Automatic skull stripping in brain MRI based on local moment of inertia structure tensor

A new automatic skull stripping method for fluid attenuated inversion recovery (FLAIR) MR images is proposed for the quantification of brain volume in multiple sclerosis (MS) patients. The proposed method is based on the use of local moment of inertia structure tensor and morphological operators. The local moment of inertia structure tensor is used to determine the boundary of the brain, instead of the conventional edge detection algorithms. Data from 30 MS patients were processed by the proposed method and the Brain Extraction Tool (BET); the results of which were also compared with manual segmentation. It was shown that the proposed method was able to produce more accurate results.

[1]  Richard M. Leahy,et al.  Surface-based labeling of cortical anatomy using a deformable atlas , 1997, IEEE Transactions on Medical Imaging.

[2]  Anders M. Dale,et al.  A hybrid approach to the Skull Stripping problem in MRI , 2001, NeuroImage.

[3]  Arthur W. Toga,et al.  A meta-algorithm for brain extraction in MRI , 2004, NeuroImage.

[4]  Frederik Barkhof,et al.  Determinants of cerebral atrophy rate at the time of diagnosis of multiple sclerosis. , 2007, Archives of neurology.

[5]  B. Sakmann,et al.  Nonlinear anisotropic diffusion filtering of three-dimensional image data from two-photon microscopy. , 2004 .

[6]  Richard M. Leahy,et al.  BrainSuite: An Automated Cortical Surface Identification Tool , 2000, MICCAI.

[7]  Bostjan Likar,et al.  A Review of Methods for Correction of Intensity Inhomogeneity in MRI , 2007, IEEE Transactions on Medical Imaging.

[8]  Anders M. Dale,et al.  Cortical Surface-Based Analysis I. Segmentation and Surface Reconstruction , 1999, NeuroImage.

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

[10]  Marco Rovaris,et al.  Intercenter agreement of brain atrophy measurement in multiple sclerosis patients using manually‐edited SIENA and SIENAX , 2007, Journal of magnetic resonance imaging : JMRI.

[11]  Gregory G. Brown,et al.  Quantitative evaluation of automated skull‐stripping methods applied to contemporary and legacy images: Effects of diagnosis, bias correction, and slice location , 2006, Human brain mapping.

[12]  Gérard G. Medioni,et al.  Motion segmentation with accurate boundaries - a tensor voting approach , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  M. Ramanathan,et al.  CSF dynamics and brain volume in multiple sclerosis are associated with extracranial venous flow anomalies: a pilot study. , 2010, International angiology : a journal of the International Union of Angiology.

[14]  R. Leahy,et al.  Magnetic Resonance Image Tissue Classification Using a Partial Volume Model , 2001, NeuroImage.

[15]  Robert T. Schultz,et al.  Segmentation and Measurement of the Cortex from 3D MR Images , 1998, MICCAI.