基于知识的颅内出血（ICH）三维医学图像分割方法

本文描述一种基于知识的三维医学图像自动分割方法，用于进行人体颅内出血(Intracranial Hemorrhage,ICH)的分割和分析。首先，数字化CT胶片，并自动对数字化后的胶片按照有无异常分类。然后，阀值结合模糊C均值聚类算法将图像分类成多个具有统一亮度的区域。最后，在先验知识以及预定义的规则的基础上，借助基于知识的专家系统将各个区域标记为背景、钙化点、血肿、颅骨、脑干。

Automatic Segmentation of Intracranial Hemorrhage by a Knowledge-Based Method

This paper presents a method for automatic segmentation and labeling of the human intracrenial hemorrhage (ICH) from computed tomography (CT) head images. CT Head images are first digitized from films and automatically classified as abnormal. In the following step, an unsuperdvised fuzzy clustering algorithm outlines the regions in the input CT head image.Extracted regions are spatially localized and have uniform brightness.Region features and regions-neighborhood relations are used to create the knowledge base for rule-based system.In the last phase,an rule-based expert system is used to perform image labeling.The proposed method has been applied to real patient CT images and has shown encouraging results.