基于空间模糊C均值与区域生长的腹部CT序列图像肾脏自动分割

来源期刊:中南大学学报(自然科学版)2014年第10期

论文作者:王晓红 赵于前 廖苗 刘苗苗

文章页码:3463 - 3470

关键词:CT序列;肾脏分割;各向异性扩散滤波;空间模糊C均值;区域生长

Key words:CT scans; kidneys segmentation; anisotropic diffusion filter; spatial fuzzy C-means; region growing

摘    要:针对腹部CT序列图像因相邻器官灰度相似以及部分容积效应等造成的肾脏分割困难问题,提出一种基于空间模糊C均值以及区域生长的腹部CT序列图像肾脏自动分割方法。首先应用经典阈值法以及形态学重构去除肋骨和脊椎,然后对图像各向异性扩散滤波,再利用空间模糊C均值对肾脏图像进行聚类。当相邻切片分割结果的相对面积变化率超出预定范围时,算法自动选择区域生长法对该图像进行重新分割,且区域生长法受空间模糊C均值算法的约束。最后,应用形态学滤波对分割结果进行处理。通过对CT序列图像进行肾脏分割试验,结果表明本文算法是可行和有效的。

Abstract: Considering that the kidneys segmentation from abdominal computer tomography (CT) scans is a great challenge for image processing because of the gray level similarity of adjacent organs, partial volume effects and so on, a novel method was proposed based on the spatial fuzzy C-means and region growing to segment kidneys from CT scans automatically. Firstly, the classical threshold method and the morphological reconstruction were applied to remove spine and fibs. Then the anisotropic diffusion filter was used to smooth the images, followed by the spatial fuzzy C-means to classify pixels belonging to kidneys. When the change rate of kidneys region area between two adjacent slices exceeds a defined range, the proposed method switches automatically to segment kidneys by region growing, whose seeds were constrained by the spatial fuzzy C-means. Finally, the morphological filtering method was used to smooth the segmented results. The results show that the proposed method can segment kidneys from CT scans successfully and effectively.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号