分形理论在肝脏CT影像分割中的应用研究

Study of application of fractal dimension theory in segmentation of liver CT image

针对肝脏CT影像的特点,提出了基于分形理论的分割算法。根据分形维数反映图像复杂程度的定义,通过计算两次突变的分维数,来确定图像的灰度值范围,并利用该灰度值范围确定阈值。并通过实验,表明利用分形维数所得到的阈值进行分割处理较传统方法有较大改进,且该方法计算的肝脏边缘分维数也为今后评价肝脏是否发生病变提供参考数据。

The segmentation arithmetic based on the fractal dimension theory is proposed to the character of liver CT image.According that the number of fractal dimension is related to the complication of the image,the gray＇s value scope of image can be calculated through the fractal dimension of the break of the object and then the threshold can be constituted.The experiment result proves that threshold value through fractal dimension can achieve good effect compared with traditional method.Furthermore, the fractal dimensions of liver edge are with great value for the estimation of the health of the liver in the later research.