基于改进动态规划的MR图像左心室分割

广西师范大学学报（自然科学版） ›› 2014, Vol. 32 ›› Issue (2): 35-41.

基于改进动态规划的MR图像左心室分割

徐胜舟¹, 许向阳², 胡怀飞³, 李波¹

1 中南民族大学计算机科学学院, 湖北武汉430074;
2 华中科技大学计算机科学与技术学院, 湖北武汉430074;
3 中南民族大学生物医学工程学院, 湖北武汉430074

收稿日期:2013-12-23 出版日期:2014-06-25 发布日期:2018-09-25
通讯作者: 胡怀飞(1975—),男,湖北武汉人,中南民族大学讲师,博士。E-mail:whkaociya@gmail.com
基金资助:
国家自然科学基金资助项目(61302192);湖北省自然科学基金资助项目(2012FFC13401);中央高校专项基金资助项目(CZQ13010)。

Left Ventricle MRI Segmentation Based on Developed Dynamic Programming

XU Sheng-zhou¹, XU Xiang-yang², HU Huai-fei³, LI Bo¹

1. College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China;
2.College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China;
3. College of Biomedical Engineering, South-Central University for Nationalities, Wuhan 430074, China;

Received:2013-12-23 Online:2014-06-25 Published:2018-09-25

摘要/Abstract

摘要： 为了在MR图像中精确提取左心室外膜,本文提出一种基于改进动态规划的分割方法。先用Otsu阈值法分割心内膜,再在此基础上设计一种改进的动态规划方法来寻找一条闭合的最小代价路径作为心外膜边界。该方法的关键在于路径代价函数的设计,它包括边界灰度因子、梯度因子和形状因子。3个因子之间的权重系数用混沌粒子群算法优化,同时,为了避免心外膜越过心包脂肪,设置了代价无穷大的心外膜“禁区”。将该方法在138幅图像上的分割结果与金标准及相关算法进行比较,结果表明该方法具有更高的分割精度和鲁棒性。

关键词: 左心室, 分割, 动态规划, 混沌粒子群

Abstract: In order to accurately extract the epicardium of the left ventricle from cardiac magnetic resonance images, a method based on developed dynamic programming is proposed. First, the endocardium is segmented by the Otsu method. Then, the epicardium is derived by designing an improved dynamic programming method to find a closed path with minimum local cost. The key to this method is the design of the local cost function, which consists of three factors: boundary gradation, boundary gradient and shape features. The weighting coefficients of the three factors are obtained by a chaos particle swarm optimization method. A comparison with other segmentation methods and the gold standard is provided based on 138 images. The experimental results show that the method proposed has high accuracy and robustness.

Key words: left ventricle, segmentation, dynamic programming, chaos particle swarm optimization

中图分类号:

TP391

徐胜舟, 许向阳, 胡怀飞, 李波. 基于改进动态规划的MR图像左心室分割[J]. 广西师范大学学报（自然科学版）, 2014, 32(2): 35-41.

XU Sheng-zhou, XU Xiang-yang, HU Huai-fei, LI Bo. Left Ventricle MRI Segmentation Based on Developed Dynamic Programming[J]. Journal of Guangxi Normal University(Natural Science Edition), 2014, 32(2): 35-41.

参考文献

[1] NAMBAKHSH C M S, YUAN Jing, PUNITHAKUMAR K, et al. Left ventricle segmentation in MRI via convex relaxed distribution matching[J]. Medical Image Analysis, 2013, 17(8):1010-1024.
[2] PETITJEAN C, DACHER J N. A review of segmentation methods in short axis cardiac MR images[J]. Medical Image Analysis, 2011, 15(2):169-184.
[3] HADHOUD M M A, ELADAWY M I, FARAG A, et al. Left ventricle segmentation in cardiac MRI images[J]. American Journal of Biomedical Engineering, 2012, 2(3):131-135.
[4] 张建伟,方林,陈允杰,等. 基于活动轮廓模型的左心室MR图像分割[J]. 电子学报, 2011, 39(11): 2670-2673.
[5] 王根, 张建伟, 陈允杰,等. 一种各向异性GVF模型的心脏左心室MR图像分割模型[J]. 计算机辅助设计与图形学学报, 2010, 22(11): 1887-1891.
[6] SCHWEIGER M, DORN O, ZACHAROPOULOS A,et al. 3D level set reconstruction of model and experimental data in diffuse optical tomography[J].Optics Express.2010,18(1):150-164.
[7] 刘利雄, 马忠梅, 赵恒博, 等. 一种基于主动轮廓模型的心脏核磁共振图像分割方法[J]. 计算机学报, 2012, 35(1):146-153.
[8] 王元全, 贾云得. 一种心脏核磁共振图像左室壁内、外膜分割方法[J]. 软件学报, 2009, 20(5): 1176-1184.
[9] MA Zhen, JORGE R N M, TAVARES J M R S. A shape guided C-V model to segment the levator ani muscle in axial magnetic resonance images[J].Medical Engineering & Physics, 2010,32(7):766-774.
[10] SONG En-min, XU Sheng-zhou, XU Xiang-yang, et al. Hybrid segmentation of mass in mammograms using template matching and dynamic programming[J]. Academic Radiology, 2010, 17(11): 1414-1424.
[11] HU Huai-fei, LIU Hai-hua, GAO Zhi-yong, et al. Hybrid segmentation of left ventricle in cardiac MRI using gaussian-mixture model and region restricted dynamic programming[J]. Magnetic Resonance Imaging, 2013, 31(4):575-584.
[12] PEDNEKAR A, KURKURE U, MUTHUPILLAI R, et al. Automated left ventricular segmentation in cardiac MRI[J]. IEEE Transactions on Biomedical Engineering, 2006, 53(7):1425-1428.
[13] KURKURE U, PEDNEKAR A, MUTHUPILLAI R, et al. Localization and segmentation of left ventricle in cardiac Cine-MR images[J]. IEEE Transactions on Biomedical Engineering, 2009, 56(5):1360-1370.
[14] LU Ying-li, RADAU P, CONNELLY K, et al.Segmentation of left ventricle in cardiac cine MRI: an automatic image-driven method[M]// Functional Imaging and Modeling of the Heart: Lecture Notes in Computer Science Volume 5528. Berlin: Springer-Verlag, 2009:339-347.
[15] KENNEDY J, EBERHART R C. Particle swarm optimization[C]// Proceedings of IEEE International Conference on Neural Networks. Piscataway, NJ: IEEE Press, 1995: 1942-1948.
[16] WANG Y, LIU J H. Chaotic particle swarm optimization for assembly sequence planning[J]. Robotics and Computer-Integrated Manufacturing, 2010, 26 (2): 212-222.
[17] DOMINGUEZ A R, NANDI A K. Improved dynamic-programming-based algorithms for segmentation of masses in mammograms[J]. Medical Physics, 2007, 34 (11): 4256-4269.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed