We propose a novel and automatic computational approach to precisely identify subjects with Brain Tumor from normal brains. As due to high rate of manual error in data acquisition and interpretation there is a need to develop efficient algorithm capable of identifying early biomarkers and exemplify brain disease. So, we have developed improved method which uses adaptive moving mapping with FK-means and 22 GLCM features which were extracted from covariance matrix. The results of comparison experiments on real DICOM images taken from MB hospital (Udaipur) and other database demonstrate the effectiveness of the proposed method. Besides the effectiveness of tissue classification and tumor extraction it also specifies advantage of multifeatures combination to the single-feature method. Moreover, early used techniques faced high MSE, low PSNR and high computational time. This paper presents comparison with existing techniques like Fuzzy K-means and self-organising mapping over validating parameters.

The MRI image analysis plays an important role disease diagnosis. With advent of new technology there are wide range of techniques such as MRI, CT scan, PET scan and many more. The MRI is better than CT scan but expensive so computational processing may reduce the cost of patient’s expense if diagnosed at early stage. The K- means can detect faster than FCM but fails to cluster image data with noise. SOM-FKM has improved dimensional reductionality but fails to detect with huge data .So, the new novel attempt to validate the improved mapping algorithm AMKSOM for disease detection is carried out in this paper. From the experimental results, we proved the effectiveness of AMKSOM which is efficient enough in satisfying are goal needs. The manual error made by physician or any other leads to delay of treatment and ignorance which can be avoided with our algorithm. This helps the patient to get treatment in the earlier stage of the tumor to avoid severity. The result produced using proposed algorithm reveals satisfactory. It can be further extended by implementing on PET images and 3-D imaging techniques for other diseases.

1. Archya Dasgupta, Tejpal Gupta, and Rakesh Jalali(2016).Indian data on central nervous tumors: A summary of published work, South Asian J Cancer,Jul-Sep;ed 5 vol. 3:pp.147–153.doi:  10.4103/2278-330X.187589[accessed:28/3/2018] 2. Govindaraj V, Vishnuvarthanan A, Thiagarajan A, Kannan M, Murugan PR(2016). Short Notes on Unsupervised Learning Method with Clustering Approach for Tumor Identification and Tissue Segmentation in Magnetic Resonance Brain Images, J Clin Exp Neuroimmunol vol 1, pp. 101,2016.doi:10.4172/jceni.100010. 3. N.NandhaGopal (2013). Automatic Detection of Brain Tumor through Magnetic Resonance Image. International Journal of Advanced Research in Computer and Communication Engineering 2( 4). 4. El-Hachemi Guerrout, Ramdane Mahiou and Samy Ait-Aoudia(2013).Medical Image Segmentation on a Cluster of PCs using Markov Random Fields, International Journal of New Computer Architectures and their Applications (IJNCAA). The Society of Digital Information and Wireless Communications (SDIWC) 3(1): 35-44 ,ISSN: 2220-9085. 5. Ortiz , J.M. Górriz , J. Ramírez , D. Salas-González , J.M. Llamas-Elvira(2013) .Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies”, Applied Soft Computing, Science Direct13, 2668–2682. 6. Sultan Aljahdali and E. A. Zanaty (2012).Automatic Fuzzy Algorithms for Reliable Image Segmentation. International Journal for Computers & Their Applications, 19( 3). 7. Ashraf Anwar and Arsalan Iqbal(2013).Image Processing Technique for Brain Abnormality Detection, International Journal of Image Processing 7(709). 8. Somasundaram K, Kalaiselvi T(2012).Fully automatic brain extraction algorithm for axial T2-weighted magnetic resonance images. PubMed Comput Biol Med 40: 811-822. 9. P.Vasuda and S.Satheesh(2010).Improved Fuzzy C-Means Algorithm for MR Brain Image Segmentation. (IJCSE) International Journal on Computer Science and Engineering Vol. 02, No. 05, 1713-1715. 10.Mohammad Javad Abdi, Seyed Mohammad Hosseini, and Mansoor Rezghi(2012).A Novel Weighted Support Vector Machine Based on Particle Swarm Optimization for Gene Selection and Tumor Classification ,Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine , Article ID 320698, 7 . doi:10.1155/2012/320698. 11. Eman Abdel Maksoud,Moh. Emlogy,Rashid Al-Awadi(2015).Brain tumor segmentation based on hybrid clustering technique. Egyptian Informatics Journal (2015) 16, 71–81. 12. Kruti Choksi, Bhavin Shah, Ompriya Kal(2016).Intrusion Detection System using Self Organizing Map: A Survey, Int. Journal of Engineering Research and Applications ISSN : 2248-9622,Vol. 4, Issue 12( Part 4), pp 11-16. 13.Nameirakpam Dhanachandra, Khumanthem Manglem and Yambem Jina Chanu(2015).Image Segmentation using K-means Clustering Algorithm and Subtractive Clustering Algorithm ,Procedia Computer Science 54 , 764 – 771, Published by Elsevier B.V. under the Eleventh International Multi-Conference on Information Processing-2015 . 14.Spanakis, Gerasimos, and Gerhard Weiss(2016).AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization, arXiv preprint arXiv:1605.06047(2016) . 15. Emal Abdel Maksoud,Moh. Emlogy,Rashid Al-Awad(2015).Brain tumor segmentation based on hybrid clustering technique. Egyptian Informatics Journal,Science Direct,16,71-81. 16.Sudipta Roy, Debnath Bhattacharyya, Samir Kumar Bandyopadhyay & Tai-Hoon Kim (2017). An Iterative Implementation of Level Set for Precise Segmentation of Brain Tissues and Abnormality Detection from MR Images, IETE Journal of Research, DOI: 10.1080/03772063.2017.1331757.