《计算机应用研究》|Application Research of Computers

基于改进粗糙集概率模型的鲁棒医学图像分割算法

Improved probability model of rough set based robust medical image segmentation algorithm

免费全文下载 (已被下载 次)  
获取PDF全文
作者 吴方,何尾莲
机构 福建医科大学 基础医学院,福州 350108
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2546-05
DOI 10.3969/j.issn.1001-3695.2017.08.069
摘要 基于参数化模型的图像分割算法对复杂的医学图像分割精度较低,提出一种基于改进粗糙集概率模型的鲁棒医学图像分割算法。首先,将粗糙集的上下逼近与概率边界区引入最大期望算法中,表征每个类簇;然后,将图像的灰度分布建模为一个有限数量的混合粗糙集概率分布;最终,通过马尔可夫随机场引入图像的空间信息,提高图像分割算法的鲁棒性。基于合成脑部MR(核磁共振)图像库与真实脑部MR图像库的分割实验结果显示,本算法的分割精度与鲁棒性均优于其他参数化模型的分割算法及其他专门的脑部MR图像分割算法。
关键词 粗糙集;参数化模型;医学图像分割;最大期望算法;马尔可夫随机场;鲁棒性
基金项目 福建省自然科学基金资助项目(2016J01373)
福建省卫生厅青年科研计划资助项目(2013-1-34)
本文URL http://www.arocmag.com/article/01-2017-08-069.html
英文标题 Improved probability model of rough set based robust medical image segmentation algorithm
作者英文名 Wu Fang, He Weilian
机构英文名 CollegeofBasicMedicalSciences,FujianMedicalUniversity,Fuzhou350108,China
英文摘要 Parametric model based image segmentation algorithms show low segmentation accuracy to complex medical images. This paper proposed an improved probability model of rough set based robust medical image segmentation algorithm to solve that problem. Firstly, it introduced lower approximation and probabilistic boundary region of rough set to expectation maximization algorithm to represent each cluster.Then it modeled intensity distribution of image as a mixed rough set probability distribution with finite number. Lastly, it incorporated the spatial information of image into Markov random field to enhance the robustness of the image segmentation algorithm. Both synthetic brain MR image database and real MR image database based segmentation experimental results show that the proposed algorithm has better performance in segmentation accuracy and robustness than other parametric model based image segmentation algorithms and other brain MR image segmentation algorithms.
英文关键词 rough set; parametric model; medical image segmentation; expectation maximization algorithm; Markov random field; robustness
参考文献 查看稿件参考文献
  [1] 江贵平, 秦文健, 周寿军, 等. 医学图像分割及其发展现状[J] . 计算机学报, 2015, 38(6):1222-1242.
[2] 温锐, 陈宏文, 张雷, 等. 基于引导滤波的多图谱医学图像分割[J] . 南方医科大学学报, 2015(9):1263-1267.
[3] 李小伟, 伍岳庆, 姚宇. 基于小波多尺度聚类水平集的医学图像分割[J] . 计算机应用, 2014, 34(S2):298-301, 316.
[4] 唐文静, 许兆新, 张小峰. 峰值检测 FCM 算法的医学图像分割[J] . 智能系统学报, 2014, 9(5):584-589.
[5] 唐文静, 邹海林, 张彩明, 等. 基于边界的分层马尔可夫模型的医学图像分割[J] . 系统仿真学报, 2014, 26(8):1747-1751.
[6] Li Yibao, Kim J. Multiphase image segmentation using a phase-field model[J] . Computers & Mathematics with Applications, 2014, 62(2):737-745.
[7] 陈峥, 石勇鹏, 吉书鹏. 一种改进的Otsu图像阈值分割算法[J] . 激光与红外, 2012, 42(5):584-588.
[8] 申铉京, 潘红, 陈海鹏. 基于一维Otsu的多阈值医学图像分割算法[J] . 吉林大学学报:理学版, 2016, 54(2):344-348.
[9] Saadatmand-Tarzjan M. Self-affine snake for medical image segmentation[J] . Pattern Recognition Letters, 2015, 59:1-10.
[10] Zhu Shiping, Gao Ruidong. A novel generalized gradient vector flow snake model using minimal surface and component-normalized method for medical image segmentation[J] . Biomedical Signal Processing & Control, 2016, 26:1-10.
[11] Kang M, Kim J M. Fuzzy C-means clustering with spatially weighted information for medical image segmentation[C] //Proc of IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing. 2014:1-8.
[12] 丛培盛, 张洪江, 朱仲良, 等. 用遗传算法C-均值聚类分割医学彩色图像[J] . 同济大学学报:自然科学版, 2003, 31(7):874-877.
[13] 王国胤, 姚一豫, 于洪. 粗糙集理论与应用研究综述[J] . 计算机学报, 2009, 32(7):1229-1246.
[14] 王文辉, 冯前进, 刘磊, 等. 基于类自适应高斯—马尔可夫随机场模型和EM算法的MR图像分割[J] . 中国图象图形学报, 2008, 13(3):488-493.
[15] Pawlak Z. Rough sets:theoretical aspects of reasoning about data[M] . [S. l. ] :Kluwer Academic Publishers, 2010.
[16] 胡庆辉, 丁立新, 陆玉靖, 等. 一种快速、鲁棒的有限高斯混合模型聚类算法[J] . 计算机科学, 2013, 40(8):191-195.
[17] 赵雪梅, 李玉, 赵泉华. 结合高斯回归模型和隐马尔可夫随机场的模糊聚类图像分割[J] . 电子与信息学报, 2014, 36(11):2730-2736.
[18] Besag J. On the statistical-analysis of dirty pictures[J] . Journal of the Royal Statistical Society, 2010, B-48(5-6):259-302.
[19] Pradipta M, Pal S K. Rough-fuzzy clustering for grouping functionally similar genes from microarray data[J] . IEEE/ACM Trans on Computational Biology & Bioinformatics, 2013, 10(2):286-299.
[20] Nguyen T M, Wu Q M J. Fast and robust spatially constrained Gaussian mixture model for image segmentation[J] . IEEE Trans on Circuits & Systems for Video Technology, 2013, 23(4):621-635.
[21] Gong Maoguo, Liang Yan, Shi Jiao, et al. Fuzzy C-means clustering with local information and kernel metric for image segmentation[J] . IEEE Trans on Image Processing, 2012, 22(2):573-584.
[22] Portela N M, Cavalcanti G D C, Ren T I. Semi-supervised clustering for MR brain image segmentation[J] . Expert Systems with Applications, 2014, 41(4):1492-1497.
[23] Ladgham A, Hamdaoui F, Sakly A, et al. Fast MR brain image segmentation based on modified shuffled frog leaping algorithm[J] . Signal Image & Video Processing, 2013, 9(5):1113-1120.
[24] Vincent R. BrainWeb:simulated brain database[EB/OL] . 2010. http://mouldy. bic. mni. mcgill. ca/brainweb.
[25] Jiang Shaofeng, Zhang Weirui, Yu Wang, et al. Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model[J] . Biomedical Engineering Online, 2012, 12(1):1-18.
[26] Banerjee A, Maji P. Rough sets for bias field correction in MR images using contra harmonic mean and quantitative index[J] . IEEE Trans on Medical Imaging, 2013, 32(11):2144-2155.
收稿日期 2016/5/27
修回日期 2016/7/4
页码 2546-2550,2556
中图分类号 TP391.41
文献标志码 A