IMPROVING MAGNETIC RESONANCE RESOLUTION WITH SUPERVISED LEARNING.
IMPROVING MAGNETIC RESONANCE RESOLUTION WITH SUPERVISED LEARNING.
复制标题
DOI：
10.1109/isbi.2014.6868038
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Prince JL
中科院分区：
文献类型：
--
作者：
Jog A;Carass A;Prince JL
尽管磁共振（MR）成像（MRI）正在不断改进，但大量的临床数据以及较小程度上的研究数据是以较低的分辨率采集的。例如，标准做法是对T1加权（T1-w）磁化准备快速梯度回波（MPG）进行1 mm各向同性采集，然而，T2加权（T2-w）-由于其较长的弛豫时间（因此扫描时间更长）-仍然是常规采集的，切片厚度为2-5 mm，平面分辨率为2-3 mm。这在试图处理T1-w和T2时产生了明显的基本问题。数据在音乐会上。我们提出了一种自动监督学习算法来生成高分辨率数据。该框架类似于卢梭的脑幻觉工作，利用了基于回归的图像重建的新发展。我们提出了验证幻影和真实的数据，展示了最先进的超分辨率技术的改进。
Despite ongoing improvements in magnetic resonance (MR) imaging (MRI), considerable clinical and, to a lesser extent, research data is acquired at lower resolutions. For example 1 mm isotropic acquisition of T1-weighted (T1-w) Magnetization Prepared Rapid Gradient Echo (MPRAGE) is standard practice, however T2-weighted (T2-w)—because of its longer relaxation times (and thus longer scan time)—is still routinely acquired with slice thicknesses of 2–5 mm and in-plane resolution of 2–3 mm. This creates obvious fundamental problems when trying to process T1-w and T2-w data in concert. We present an automated supervised learning algorithm to generate high resolution data. The framework is similar to the brain hallucination work of Rousseau, taking advantage of new developments in regression based image reconstruction. We present validation on phantom and real data, demonstrating the improvement over state-of-the-art super-resolution techniques.