医学图像分割技术仿真研究

医学图像分割技术仿真研究

范继红;张健

【期刊名称】《计算机仿真》 【年(卷),期】2011(028)012

【摘要】研究医学图像优化分割问题,医学诊断图像要求位置精确,并应精确标注.针对放射治疗以及外科手术过程中对人体器官组织医学图像分割的极大依赖,传统的医学图像分割算法难以分割出清晰有用的图像区域,为了提高分割精度,提出了一种精确的半自动医学图像分割算法,用于提高图像分割的清晰度.首先,通过用户的简单初始输入,确定目标器官和非目标器官的初始定位.然后,根据用户提供的初始定位的统计特性,利用条件随机场模型(CRF)和Graph Cut算法在图像中精确定位器官并进行分割.根据统计特性的分割结果可以在相关医学图像中重复使用以提高分割效率.试验表明,利用CRF和Graph Cut能有效的提高医学图像分割准确度,获得满意的医学图像分割结果.%Planning radiotherapy and surgical procedures usually require onerous manual segmentation of anatomical structures from medical images. In this paper, we presented a semi - automatic and accurate segmentation method to dramatically reduce the time and effort required for expert users. This was accomplished by giving a user an intuitive graphical interface to indicate samples of target and non - target tissue by loosely drawing a few brush strokes on the image. We used these brush strokes to provide the statistical input for a Conditional Random Field (CRF) and graph cuts based segmentation. A new feature of our method is that the