Ihab ELAFF, Ali EL-KEMANY, Mohamed KHOLIF

Universal and stable medical image generation for tissue segmentation (The unistable method)

Segmentation of medical images has been one of the most important research areas because of its impact in modeling and diagnosing the structure and the functions of various organs. The lack of unique solution for the segmentation problem of medical images is caused by the wide range of selections among different medical imaging modalities and clustering methods where each setting has its own estimates for solving this problem. The unistable method is a novel method that generates enhanced images with high contrast, which can reduce boundary overlap between different tissues. This is accomplished by fusion of different clustering maps, which are generated from selected medical images using some clustering methods. The improved unistable images are somehow universal, where all estimates of different regular segmentation settings are considered in the solution, and they are relatively stable, because results of their segmentation are proved to be relatively independent of clustering method.

PDF

___

[1] Mori S. Introduction to Diffusion Tensor Imaging. 1st ed. Oxford, UK: Elsevier, 2007.
[2] Liu T, Li H, Wong K, Tarokh A, Guo L, Wong S. Brain tissue segmentation based on DTI data. Neuroimage 2007; 38: 114-123.
[3] Zarei M, Johansen Berg H, Matthews PM. Diffusion tensor imaging and tractography in clinical neurosciences. Iranian Journal of Radiology 2003; 1: 45-52.
[4] Khotanlou H, Colliot O, Atif J, Bloch I. 3D brain tumor segmentation in MRI using fuzzy classi cation, symmetry analysis and spatially constrained deformable models. Fuzzy Set Syst 2009; 160: 1457-1473.
[5] Dubey RB, Hanmandlu M, Gupta SK, Gupta SK. The brain MR image segmentation techniques and use of diagnostic packages. Acad Radiol 2010; 17: 658-671.
[6] Sidaros A, Engberg AW, Sidaros K, Liptrot MG, Herning H, Petersen P, Paulson OB, Jernigan TL, Rostrup E. Diffusion tensor imaging during recovery from severe traumatic brain injury and relation to clinical outcome: a longitudinal study. Brain 2008; 131: 559-572.
[7] Holtmannspotter M, Peters N, Opherk C, Martin D, Herzog J, Bruckmann H, Samann P, Gschwendtner A, Dichgans M. Diffusion magnetic resonance histograms as a surrogate marker and predictor of disease progression in CADASIL: a two-year follow-up study. Stroke 2005; 36: 2559-2565.
[8] Albrecht J, Dellani PR, Muller MJ, Schermuly I, Beck M, Stoeter P, Gerhard A, Fellgiebel A. Voxel based analyses of diffusion tensor imaging in Fabry disease. J Neurol Neurosur Ps 2007; 78: 964-969.
[9] Concha L, Gross DW, Beaulieu C. Diffusion tensor tractography of the limbic system. Am J Neuroradiol 2005; 26: 2267-2274.
[10] Bomans M, Hohne KH, Kramer LH, Riemer M. 3-D segmentation of MR images of the head for 3-D display. IEEE T Med Imaging. 1990; 9: 177-183.
[11] Westbrook C, Roth CK, Talbot J. MRI in Practice. 4th ed. Oxford, UK: Wiley-Blackwell, 2011.
[12] Goldman LW. Principles of CT and CT technology. J Nucl Med Technol 2007; 35: 115-128.
[13] Portela NM, Cavalcanti G, Ren TI. Semi-supervised clustering for MR brain image segmentation. Expert Syst Appl 2014; 41: 1492-1497.
[14] El-Aff I. Human brain tissues segmentation based on DTI data. In: 11th International Conference on Information Science, Signal Processing and Their Applications; 2{5 July 2012; Montreal, Canada. New York, NY, USA: IEEE. pp. 876-881.
[15] Clarke LP, Velthuizen RP, Camacho MA. MRI Segmentation: methods and applications. Magn Reson Imaging 1995; 13: 343-368.
