摘要
利用颅脑CT图像各个主要组成区域的CT值分布差异和形态学特点等先验知识,以及DICOM图像文件提供的有关信息实现了颅脑CT图像中包括头架、头皮、颅骨、脑脊液和脑实质等区域的完全自动化分割。该算法对复杂图像处理研究的预处理,可视化三维重建,脑萎缩定量诊断以及数字化脑图谱制作等方面均具有的应用价值。
Based on the prior knowledge that there are distinct difference of CT values and morphologic characteristics among
different regions of cerebral CT images, and some information stored in the DICOM file, we have been successful in
automatically segmenting the different regions of cerebral CT images, including the headrest, scalp, skull, CSF and the
brain. This method could be used as the pre-process of more advanced algorithm, 3D reconstruction, quantification of
cerebral atrophy and digital brain atlas.
出处
《中国医疗器械杂志》
CAS
2004年第3期168-171,共4页
Chinese Journal of Medical Instrumentation
基金
安徽省教委自然科学基金
