Fully Automated Segmentation of Cerebral Ventricles from 3-D SPGR MR Images using Fuzzy Representative Line

Generating surface shaded display images and measuring the volumes of cerebral ventricles using 3-D SPGR MR images will help to diagnose many types of cerebral diseases with quantitatively and qualitatively. However, manual segmentation of cerebral ventricles is time-consuming and is subject to inter- and intra-operator variation. This article proposes a fully automated method for segmenting cerebrospinal fluid (CSF) and cerebral ventricles from MR images. Our method segments the cerebral ventricles by using a representative line (RL), which can represent the abstract of the shape and position of the cerebral ventricles. The RL is found by fuzzy If-Then rules that can implement physicians’ knowledge on the cerebral ventricles. The proposed method was applied to MR volumes of 20 normal subjects, 20 Alzheimer disease (AD) and 20 normal pressure hydrocephalus (NPH) patients. The segmentation error ratio of the lateral ventricles was 1.98% in comparison with the volumes of manually delineated region by a physician. Using the proposed method, we found that patients of NPH significantly increased the ratio of volume of the lateral ventricles to the total CSF volume in comparison with that of AD (significance level < 0.001)