Un-supervised MR Images Segmentation Using SOM and Anisotropic Diffusion Filter
DOI:
https://doi.org/10.18486/ijcsnt/4.3.057Keywords:
Feature Selection, Principle Component Analysis, Self Organizing Map, Anisotropic Diffusion Filter, CLAHEAbstract
The primary aim in brain image segmentation is to perform partition a given brain image into different regions which are homogeneous with some criterion. Magnetic resonance image (MRI) segmentation plays crucial role in accurate representation of white matter (WM), grey matter (GM) and cerebrospinal fluid (CSF) provides a way to identify many brain disorders, such as Alzheimer’s disease, schizophrenia or dementia. In this paper presents a unsupervised method for MR image segmentation based on Self Organizing Maps (SOMs). the proposed method is consisting of five stages these are image acquisition, pre-processing step contain anisotropic diffusion filter and contrast limited adaptive histogram equalization (CLAHE), feature extraction using haralick features, feature selection using principal component analysis (PCA) and tissue classification using SOM. Our proposed method is performed over real MR data provided by Internet Brain Repository (IBSR 2.0) database. Performance evaluation using Tanimoto performance index indicate that the proposed method has good segmentation results. Tanimoto performance index gives mean and standard deviation of 0.66}04 for white matter and 0.59}06 for gray matter.
References
Kannan SR. A new segmentation system for brain MR image based on fuzzy techniques. Applied Soft Computing 2008; : 1599–1606. DOI: https://doi.org/10.1016/j.asoc.2007.10.025
Portela NM, Calvalcanti GD and Ren TI. Semi-supervised clustering for MR image segmentation. Expert Systems with Applications 2014; : 1492–1497. DOI: https://doi.org/10.1016/j.eswa.2013.08.046
El-Dahshan EA, Hosny T and Salem AM. Hybrid intelligent techniques for MRI image classification. Digital Signal Processing 2010; : 433–441. DOI: https://doi.org/10.1016/j.dsp.2009.07.002
Ortiz A, Gorriz JM, Ramirez J et al. Two fully unsupervised method for MR brain image segmentation using SOM based strategies. Applied Soft Computing 2013; : 2668–2682. DOI: https://doi.org/10.1016/j.asoc.2012.11.020
El-Dahshan EA, Mohsen HM, Revett K et al. Computer aided diagnosis of human brain tumor through MRI. Expert Systems with Applications 2014; : 5526–5545. DOI: https://doi.org/10.1016/j.eswa.2014.01.021
Ortiz A, Gorriz JM, Ramirez J et al. Improving MR brain image segmentation using self-organising maps and entropy-gradient clustering. Information Science 2014; : 117–136. DOI: https://doi.org/10.1016/j.ins.2013.10.002
Salas-Gonzalez D, Ramirez J, Gorriz JM et al. Improving MRI segmentation with probabilistic GHSOM and multiobjective optimization. Neurocomputing 2013; : 118–131. DOI: https://doi.org/10.1016/j.neucom.2012.08.047
Gerig G, Kikinis R, Kubler O et al. Nonlinear anisotropic filtering of MRI data. IEEE Transactions on Medical Imaging 1992; : 221–232. DOI: https://doi.org/10.1109/42.141646
Perona P and Malik J. Scale-space and edge detection using neural anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 1990; : 629–639. DOI: https://doi.org/10.1109/34.56205
Haralick RM, Shanmugam K and Dinstein I. Textural feature for image classification. IEEE Transactions on Systems, Man and Cybernetics 1973; 3: 610–621. DOI: https://doi.org/10.1109/TSMC.1973.4309314
Zulpe N and Pawar V. GLCM textural feature for brain tumor classification. International Journal of Computer Science Issues 2012; 9(3).
Kohonen T. Self Organizing Maps. Springer, 2001. DOI: https://doi.org/10.1007/978-3-642-56927-2
M J and Raimond K. MR brain image segmentation based on principle component analysis and self organizing map. International Journal for Research in Applied Science and Engineering Technology 2014; 2(3).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Praveen Kumar Prajapati, Manish Dixit
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
