摘要
为了实现颈动脉血管的高精度配准,进而可以计算出颈动脉血管的位移场,提出了一种基于目标形状特征和纹理特征的迭代配准的方法,这在医学诊疗中具有重要意义.目标图像的匹配可以通过提取形状轮廓,利用形状上下文信息实现;与此同时,SIFT特征在目标匹配时具有很好的鲁棒性,图像间的稠密对应关系可以利用图像中逐像素的SIFT特征来建立.将二者相结合可以达到一个很好的配准效果,进一步利用迭代的思想,配准精度再次得到提高.配准颈动脉血管的实验结果证明了其具有很好的鲁棒性,并且在精度上超越了传统的配准方法,在时间上也具有可接受的水平.
To realize high accuracy registration of carotid artery,and then the displacement field in carotid artery can be calculated,an iterative registration method based on shape feature and textural feature is proposed in this paper. It is of great significance in medical diagnosis and treatment. Image matching can be realized by extracting the shape information and using shape context descriptor.Meanwhile, the SIFT feature has good robustness in target matching, so dense pixel-to-pixel correspondences between two images can be built by getting per-pixel SIFT descriptor. By combining the two ways,this method can obtain a good registration result. Furthermore,the result will be better after iteration. The experiment result of carotid artery registration proves that the proposed method has robustness,higher accuracy and acceptable time consumption.
作者
张剑华
盖铖
陈胜勇
ZHANG Jianhua;GAI Cheng;CHEN Shengyong(College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310014, China)
出处
《浙江工业大学学报》
CAS
北大核心
2018年第1期33-37,共5页
Journal of Zhejiang University of Technology
基金
国家自然科学基金资助项目(U1509207
61325019)