Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 30172
Brain MRI Segmentation and Lesions Detection by EM Algorithm

Authors: Mounira Rouaïnia, Mohamed Salah Medjram, Noureddine Doghmane

Abstract:

In Multiple Sclerosis, pathological changes in the brain results in deviations in signal intensity on Magnetic Resonance Images (MRI). Quantitative analysis of these changes and their correlation with clinical finding provides important information for diagnosis. This constitutes the objective of our work. A new approach is developed. After the enhancement of images contrast and the brain extraction by mathematical morphology algorithm, we proceed to the brain segmentation. Our approach is based on building statistical model from data itself, for normal brain MRI and including clustering tissue type. Then we detect signal abnormalities (MS lesions) as a rejection class containing voxels that are not explained by the built model. We validate the method on MR images of Multiple Sclerosis patients by comparing its results with those of human expert segmentation.

Keywords: EM algorithm, Magnetic Resonance Imaging, Mathematical morphology, Markov random model.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1328952

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1621

References:


[1] I.Grosman, J.C.Mc Gowan, "Perspectives on Multiple Sclerosis" AJNR n┬░ 19, 1998, pp 1251-1265.
[2] J.Rajapakse, J.Giedd, J.Rapoport, "Statistical approach to segmentation of single channel cerebral MRimages" IEEE Trans Med Imag vol 16(2), 1997, pp 176-186.
[3] K.Held, E.R.Kops, B.J.Kraus, W.M.Wells, R.Kikinis, H.W.Mullet- Gartner, "Markov random field segmentation of brain MR images" IEEE Trans Med Imag vol 16 (6) 1997, pp 878-886.
[4] W.M.Wells, W.E.L.Grimson, R.Kikinis, F.A.Jolesz, "Adaptive segmentation of MRI data" IEEE Trans Med Imag vol 15 (4) 1996, pp429-442.
[5] Y.Zhang, M.Brady, S.Smith "Segmentation of brain MR images through a Hidden Markov random field model and the expectation maximization algorithm" IEEE Trans Med Imag vol. 20 (01) Jan 2001, p 45-57.
[6] J.L.Marroquin, B.C.Venuri, S.Botello, F.Calderon, A.Fernandez-Bouzas "An accurate and efficient Bayesian method for automatic segmentation of brain MRI" IEEE Trans Med Imag vol. 21(08) Aout 2002, p 934-945.
[7] H.Yang, "Signal processing for Magnetic Resonance Imaging and Spectroscopy" Marcel Dekker London, 2002 chapter 13.
[8] R.Guillemaud, M.Brady, "Estimating the bias field of MR images" IEEE Trans Med Imag vol 16 (3) 1997, pp 238-251.
[9] K.Van Leemput, F.Maes, D.Vandermeulen, P.Suetens, "Automatic segmentation of brain tissues and MR bias field correction using a digital brain atlas" Proceedings of MICCAI-98 vol 1496 of Lecture notes in computer sciences, Springer 1998, pp1222-1229.
[10] F.Bello, A.C.F.Colchester, "Measuring global and local spatial correspondence using information theory"Proceedings of MICCAI-98 volume 1496 of Lecture notes in computer science, Springer 1998, pp 964-973.