Three Dimensional Tissue Classifications in MR Brain Images
This paper presents an algorithm for classifying different tissue types in T1-weighted MR brain images using fuzzy segmentation. The main aim in this study is to compensate for the blurring effect on tissue boundaries due to partial volume effects. This paper is organized as follows: first, an adaptive greedy contour model has been developed to separate the intracranial volume (ICV) from the scalp and skull. Second, in order to deal with the problem of the partial volume effect, an algorithm for fuzzy segmentation is presented which has integrated fuzzy spatial affinity with statistical distributions of image intensities for each of the three tissues – cerebrospinal fluid, white matter and grey matter. This algorithm is tested on well-established simulated MR brain volumes to generate an extensive quantitative comparison with different noise levels and different slice thicknesses ranging from 1mm to 5mm. Finally, the results of this algorithm on clinical MR brain images are demonstrated.
KeywordsGrey Matter Percentage Error Partial Volume Effect Active Contour Model Fuzzy Classification
Unable to display preview. Download preview PDF.
- 1.Guttmann, C.R.G., Jolesz, F.A., Kikinis, R., Killiany, R.J., Moss, M.B., Sandor, T.: White Matter Changes with Normal Aging. Neurology 50, 972–978 (1998)Google Scholar
- 3.Parveen, R., Todd-Pokropek, A.: Segmentation of MR Brain Images Using Region Growing Combined with an Active Contour Model. In: Conf. Proc. Comp. Aided Radiol. Surg. (2002)Google Scholar
- 8.Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. In: IEEE Proc. 1st International Conf. Comp. Vis., pp. 259–268 (1987)Google Scholar
- 10.Parveen, R., Ruff, C., Mcdonald, D., Lambrou, T., Todd-Pokropek, A.: Three-Dimensional Voxel Morphometry of MR Brain Images Using Deformable Models, Relative Fuzzy Clasification and Spatial Affinity. In: Proc. MIUA 2004, pp. 117–120 (2004)Google Scholar
- 11.Rosenfield, A.: Connectivity in Digital Pictures. J. Assoc. Comp. Mach. 17, 146–160 (1970)Google Scholar