腰椎间盘突出症MR图像分割新算法

New Algorithm for MR Image Segmentation of the Lumbar Intervertebral Disc Protrusion

针对标准模糊C均值图像分割算法进行了改进,提出了一种针对T2加权腰椎间盘突出症核磁共振图像分割的新算法。该算法将图像从像素空间映射到其灰度统计直方图空间,并利用像素的邻域特性,对隶属度函数作出了修正。实验结果表明,该算法能快速有效地分割图像,并在器官轮廓分割中有效,具有较好的抗噪能力。

The Image segmentation algorithm of standard fuzzy C-means is improved. The paper proposes a new image segmentation algorithm in T2-weighted Magnetic Resonance Images. With the modified algorithm, images can be mapped to gray-scale histogram space from pixel space. Membership funtion can be improved by the full use of pixel＇s neighborhood feature. The experimental result shows that the algorithm can divide the image effectively quickly, and is effective in the organ contour, and has good performance of resisting noise.