[16] Zhang Y, Brady M, Smith S. Segmentation of brain MR images through a hidden Markov random eld model and the expectation-maximization algorithm. IEEE T Med Imaging 2001; 20: 45-57.
[17] Chen T, Huang TS. Region based hidden Markov random eld model for brain MR image segmentation. Interna- tional Journal of Computer, Electrical, Automation, Control and Information Engineering 2007; 1: 1129-1132.
[18] Perez P. Markov random elds and images. CWI Quarterly 1998; 11: 413-437.
[19] Demirkaya O, Asyali MK, Sahoo PK. Image Processing with MATLAB: Application in Medicine and Biology. Boca Raton, FL, USA: CRC Press, 2009.
[20] Otsu N. A threshold selection method from gray-level histograms. IEEE T Syst Man Cyb 1979; 9: 62-66.
[21] Wagsta K, Cardie C, Rogers S, Schroedl S. Constrained K-means clustering with background knowledge. In: Proceedings of the Eighteenth International Conference on Machine Learning; 28 June{1 July 2001; Williamstown, MA, USA. Burlington, MA, USA: Morgan Kaufmann. pp. 577-584.
[22] Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc 1977; 39: 1-38.
[23] Wen Y, He L, Von Deneen KM, Lu Y. Brain tissue classi cation based on DTI using an improved fuzzy C-means algorithm with spatial constraints. Magn Reson Imaging 2013; 31: 1623-1630.
[24] Freitas P, Rittner L, Appenzeller S, Lotufo R. Watershed-based segmentation of the midsagittal section of the corpus callosum in diffusion MRI. In: 24th SIBGRAPI Conference on Graphics, Patterns and Images; 28{31 August 2011; Alagoas, Brazil. pp. 274-281.
[25] Song Z, Tustison N, Avants B, Gee JC. Integrated graph cuts for brain MRI segmentation. In: 9th International Conference in Medical Image Computing and Computer-Assisted Intervention; 1{6 October 2006; Copenhagen, Denmark. Berlin, Germany: Springer. pp. 831-838.
[26] Awate PS, Tasdizen T, Foster N, Whitaker RT. Adaptive Markov modeling for mutual-information-based, unsu- pervised MRI brain-tissue classi cation. Med Image Anal 2006; 10: 726-739.
[27] Li H, Liu T, Young G, Guo L, Wong ST. Brain tissue segmentation based on DWI/DTI data. In: 3rd IEEE International Symposium on Biomedical Imaging; 6{9 April 2006; Arlington, VA, USA. New York, NY, USA: IEEE. pp. 57-60.
[28] Mortamet B, Zeng D, Gerig G, Prastawa M, Bullitt E. Effects of healthy aging measured by intracranial compart- ment volumes using a designed MR brain database. In: 8th International Conference on Medical Image Computing and Computer-Assisted Intervention; 26{29 October 2005; Palm Springs, CA, USA. Berlin, Germany: Springer. pp. 383-391.
[29] Gur RC, Gunning-Dixon F, Bilker WB, Gur RE. Sex differences in temporo-limbic and frontal brain volumes of healthy adults. Cereb Cortex 2002; 12: 998-1003.
[30] Basser PJ, Mattiello J, LeBihan D. MR diffusion tensor spectroscopy and imaging. Biophys J 1994; 66: 259-267.
[31] Basser PJ, Pierpaoli C. Microstructural and physiological features of tissues elucidated by quantitative-diffusion- tensor MRI. J Magn Reson 1996; 111: 209-219.
[32] Vilanova A, Zhang S, Kindlmann G, Laidlaw D. An introduction to visualization of diffusion tensor imaging and its applications. In: Weickert J, Hagen H, editors. Visualization and Processing of Tensor Fields. Berlin, Germany: Springer, 2005. pp. 121-153.
[33] El-Aff I. Extraction of human heart conduction network from diffusion tensor MRI. In: Bipmed2010; 17{19 February 2010; Innsbruck, Austria. Calgary, Canada: ACTA Press. p. 680-051.
[34] Arlot S, Celisse A. A survey of cross-validation procedures for model selection. Stat Surv J 2010; 4: 40-79.
[35] Seehaus A, Roebroeck A, Bastiani M, Fonseca L, Bratzke H, Lori N, Vilanova A, Goebel R, Galuske R. Histological validation of high-resolution DTI in human post mortem tissue. Front Neuroanat 2015; 9: 98.