4Dflow-VP-Net: A deep convolutional neural network for noninvasive estimation of relative pressures in stenotic flows from 4D flow MRI.
4Dflow-VP-Net: A deep convolutional neural network for noninvasive estimation of relative pressures in stenotic flows from 4D flow MRI.
复制标题
DOI：
10.1002/mrm.29791
复制
发表时间：
2023-11
影响因子：
3.3
通讯作者：
Amini, Amir A.
中科院分区：
文献类型：
--
作者：
Nath, Ruponti;Kazemi, Amirkhosro;Callahan, Sean;Stoddard, Marcus F.;Amini, Amir A.
应用4D Flow MRI无创性评价相对跨瓣压差(TVPG)。提出了一种新的基于深度学习的四维Flow MRI(4D Flow MRI)速度估计狭窄处压力梯度的方法。为了学习狭窄血管中速度与压力之间的时空关系，训练了一个深度神经网络四维Flow-VP-Net(4Dflow-VP-net)。利用计算流体力学(CFD)对不同脉动流动条件下的训练数据进行了模拟。根据CFD模拟的速度数据、体外4D Flow MRI数据和体内4D Flow MRI数据，对中度和重度主动脉狭窄患者的压力进行了测试。从4Dflow-VP-net获得的TVPG与基于导管的压力测量、体外可用流速和基于多普勒超声的在体压力测量进行了比较。4Dflow-VP-net计算的相对压力与体外压力导管法计算的相对压力有很强的相关性(R2=0.91)。对于450个模拟流动条件，参考CFD和4Dflow-VP-Net得到的TVPG具有很强的相关性(R2=0.99)。来自体外MRI的TVPG与参考CFD的相关系数R2=0.98。4Dflow-VP-Net应用于16例4D Flow MRI，TVPG测量结果与多普勒超声心动图相当(R2=0.85)。BLAND-ALTMAN分析表明，−模拟流速和体外4D流速的平均偏差和一致性限分别为0.20±2.07和0.19±0.45毫米汞柱。在患者中，高估了4Dflow-VP-net的超声心动图相对于TVPG的值(10.99±6.77 mm Hg)。该方法可以预测高保真的主动脉狭窄患者体内和体外4D Flow MRI的相对压力。
To estimate relative transvalvular pressure gradient (TVPG) noninvasively from 4D flow MRI. A novel deep learning–based approach is proposed to estimate pressure gradient across stenosis from four-dimensional flow MRI (4D flow MRI) velocities. A deep neural network 4D flow Velocity-to-Presure Network (4Dflow-VP-Net) was trained to learn the spatiotemporal relationship between velocities and pressure in stenotic vessels. Training data were simulated by computational fluid dynamics (CFD) for different pulsatile flow conditions under an aortic flow waveform. The network was tested to predict pressure from CFD-simulated velocity data, in vitro 4D flow MRI data, and in vivo 4D flow MRI data of patients with both moderate and severe aortic stenosis. TVPG derived from 4Dflow-VP-Net was compared to catheter-based pressure measurements for available flow rates, in vitro and Doppler echocardiography–based pressure measurement, in vivo. Relative pressures calculated by 4Dflow-VP-Net and in vitro pressure catheterization revealed strong correlation (r2 = 0.91). Correlations analysis of TVPG from reference CFD and 4Dflow-VP-Net for 450 simulated flow conditions showed strong correlation (r2 = 0.99). TVPG from in vitro MRI had a correlation coefficient of r2 = 0.98 with reference CFD. 4Dflow-VP-Net, applied to 4D flow MRI in 16 patients, showed comparable TVPG measurement with Doppler echocardiography (r2 = 0.85). Bland–Altman analysis of TVPG measurements showed mean bias and limits of agreement of −0.20 ± 2.07 mmHg and 0.19 ± 0.45 mmHg for CFD-simulated velocities and in vitro 4D flow velocities. In patients, overestimation of Doppler echocardiography relative to TVPG from 4Dflow-VP-Net (10.99 ± 6.77 mmHg) was observed. The proposed approach can predict relative pressure in both in vitro and in vivo 4D flow MRI of aortic stenotic patients with high fidelity.
登录
查看更多内容
影响因子：
3.3
作者：
Berhane, Haben;Scott, Michael B.;Barker, Alex J.;McCarthy, Patrick;Avery, Ryan;Allen, Brad;Malaisrie, Chris;Robinson, Joshua D.;Rigsby, Cynthia K.;Markl, Michael
通讯作者：
Markl, Michael
影响因子：
14
作者：
Dyverfeldt, Petter;Hope, Michael D.;Tseng, Elaine E.;Saloner, David
通讯作者：
Saloner, David
影响因子：
10.9
作者：
Donati, Fabrizio;Figueroa, C. Alberto;Nordsletten, David A.
通讯作者：
Nordsletten, David A.
影响因子：
4.4
作者：
Falahatpisheh, Ahmad;Rickers, Carsten;Kheradvar, Arash
通讯作者：
Kheradvar, Arash
影响因子：
10.9
作者：
Nolte, David;Urbina, Jesus;Bertoglio, Cristobal
通讯作者：
Bertoglio, Cristobal