Pablo Martínez‐Legazpi

This paper introduces Bayesian VFM (B-VFM) to address ill-posedness in vector flow mapping by jointly inferring velocity fields, segmentation masks, and uncertainties using Bayesian inference.

This paper develops two methods to estimate left atrial blood residence time from 4D CT contrast data, showing that indicator dilution theory provides faster, more accurate results than a physics-informed neural network.

The paper develops porcine ventricular digital twins using multi-modal data to study myocardial infarction effects on cardiac function and ECG patterns.

The paper develops queue models to assess left ventricular blood transit and shows that flow transport, not ejection fraction, determines stasis in patients with impaired systolic function.

This study simulates blood flow and coagulation in patient-specific left atrium models to assess how hemodynamics affect the efficacy of factor XI/XII inhibitors in preventing thrombosis.

This paper uses multi-physics simulations to show how fibrosis in left atrial tissue affects hemodynamics and increases stroke risk by altering flow patterns and reducing emptying fractions.

This paper introduces AI-VFM, a physics-informed neural network method for super-resolution left ventricular flow and pressure mapping from echocardiographic data.