用于脑部核磁共振图像分割的具有抗噪能力的BCFCM算法

摘要/Abstract

摘要： 脑部核磁共振成像(MRI)是脑疾病临床诊断的重要手段,而脑组织的准确分割则是其中一个重要的环节。然而MRI图像中普遍存在的噪声和偏移场给脑组织的准确分割造成了很大的困难。在MRI图像分割算法中,偏移场矫正模糊C-均值算法(BCFCM)在模糊C-均值聚类算法(FCM)的基础上增加了对偏移场的估计和空间信息的使用,可以很好地消除图像偏移场对分割造成的影响。但是BCFCM算法由于没有考虑到噪声对偏移场估计的影响,因此对高噪声图像的分割效果欠佳。针对MRI脑组织分割,在图像预处理过程中提出一种快速的分割方法来去除颅骨及其附属物。此外,提出基于BCFCM的改进算法,该改进算法在迭代过程中可以通过对噪声强度的估计来自适应地改变目标函数窗口的大小。同时,该算法引入高斯核函数对偏移场进行平滑处理,并通过阈值限制偏移场的估计值,以有效地避免偏移场的错误估计对分割结果的影响。实验结果表明,改进后的算法不仅可以有效准确地分割脑组织,而且具有较强的抗噪声和处理偏移场的能力。

关键词: 磁共振成像,偏移场矫正模糊C-均值聚类,噪声估计,自适应,偏移场限制

Abstract: Magnetic resonance imaging (MRI) of brain is an important tool for the clinical diagnosis of brain diseases.The accurate segmentation for brain tissues is one of the important parts.However,it is difficult to acquire the accurate segmentation results because of the noise and intensity inhomogeneities in MRI.Among the MRI segmentation me-thods,Bias-Corrected FCM (BCFCM) algorithm based on Fuzzy C-Means (FCM) algorithm utilizes the spatial information and estimation of intensity inhomogeneities which can deal with the problem caused by intensity inhomogeneities.Because the BCFCM algorithm fails to consider the high level noise when estimating intensity inhomogeneities,the segmentation results are not accurate enough.For the MRI of brain tissue segmentation,this paper proposed a fast segmentation method to remove the brain skull and its appendages during the image preprocessing.In addition,we proposed an improved algorithm based on the BCFCM algorithm.The improved BCFCM algorithm can automatically change the size of window in the objective function by estimating the noise level in the iterative processing.Besides,the Gaussian kernel in the object function was utilized to smooth the intensity inhomogeneities,and the estimation value of intensity inhomogeneities was limited by using an experimental threshold which can effectively avoid the incorrect estimation of intensity inhomogeneities in the segmentation results.The experimental results show that the proposed algorithm can not only effectively and accurately segment the brain tissues,but also deal with high level noise and intensity inhomogeneities.

Key words: Magnetic resonance imaging,Bias-corrected FCM,Noise estimation,Adaptive,Bias-limited

栾方军,周佳鹏,曾子铭. 用于脑部核磁共振图像分割的具有抗噪能力的BCFCM算法[J]. 计算机科学, 2015, 42(10): 311-315. https://doi.org/

LUAN Fang-jun, ZHOU Jia-peng and ZENG Zi-ming.  Anti-noise BCFCM Algorithm for Brain MRI Segmentation[J]. Computer Science, 2015, 42(10): 311-315. https://doi.org/

参考文献

[1] 廖亮,林土胜.基于核聚类算法和模糊Markov随机场模型的脑部MR图像的分割[J].中国图象图形学报,2009,14(9):1732-1738 Liao Liang,Lin Tu-sheng.A kernelized fuzzy C-means clustering using fuzzy markov random field model for brain MR image segmentation[J].Journal of Image and Graphics,2009,14(9):1732-1738
[2] 蒋世忠,易法令,汤浪平,等.基于图割的MRI脑部图像肿瘤提取方法[J].计算机工程,2010,36(7):217-219 Jiang Shi-zhong,Yi Fa-ling,Tang Lang-ping,et al.Tumor extraction method of MRI cerebral image based on graph CUTS[J].Computer Engineering,2010,36(7):217-219
[3] Ahmed M N,Yamany S M,Mohamed N,et al.A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data[J].IEEE Transactions on Medical Imaging,2002,21(6):193-199
[4] Ségonne F,Dale A M,Busa E,et al.A hybrid approach to the skull stripping problem in MRI[J].Neuroimage,2004,22(6):1060-1075
[5] Xu C,Pham D L,Prince J L.Image segmentation using defor-mable models[M]∥Handbook of Medical Imaging Vol 2 Medical Image Processing and Analysis,2000(4):175-272
[6] Kass M,Withkinm A,Terzopoulos D.Snakes:Active contourmodels[J].International Journal of Computer Vision,1998,1(4):321-331
[7] Osher S,Sethian J A.Fronts propagating with curvature-de-pendent speed:algorithms based on Hamilton-Jacobi formulations[J].Journal of Computational Physics,1988,79(1):12-49
[8] Fedkiw R,Osher S.Level set methods and dynamic implicit surfaces[M].Springer,2003
[9] Cabezas M,Oliver A,Lladó X,et al.A review of atlas-based segmentation for magnetic resonance brain images[J].Computer Methods and Programs in Biomedicine,2011,104(6):158-177
[10] Li S Z.Markov random field models in computer vision[M]∥Computer Vision—ECCV’94.Springer Berlin Heidelberg,1994:361-370
[11] Zeng Z,Han C,Wang L,et al.Unsupervised Brain Tissue Segmentation by Using Bias Correction Fuzzy C-Means and Class-Adaptive Hidden Markov Random Field Modelling [M]∥Frontier and Future Development of Information Technology in Medi-cine and Education.Springer Netherlands,2014:579-587
[12] Balafar M A,Ramli A R,Iqbal S M,et al.Medical image segmentation using fuzzy C-mean(FCM) and dominant grey levels of image[C]∥5th International Conference on Visual Information Engineering,2008(VIE 2008).IET,2008:314-317
[13] 郭鹏飞,刘万军,林琳,等.结合随机游走与FCM的脑图像分割方法[J].计算机科学,2014,1(7):322-324Guo Peng-fei,Liu Wan-jun,Lin Lin,et al.Brain Image Segmenta-tion Method Based on FCM and Random Walk[J].Computer Science,2014,1(7):322-324
[14] Wells III W M,Grimson W E L,Kikinis R,et al.Adaptive segmentation of MRI data[J].IEEE Transactions on Medical Imaging,1996,15(6):429-442
[15] 纪则轩.基于模糊聚类的脑磁共振图像分割技术研究[D].南京:南京理工大学,2012 Ji Ze-xuan.Research on brain Mr image segmentation with fuzzy clustering based model[D].Nanjing:Nanjing University of Scien-ce and Technology,2012
[16] Vovk U,Pernus F,Likar B.A review of methods for correction of intensity inhomogeneity in MRI[J].IEEE Transactions on Medical Imaging,2007,26(3):405-421
[17] Wang Q.HMRF-EM-image:implementation of the hiddenmarkov random field model and its expectation-maximization algorithm[J/OL].http://arxiv.org/abs/1207.3510

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed