scholarly journals 4DFlowNet: Super-Resolution 4D Flow MRI Using Deep Learning and Computational Fluid Dynamics

2020 ◽  
Vol 8 ◽  
Author(s):  
Edward Ferdian ◽  
Avan Suinesiaputra ◽  
David J. Dubowitz ◽  
Debbie Zhao ◽  
Alan Wang ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Deep Learning ◽  
Super Resolution ◽  
4D Flow Mri ◽  
4D Flow ◽  
Flow Mri

scholarly journals Enhancement of cerebrovascular 4D flow MRI velocity fields using machine learning and computational fluid dynamics simulation data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
David R. Rutkowski ◽  
Alejandro Roldán-Alzate ◽  
Kevin M. Johnson
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Velocity Fields ◽  
Dynamics Simulation ◽  
Patient Specific ◽  
4D Flow Mri ◽  
4D Flow ◽  
Flow Phase ◽  
Flow Mri ◽  
Trained Network

AbstractBlood flow metrics obtained with four-dimensional (4D) flow phase contrast (PC) magnetic resonance imaging (MRI) can be of great value in clinical and experimental cerebrovascular analysis. However, limitations in both quantitative and qualitative analyses can result from errors inherent to PC MRI. One method that excels in creating low-error, physics-based, velocity fields is computational fluid dynamics (CFD). Augmentation of cerebral 4D flow MRI data with CFD-informed neural networks may provide a method to produce highly accurate physiological flow fields. In this preliminary study, the potential utility of such a method was demonstrated by using high resolution patient-specific CFD data to train a convolutional neural network, and then using the trained network to enhance MRI-derived velocity fields in cerebral blood vessel data sets. Through testing on simulated images, phantom data, and cerebrovascular 4D flow data from 20 patients, the trained network successfully de-noised flow images, decreased velocity error, and enhanced near-vessel-wall velocity quantification and visualization. Such image enhancement can improve experimental and clinical qualitative and quantitative cerebrovascular PC MRI analysis.

Thoracic aortic aneurysm: 4D flow MRI and computational fluid dynamics model

2015 ◽  
Vol 18 (sup1) ◽  
pp. 1894-1895 ◽  
Author(s):  
F. M. Callaghan ◽  
J. Karkouri ◽  
K. Broadhouse ◽  
M. Evin ◽  
D. F. Fletcher ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Aortic Aneurysm ◽  
Thoracic Aortic Aneurysm ◽  
Dynamics Model ◽  
4D Flow Mri ◽  
4D Flow ◽  
Computational Fluid Dynamics Model ◽  
Flow Mri

scholarly journals Fluid–structure interaction simulations outperform computational fluid dynamics in the description of thoracic aorta haemodynamics and in the differentiation of progressive dilation in Marfan syndrome patients

2020 ◽  
Vol 7 (2) ◽  
pp. 191752
Author(s):  
R. Pons ◽  
A. Guala ◽  
J. F. Rodríguez-Palomares ◽  
J. C. Cajas ◽  
L. Dux-Santoy ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Maximum Velocity ◽  
Ascending Aorta ◽  
4D Flow Mri ◽  
4D Flow ◽  
Cfd Simulations ◽  
Structure Interaction ◽  
Flow Displacement ◽  
Flow Mri

Abnormal fluid dynamics at the ascending aorta may be at the origin of aortic aneurysms. This study was aimed at comparing the performance of computational fluid dynamics (CFD) and fluid–structure interaction (FSI) simulations against four-dimensional (4D) flow magnetic resonance imaging (MRI) data; and to assess the capacity of advanced fluid dynamics markers to stratify aneurysm progression risk. Eight Marfan syndrome (MFS) patients, four with stable and four with dilating aneurysms of the proximal aorta, and four healthy controls were studied. FSI and CFD simulations were performed with MRI-derived geometry, inlet velocity field and Young's modulus. Flow displacement, jet angle and maximum velocity evaluated from FSI and CFD simulations were compared to 4D flow MRI data. A dimensionless parameter, the shear stress ratio (SSR), was evaluated from FSI and CFD simulations and assessed as potential correlate of aneurysm progression. FSI simulations successfully matched MRI data regarding descending to ascending aorta flow rates ( R 2 = 0.92) and pulse wave velocity ( R 2 = 0.99). Compared to CFD, FSI simulations showed significantly lower percentage errors in ascending and descending aorta in flow displacement (−46% ascending, −41% descending), jet angle (−28% ascending, −50% descending) and maximum velocity (−37% ascending, −34% descending) with respect to 4D flow MRI. FSI- but not CFD-derived SSR differentiated between stable and dilating MFS patients. Fluid dynamic simulations of the thoracic aorta require fluid–solid interaction to properly reproduce complex haemodynamics. FSI- but not CFD-derived SSR could help stratifying MFS patients.

