计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 260-265.doi: 10.11896/j.issn.1002-137X.2017.12.047

所属专题: 医学图像

• 图形图像与模式识别 • 上一篇    下一篇

基于小波图像融合算法和改进FCM聚类的MR脑部图像分割算法

耿艳萍,郭小英,王华夏,陈磊,李雪梅   

  1. 山西大学软件学院 太原030013,山西大学软件学院 太原030013,西北工业大学自动化学院 西安710072,北京交通大学计算机与信息技术学院 北京100044,山西大学软件学院 太原030013
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金青年基金项目(61603228),国家自然科学基金(61702315)资助

MR Brain Image Segmentation Method Based on Wavelet Transform Image Fusion Algorithm and Improved FCM Clustering

GENG Yan-ping, GUO Xiao-ying, WANG Hua-xia, CHEN Lei and LI Xue-mei   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对很多基于模糊C均值(FCM)的图像分割算法存在对噪声敏感和分割轮廓不清晰等问题,提出一种基于小波变换图像融合算法和FCM聚类算法的MR医学图像分割算法。在图像分割系统的第一阶段,利用Haar小波多分辨率特性保持像素间的空间信息;第二阶段,利用小波图像融合算法对得到的多分辨率图像和原始图像进行融合,进而增强被处理图像的清晰度并降低噪声;第三阶段,利用改进型FCM技术对所处理的图像进行分割。在BrainWeb数据集上进行实验,与现有相关算法相比,提出的算法具有较高的分割精度,且对噪声的鲁棒性比较强,处理时间也没有明显增加。

关键词: MR脑部图像分割,小波图像融合,模糊C均值聚类,鲁棒性

Abstract: Concerning the problems that many image segmentation algorithms based on fuzzy C mean (FCM) are sensitive to noise and contour segmentation is not clear,an improved algorithm based on wavelet image fusion and FCM clustering algorithm was proposed.And it is applied to MR medical image segmentation successfully.In the first stage of the image segmentation system,the Haar wavelet multi-resolution characteristics were used to maintain spatial information between pixels.In the second stage,wavelet image fusion algorithm was adopted to fuse the obtained multi-resolution image and original image,thus to enhance the clarity of processed images and to reduce noise.In the third stage,FCM technology was used for image segmentation.Experiments on BrainWeb datasets show that compared with the current algorithms,the proposed algorithm has higher segmentation accuracy and robustness to noise,and the processing time is not obviously increased.

Key words: MR brain image segmentation,Wavelet image fusion,Fuzzy C-means clustering,Robustness

[1] LIN X L,CHEN X H,XIAO L Y.Medical Image Segmentation Based on Region-based Hybrid Active Contour Model [J].Computer Science,2016,43(4):303-307.(in Chinese) 林喜兰,陈秀宏,肖林云.基于区域混合活动轮廓模型的医学图像分割[J].计算机科学,2016,43(4):303-307.
[2] ZHOU W G,SUN T,ZHU H.Image segmentation algorithm based on FCM optimized by adaptive spatial information[J].Application Research of Computers,2015,32(7):2205-2208.(in Chinese) 周文刚,孙挺,朱海.一种基于自适应空间信息改进FCM的图像分割算法[J].计算机应用研究,2015,32(7):2205-2208.
[3] CUI Z H,SUN S,CHEN S G,et al.Mean shift based FCM ima-ge segmentation algorithm[J].Control and Decision,2014,29(6):1130-1134.(in Chinese) 崔兆华,孙穗,陈思国,等.Mean shift模糊C均值聚类图像分割算法[J].控制与决策,2014,29(6):1130-1134.
[4] AGRAWAL S,PANDA R,DORA L.A study on fuzzy clustering for magnetic resonance brain image segmentation using soft computing approaches[J].Applied Soft Computing,2014,24(12):522-533.
[5] WANG W H,FENG Q J,LIU L,et al.Segmentation of Brain MR Images Through Class-adaptive Gauss-Markov Random Field Model and the EM Algorithm[J].Journal of Image and Graphics,2008,13(3):488-493.(in Chinese) 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.
[6] KHALIFA I,YOUSTSAF A,YOUSSRY H.MRI Brain Image Segmentation based on Wavelet and FCM Algorithm[J].International Journal of Computer Applications,2012,47(16):32-39.
[7] ZHANG F,FAN H.Research on medical image segmentationbased on fuzzy C-means clustering algorithm[J].Computer Engineering and Applications,2014,4(4):144-151.(in Chinese) 张翡,范虹.基于模糊C均值聚类的医学图像分割研究[J].计算机工程与应用,2014,4(4):144-151.
[8] PARVATHI K,RAO B S P,DAS M M,et al.Pyramidal Watershed Segmentation Algorithm for High-Resolution Remote SenTSAng Images UTSAng Discrete Wavelet Transforms[J].Discrete Dynamics in Nature & Society,2009,57(2):332-337.
[9] FRANCIS K J,PREMI M S G.Kernel weighted FCM based MR image segmentation for brain tumor detection[C]∥International Conference on Circuit,Power and Computing Technologies.IEEE,2015:1-6.
[10] JAVED A,CHAI W Y,THURAMAIYER N K,et al.Automated segmentation of brain MR images by combining contourlet transform and K-Means clustering techniques[J].Theor.Appl.Inf.Technol.,2013,54(2):82-91.
[11] CHEN G B,ZHANG G Q.Prediction method of actual traffic based on α-stable distribution and wavelet transform[J].Application Research of Computers,2014,31(8):2457-2460.(in Chinese) 陈国彬,张广泉.基于α-稳定分布和小波变换的实际流量预测算法[J].计算机应用研究,2014,31(8):2457-2460.
[12] BORA D J,GUPTA A K.Clustering Approach Towards Image Segmentation:An Analytical Study[J].Eprint Arxiv,2014,2(7):115-124.
[13] RAJIV S,ASHISH K.Multiscale medical image fuTSAon inwavelet domain.[J].Scientific World Journal,2013,17(5):1-10.
[14] YANG Y,HUANG S.Image Segmentation by Fuzzy C-Means Clustering Algorithm with a Novel Penalty Term[J].Computing & Informatics,2007,26(1):17-31.
[15] COCOSCO C A,KOLLOKIAN V,KWAN K S,et al.Brain-Web:Online Interface to a 3D MRI Simulated Brain Database [J].Neuroimage,1997,5(3):425-429.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!