View Presentation Video

Keywords: Contrast mechanisms: Flow, Cardiovascular: Vascular, Image acquisition: Machine learning

4D flow MRI can be used to visualize and quantify blood flow for the diagnosis and treatment of cardiovascular disease. However, 4D flow MRI has several limitations such as long acquisition times and inaccuracies in velocity estimations due to partial volume effects and phase errors. In recent years, machine learning (ML) techniques have been proposed to address these limitations. ML methods developed for 4D flow MRI include image reconstruction methods, super-resolution methods, and ML-based post-processing tools for phase correction and vessel delineation and the statistical evaluation of blood flow. This talk summarizes the latest ML advances in 4D flow MRI.

View Presentation Video

Keywords: Cardiovascular: Hemodynamics

In this educational talk, we will talk about the relationship between the velocity to noise ratio and acquisition related parameters. The preprocessing of 4D flow MRI is also important, because the acquisition could be affected by gradient-induced eddy currents, concomitant gradient fields, gradient non-linearity and phase wraps resulting in velocity aliasing, these problems need to be addressed to avoid additional errors in the quantification of hemodynamic parameters. Finally we will explore different methods used to validate 4D flow MRI advanced parameters as; wall shear stress, vorticity, helicity density, viscous energy loss, kinetic energy, circulation, pressure gradients, among others.