scholarly journals Cerebrovascular super-resolution 4D Flow MRI – using deep learning to non-invasively quantify velocity, flow, and relative pressure

2021 ◽  
Author(s):  
E. Ferdian ◽  
D. Marlevi ◽  
J. Schollenberger ◽  
M. Aristova ◽  
E.R. Edelman ◽  
...  
Keyword(s):  
Deep Learning ◽  
Relative Error ◽  
Super Resolution ◽  
Patient Specific ◽  
Relative Pressure ◽  
4D Flow Mri ◽  
4D Flow ◽  
Velocity Flow ◽  
Flow Mri ◽  
Cerebrovascular Hemodynamics

ABSTRACTThe development of cerebrovascular disease is tightly coupled to changes in cerebrovascular hemodynamics, with altered flow and relative pressure indicative of the onset, development, and acute manifestation of pathology. Image-based monitoring of cerebrovascular hemodynamics is, however, complicated by the narrow and tortuous vasculature, where accurate output directly depends on sufficient spatial resolution. To address this, we present a method combining dedicated deep learning and state-of-the-art 4D Flow MRI to generate super-resolution full-field images with coupled quantification of relative pressure using a physics-driven image processing approach. The method is trained and validated in a patient-specific in-silico cohort, showing good accuracy in estimating velocity (relative error: 12.0 ± 0.1%, mean absolute error (MAE): 0.07 ± 0.06 m/s at peak velocity), flow (relative error: 6.6 ± 4.7%, root mean square error (RMSE): 0.5 ± 0.1 mL/s at peak flow), and with maintained recovery of relative pressure through the circle of Willis (relative error: 11.0 ± 7.3%, RMSE: 0.3 ± 0.2 mmHg). Furthermore, the method is applied to an in-vivo volunteer cohort, effectively generating data at <0.5mm resolution and showing potential in reducing low-resolution bias in relative pressure estimation. Our approach presents a promising method to non-invasively quantify cerebrovascular hemodynamics, applicable to dedicated clinical cohorts in the future.

scholarly journals Multi-modality cerebral aneurysm haemodynamic analysis: in vivo 4D flow MRI, in vitro volumetric particle velocimetry and in silico computational fluid dynamics

2019 ◽  
Vol 16 (158) ◽  
pp. 20190465 ◽  
Author(s):  
Melissa C. Brindise ◽  
Sean Rothenberger ◽  
Benjamin Dickerhoff ◽  
Susanne Schnell ◽  
Michael Markl ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Cerebral Aneurysm ◽  
Patient Specific ◽  
4D Flow Mri ◽  
4D Flow ◽  
Relative Residence Time ◽  
Flow Mri

Typical approaches to patient-specific haemodynamic studies of cerebral aneurysms use image-based computational fluid dynamics (CFD) and seek to statistically correlate parameters such as wall shear stress (WSS) and oscillatory shear index (OSI) to risk of growth and rupture. However, such studies have reported contradictory results, emphasizing the need for in-depth multi-modality haemodynamic metric evaluation. In this work, we used in vivo 4D flow MRI data to inform in vitro particle velocimetry and CFD modalities in two patient-specific cerebral aneurysm models (basilar tip and internal carotid artery). Pulsatile volumetric particle velocimetry experiments were conducted, and the particle images were processed using Shake-the-Box, a particle tracking method. Distributions of normalized WSS and relative residence time were shown to be highly yet inconsistently affected by minor flow field and spatial resolution variations across modalities, and specific relationships among these should be explored in future work. Conversely, OSI, a non-dimensional parameter, was shown to be more robust to the varying assumptions, limitations and spatial resolutions of each subject and modality. These results suggest a need for further multi-modality analysis as well as development of non-dimensional haemodynamic parameters and correlation of such metrics to aneurysm risk of growth and rupture.

