FReSCO: Flow Reconstruction and Segmentation for low-latency Cardiac Output monitoring using deep artifact suppression and segmentation.
FReSCO: Flow Reconstruction and Segmentation for low-latency Cardiac Output monitoring using deep artifact suppression and segmentation.
复制标题
DOI：
10.1002/mrm.29374
复制
发表时间：
2022-11
影响因子：
3.3
通讯作者：
Muthurangu, Vivek
中科院分区：
文献类型：
--
作者：
Jaubert, Olivier;Montalt-Tordera, Javier;Brown, James;Knight, Daniel;Arridge, Simon;Steeden, Jennifer;Muthurangu, Vivek
心输出量(CO)的实时监测需要低潜伏期的重建和实时相位对比MR的分割，这在以前是很难实现的。在这里，我们提出了一个深度学习框架的“FRECCO”(流重建和分割的低潜伏期心输出量监测)。对深度伪影抑制和分割U-Net进行了独立训练。采用可变密度螺旋采样模式对屏气螺旋相位差MR数据(N=1516)进行综合欠采样，并将其栅格化以创建用于伪影抑制U网训练的混叠数据。对数据的子集(N=0.96)进行分割，并用于训练分割U-网。在10名健康受试者的休息、运动和恢复期，前瞻性地获取实时螺旋相位对比MR，然后使用训练好的模型(FRESCO)在扫描仪上进行低潜伏期重建和分割。将FRESCO获得的心输出量与参考的静息CO、静息和运动压缩感知CO进行比较。FRESCO框架在扫描仪上进行了前瞻性演示。心搏间期心率、每搏量和心输出量均可显示，平均潜伏期为622 ms。与安静时的参考值(偏差−=0.21 ± 0.50 L/分钟，p=0.246)或高峰运动时的压缩感知(偏差=0.12 ± 0.48 L/分钟，p=0.458)相比，差异均无统计学意义。FRESCO框架被成功地用于运动期间CO的实时监测，并为评估对一系列应激源的血流动力学反应提供了一种方便的工具。单击此处查看作者与读者的讨论
Real‐time monitoring of cardiac output (CO) requires low‐latency reconstruction and segmentation of real‐time phase‐contrast MR, which has previously been difficult to perform. Here we propose a deep learning framework for “FReSCO” (Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring). Deep artifact suppression and segmentation U‐Nets were independently trained. Breath‐hold spiral phase‐contrast MR data (N = 516) were synthetically undersampled using a variable‐density spiral sampling pattern and gridded to create aliased data for training of the artifact suppression U‐net. A subset of the data (N = 96) was segmented and used to train the segmentation U‐net. Real‐time spiral phase‐contrast MR was prospectively acquired and then reconstructed and segmented using the trained models (FReSCO) at low latency at the scanner in 10 healthy subjects during rest, exercise, and recovery periods. Cardiac output obtained via FReSCO was compared with a reference rest CO and rest and exercise compressed‐sensing CO. The FReSCO framework was demonstrated prospectively at the scanner. Beat‐to‐beat heartrate, stroke volume, and CO could be visualized with a mean latency of 622 ms. No significant differences were noted when compared with reference at rest (bias = −0.21 ± 0.50 L/min, p = 0.246) or compressed sensing at peak exercise (bias = 0.12 ± 0.48 L/min, p = 0.458). The FReSCO framework was successfully demonstrated for real‐time monitoring of CO during exercise and could provide a convenient tool for assessment of the hemodynamic response to a range of stressors. Click here for author‐reader discussions
登录
查看更多内容
影响因子：
3.3
作者：
Pipe, James G.;Zwart, Nicholas R.
通讯作者：
Zwart, Nicholas R.
影响因子：
3.3
作者：
Jaubert O;Montalt-Tordera J;Knight D;Coghlan GJ;Arridge S;Steeden JA;Muthurangu V
通讯作者：
Muthurangu V
影响因子：
19.7
作者：
Steeden, Jennifer A.;Atkinson, David;Muthurangu, Vivek
通讯作者：
Muthurangu, Vivek
影响因子：
4.4
作者：
Klein, C;Schalla, S;Nagel, E
通讯作者：
Nagel, E
影响因子：
2.5
作者：
Jaubert, Olivier;Steeden, Jennifer;Muthurangu, Vivek
通讯作者：
Muthurangu, Vivek