Department of Computer Science, University College London, London, United Kingdom.
UCL Centre for Translational Cardiovascular Imaging, University College London, London, United Kingdom.
Magn Reson Med. 2021 Oct;86(4):1904-1916. doi: 10.1002/mrm.28834. Epub 2021 May 25.
Real-time low latency MRI is performed to guide various cardiac interventions. Real-time acquisitions often require iterative image reconstruction strategies, which lead to long reconstruction times. In this study, we aim to reconstruct highly undersampled radial real-time data with low latency using deep learning.
A 2D U-Net with convolutional long short-term memory layers is proposed to exploit spatial and preceding temporal information to reconstruct highly accelerated tiny golden radial data with low latency. The network was trained using a dataset of breath-hold CINE data (including 770 time series from 7 different orientations). Synthetic paired data were created by retrospectively undersampling the magnitude images, and the network was trained to recover the target images. In the spirit of interventional imaging, the network was trained and tested for varying acceleration rates and orientations. Data were prospectively acquired and reconstructed in real time in 1 healthy subject interactively and in 3 patients who underwent catheterization. Images were visually compared to sliding window and compressed sensing reconstructions and a conventional Cartesian real-time sequence.
The proposed network generalized well to different acceleration rates and unseen orientations for all considered metrics in simulated data (less than 4% reduction in structural similarity index compared to similar acceleration and orientation-specific networks). The proposed reconstruction was demonstrated interactively, successfully depicting catheters in vivo with low latency (39 ms, including 19 ms for deep artifact suppression) and an image quality comparing favorably to other reconstructions.
Deep artifact suppression was successfully demonstrated in the time-critical application of non-Cartesian real-time interventional cardiac MR.
实时低延迟 MRI 用于指导各种心脏介入。实时采集通常需要迭代图像重建策略，这会导致重建时间长。在这项研究中，我们旨在使用深度学习对低延迟进行高度欠采样的径向实时数据进行重建。
提出了一种具有卷积长短时记忆层的 2D U-Net，以利用空间和先前的时间信息来重建具有低延迟的高度加速的微小金径向数据。该网络使用屏气 CINE 数据的数据集进行训练（包括来自 7 个不同方向的 770 个时间序列）。通过回顾性地对幅度图像进行欠采样来创建合成配对数据，并且网络被训练以恢复目标图像。本着介入成像的精神，对网络进行了训练和测试，以适应不同的加速率和方向。在 1 名健康受试者和 3 名接受导管插入术的患者中进行了前瞻性采集和实时重建。将图像与滑动窗口和压缩感知重建以及传统笛卡尔实时序列进行了视觉比较。
在模拟数据中，对于所有考虑的指标，所提出的网络都很好地推广到不同的加速率和看不见的方向（与类似的加速和特定于方向的网络相比，结构相似性指数的降低小于 4%）。提出的重建可以实时交互显示，成功地以低延迟（39ms，包括 19ms 的深度伪影抑制）描绘体内导管，并且图像质量与其他重建相比具有优势。
在非笛卡尔实时介入心脏磁共振的时间关键应用中，成功地演示了深度伪影抑制。
