Rule-Based Labeling of CT Head Image

A rule-based approach to the labeling of computed tomography (CT) head images containing intracerebral brain hemorrhage (ICH) is presented in this paper. Fully automated segmentation of CT image is achieved by the system composed of two components: an unsupervised fuzzy clustering algorithm and a rule-based system. The unsupervised fuzzy clustering algorithm outlines the regions in the input CT head image. Extracted regions are spatially localized and have uniform brightness. Region features and region-neighborhood relations are used to create the knowledge base for rule-based system. The rule-based system performs the labeling of the segmented regions into one of the following labels: background, skull, brain, ICH, and calciications. The rules are determined from the a priori knowledge about the relations between the CT image regions and their characteristics. The system has been applied to a number of real CT head images and shown satisfactory results.