计算机应用 ›› 2019, Vol. 39 ›› Issue (11): 3366-3369.DOI: 10.11772/j.issn.1001-9081.2019040611

• 虚拟现实与多媒体计算 • 上一篇    下一篇

基于空间约束的模糊C均值聚类肝脏CT图像分割

王荣淼1, 张峰峰1,2, 詹蔚3, 陈军1, 吴昊1   

  1. 1. 苏州大学 机电工程学院, 江苏 苏州 215131;
    2. 苏州大学 苏州纳米科技协同创新中心, 江苏 苏州 215123;
    3. 苏州大学附属第一医院, 江苏 苏州 215006
  • 收稿日期:2019-04-15 修回日期:2019-06-21 出版日期:2019-11-10 发布日期:2019-08-21
  • 通讯作者: 张峰峰
  • 作者简介:王荣淼(1995-),男,江苏南通人,硕士研究生,主要研究方向:医学图像处理、三维可视化;张峰峰(1979-),男,山东日照人,副教授,博士,主要研究方向:医疗机器人、虚拟手术仿真;詹蔚(1981-),男,江苏无锡人,工程师,硕士,主要研究方向:肿瘤放射治疗;陈军(1995-),男,安徽广德人,硕士研究生,主要研究方向:虚拟现实技术与仿真;吴昊(1995-),女,江苏常州人,硕士研究生,主要研究方向:虚拟手术仿真。
  • 基金资助:
    国家863计划项目(2015AA043201)。

Liver CT images segmentation based on fuzzy C-means clustering with spatial constraints

WANG Rongmiao1, ZHANG Fengfeng1,2, ZHAN Wei3, CHEN Jun1, WU Hao1   

  1. 1. College of Mechanical and Electrical Engineering, Soochow University, Suzhou Jiangsu 215131, China;
    2. Collaborative Innovation Center of Suzhou Nano Science and Technology, Soochow University, Soochow Jiangsu 215123, China;
    3. The First Affiliated Hospital of Soochow University, Suzhou Jiangsu 215006, China
  • Received:2019-04-15 Revised:2019-06-21 Online:2019-11-10 Published:2019-08-21
  • Supported by:
    This work is partially supported by the National High Technology Research and Development Program of China (2015AA043201)

摘要: 传统模糊C均值(FCM)聚类算法应用于肝脏CT图像分割时仅考虑像素本身特征,无法解决灰度不均匀造成的影响以及肝脏边界模糊造成的边界泄露的问题。为解决上述问题,提出一种结合空间约束的模糊C均值(SFCM)聚类分割算法。首先,使用二维高斯分布函数构建卷积核,利用该卷积核对源图像进行空间信息提取得到特征矩阵;然后,引入空间约束惩罚项,更新并优化目标函数得到新的迭代方程;最后,通过多次迭代,完成对肝脏CT图像的分割。实验结果表明,SFCM算法分割具有灰度不均匀和边界粘连的肝脏CT图像时得到的肝脏轮廓形状更加规则,准确率达到92.8%,比FCM和直觉模糊C均值(IFCM)算法的分割准确率分别提升了2.3和4.3个百分点,过分割率分别降低了4.9和5.3个百分点。

关键词: 模糊C均值算法, 空间约束, 图像分割, 肝脏CT, 灰度不均匀, 边界泄露

Abstract: Traditional Fuzzy C-Means (FCM) clustering algorithm only considers the characteristics of a single pixel when applied to liver CT image segmentation, and it can not overcome the influence of uneven gray scale and the problem of boundary leakage caused by blurred liver boundary. In order to solve the problems, a Spatial Fuzzy C-Means (SFCM) clustering segmentation algorithm combined with spatial constraints was proposed. Firstly, the convolution kernel was constructed by using two-dimensional Gauss distribution function, and the feature matrix could be obtained by using the convolution kernel to extract the spatial information of the source image. Then, the penalty term of spatial constraint was introduced to update and optimize the objective function to obtain a new iteration equation. Finally, the liver CT image was segmented by using the new algorithm. As shown in results, the shape of liver contour splited by SFCM is more regular when segmenting liver CT images with gray unevenness and boundary leakage. The accuracy of SFCM reaches 92.8%, which is 2.3 and 4.3 percentage points higher than that of FCM and Intuitionistic Fuzzy C-Means (IFCM). Also, over-segmentation rate of SFCM is 4.9 and 5.3 percentage points lower than that of FCM and IFCM.

Key words: Fuzzy C-means (FCM) algorithm, spatial constraint, image segmentation, liver CT, gray unevenness, boundary leakage

中图分类号: