欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对基于互信息的图像配准容易出现局部极值的问题，提出了一种交互方差和互信息相结合的测度方法，应用于肺部PET-CT图像的配准中，并根据自由形变的思想，结合B样条曲面技术，实现了可以控制局部变形的肺部图像的非刚性配准。实验结果表明：该算法能有效地实现肺部图像的配准，使结节在CT图像中解剖结构区域和PET图像中功能高亮区域较好地重叠在一起。
英文摘要：
Local minima problems can not be easily avoided in image registration based on mutual information. A measuring method was developed which combines the cross variance with the mutual information for lung PET-CT registration. The local deformation of lung images was effectively controlled based on the idea of free deformation and B-spline surface technology. Experimental results show that the developed method can realize lung image registration, while overlapping the nodule lesion anatomical structure area in the CT image and the nodule highlighted functional area in the PET image.
同期刊论文项目
同项目期刊论文
A cloud scheduling strategy based on the combination of Fuzzy Quotient Space Cluster and an Improved
Lung CT image segmentation based on combined multi-scales watershed method and region growing method
期刊信息
位置：