Image processing is an important aspect of medical science to visualize the different anatomical structures of human body. Sometimes it becomes very difficult or impossible to detect or visualize such hidden abnormal structures by using simple imaging. Brain tumor is one of the major causes for mortality among children and adults. Extensive research is being carried out to develop automatic algorithms for detection of Tumor from Brain images captured using MR imaging. Still there are challenges like time requirements, inaccuracy, need of human intervention and complexity of images in detecting region of interest. In this study, an algorithm is proposed for detection of Tumor from MR Brain images, which is based upon thresholding, region growing and genetic algorithm. Performance evaluation of proposed algorithm and studied state-of-the-art algorithms suggests that proposed algorithm gives best results for Tumor detection from MR brain images.

Brain tumor detection, medical image, segmentation, magnetic resonance imaging (MRI).

[1] G.R. Chandra, K.R. Rao, “Tumor detection in brain using Genetic Algorithm” In the Proceedings of the 2016 7th International Conference on Communication, Computing and Virtualization, pp.449-457, 2016.
[2] C. Li , R. Chiao, “Multi-resolution genetic clustering algorithm for texture segmentation”, Image and Vision Computing, Vol. 21, pp. 955 – 966, 2003.
[3] E.Y. Kim, S.H. Park, H.J. Kim, “A genetic algorithm-based segmentation of Markov random field modeled images”, IEEE Transaction, Vol. 7, pp. 301- 315, 2000.
[4] M. Gong, Y.H. Yang, “Genetic-based multi resolution color image segmentation”, Vision Interface, pp. 141–148. 2001.
[5] Abdullah, “Implementation of an improved cellular neural network algorithm for brain tumor detection”, In International Conference on Biomedical Engineering , pp.611-615, 2012.
[6] A. Bianchi, J. V. Miller, A. Montillo, “Brain tumor segmentation with symmetric texture and symmetric intensity-based decision forests”, In IEEE 10th International Symposium on Biomedical Imaging, pp.748-751, 2013.
[7] A. Halder, D.K. Kole, “Automatic Brain Tumor Detection and Isolation of Tumor Cells from MRI Images”, International Journal of Computer Applications, Vol.39, No.2, 2012.
[8] Gajanayake, Randike, Yapa, R. Dharshana, Badra, “Comparison of standard image segmentation methods for segmentation of brain tumors from 2D MR images”, In the Proceedings of the 2009 IEEE 4th International Conference on Industrial and Information Systems, pp. 301-305, 2009.
[9] I. Maiti, M. Chakraborty, “A new method for brain tumor segmentation based on watershed and edge detection algorithms in HSV colour model”, In National Conference onComputing and Communication Systems, 2012.
[10] N. Sohi, L. Kaur, S. Gupta, “Enhanced Thresholding algorithm to Extract Tumor region from MR brain images”, In the Proceedings of International Conference on Electrical engineering and Computer Science,2012.
[11] S. Albayrak, F. Amasyali, “Fuzzy C-Means Clustering on Medical Diagnosis Systems”, International 12th Turkish Symposium on Artificial Intelligence and Neural Networks, 2003.
[12] K. Thapaliya and G. Kwon, “Extraction of brain tumor based on morphological operations”, In the Proceedings of 2012 IEEE-8th international Conference on Computing Technology and Information Management, pp. 515-520, 2012.
[13] K. J Gorgolewski, P. L Bazin, D. S Margulies,“Fifty Shades of Gray Matter: using bayesian priors to improve the power of whole-brain Voxel and connexe lwise inferences”, In International Workshop, Pattern Recognition in Neuro-imaging, pp.194-197, 2013.
[14] F.W. Prior, S. J. Fouke, T. Benzinger, A. Boyd, L.Kim,“Predicting a multi-parametric probability map of active tumor extent using random forests”, In Annual International Conference on Engineering in Medicine and Biology Society, pp.6478-6481, 2014.
[15] A. Q. Syedi, K. Narayanan, “Detection of Tumour in MRI Images Using Artificial Neural Networks”, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol. 3, Issue 9, 2012.
[16] J.C. Dunn, “A fuzzy relative of the ISODATA process and its use in detecting compact well separated clusters”, Journal of Cybernetics, Vol. 3, No.3, pp. 32–57, 1973.