ABSTRACT
This paper proposes an Enhanced Kernelized Conditional Spatial Fuzzy C Means (EKCSFCM) clustering algorithm targeted at segmentation of Brain Magnetic Resonance (MR) image data. The approach amalgamates kernel mapping with a spatially relevant fuzzy clustering paradigm for image segmentation. A technique for rank-based consideration of spatial information is introduced and is used along with spatial tuning parameters for controlling neighborhood effects during data point clustering. The kernelized approach and the spatial parameters handle intensity inhomogeneities and strengthen the performance of the algorithm by improving resiliency against noise and other aberrations. For analyzing the robustness of the approach, four volumes of brain MR data, each comprising 71 images are used. These images are also corrupted with noise and inhomogeneities for evaluating the efficiency of different approaches in noisy image segmentation. The experimentation results along with the qualitative and quantitative inferences verify the robustness of the algorithm across a wide variety of test cases.
- Sudip Kumar Adhikari, Jamuna Kanta Sing, Dipak Kumar Basu, and Mita Nasipuri. 2015. Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images. Applied soft computing 34 (2015), 758–769.Google Scholar
- Mohamed N Ahmed, Sameh M Yamany, Nevin Mohamed, Aly A Farag, and Thomas Moriarty. 2002. A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data. IEEE transactions on medical imaging 21, 3 (2002), 193–199.Google ScholarCross Ref
- Weiling Cai, Songcan Chen, and Daoqiang Zhang. 2007. Fast and robust fuzzy c-means clustering algorithms incorporating local information for image segmentation. Pattern recognition 40, 3 (2007), 825–838.Google Scholar
- Songcan Chen and Daoqiang Zhang. 2004. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 34, 4(2004), 1907–1916.Google ScholarDigital Library
- Keh-Shih Chuang, Hong-Long Tzeng, Sharon Chen, Jay Wu, and Tzong-Jer Chen. 2006. Fuzzy c-means clustering with spatial information for image segmentation. computerized medical imaging and graphics 30, 1 (2006), 9–15.Google Scholar
- Chris A Cocosco, Vasken Kollokian, Remi K-S Kwan, G Bruce Pike, and Alan C Evans. 1997. Brainweb: Online interface to a 3D MRI simulated brain database. In NeuroImage. Citeseer.Google Scholar
- BR Condon, J Patterson, D Wyper, A Jenkins, and DM Hadley. 1987. Image non-uniformity in magnetic resonance imaging: its magnitude and methods for its correction. The British journal of radiology 60, 709 (1987), 83–87.Google Scholar
- Pierrick Coupé, José V Manjón, Elias Gedamu, Douglas Arnold, Montserrat Robles, and D Louis Collins. 2010. Robust Rician noise estimation for MR images. Medical image analysis 14, 4 (2010), 483–493.Google Scholar
- Poulomi Das and Arpita Das. 2019. A fast and automated segmentation method for detection of masses using folded kernel based fuzzy c-means clustering algorithm. Applied Soft Computing 85 (2019), 105775.Google ScholarDigital Library
- Ivana Despotović, Bart Goossens, and Wilfried Philips. 2015. MRI segmentation of the human brain: challenges, methods, and applications. Computational and mathematical methods in medicine 2015 (2015).Google Scholar
- Hákon Gudbjartsson and Samuel Patz. 1995. The Rician distribution of noisy MRI data. Magnetic resonance in medicine 34, 6 (1995), 910–914.Google Scholar
- Timothy C Havens, James C Bezdek, Christopher Leckie, Lawrence O Hall, and Marimuthu Palaniswami. 2012. Fuzzy c-means algorithms for very large data. IEEE Transactions on Fuzzy Systems 20, 6 (2012), 1130–1146.Google ScholarDigital Library
- Jiayin Kang, Lequan Min, Qingxian Luan, Xiao Li, and Jinzhu Liu. 2009. Novel modified fuzzy c-means algorithm with applications. Digital signal processing 19, 2 (2009), 309–319.Google Scholar
- Stelios Krinidis and Vassilios Chatzis. 2010. A robust fuzzy local information C-means clustering algorithm. IEEE transactions on image processing 19, 5 (2010), 1328–1337.Google ScholarDigital Library
- ER McVeigh, MJ Bronskill, and RM Henkelman. 1986. Phase and sensitivity of receiver coils in magnetic resonance imaging. Medical physics 13, 6 (1986), 806–814.Google Scholar
