低对比度医学图像全自动分割算法

Low-Contrast Medical Images Automatic Segmentation Algorithm

由于医学图像的对比度较低以及各种组织器官的边缘往往较为模糊,医学图像的分割是医学图像处理中的一个经典难题。如果能将各种分割对象的先验信息加入到分割算法中,将会改善分割效果。针对CT图像中的前列腺器官分割问题,利用水平集函数获得初始分割轮廓,结合从手工分割图像中获得的形状和纹理先验信息,采用遗传算法来演化分割轮廓。仿真实验结果证明该方法能有效地分割出低对比度的医学器官。

Image segmentation is a crucial step in a wide range of medical image processing systems. In this paper, a prostate segmentation method based on searching fitting curve is proposed by considering the shape and texture information as the prior knowledge. Then the prior knowledge is merged into active contour model with its contour evolution that is evolved by a genetic algorithm technique. The proposed method has some advantages over classical level set methods for the images with weak and fuzzy edges. The simulation experiments verify the effectiveness of the proposed method.