论文标题
贪婪政策搜索的MRI实验设计
Experimental design for MRI by greedy policy search
论文作者
论文摘要
在当今的临床实践中，磁共振成像（MRI）通常通过相关傅立叶结构域的子采样来加速。当前，这些子采样策略的构建（称为实验设计）主要依赖于启发式方法。我们建议通过政策梯度方法来学习加速MRI的实验设计策略。出乎意料的是，我们的实验表明，对目标的简单贪婪近似几乎可以通过更通用的非怪兽方法进行解决方案。我们为这种现象提供了部分解释，该现象源于非怪兽目标的梯度估计中的较大差异，并在实验上验证了这种差异在将其策略调整到各个MR图像中会缩减非怪异模型。我们从经验上表明，这种适应性是改善亚次采样设计的关键。
In today's clinical practice, magnetic resonance imaging (MRI) is routinely accelerated through subsampling of the associated Fourier domain. Currently, the construction of these subsampling strategies - known as experimental design - relies primarily on heuristics. We propose to learn experimental design strategies for accelerated MRI with policy gradient methods. Unexpectedly, our experiments show that a simple greedy approximation of the objective leads to solutions nearly on-par with the more general non-greedy approach. We offer a partial explanation for this phenomenon rooted in greater variance in the non-greedy objective's gradient estimates, and experimentally verify that this variance hampers non-greedy models in adapting their policies to individual MR images. We empirically show that this adaptivity is key to improving subsampling designs.