- Nevin A Mohamed, Mohamed N Ahmed, and A Farag. 1999. Modified fuzzy c-mean in medical image segmentation. In 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No. 99CH36258), Vol. 6. IEEE, 3429–3432.Google ScholarDigital Library
- Anupama Namburu, Srinivas kumar Samay, and Srinivasa Reddy Edara. 2017. Soft fuzzy rough set-based MR brain image segmentation. Applied Soft Computing 54 (2017), 456–466.Google ScholarDigital Library
- Alireza Norouzi, Mohd Shafry Mohd Rahim, Ayman Altameem, Tanzila Saba, Abdolvahab Ehsani Rad, Amjad Rehman, and Mueen Uddin. 2014. Medical image segmentation methods, algorithms, and applications. IETE Technical Review 31, 3 (2014), 199–213.Google ScholarCross Ref
- Nikhil R Pal, Kuhu Pal, James M Keller, and James C Bezdek. 2005. A possibilistic fuzzy c-means clustering algorithm. IEEE transactions on fuzzy systems 13, 4 (2005), 517–530.Google ScholarDigital Library
- Dzung L Pham and Jerry L Prince. 1999. Adaptive fuzzy segmentation of magnetic resonance images. IEEE transactions on medical imaging 18, 9 (1999), 737–752.Google ScholarCross Ref
- Chandan Singh and Anu Bala. 2019. A transform-based fast fuzzy C-means approach for high brain MRI segmentation accuracy. Applied Soft Computing 76 (2019), 156–173.Google ScholarDigital Library
- László Szilagyi, Zoltán Benyo, Sándor M Szilágyi, and HS Adam. 2003. MR brain image segmentation using an enhanced fuzzy c-means algorithm. In Proceedings of the 25th annual international conference of the IEEE engineering in medicine and biology society (IEEE Cat. No. 03CH37439), Vol. 1. IEEE, 724–726.Google ScholarCross Ref
- Marinus T Vlaardingerbroek and Jacques A Boer. 2013. Magnetic resonance imaging: theory and practice. Springer Science & Business Media.Google Scholar
- David AG Wicks, Gareth J Barker, and Paul S Tofts. 1993. Correction of intensity nonuniformity in MR images of any orientation. Magnetic resonance imaging 11, 2 (1993), 183–196.Google Scholar
- Chengmao Wu and Xiaoqiang Yang. 2020. Robust credibilistic fuzzy local information clustering with spatial information constraints. Digital Signal Processing 97 (2020), 102615.Google ScholarCross Ref
- Chenyang Xu, Dzung L Pham, and Jerry L Prince. 2000. Image segmentation using deformable models. In Handbook of medical imaging. Vol. 2. SPIE, 129–174.Google ScholarCross Ref
- Dao-Qiang Zhang and Song-Can Chen. 2004. A novel kernelized fuzzy c-means algorithm with application in medical image segmentation. Artificial intelligence in medicine 32, 1 (2004), 37–50.Google Scholar
- Xiaofeng Zhang, Muwei Jian, Yujuan Sun, Hua Wang, and Caiming Zhang. 2020. Improving image segmentation based on patch-weighted distance and fuzzy clustering. Multimedia Tools and Applications 79, 1 (2020), 633–657.Google ScholarDigital Library
- Xiaofeng Zhang, Yujuan Sun, Gang Wang, Qiang Guo, Caiming Zhang, and Beijing Chen. 2017. Improved fuzzy clustering algorithm with non-local information for image segmentation. Multimedia Tools and Applications 76, 6 (2017), 7869–7895.Google ScholarDigital Library
Index Terms
- Enhanced Kernelized Conditional Spatial Fuzzy C Means Algorithm for Noisy Brain MRI Tissue Segmentation
Recommendations
A novel brain image segmentation using intuitionistic fuzzy C means algorithm
A process of splitting the image into pixel bands is the image segmentation. As medical imaging contain uncertainties, there are difficulties in classification of images into homogeneous regions. There is a need for segmentation algorithm for removing ...
Unsupervised segmentation of brain tissue in multivariate MRI
ISBI'10: Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to MacroIn this paper, we present an unsupervised, automated technique for brain tissue segmentation based on multivariate magnetic resonance (MR) and spectroscopy images, for patients with gliomas. The algorithm uses spectroscopy data for coarse detection of ...
Conditional spatial fuzzy C-means clustering algorithm for segmentation of MRI images
A conditional spatial fuzzy C-means (csFCM) clustering algorithm to improve the robustness of the conventional FCM algorithm is presented.The method incorporates conditional affects and spatial information into the membership functions.The algorithm ...
Comments