摘要
针对当前在肝纤维化早期CT影像无法检测的问题,提出了基于多重分形理论的肝脏边缘粗糙度分析方法。该方法计算了图像像素点的粗粒化holder指数,并用核估计方法估计出图像与该粗粒化指数相对应的多重分形奇异频谱。实验结果表明,该方法能在肝纤维化早期分辨出肝脏CT影像边缘粗糙度的改变,而且与传统分形维方法相比效果更明显。
To solve the problem that liver fibrosis can not be detected by current CT images at early stage,this paper proposed an analysis of roughness of liver edge based on multifractal theory.Computed the coarse exponent of the image pixels,and then estimated its multifractal spectrum in the kernel estimation method.Experimental results show that the method can distinguish the change of live edge roughness of CT images at the early stage of liver fibrosis.Compared with the traditional fractal dimension method,moreover,it is more effective.
出处
《计算机应用研究》
CSCD
北大核心
2011年第6期2398-2400,共3页
Application Research of Computers
基金
上海市重点学科建设资助项目(S30501)
国家科技支撑资助项目(2008BAI08B02_6)
关键词
图像识别
多重分形
粗糙度
肝纤维化
CT影像
image recognition
multifractal theory
roughness
liver fibrosis
CT image