Collaborative rough-fuzzy clustering: An application to intensity non-uniformity correction in brain MR images

Automatic segmentation of Magnetic Resonance Images (MRI) for tissue classification becomes more challenging when the image is corrupted with noise and intensity non-uniformity (INU). Several fuzzy clustering based statistical retrospective methods exist for simultaneous correction and segmentation of images but most of them fail to be robust in presence of noise, outliers and INU artifacts. In this paper, a hybridization of rough c-means and spatial fuzzy c-means clustering is presented whose objective function has been modified to accommodate INU field as well. While the membership function of fuzzy sets enables efficient handling of overlapping partitions, the concept of lower and upper approximations of rough sets deals with uncertainty, vagueness, and incompleteness in class definition. The experiments conducted on brain MR images show promising results in terms of segmentation accuracy and class separability. The usefulness of proposed algorithm is also investigated on high field MR images. The proposed algorithm Rough-Theoretic Bias-Corrected Fuzzy C-Means Algorithm (R-BCFCM) has significant performance improvement over other similar methods from rough-fuzzy family and can be employed for MRI corrupted with high intensity non-uniformity and noise.

[1]  D. Dubois,et al.  ROUGH FUZZY SETS AND FUZZY ROUGH SETS , 1990 .

[2]  Jerry L. Prince,et al.  Adaptive fuzzy segmentation of magnetic resonance images , 1999, IEEE Transactions on Medical Imaging.

[3]  Z. Pawlak Rough Sets: Theoretical Aspects of Reasoning about Data , 1991 .

[4]  M. Bhattacharya,et al.  A fast and noise-adaptive rough-fuzzy hybrid algorithm for medical image segmentation , 2010, 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[5]  Koenraad Van Leemput,et al.  Automated model-based bias field correction of MR images of the brain , 1999, IEEE Transactions on Medical Imaging.

[6]  Sushmita Mitra,et al.  Application of Rough Sets in Pattern Recognition , 2007, Trans. Rough Sets.

[7]  Sankar K. Pal,et al.  Maximum Class Separability for Rough-Fuzzy C-Means Based Brain MR Image Segmentation , 2008, Trans. Rough Sets.

[8]  Witold Pedrycz,et al.  Rough–Fuzzy Collaborative Clustering , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Sankar K. Pal,et al.  Rough-Fuzzy Pattern Recognition: Applications in Bioinformatics and Medical Imaging , 2012 .

[10]  Pawan Lingras,et al.  Interval Set Clustering of Web Users with Rough K-Means , 2004, Journal of Intelligent Information Systems.

[11]  Aly A. Farag,et al.  A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data , 2002, IEEE Transactions on Medical Imaging.

[12]  Bostjan Likar,et al.  A Review of Methods for Correction of Intensity Inhomogeneity in MRI , 2007, IEEE Transactions on Medical Imaging.

[13]  Mohammed Yakoob Siyal,et al.  An intelligent modified fuzzy c-means based algorithm for bias estimation and segmentation of brain MRI , 2005, Pattern Recognit. Lett..

[14]  Arpit Srivastava,et al.  Hybrid softcomputing model for lesion identification and information combination: some case studies , 2012, Int. J. Data Min. Bioinform..

[15]  László Szilágyi,et al.  A Modified FCM Algorithm for Fast Segmentation of Brain MR Images , 2007, Analysis and Design of Intelligent Systems using Soft Computing Techniques.

[16]  M. Stella Atkins,et al.  Difficulties of T1 brain MRI segmentation techniques , 2002, SPIE Medical Imaging.