Towards multi‐modal data fusion for super‐resolution and denoising of <scp>4D‐Flow MRI</scp>

Perez-Raya, Isaac; Fathi, Mojtaba F.; Baghaie, Ahmadreza; Sacho, Raphael; Koch, Kevin M.; D’Souza, Roshan

doi:10.1002/cnm.3381

Cited by 13 publications

(6 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, CFD simulations are based on nonlinear equations named Navier-Stokes, whose numerical resolution requires a precise estimation of the fluid domain and the inlet/outlet velocity fields (or by default the mass flow rate). To improve the CFD simulation and the data matching process, previous contributions were inspired from computer vision [6,7], machine learning [8,9] and inverse problem theory [10,11,12,13]. In the latter category, some data assimilation approaches enforce the Navier-Stokes equations as a hard constraint which leads to run several CFD simulations with an iteratively updated inflow [11,12].…”

Section: Introductionmentioning

confidence: 99%

Navier-Stokes-Based Regularization for 4d Flow MRI Super-Resolution

Levilly

Moussaoui

Serfaty

2022

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

4D flow MRI is a promising tool in cardiovascular imaging. However, its lack of resolution can degrade some biomarkers' evaluation accuracy. The computational fluid dynamics (CFD) simulation is considered as the reference method to improve numerically the image resolution. However, CFD simulations are complex and time consuming, and matching their results with 4D Flow MRI data is very challenging. This paper aims to introduce a fast and efficient super-resolution (SR) approach thanks to the minimization of a L 2 -penalized criterion, which combines a weighted least-squares data fidelity term and Navier-Stokes equations. The algorithm has been validated on synthetic and phantom datasets and compared to state-of-the-art solutions. Moreover, a prospective study is conducted on the segmentationfree application of the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Navier-Stokes-Based Regularization for 4d Flow MRI Super-Resolution

Levilly

Moussaoui

Serfaty

2022

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

show abstract

“…Adjoint-based optimization approaches have been introduced to minimize the differences between the CFD and in vivo 4D flow MRI measurements [21][22][23] to achieve higher fidelity. The patient-specific CFD solutions have also been used to enhance 4D flow MRI data with data fusion techniques [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

A multi-modality approach for enhancing 4D flow magnetic resonance imaging via sparse representation

Zhang

Brindise

Rothenberger

et al. 2022

J. R. Soc. Interface.

View full text Add to dashboard Cite

This work evaluates and applies a multi-modality approach to enhance blood flow measurements and haemodynamic analysis with phase-contrast magnetic resonance imaging (4D flow MRI) in cerebral aneurysms (CAs). Using a library of high-resolution velocity fields from patient-specific computational fluid dynamic simulations and in vitro particle tracking velocimetry measurements, the flow field of 4D flow MRI data is reconstructed as the sparse representation of the library. The method was evaluated with synthetic 4D flow MRI data in two CAs. The reconstruction enhanced the spatial resolution and velocity accuracy of the synthetic MRI data, leading to reliable pressure and wall shear stress (WSS) evaluation. The method was applied on in vivo 4D flow MRI data acquired in the same CAs. The reconstruction increased the velocity and WSS by 6–13% and 39–61%, respectively, suggesting that the accuracy of these quantities was improved since the raw MRI data underestimated the velocity and WSS by 10–20% and 40–50%, respectively. The computed pressure fields from the reconstructed data were consistent with the observed flow structures. The results suggest that using the sparse representation flow reconstruction with in vivo 4D flow MRI enhances blood flow measurement and haemodynamic analysis.

show abstract

“…Outside of phantom applications [6], CFD simulation and 4D flow MRI matching is complex and a non-applicable task in the clinical routine. To manage this issue, previous contributions proposed machine learning strategies embedding CFD simulation datasets [7,8], or used directly Navier-Stokes equations with computer vision approaches [9,10] or adopted inverse problem solutions [11,12,13,14]. In the latter category, some data assimilation methods minimize a data fidelity term under the constraint of Navier-Stokes equations applied within a pre-established segmentation [12,13], which results in an iterative estimation of the optimal inflow, and then multiple CFD simulations.…”

Section: Introductionmentioning

confidence: 99%

Segmentation-Free Super-Resolved 4D flow MRI Reconstruction Exploiting Navier-Stokes Equations and Spatial Regularization

Levilly

Moussaoui

Serfaty

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Interest in 4D blood flow MRI grows due to its ability to image the anatomic shape and the three velocity components within a volume along the cardiac cycle. However, some biomarkers' quantification from these data can be inaccurate due to the low resolution of the images. The reference method to improve the spatial resolution numerically is to run computational fluid dynamic (CFD) simulations in order to deduce the associated images in a higher resolution grid. However, such approaches induce complex time-consuming steps and require precise estimates of the vessel wall and the inlet velocity. In this work, an original segmentation-free superresolution (SR) solution is proposed using an inverse problem resolution approach by the minimization of a compound criterion involving three terms, a mechanical term based on Navier-Stokes equations, and a velocity smoothness promoting term, and a spatially weighted data fidelity term. The proposed solution has been validated regarding estimation error and computation time on simulated data and experimental acquisition from a phantom. Super-resolved velocity reconstruction demonstrates promising performance, even without segmentation knowledge, compared to state-of-the-art solutions.

show abstract

Towards multi‐modal data fusion for super‐resolution and denoising of 4D‐Flow MRI

Cited by 13 publications

References 74 publications

Navier-Stokes-Based Regularization for 4d Flow MRI Super-Resolution

Navier-Stokes-Based Regularization for 4d Flow MRI Super-Resolution

A multi-modality approach for enhancing 4D flow magnetic resonance imaging via sparse representation

Segmentation-Free Super-Resolved 4D flow MRI Reconstruction Exploiting Navier-Stokes Equations and Spatial Regularization

Contact Info

Product

Resources

About