The International Arab Journal of Information Technology (IAJIT)


Brain Tumor Segmentation in MRI Images Using Integrated Modified PSO Fuzzy Approach

An image segmentation technique based on maximum fu zzy entropy is applied for Magnetic Resonance (MR) brain images to detect a brain tumor is presented in this paper. The proposed method performs image segmenta tion based on adaptive thresholding of the input MR brain images. The MR brain image is classified into two Membersh ip Function (MF), whose MFs of the fuzzy region are Z-function and S- function. The optimal parameters of these fuzzy MFs are obtained using Modified Particle Swarm Optimization (MPSO) algorit hm. The objective function for obtaining the optimal fuzzy MF parameters is considered to be the maximum the fuzz y entropy. In the course of a number of examples, the performance is compared with those using existing entropy-based ob ject segmentation approaches and the superiority of the proposed MPSO method is demonstrated. The experimental results ar e compared with the exhaustive search method and Ot su segmentation technique. The result shows the proposed fuzzy entr opy based segmentation method optimized using MPSO achieves maximum entropy with proper segmentation of tumor and with minimum computational time.

[1] Brink A. and Pendock N., Minimum Cross Entropy Threshold Selection, Pattern Recognition , vol. 29, no. 1, pp. 1798188, 1996.

[2] Cheng H., Chen Y., and Jiang X., Thresholding using Two Dimensional Histogram and Fuzzy Entropy Principle, IEEE Transaction Image Process , vol. 9, no. 4, pp. 7328735, 2000.

[3] Dombi J., Membership Function as an Evaluation, Fuzzy Sets and Systems , vol. 35, no. 1, pp. 1821, 1990.

[4] Ebanks B., On Measures of Fuzziness and Their Representations, Journal of Mathematical Analysis and Applications , vol. 94, no. 1, pp. 248 37, 1983.

[5] Eberhart R. and Shi Y., Particle Swarm Optimization: Developments, Applications and Resources, in Proceedings of Congress on Evolutionary Computation , Seoul, Korea, pp. 818 86, 2001.

[6] Elnomery Z. and Sultan A., Improving Fuzzy Algorithms for Automatic MRI Segmentation, the International Arab Journal of Information Technology , vol. 7, no. 3, pp. 2718279, 2010.

[7] Kennedy J. and Eberhart R., A New Optimizer using Particle Swarm Theory, in Proceedings of the 6 th International Symposium Micromachine Human Science , Nagoya, Japan, pp. 39843, 1995.

[8] Kennedy J., Eberhart R., and Shi Y., Swarm Intelligence , San Mateo, CA: Morgan Kaufmann, 2001.

[9] Kapur J., Sahoo P., and Wong A., A New Method for Gray8Level Picture Threshold using the Entropy of the Histogram, Computer Vision, Graphics , and Image Processing , vol. 29, no. 3, pp. 2738285, 1985.

[10] Luca A. and Termini S., Definition of a Non Probabilistic Entropy in the Setting of Fuzzy Sets Theory, Information and Control , vol. 20, no. 4, pp. 3018315, 1972.

[11] Otsu N., A Threshold Selection Method from Gray8Level Histograms, IEEE Transactions on Systems , Man and Cybernetics , vol. 9, no. 1, pp. 62866, 1979.

[12] Pal N. and Pal S., A Review on Image Segmentation Techniques, Pattern Recognition, vol. 26, no. 9, pp. 127781294, 1993.

[13] Pun T., Entropic Thresholding: A New Approach, Computer Vision , Graphics , and Image Processing , vol. 16, no. 3, pp. 2108239, 1981.

[14] Ratnaweera A., Halgamug S., and Watson C., Self8organizing Hierarchical Particle Swarm Optimizer with Time8Varying Acceleration Coefficients, IEEE Transactions on Evolutionary Computation , vol. 8, no. 3, pp. 2408 255, 2004.

[15] Sahoo P., Solutani S., and Wong A., A Survey of Thresholding Techniques, Computer Vision, Graphics , and Image Processing , vol. 41, no. 2, pp. 2338260, 1988.

[16] Sahoo P., Wilkins C., and Yeager J., Threshold Selection using Renyi s Entropy, Pattern Recognition , vol. 30, no. 1, pp. 71884, 1997.

