摘要
非刚性医学图像配准是医学图像研究领域的热门专题之一,具有重要的临床应用价值。本文提出一种改进的Demons算法,将灰度守恒模型和局部结构张量守恒模型结合起来,构造一个新的能量函数处理多模态配准问题,然后采用L-BFGS算法优化能量函数,解决复杂三维数据的优化问题,并采用多尺度分层细化的思想解决大形变配准。实验表明,本文算法对大形变和多模态三维医学图像配准都有较好的效果。
Non-rigid medical image registration is a popular subject in the research areas of the medical image and has an important clinical value. In this paper we put forward an improved algorithm of Demons, together with the conservation of gray model and local structure tensor conservation model, to construct a new energy function processing multi-modal registration problem. We then applied the L-BFGS algorithm to optimize the energy function and solve complex three-dimensional data optimization problem. And finally we used the multi-scale hierarchical refinement ideas to solve large deformation registration. The experimental results showed that the proposed algorithm for large deformation and multi-modal three-dimensional medical image registration had good effects.
出处
《生物医学工程学杂志》
EI
CAS
CSCD
北大核心
2014年第1期161-165,共5页
Journal of Biomedical Engineering
基金
国家自然科学基金资助项目(60963003)
教育部科学技术研究重点课题资助(206080)
航空科学基金资助项目(08ZC56002)
江西省自然科学基金资助项目(2009GZS1109)
江西省国际合作项目资助(2060402108)
江西省教育厅科学技术研究项目资助(GJJ09018)
关键词
DEMONS算法
结构张量守恒
非刚性配准
三维图像配准
demons algorithm
conservation of structure tensor
non-rigid registration
3D image registration
