基于马尔可夫随机场的医学图像分割

Medical Image Segmentation Based on Markov Random Field

图像分割是一个经典难题,随着影像医学的发展,图像分割在医学应用中具有特殊的重要意义。马尔可夫随机场(Markov Random Field,即MRF)方法是图像分割中一个极为活跃的研究方向。本文介绍了基于马尔可夫随机场模型的一般理论与图像的关系。并对基于MRF的传统条件迭代模式算法(ICM)进行改进,在初始分割后,对图像的像素点分为两类:稳定点和不稳定点,用队列存储不稳定点,每次迭代只对队列里面的不稳定点进行计算,以减少运算量。实验结果表明,改进的算法能够大幅度提高计算效率。

Image segmentation is a classical problem. With the development of medical image, it has important meaning in the application of medical. Markov Random Field（MRF）method is an extremely active research field in image segmentation. This paper introduces the relationship between a general theory based on Markov random field model and the images. And the traditional ICM algorithm is improved. After the pre-segmentation of the image, image pixels are divided into two classes：the stable points and the unstable. The unstable points are stored by a queue. Only the unstable points are dealt with in each iteration to reduce computation of load. The experiment results indicate that the improved ICM algorithm can greatly improve the computational efficiency.