[17] Sezgin M. and Sankur B., Survey Over Image Thresholding Techniques and Quantitative Performance Evaluation, Journal of Electronic Imaging , vol. 13, no. 1, pp. 1468165, 2004.

[18] Shelokar P., Jayaraman V., and Kulkarni B., An Ant Colony Approach for Clustering, Analytica Chimica Acta , vol. 509, no. 2, pp. 1878195, 2004.

[19] Tao W., Tian J., and Liu J., Image Segmentation by Three8Level Thresholding based on Maximum Fuzzy Entropy and Genetic Algorithm, Pattern Recognition Letters , vol. 24 no. 16, pp. 306983078, 2003.

[20] Tao W., Tian J., and Liu J., Object Segmentation using Ant Colony Optimization Algorithm and Fuzzy Entropy, Pattern 804 The International Arab Journal of In formation Technology, Vol. 12, No. 6A, 2015 Recognition Letters, vol. 28, no. 7, pp. 7888796, 2007.

[21] Yen J., Chang F., and Chang S., A New Criterion for Automatic Multilevel Thresholding, IEEE Transaction on Image Process , vol. 4, no. 3, pp. 3708378, 1995.

[22] Zhao M., Fu A., and Yan H., A Technique of Three8Level Thresholding Based on Probability Partition and Fuzzy 38Partition, IEEE Transaction on Fuzzy System , vol. 9, no. 3, pp. 4698479, 2001. Krishna Priya Remamany received BE from Noorul Islam college of Engineering affiliated to Manonmaniam Sundarnar University, in 2004, ME from Arulmigu Kalasalingam College of Engineering, affiliated to Anna University with 2nd Rank, in 2006. She received PhD from Kalasalingam University in 2014. Her area of interests includes medical imaging, soft computing, optimization techniques and control engineering. She is a reviewer for Springer journal and editorial member for many journals. Currently, she is an Associate Professor in Department of Applied Electronics and Instrumentation, SAINTGITS College of Engineering, India. Chelliah Thangaraj received his BE from Thiagarajar College of Engineering, Madurai, affiliated to Madurai Kamaraj University, in 1979. M. Tech from I.I.T., Kanpur, in 1981 and PhD from I.I.T., Delhi in 1985. His professional experience includes Teaching, research and administration. He completed projects worth of 20 crores. His area of interest includes parallel and object oriented computing, remote sensing and GIS, hydraulic and hydrologic modeling, large scale systems, facility planning, medical imaging, soft computing and senso r networks. He was awarded the Common wealth Academic Fellowship of British Council and was also awarded the Netherlands Fellowship program at ITC, Enschede, Netherlands. He was also a DAAD Senior Fellow at Aachen University of Technology, RWTH, Germany during the year 2000. Chandrasekaran Kesavadas received his MBBS from Calicut Medical College, University of Calicut in 1989, MD (Radio8 Diagnosis) from Medical College, Trivandrum under University of Kerala in 1994. He received Fellowship in Neuroradiology from Scientific Instit ute and University Hospital San Raffaele, Italy in 2002 . His area of interests include Magnetic Resonance Imaging (including MR spectroscopy, Diffusion/Perfusion Imaging, Susceptibility weighte d imaging and fMRI), Neuroradiology (Especially Neuroimaging in Epilepsy, Brain tumor, Pediatric Neuroradiology, Movement disorders, Dementia and Stroke) and Medical Imaging Informatics. He has collaborated with University of Tunbingen, Germany, Biomedical Technology wing, SCTIMST. Currently, he is a Professor in Department of Imaging Sciences and Interventional Radiology, SCTIMST. He is a reviewer of scientific projects of Indian Council o f Medical Research and Department of Biotechnology, DST, BRNS and Department of Atomic Energy. Kannan Subramanian received his BE, ME and PhD Degrees from Madurai Kamaraj University, India in 1991, 1998 and 2005 respectively. His research interests include power system deregulation and evolutionary computation. He was a visiting scholar in Iowa State University, USA (October 20068September 2007) supported by the Department of Science and Technology, Government of India with BOYSCAST Fellowship. Currently, he is a Professor and Head of Electrical and Electronics Engineering Department, Ramco Institute of Technology, Rajapalayam, India. He is a Sr. Member of IEEE, Member in IET, Fellow of IE (I), Sr. Membe r in CSI, Fellow in IETE, Life member SSI and Life member of ISTE.