scholarly journals Hemodynamic Study of a Patient-Specific Intracranial Aneurysm: Comparative Assessment of Tomographic PIV, Stereoscopic PIV, In Vivo MRI and Computational Fluid Dynamics

2021 ◽  
Author(s):  
Xiaolin Wu ◽  
Stefanie Gürzing ◽  
Christiaan Schinkel ◽  
Merel Toussaint ◽  
Romana Perinajová ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Intracranial Aneurysm ◽  
Comparative Assessment ◽  
Patient Specific ◽  
4D Flow Mri ◽  
4D Flow ◽  
Flow Mri

Abstract Introduction Wall shear stress (WSS) is associated with the growth and rupture of an intracranial aneurysm. To reveal their underlying connections, many image-based computational fluid dynamics (CFD) studies have been conducted. However, the methodological validations using both in vivo medical imaging and in vitro optical flow measurements were rarely accompanied in such studies. Methods In the present study, we performed a comparative assessment on the hemodynamics of a patient-specific intracranial saccular aneurysm using in vivo 4D Flow MRI, in silico CFD, in vitro stereoscopic and tomographic particle imaging velocimetry (Stereo-PIV and Tomo-PIV) techniques. PIV experiments and CFD were conducted under steady state corresponding to the peak systole of 4D Flow MRI. Results The results showed that all modalities provided similar flow features and overall surface distribution of WSS. However, a large variation in the absolute WSS values was found. 4D Flow MRI estimated a 2- to 4-fold lower peak WSS (3.99 Pa) and a 1.6- to 2-fold lower mean WSS (0.94 Pa) than Tomo-PIV, Stereo-PIV, and CFD. Bland-Altman plots of WSS showed that the differences between PIV-/CFD-based WSS and 4D Flow MRI-based WSS increase with higher WSS magnitude. Such proportional trend was absent in the Bland-Altman comparison of velocity where the resolutions of PIV and CFD datasets were matched to 4D Flow MRI. We also found that because of superior resolution in the out-of-plane direction, WSS estimation by Tomo-PIV was higher than Stereo-PIV. Conclusions Our results indicated that the differences in spatial resolution could be the main contributor to the discrepancies between each modality. The findings of this study suggest that with current techniques, care should be taken when using absolute WSS values to perform a quantitative risk analysis of aneurysm rupture.

New imaging tools in cardiovascular medicine: computational fluid dynamics and 4D flow MRI

2017 ◽  
Vol 65 (11) ◽  
pp. 611-621 ◽  
Author(s):  
Keiichi Itatani ◽  
Shohei Miyazaki ◽  
Tokoki Furusawa ◽  
Satoshi Numata ◽  
Sachiko Yamazaki ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
4D Flow Mri ◽  
Cardiovascular Medicine ◽  
4D Flow ◽  
Flow Mri

scholarly journals Merging computational fluid dynamics and 4D Flow MRI using proper orthogonal decomposition and ridge regression

2017 ◽  
Vol 58 ◽  
pp. 162-173 ◽  
Author(s):  
Ali Bakhshinejad ◽  
Ahmadreza Baghaie ◽  
Alireza Vali ◽  
David Saloner ◽  
Vitaliy L. Rayz ◽  
...  
Keyword(s):  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
Proper Orthogonal Decomposition ◽  
Ridge Regression ◽  
Orthogonal Decomposition ◽  
4D Flow Mri ◽  
4D Flow ◽  
Flow Mri ◽  
Proper Orthogonal
Sign in / Sign up

Export Citation Format

Share Document