Unsupervised MRI segmentation with spatial connectivity

Magnetic Resonance Imaging (MRI) offers a wealth of information for medical examination. Fast, accurate and reproducible segmentation of MRI is desirable in many applications. We have developed a new unsupervised MRI segmentation method based on k-means and fuzzy c-means (FCM) algorithms, which uses spatial constraints. Spatial constraints are included by the use of a Markov Random Field model. The result of segmentation with a four-neighbor Markov Random Field model applied to multi-spectral MRI (5 images including one T1-weighted image, one Proton Density image and three T2-weighted images) in different noise levels is compared to the segmentation results of standard k-means and FCM algorithms. This comparison shows that the proposed method outperforms previous methods.

[1]  J. Laurie Snell,et al.  Markov Random Fields and Their Applications , 1980 .

[2]  Xavier Descombes,et al.  Spatio-temporal fMRI analysis using Markov random fields , 1998, IEEE Transactions on Medical Imaging.

[3]  Thrasyvoulos N. Pappas.  An adaptive clustering algorithm for image segmentation , 1992, IEEE Trans. Signal Process..

[4]  R P Velthuizen,et al.  Review and evaluation of MRI nonuniformity corrections for brain tumor response measurements. , 1998, Medical physics.

[5]  Jongwon Kim,et al.  Volumetric object reconstruction using the 3D-MRF model-based segmentation [magnetic resonance imaging] , 1997, IEEE Transactions on Medical Imaging.

[6]  Hamid Soltanian-Zadeh,et al.  Semisupervised segmentation of MRI stroke studies , 1997, Medical Imaging.

[7]  Nuggehally Sampath Jayant,et al.  An adaptive clustering algorithm for image segmentation , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[8]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[9]  M. Brandt,et al.  Estimation of CSF, white and gray matter volumes in hydrocephalic children using fuzzy clustering of MR images. , 1994, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[10]  Ron Kikinis,et al.  Markov random field segmentation of brain MR images , 1997, IEEE Transactions on Medical Imaging.

[11]  L O Hall,et al.  Review of MR image segmentation techniques using pattern recognition. , 1993, Medical physics.