Zhang Chaoping, Karkalousos Dimitrios, Bazin Pierre-Louis, Coolen Bram F, Vrenken Hugo, Sonke Jan-Jakob, Forstmann Birte U, Poot Dirk H J, Caan Matthan W A
Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Neuroscience, Brain Imaging, Amsterdam, the Netherlands; Netherlands Cancer Institute, Amsterdam, the Netherlands.
Amsterdam UMC location University of Amsterdam, Biomedical Engineering and Physics, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Neuroscience, Brain Imaging, Amsterdam, the Netherlands.
Neuroimage. 2022 Dec 1;264:119680. doi: 10.1016/j.neuroimage.2022.119680. Epub 2022 Oct 12.
Quantitative MRI (qMRI) acquired at the ultra-high field of 7 Tesla has been used in visualizing and analyzing subcortical structures. qMRI relies on the acquisition of multiple images with different scan settings, leading to extended scanning times. Data redundancy and prior information from the relaxometry model can be exploited by deep learning to accelerate the imaging process. We propose the quantitative Recurrent Inference Machine (qRIM), with a unified forward model for joint reconstruction and R-mapping from sparse data, embedded in a Recurrent Inference Machine (RIM), an iterative inverse problem-solving network. To study the dependency of the proposed extension of the unified forward model to network architecture, we implemented and compared a quantitative End-to-End Variational Network (qE2EVN). Experiments were performed with high-resolution multi-echo gradient echo data of the brain at 7T of a cohort study covering the entire adult life span. The error in reconstructed R from undersampled data relative to reference data significantly decreased for the unified model compared to sequential image reconstruction and parameter fitting using the RIM. With increasing acceleration factor, an increasing reduction in the reconstruction error was observed, pointing to a larger benefit for sparser data. Qualitatively, this was following an observed reduction of image blurriness in R-maps. In contrast, when using the U-Net as network architecture, a negative bias in R in selected regions of interest was observed. Compressed Sensing rendered accurate, but less precise estimates of R. The qE2EVN showed slightly inferior reconstruction quality compared to the qRIM but better quality than the U-Net and Compressed Sensing. Subcortical maturation over age measured by a linearly increasing interquartile range of R in the striatum was preserved up to an acceleration factor of 9. With the integrated prior of the unified forward model, the proposed qRIM can exploit the redundancy among repeated measurements and shared information between tasks, facilitating relaxometry in accelerated MRI.
在7特斯拉超高场强下采集的定量磁共振成像（qMRI）已用于可视化和分析皮层下结构。qMRI依赖于使用不同扫描设置采集多个图像，这导致扫描时间延长。深度学习可以利用数据冗余和来自弛豫测量模型的先验信息来加速成像过程。我们提出了定量递归推理机（qRIM），它具有一个统一的前向模型，用于从稀疏数据进行联合重建和R映射，并嵌入到递归推理机（RIM）中，这是一个迭代逆问题求解网络。为了研究统一前向模型的扩展对网络架构的依赖性，我们实现并比较了定量端到端变分网络（qE2EVN）。在一项涵盖整个成年寿命的队列研究中，使用7T时大脑的高分辨率多回波梯度回波数据进行了实验。与使用RIM进行顺序图像重建和参数拟合相比，统一模型从欠采样数据重建的R相对于参考数据的误差显著降低。随着加速因子的增加，重建误差的降低也越来越明显，这表明对更稀疏的数据有更大的益处。定性地说，这伴随着R图中观察到的图像模糊度的降低。相比之下，当使用U-Net作为网络架构时，在选定的感兴趣区域中观察到R存在负偏差。压缩感知给出了准确但不太精确的R估计。qE2EVN的重建质量略逊于qRIM，但优于U-Net和压缩感知。纹状体中R的四分位间距线性增加所测量的皮层下成熟度在加速因子为9时仍得以保留。通过统一前向模型的集成先验，所提出的qRIM可以利用重复测量之间的冗余和任务之间的共享信息，促进加速MRI中的弛豫测量。
