A New Hybrid RMN Image Segmentation Algorithm

Authors: Abdelouahab Moussaoui, Nabila Ferahta, Victor Chen

Abstract:

The development of aid's systems for the medical diagnosis is not easy thing because of presence of inhomogeneities in the MRI, the variability of the data from a sequence to the other as well as of other different source distortions that accentuate this difficulty. A new automatic, contextual, adaptive and robust segmentation procedure by MRI brain tissue classification is described in this article. A first phase consists in estimating the density of probability of the data by the Parzen-Rozenblatt method. The classification procedure is completely automatic and doesn't make any assumptions nor on the clusters number nor on the prototypes of these clusters since these last are detected in an automatic manner by an operator of mathematical morphology called skeleton by influence zones detection (SKIZ). The problem of initialization of the prototypes as well as their number is transformed in an optimization problem; in more the procedure is adaptive since it takes in consideration the contextual information presents in every voxel by an adaptive and robust non parametric model by the Markov fields (MF). The number of bad classifications is reduced by the use of the criteria of MPM minimization (Maximum Posterior Marginal).

Keywords: Clustering, Automatic Classification, SKIZ, MarkovFields, Image segmentation, Maximum Posterior Marginal (MPM).

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1061916

References:

[1] Bardinet E., Cohen L., and Ayache N., "A parametric deformable model to fit unstructured 3D data", Technical Report 2617, INRIA Sophia Antipolis, 1995.
[2] Barillot C., and al., "Représentation mixte numérique/symbolique des sillons corticaux", In Proc. of 11e congrès Reconnaissance des Formes et Intelligence Artificielle, Paris, France, pp. 165-174,1998.
[3] Bezdek J.C. and Pal N.R., "Some new indexes of cluster validity". IEEE Trans. Systems Man. Cybern., vol. 28, pp. 301-315, 1998.
[4] Chiou G. and Hwang J.N., "A Neural Network-Based Stochastic Active Contour Model (NNS-SNAKE) for Contour Finding of Distinct Features", IEEE Transactions on Image Processing, vol. 4, no. 10, pp. 1407-1416, 1995.
[5] Cootes T.F., and al., "Active Shape Models- Their Training and Application", Computer Vision and Image Understanding, vol. 61, no.1 1, pp. 38-59, January 1995.
[6] Davatzikos C. and Prince J.L., "An active contour model for mapping the cortex", IEEE Transactions on Medical Imaging, vol. 14, no. 1, pp. 65-80, 1995.
[7] Dellepiane S., Venturi G., and Vernazza G., "A fuzzy model for the processing and recognition of MR pathological images", In Lecture notes in computer science, IPMI proceedings, pp. 444-457, 1991.
[8] Descombes X., Moris R. and Zerubia J., "Quelques améliorations ├á la segmentation d'images bayesienne", Traitement du signal, vol. 14, no. 4, pp. 373-382, 1997.
[9] Descombes X., Sigelle M., and Préteux F., "Estimating Gaussian Markov random field parameters in a non-stationary framework", IEEE Transaction On Image Processing, 1998.
[10] Duta N. and Sonka M., "Segmentation and Interpretation of MR Brain Images : An Improved Active Shape Model", EEE Transactions on Medical Imaging, vol. 17, no. 6, pp. 1049-1062, 1998.
[11] Friston K. and al., "Statistical Parametric Maps in Functional Imaging : a general linear approach", Human Brain Mapping, vol. 2, pp. 189-210, 1995.
[12] Geman D., Renolds G., "Constrained restoration and the recovery of discontinuities", IEEE Transaction On Pattern Analysis and Machine Intelligence, vol. 14, no. 3, pp. 367-383, Marsh 1992.
[13] Géraud T., "Segmentation des structures internes du cerveau en imagerie par résonance magnétique 3D", Thèse de doctorat, Télécom Paris, 1998.
