摘要
根据肝癌病灶的特征用计算机辅助CT图像诊断肝癌,达到辅助放射科医生诊断的目的.采用Snake算法提取肝脏组织,对已分割出的肝脏做相应的预处理后,通过选择合适的算法提取兴趣区,对比CT图像动脉期和静脉期或者平衡期的兴趣区以及提取兴趣区后剩余肝脏区域的灰度均值,对造影后典型肝癌进行判断.用自动化处理,对做过造影增强的腹部CT图片肝癌病例做初步筛选.结果表明,符合典型肝癌CT图片序列的病例89.5%可以被计算机自动筛选出来,为计算机辅助诊断提供了重要依据.
Our objective is to diagnose the liver cancer with the aid of CT images and the computer,and to help the radiologists to do better treatments.Our method is to extract the tissue of the liver by Snake algorithm and to do appropriate pretreatments on it and then to select the appropriate region of interest;finally by calculating the mean value of gray area of CT images of arterial and venous interest or the balanced area of interest and the remaining area of the liver,the diagnosis of typical liver cancer is made after the completion of angiography.Results show that a large number of contrast-enhanced abdominal CT cases for liver cancer are screened in a preliminary way.Our conclusion is that the typical cases in line with liver CT image sequences can be automatically screened out,so the computer plays an important role in computer-aided diagnosis of liver cancers.
出处
《甘肃科学学报》
2012年第1期60-64,共5页
Journal of Gansu Sciences
基金
咸宁学院校级青年项目(KY10054)
