Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery
Bi-Linear Modeling of Data Manifolds for Dynamic-MRI Recovery
复制标题
DOI：
10.1109/tmi.2019.2934125
复制
发表时间：
2018-12
影响因子：
10.6
通讯作者：
Gaurav N. Shetty;K. Slavakis;Abhishek Bose;Ukash Nakarmi;G. Scutari;L. Ying
中科院分区：
文献类型：
--
作者：
Gaurav N. Shetty;K. Slavakis;Abhishek Bose;Ukash Nakarmi;G. Scutari;L. Ying
本文提出了一种新的双线性建模框架，通过流形学习和稀疏近似参数的数据恢复，并考虑其应用于动态磁共振成像（dMRI）。每个时域MR图像被看作是一个点，位于或接近一个光滑的流形，和标志点被识别，以简洁地描述点云。为了便于计算，降维模块生成界标点的低维/压缩再现。高保真MRI数据的恢复是通过求解线性解压缩算子的非凸最小化任务和局部近似潜在流形几何的地标点的仿射组合来实现的。还提供了一个算法，保证收敛到固定的解决方案的非凸最小化任务。上述框架利用所获取的数据的潜在时空模式和几何形状，而无需对外部数据或信息进行任何先前训练。模拟以及真实的心脏电影MRI数据的大量数值结果表明，与最先进的重建技术相比，所倡导的机器学习框架有了显著的改进。
This paper puts forth a novel bi-linear modeling framework for data recovery via manifold-learning and sparse-approximation arguments and considers its application to dynamic magnetic-resonance imaging (dMRI). Each temporal-domain MR image is viewed as a point that lies onto or close to a smooth manifold, and landmark points are identified to describe the point cloud concisely. To facilitate computations, a dimensionality reduction module generates low-dimensional/compressed renditions of the landmark points. Recovery of high-fidelity MRI data is realized by solving a non-convex minimization task for the linear decompression operator and affine combinations of landmark points which locally approximate the latent manifold geometry. An algorithm with guaranteed convergence to stationary solutions of the non-convex minimization task is also provided. The aforementioned framework exploits the underlying spatio-temporal patterns and geometry of the acquired data without any prior training on external data or information. Extensive numerical results on simulated as well as real cardiac-cine MRI data illustrate noteworthy improvements of the advocated machine-learning framework over state-of-the-art reconstruction techniques.