Automated segmentation of the cerebrospinal fluid and the lateral ventricles from human brain MR images

This paper presents a computer-aided diagnosis (CAD) system, which be able to segment the whole brain, the brain portions, the cerebrospinal fluid (CSF) and the lateral ventricles from human brain MR images, and then to give the volumes and the 3-D volume renderings. In the system, the whole brain and the brain portions are automatically segmented by using previously developed software (Hata et al, IEEE SMC-C, 2000). In this paper, we introduce a new concept of a representative line to segment the CSF and the lateral ventricles. The representative line is automatically detected by inferring its direction with evaluating the location in the head, the position in the CSF, and the shape of the line. The inference is preformed with fuzzy inference technique. The developed system was applied to MR volumes of 20 normal subjects, 20 Alzheimer disease and 20 hydrocephalus patients. The segmentation error ratio was 1.98% in comparison with the volumes of manually delineated region. This allows us to experimentally characterize modes of variation that are indicative of disease processes.