Combining Robust Expectation Maximization and Mean Shift algorithms for Multiple Sclerosis Brain Segmentation

A new algorithm for segmentation of white matter lesions and normal appearing brain tissues in Multiple Sclerosis (MS) is presented. Two different segmentation methods are combined in order to have a better and more meaningful segmentation. On the one hand, a local segmentation approach, the Mean Shift, is used to generate local regions in our images. On the other hand, a variant of the Expectation Maximization is employed to classify these regions as Normal Appearing Brain Tissues (NABT) or lesions. Validation of this method is performed with synthetic and real data. The output is a more powerful algorithm that employs at the same time global and local information to improve image segmentation.

[1]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  Benoit M. Dawant,et al.  Morphometric analysis of white matter lesions in MR images: method and validation , 1994, IEEE Trans. Medical Imaging.

[4]  G. Comi,et al.  Comparison of MRI criteria at first presentation to predict conversion to clinically definite multiple sclerosis. , 1997, Brain : a journal of neurology.

[5]  S. Reingold,et al.  The role of magnetic resonance techniques in understanding and managing multiple sclerosis. , 1998, Brain : a journal of neurology.

[6]  D. Louis Collins,et al.  Design and construction of a realistic digital brain phantom , 1998, IEEE Transactions on Medical Imaging.

[7]  Aggelos K. Katsaggelos,et al.  Hybrid image segmentation using watersheds and fast region merging , 1998, IEEE Trans. Image Process..

[8]  Object-Oriented Real-Time.  Third IEEE International Symposium on , 2000 .

[9]  Mark S. Drew,et al.  Towards automatic segmentation of MS lesions in PD/T2 MR images , 2000, Medical Imaging: Image Processing.

[10]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[11]  Alan C. Evans,et al.  Automatic "pipeline" analysis of 3-D MRI data for clinical trials: application to multiple sclerosis , 2002, IEEE Transactions on Medical Imaging.

[12]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[14]  Grégoire Malandain,et al.  Hierarchical segmentation of multiple sclerosis lesions in multi-sequence MRI , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[15]  Pierre Hellier,et al.  STREM: A Robust Multidimensional Parametric Method to Segment MS Lesions in MRI , 2005, MICCAI.

[16]  Verónica Médina-Bañuelos,et al.  Data-driven brain MRI segmentation supported on edge confidence and a priori tissue information , 2006, IEEE Transactions on Medical Imaging.

[17]  Hayit Greenspan,et al.  Segmentation of brain MRI by adaptive mean shift , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[18]  Peter Filzmoser,et al.  Robust fitting of mixtures using the trimmed likelihood estimator , 2007, Comput. Stat. Data Anal..

[19]  Hayit Greenspan,et al.  LESION DETECTION IN NOISY MR BRAIN IMAGES USING CONSTRAINED GMM AND ACTIVE CONTOURS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[20]  Jean-Paul Armspach,et al.  An a contrario approach for outliers segmentation: Application to Multiple Sclerosis in MRI , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.