Correction of Intensity In-Homogeneity of MR Image Based on Average Median Intensity Value Method

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2015 by IJCTT Journal
Volume-28 Number-2
Year of Publication : 2015
Authors : R. Rubesh Selvakumar, C G Ravichandran
  10.14445/22312803/IJCTT-V28P119

MLA

R. Rubesh Selvakumar, C G Ravichandran "Correction of Intensity In-Homogeneity of MR Image Based on Average Median Intensity Value Method". International Journal of Computer Trends and Technology (IJCTT) V28(2):107-110, October 2015. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
The Magnetic Resonance Image (MRI) may be valuable techniques for learning the structural property of the human brain. However, the reproducibility of imaging results, that arises from swish intensity variation happens the entirety MR image, named as Intensity in-homogeneity or nonuniformity. The intensity in-homogeneity may be a hurdles encountered in human and computer interpretations and analysis of MRI. Automated methods for MRI non-homogeneity correction could fails as a result of resolution because solution for them need identification regions on behalf of an equivalent tissue for a a varietyof various tissue, regardless of the approach could fails this job. Normally, MRI brain image contain intensity inhomogeneity. Therefore accurate process of brain image may be a terribly trouble some task. Thus will use one amongst the correction technique could useful for proper diagnosis for clinical purpose and conjointly segmentation of the image process or segmentation primarily based fusion process. During this paper, we tend to project a brand new technique on the Average Median Intensity Value. This algorithm initial to ascertain the background and foreground voxels then estimate the intensity value of foreground and replacement all the values of background voxels by average median intensity value. This computation time is quick and best compared with the prevailing algorithms, analysis primarily based results is nice for than the source image.

References
[1]. Zhaohui Li, Qiang Link and Yi Yu, 2015, “A Novel Gradient Based Algorithm to correct the intensity in-homogeneity of MR Images”, Journal of Computational Information Systems, Vol. 11:6, p-2155-2162.
[2]. Mohammad Ali Balafar, 2012, “Review of Intensity inhomogeneity Correction Methods for Brain MR Iamges”, International Journal on Technical and Physical Problems of Engineering, Vol.4, issue-14, No.4, p-60-66.
[3]. S.H.Lai and M.Fang,1999, “ A New Variational shape-fromorientation approach to correcting intensity in-homogeneity in magnetic resonance images”, Medical Images Analysis, Vol.3, p- 409-424.
[4]. C.Hui, Y.X. Zhou and P. Narayana, 2010, “ Fast Algorithm for calculation in in-homogeneity gradient in magnetic resonance imaging data”, Journal of Magnetic Resonance Imaging,Vol.32(5), p-1197-1208.
[5]. E. Ardizzone, R. Pirrone and O. Gambino, 2005, “ Exponential Entropy Driven AUM on knee MR Images”, 27th International Conference of the Engineering in Medicine and Biology Society.
[6]. B. Likar, J. Dengance and F. Fernus , 2002, “ Segmentation Based Retrospective Correction of Intensity non-uniformity in Multi-Spectral MR Images”, Proceeding of SPIE Medical Imaging, Image Processing, Sen Diege, P. 1531-1540.
[7]. D. Shattuck, S. Sandor-Leahy, K. Schaper, D. Rottenberg and R. Leahy, 2001, “ Magnetic Resonance Image Tissue Classification Using a Partial “, Neroimage, Vol.13,p.856-876.
[8]. M.A. B alafar, A.R. Ramli, S. Mashohor, 2010, “A New Method for MR Grayscale Inhomogeneity Correction”, Artificial Intelligence Review, Springer, Vol. 34, pp. 195- 204.
[9]. B. Johnston, M.S. Atkins, B. Mackiewich, M. Anderson, 1996, “Segmentation of Multiple Sclerosis Lesions in Intensity Corrected ulti Spectral MRI”, IEEE Transactions on Medical Imaging, Vol. 15, pp. 154-169.
[10]. U. Vovk, F. Pernus, B. Likar, 2007, “A Review of Methods for Correction of Intensity Inhomogeneity in MRI”, IEEE Transactions on Medical Imaging, Vol. 26, pp. 405-421.
[11]. R. Guillemaud, M. Brady, 1997 , “Estimating the Bias Field of MR Images”, IEEE Transactions on Medical Imaging, Vol. 16, pp. 238-251,
[12]. B.H. Brinkmann, A. Manduca, R.A. Robb, 1998, “Optimized Homomorphic Unsharp Masking for MR Grayscale nhomogeneity Correction”, IEEE Transactions on Medical Imaging, Vol. 17, pp. 161-171.
[13]. M.S. Cohen, R.M. Dubois, M.M. Zeineh, 2000, “Rapid and Effective Correction of RF Inhomogeneity for High Field Magnetic Resonance Imaging”, Human Brain Mapping, Vol. 10, pp. 204-211.
[14]. J. Sled, A. Zijdenbos, A. Evans, 1998, “A Nonparametric Method for Automatic Correction of Intensity Nonuniformity in MRI Data”, IEEE Transactions on Medical Imaging, Vol. 17, pp. 87-97.
[15]. B. Likar, M.A. Viergever, F. Pernus, 2001, “Retrospective Correction of MR Intensity Inhomogeneity by Information Minimization”, IEEE Transactions on Medical Imaging, Vol. 20, pp. 1398-1410.
[16]. J.V. Manjon, J.J. Lull, J. Carbonell-Caballero, G.N. Garciaa- Marti, L.S. Marti-Bonmati, M. Robles, 2007, “A Nonparametric MRI Inhomogeneity Correction Method”, Medical Image Analysis, Vol. 11, pp. 336-345.
[17]. D.W. Shattuck, R.M. Leahy, 2001 ,“Automated Graph- Based Analysis and Correction of Cortical Volume Topology”, IEEE Transactions on Medical Imaging, Vol. 20, pp. 1167-1177.
[18]. Zhen Quan, 2007, “Model Based Image Segmentation in Medical Application”, A Thesis, Graduate Schools, New Brunswick, New Jercy.

Keywords
MRI, in-homogeneity, Average Median Intensity.