Liver DCE-MRI Registration in Manifold Space Based on Robust Principal Component Analysis.
Liver DCE-MRI Registration in Manifold Space Based on Robust Principal Component Analysis.
复制标题
基于稳健主成分分析的肝脏 DCE-MRI 歧管空间配准
DOI：
10.1038/srep34461
复制
发表时间：
2016-09-29
影响因子：
4.6
通讯作者：
Chen W
中科院分区：
文献类型：
--
作者：
Feng Q;Zhou Y;Li X;Mei Y;Lu Z;Zhang Y;Feng Y;Liu Y;Yang W;Chen W
动态对比增强磁共振（DCE-MR）在肝脏成像注册中的一个技术挑战是由造影剂引起的强度变化。这种变化导致传统的基于强度的配准方法失效。为了解决这一问题，提出了一种基于流形的肝脏DCE-MR时间序列配准框架。我们假设肝脏DCE-MR时间序列位于低维流形上，并确定帧之间的内在相似性。在得到的流形基础上，通过每帧沿测地线路径向模板图像渐变，将两幅不同图像的大变形分解为流形上相邻图像之间的一系列小变形。此外，流形构造在模板图像的自动化选择中很重要，模板图像是测地线平均值的近似。进行稳健的主成分分析，从对比剂引起的强度变化中分离运动成分；利用运动引起的分量来指导配准，消除对比度增强的影响。进一步对临床数据集注册进行目视检查和定量评估。实验表明，该方法在保留对比度增强结构拓扑结构的同时，有效地减少了运动，提高了配准性能。
A technical challenge in the registration of dynamic contrast-enhanced magnetic resonance (DCE-MR) imaging in the liver is intensity variations caused by contrast agents. Such variations lead to the failure of the traditional intensity-based registration method. To address this problem, a manifold-based registration framework for liver DCE-MR time series is proposed. We assume that liver DCE-MR time series are located on a low-dimensional manifold and determine intrinsic similarities between frames. Based on the obtained manifold, the large deformation of two dissimilar images can be decomposed into a series of small deformations between adjacent images on the manifold through gradual deformation of each frame to the template image along the geodesic path. Furthermore, manifold construction is important in automating the selection of the template image, which is an approximation of the geodesic mean. Robust principal component analysis is performed to separate motion components from intensity changes induced by contrast agents; the components caused by motion are used to guide registration in eliminating the effect of contrast enhancement. Visual inspection and quantitative assessment are further performed on clinical dataset registration. Experiments show that the proposed method effectively reduces movements while preserving the topology of contrast-enhancing structures and provides improved registration performance.
登录
查看更多内容
影响因子：
10.9
作者：
Hamy, Valentin;Dikaios, Nikolaos;Atkinson, David
通讯作者：
Atkinson, David
影响因子：
2.5
作者：
Rajaraman, Sivaramakrishnan;Rodriguez, Jeffrey J.;Graff, Christian;Altbach, Maria I.;Dragovich, Tomislav;Sirlin, Claude B.;Korn, Ronald L.;Raghunand, Natarajan
通讯作者：
Raghunand, Natarajan
影响因子：
10.6
作者：
Ghaffari, Aboozar;Fatemizadeh, Emad
通讯作者：
Fatemizadeh, Emad
影响因子：
3
作者：
Kuybeda, Oleg;Frank, Gabriel A.;Bartesaghi, Alberto;Borgnia, Mario;Subramaniam, Sriram;Sapiro, Guillermo
通讯作者：
Sapiro, Guillermo
影响因子：
3.5
作者：
Melbourne, A.;Atkinson, D.;Hawkes, D.
通讯作者：
Hawkes, D.