Comparative Analysis of Different Classifiers to Detect the Disease in Brain MRI Images

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2016 by IJCTT Journal
Volume-39 Number-1
Year of Publication : 2016
Authors : S.P.Washimkar, S.D.Chede
  10.14445/22312803/IJCTT-V39P101

MLA

S.P.Washimkar, S.D.Chede "Comparative Analysis of Different Classifiers to Detect the Disease in Brain MRI Images". International Journal of Computer Trends and Technology (IJCTT) V39(1):1-5, September 2016. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
Multiple Sclerosis is an autoimmune demylinating disease that occurs in brain white matter. It forms number of bright spots which appears and disappears with the period of dimension that initiates the researcher to find out the progression detection of the disease. Different classifiers are studied and applied on the segmented image and implemented on GUI Matlab which categories the disease into different classes depending on disease progression. The six classifiers are linear classifier, Quadratic classifier, Linear diagonal classifier, Quadratic Diagonal classifier, Mahalanobis classifier and K-NN classifier. The comparative study reveals that a KNN classifier gives more accuracy than others in its initial stages of the disease which helps in early stage detection of the disease.

References
[1] Victor Murray, Paul Rodriguez, and Marios S. Pattichis, ”Multiscale AM- FM Demodulation and Image Reconstruction Methods With Improved accuracy”, IEEE Transactions on image processing, VOL. 19, NO. 5.
[2] C.P. Loizou, V. Murray, M.S. Pattichis, I Seimenis, M. Pantziaris, C.S Pattichis,” Multiscale Amplitude- Modulation Frequency Modulation AM-FM) Texture analysis of Multiple Sclerosis in Brain MRI Images”.IEEE Transactions on Information technology in Biomedicine, vol.15, no.1, January 2011.
[3] L. P. Clarke and Heine, et al., “MRI Segmentation: Methods and Applications”, Elsevier Publishers, Magnetic Resonance Imaging, vol. 13, no. 3, (1995).
[4] J. Sastre-Garriga, et al., “Grey and White Matter Volume Changes in Early Primary Progressive Multiple Sclerosis: a Longitudinal Study”, Brain, vol. 128, (2005), pp. 1454– 1460.
[5] Segmentation of Fingerprint Images using linear Classifier, EURASIP Journal on Applied Signal Processing,2004 ;4 , 480-494.
[6]M.FauvelKernal,A.Villa,J.Chanussot,J.A.Benediktsson”Mahal anobis Kernel for the classification of hyper spectral images.”IEEE 2010,pp 3724- 3727.
[7] Santosh Shrivastava, Maya R.Gupta,Bela A. Frigyik”Bayesian Quadratic Discriminant Analysis.” Journal of machine learning research,2007,pp 1277-1305.
[8] Herbert Pang,Teijin Tang,Hongyu Zhab,”Shrinkage based Diagonal Discriminant Analysis and its Application in High Dimensional Data ,2009 Dec 65(4),pp 1021-1029.
[9] J.P.Hoffback and D.A.landgrebe, Covariance matrix esimatation and Classification with limited Training Data, IEEE Transaction on Pattern Analysis and Machine Intelligence Vol. 18,pp763-767,July 1996.
[10] Tadjudin and D.A.landgrebe,”Covariance Estimation with Limited Training Samples,”IEEE Transactions on Geosciences and Remote sensing, Vol.37,no.4,July 1999.
[11]Weinberger, K.Q., Blitzer, J., Sau l, L. K, Distance metric learning for large margin nearest neighbour classification , NIPS, 2005.

Keywords
Magnetic Resonance Imaging (MRI), Amplitude-Modulation, Frequency-Modulation (AMFM), Multiple Sclerosis (MS), Texture analysis, Classifier.