[14] Gong L. and Kulikowski A., "Composition of image Analysis Processes Through Object-centered Hierarchical Planning", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 10, pp. pp. 997- 1009, 1995.
[15] Held K., and al., "Markov Random Field Segmentation of Brain MR Images", IEEE Transactions on Medical Imaging, vol. 16, no. 6, pp. 878-886, 1997.
[16] Herbin M., Bonnet N. and Vautrot P., "Estimation of the number of clusters by influence zones", Pattern Recognition Letters, vol. 22, pp. 1557-1568, 2001.
[17] Jaggi C., Segmentation par méthode markovienne de l-encéphale humain par résonance magnétique : théorie, mise en oeuvre et évaluation, Thèse de doctorat de l-université de Caen, 1998.
[18] Kapur T. and al., "Segmentation of brain tissue from magnetic resonance images", Medical Image Analysis, vol.1, no. 2, pp. 109-127, 1996.
[19] Li H., and al., "Object-recognition in brain CTscans : knowledge-based fusion of data from multiple feature extractors", IEEE Transactions on Medical Imaging, vol. 14, no. 2, pp. 212-229, 1995.
[20] Liew A.W.-C., Hong Yan, "Adaptive fuzzy segmentation of 3D MR brain images", Fuzzy Systems, The 12th IEEE International Conference on Fuzzy System, vol. 2 , pp. 25-28, May 2003
[21] Mangin J.F. and al., "A MRF based random graph modeling the human cortical topography", In First International Conference CVRMed, Nice, pp. 177-183, 1995.
[22] Moussaoui A. and Chen V., "Fuzzy automatic classification without a prior knowledge-mean shift application to MRN brain images segmentation", In Symposium of Electronics and Telecommunications, Timisoara, Romania, pp. 213-219, October 2004.
[23] Moussaoui A. and Chen V., "Segmentation d'images médicales par coopération de classifieurs", In Proc. of International Symposium on Medical Image Processing, Blida, Algeria, pp. 57-62, November 2004.
[24] Moussaoui A. and Chen V., "Segmentation neuro-floue des tissus cérébraux pathologiques en IRM 3D", In Proc. of International Symposium on Medical Image Processing, Blida, Algeria, pp. 81-86, November 2004.
[25] Palubinskas G., Miter S. and Poggio T., "An unsupervised clustering method using the entropy minimisation". In ICPR. - Austria, August 1998.
[26] Parzen E., "On estimation of a probability density function and mode". Ann. Math. Statist., vol. 33, pp. 1065-1076, 1962.
[27] Rajapakse J., Giedd J., Rapoport and J., "Statistical Approach to segmentation of single-channel cerebral MR images", IEEE Transactions on Medical Imaging, vol. 16, pp. 176-186, 1997.
[28] Sandor S. and Leahy R., "Surface-Based Labeling of Cortical Anatomy Using a Deformable Atlas", IEEE Transactions on Medical Imaging, vol. 16, no. 1, pp. 41-54, 1997.
[29] Sigele M. and Ronfard R., "Modèles de potts et relaxation d'images de labels par champs de Markov", Traitement du signal, vol. 6, no. 9, pp. 449-458, 1992.
[30] Silverman B. W., "Density Estimation for Statistics and Data Analysis", Chapman and Hall, London, 1986.
[31] Soltanian-Zadeh H., and al, "Model-independent method for fMRI analysis ", EEE Transactions on Medical Imaging, vol. 23, no.3, pp. 285 - 296, March 2004.
[32] Sonka M., Tadikonda S., and Collins A. M., "Knowledge-Based Interpretation of MR brain Images", IEEE transactions on Medical Imaging, vol. 15, no. 4, 1996.
[33] Staib L.H. and Duncan J.S., "Boundary Finding with Parametrically Deformable Models", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 11, pp. 1061-1075, 1992.
[34] Vaillant M. and C.Davatzikos, "Finding parametric representations of the cortical sulci using an active contour model", Medical Image Analysis, vol. 1, no. 4, pp. 295-315, 1997.
[35] Wells W.M., and al., "Adaptative Segmentation of MRI data", IEEE Transactions on Medical Imaging, vol. 15, no. 4, pp. 429-442, 1996.