Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images

被引:117
作者
Adhikari, Sudip Kumar [1 ]
Sing, Jamuna Kanta [2 ]
Basu, Dipak Kumar [2 ]
Nasipuri, Mita [2 ]
机构
[1] Neotia Inst Technol Management & Sci, Dept Comp Sci & Engn, Parganas, India
[2] Jadavpur Univ, Dept Comp Sci & Engn, Kolkata 700032, India
关键词
Image segmentation; MRI brain image; Fuzzy C-means; Conditional spatial FCM; INFORMATION; FCM;
D O I
10.1016/j.asoc.2015.05.038
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The fuzzy C-means (FCM) algorithm has got significant importance due to its unsupervised form of learning and more tolerant to variations and noise as compared to other methods in medical image segmentation. In this paper, we propose a conditional spatial fuzzy C-means (csFCM) clustering algorithm to improve the robustness of the conventional FCM algorithm. This is achieved through the incorporation of conditioning effects imposed by an auxiliary (conditional) variable corresponding to each pixel, which describes a level of involvement of the pixel in the constructed clusters, and spatial information into the membership functions. The problem of sensitivity to noise and intensity inhomogeneity in magnetic resonance imaging (MRI) data is effectively reduced by incorporating local and global spatial information into a weighted membership function. The experimental results on four volumes of simulated and one volume of real-patient MRI brain images, each one having 51 images, show that the csFCM algorithm has superior performance in terms of qualitative and quantitative studies such as, cluster validity functions, segmentation accuracy, tissue segmentation accuracy and receiver operating characteristic (ROC) curve on the image segmentation results than the k-means, FCM and some other recently proposed FCM-based algorithms. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:758 / 769
页数:12
相关论文
共 33 条
[1]  
Adhikari S.K., 2012, P INT C COMM DEV INT, P133
[2]   A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data [J].
Ahmed, MN ;
Yamany, SM ;
Mohamed, N ;
Farag, AA ;
Moriarty, T .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2002, 21 (03) :193-199
[3]  
[Anonymous], Pattern Recognition with Fuzzy Objective Function Algorithms,, DOI 10.1007/978-1-4757-0450-1_3
[4]   Review of brain MRI image segmentation methods [J].
Balafar, M. A. ;
Ramli, A. R. ;
Saripan, M. I. ;
Mashohor, S. .
ARTIFICIAL INTELLIGENCE REVIEW, 2010, 33 (03) :261-274
[5]   Improved spatial fuzzy c-means clustering for image segmentation using PSO initialization, Mahalanobis distance and post-segmentation correction [J].
Benaichouche, A. N. ;
Oulhadj, H. ;
Siarry, P. .
DIGITAL SIGNAL PROCESSING, 2013, 23 (05) :1390-1400
[6]  
Bezdek J. C., 1973, Journal of Cybernetics, V3, P58, DOI 10.1080/01969727308546047
[7]  
Bezdek J. C, 1975, PROC 8 INT C NUMER, P143
[8]   Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation [J].
Cai, Weiling ;
Chen, Songean ;
Zhang, Daoqiang .
PATTERN RECOGNITION, 2007, 40 (03) :825-838
[9]   Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure [J].
Chen, SC ;
Zhang, DQ .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (04) :1907-1916
[10]   Fuzzy c-means clustering with spatial information for image segmentation [J].
Chuang, KS ;
Tzeng, HL ;
Chen, S ;
Wu, J ;
Chen, TJ .
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2006, 30 (01) :9-15