arXiv subjects

Hernán Mella

Publications and source records attributed to Hernán Mella.

4 recordsLinked to original sources

arXiv2026

Unsupervised 4D Flow MRI Velocity Enhancement and Unwrapping Using Divergence-Free Neural Networks

This work introduces an unsupervised Divergence and Aliasing-Free neural network (DAF-FlowNet) for 4D Flow Magnetic Resonance Imaging (4D Flow MRI) that jointly enhances noisy velocity fields and corrects phase wrapping artifacts. DAF-FlowNet parameterizes velocities as the curl of a vector potential, enforcing mass conservation by construction and avoiding explicit divergence-penalty tuning. A cosine data-consistency loss enables simultaneous denoising and unwrapping from wrapped phase images. On synthetic aortic 4D Flow MRI generated from computational fluid dynamics, DAF-FlowNet achieved lower errors than existing techniques (up to 11% lower velocity normalized root mean square error, 11% lower directional error, and 44% lower divergence relative to the best-performing alternative across noise levels), with robustness to moderate segmentation perturbations. For unwrapping, at peak velocity/velocity-encoding ratios of 1.4 and 2.1, DAF-FlowNet achieved 0.18% and 5.2% residual wrapped voxels, representing reductions of 72% and 18% relative to the best alternative method, respectively. In scenarios with both noise and aliasing, the proposed single-stage formulation outperformed a state-of-the-art sequential pipeline (up to 15% lower velocity normalized root mean square error, 11% lower directional error, and 28% lower divergence). Across 10 hypertrophic cardiomyopathy patient datasets, DAF-FlowNet preserved fine-scale flow features, corrected aliased regions, and improved internal flow consistency, as indicated by reduced inter-plane flow bias in aortic and pulmonary mass-conservation analyses recommended by the 4D Flow MRI consensus guidelines. These results support DAF-FlowNet as a framework that unifies velocity enhancement and phase unwrapping to improve the reliability of cardiovascular 4D Flow MRI.

cs.LG↗

arXiv2025

Enhancing Hemodynamic Parameter Estimations: Nonlinear Blood Behavior in 4D Flow MRI

Hemodynamic parameters are often estimated assuming a constant Newtonian viscosity, even though blood exhibits shear-thinning behavior. This article investigates the influence of blood rheology and hematocrit (Hct) percentage on the estimation of Wall Shear Stress (WSS), rate of viscous Energy Loss ($\dot{E}_L$) at different points in the cardiac cycle, and the Oscillatory Shear Index (OSI). We focus on a hematocrit-dependent power-law non-Newtonian model, considering a wide range of Hct values at physiological temperature, with rheological parameters obtained from previously reported experimental data. In all cases, we systematically compared WSS, $\dot{E}_L$, and OSI using both Newtonian and power-law models, underscoring the crucial role of blood rheology in accurately assessing cardiovascular diseases. Our results show that, in in-silico experiments, differences in WSS and $\dot{E}_L$ across a wide range of Hct values can reach as high as 190\% and 113\% at systole, and as low as -72\% and -74\% at diastole, respectively. In in-vivo data, differences in WSS and $\dot{E}_L$ can reach up to -45\% and -60\% at systole, and range from -69\% to 73\% at diastole. This study enhances our understanding of the impact of blood rheology on hemodynamic parameter estimations using both in-silico and in-vivo aortic 4D Flow MRI data.

eess.SP↗

arXiv2023

A hybrid PML formulation for the 2D three-field dynamic poroelastic equations

Simulation of wave propagation in poroelastic half-spaces presents a common challenge in fields like geomechanics and biomechanics, requiring Absorbing Boundary Conditions (ABCs) at the semi-infinite space boundaries. Perfectly Matched Layers (PML) are a popular choice due to their excellent wave absorption properties. However, PML implementation can lead to problems with unknown stresses or strains, time convolutions, or PDE systems with Auxiliary Differential Equations (ADEs), which increases computational complexity and resource consumption. This article presents two new PML formulations for arbitrary poroelastic domains. The first formulation is a fully-mixed form that employs time-history variables instead of ADEs, reducing the number of unknowns and mathematical operations. The second formulation is a hybrid form that restricts the fully-mixed formulation to the PML domain, resulting in smaller matrices for the solver while preserving governing equations in the interior domain. The fully-mixed formulation introduces three scalar variables over the whole domain, whereas the hybrid form confines them to the PML domain. The proposed formulations were tested in three numerical experiments in geophysics using realistic parameters for soft sites with free surfaces. The results were compared with numerical solutions from extended domains and simpler ABCs, such as paraxial approximation, demonstrating the accuracy, efficiency, and precision of the proposed methods. The article also discusses the applicability of these methods to complex media and their extension to the Multiaxial PML formulation. The codes for the simulations are available for download from \url{https://github.com/hmella/POROUS-HYBRID-PML}.

math.NA↗

arXiv2022

WarpPINN: Cine-MR image registration with physics-informed neural networks

Heart failure is typically diagnosed with a global function assessment, such as ejection fraction. However, these metrics have low discriminate power, failing to distinguish different types of this disease. Quantifying local deformations in the form of cardiac strain can provide helpful information, but it remains a challenge. In this work, we introduce WarpPINN, a physics-informed neural network to perform image registration to obtain local metrics of the heart deformation. We apply this method to cine magnetic resonance images to estimate the motion during the cardiac cycle. We inform our neural network of near-incompressibility of cardiac tissue by penalizing the jacobian of the deformation field. The loss function has two components: an intensity-based similarity term between the reference and the warped template images, and a regularizer that represents the hyperelastic behavior of the tissue. The architecture of the neural network allows us to easily compute the strain via automatic differentiation to assess cardiac activity. We use Fourier feature mappings to overcome the spectral bias of neural networks, allowing us to capture discontinuities in the strain field. We test our algorithm on a synthetic example and on a cine-MRI benchmark of 15 healthy volunteers. We outperform current methodologies both landmark tracking and strain estimation. We expect that WarpPINN will enable more precise diagnostics of heart failure based on local deformation information. Source code is available at https://github.com/fsahli/WarpPINN.

eess.IV↗