A two-stage human brain MRI segmentation scheme using fuzzy logic

The authors have developed a two-stage image segmentation scheme using fuzzy logic. Based on the scheme, a two-stage fuzzy system has been built for segmenting human brain MR images. The first stage is a fuzzy rule-based system that assigns memberships to pixels, classifies the pixels that have only one high membership and calculates the initial conditions for the next stage. The second stage is the fuzzy c-means algorithm, which classifies the undetermined pixels. Preliminary segmentation of the human brain MR images shows that the two-stage fuzzy system could accurately determine white matter, gray matter, cerebrospinal fluid and HIV+lesion. The results were visually confirmed by expert observers. The satisfactory results achieved in this paper suggest the feasibility of developing similar segmentation systems for other types of images and the possibility of extending the two-stage scheme to multiple-stage schemes.<<ETX>>

[1]  D G Brunder,et al.  Measurement of brain compartment volumes in MR using voxel composition calculations. , 1991, Journal of computer assisted tomography.

[2]  Gilbert R. Hillman,et al.  Measurement of brain compartment volumes from MRI data using region growing and mixed-volume methods , 1992, Other Conferences.

[3]  S. Strother,et al.  Graphical Analysis of MR Feature Space for Measurement of CSF, Gray‐Matter, and White‐Matter Volumes , 1993, Journal of computer assisted tomography.

[4]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[5]  James C. Bezdek,et al.  Fuzzy mathematics in pattern classification , 1973 .

[6]  Lawrence O. Hall,et al.  Knowledge-based classification and tissue labeling of MR images of human brain , 1993, IEEE Trans. Medical Imaging.

[7]  Sang Uk Lee,et al.  On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques , 1990, Pattern Recognit..

[8]  J. C. Dunn,et al.  A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters , 1973 .

[9]  James C. Bezdek,et al.  A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain , 1992, IEEE Trans. Neural Networks.

[10]  S P Raya,et al.  Low-level segmentation of 3-D magnetic resonance brain images-a rule-based system. , 1990, IEEE transactions on medical imaging.

[11]  Thomas A. Kent,et al.  Segmentation of rat brain MR images using a hybrid fuzzy system , 1994, NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intellige.