心脏MR图像.该方法通过图划分理论将图像分割问题转化为最优化问题,所以能够得到全局最优解,具有较大的捕捉范围.还引入形状统计来引导曲线的演化,有效处理曲线演化时存在的边缘泄漏问题,提高分割精度.实验结果表明,本文方法较以往方法具有更高的分割精度和更好的稳定性,为临床应用提供一种较可行的方法.

References

[1]  Paragios N. A Variational Approach for the Segmentation of the Left Ventricle in MR Cardiac Image Analysis. International Journal of Computer Vision, 2002, 50(3): 345-362
[2]  Chen Qiang, Zhou Zeming, Tang Min, et al. Shape Statistics Variational Approach for the Outer Contour Segmentation of Left Ventricle MR Images. IEEE Trans on Information Technology in Biomedicine, 2006, 10(3): 588-597
[3]  Cremers D, Tischhuser F, et al. Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional. International Journal of Computer Vision, 2002, 50(3): 295-313
[4]  Mitchell S C, Lelieveldt B P F, van der Geest R J, et al. Multistage Hybrid Active Appearance Model Matching: Segmentation of Left and Right Ventricles in Cardiac MR Images. IEEE Trans on Medical Imaging, 2001, 20(5): 415-423
[5]  Xu Ning, Bansal R, Ahuja N. Object Segmentation Using Graph Cuts Based Active Contours // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA, 2003, Ⅱ: 46-53
[6]  Cootes T F, Taylor C J, Cooper D, et al. Active Shape Models—Their Training and Application. Computer Vision Image Understanding, 1995, 61(1): 38-59
[7]  Ford L, Fulkerson D. Flow in Networks. Princeton, USA: Princeton University Press, 1962
[8]  Boykov Y, Kolmogorov V. An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137
[9]  Xu Chenyang, Prince J L. Snakes, Shapes, and Gradient Vector Flow. IEEE Trans on Image Processing, 1998: 7(3): 359-369
[10]  Mikic I, Krucinski S, Thomas J D. Segmentation and Tracking in Echocardiographic Sequences: Active Contours Guided by Optical Flow Estimates. IEEE Trans on Medical Imaging, 1998, 17(2): 274- 283
[11]  de Bruijne M, Nielsen M. Shape Particle Filtering for Image Segmentation // Proc of the 7th International Conference on Medical Image Computing and Intervention. Rennes, France, 2004: 168-175
[12]  Lelieveldt B P F, zümcü M, van der Geest R J, et al. Multi-View Active Appearance Models for Consistent Segmentation of Multiple Standard Views: Application to Long- and Short-Axis Cardiac MR Images // Proc of the 17th International Congress and Exhibition on Computer Assisted Radiology and Survey. London, UK, 2003: 1141-1146
[13]  Stegmann M B, Fisker R, Ersbll B K. Extending and Applying Active Appearance Models for Automated, High Precision Segmentation in Different Image Modalities // Proc of the 12th Scandinavian Conference on Image Analysis. Bergen, Norway, 2001: 90-97

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133