ESTIMATION OF CSF, WHITE AND GRAY-MATTER VOLUMES IN HYDROCEPHALIC CHILDREN USING FUZZY CLUSTERING OF MR-IMAGES

An algorithm and set of procedures for measuring volumes of cerebrospi nal fluid (CSF), white matter, and gray matter from transaxial magneti c resonance images (MRI) of the brain are described. The algorithm is a variant of the fuzzy c-means clustering method for texture identific ation. This technique is used mainly to solve the problem of volume av eraging of tissue compartments, but also has other advantages. It is f ast, accurate, and relatively operator independent. Furthermore, it do es not depend on statistical assumptions such as data normality, nor d oes it require any a priori heuristics. The procedure was tested succe ssfully on imaged phantoms of known volume composition and compared wi th results achieved using a standard morphometric measurement approach . The procedure was also applied to brain MRIs of three clinically nor mal children and three age-matched children with hydrocephalus using b oth proton density and T-2-weighted images. The algorithm was able to detect the expected increased amounts of CSF and decreased amounts of white matter characteristic of the hydrocephalic brain.