Cerebrovascular 4DFlowNet - Super Resolution 4D Flow MRI

<div>In this study, we showcased how super-resolution 4D Flow MRI may improve non-invasive quantification of cerebrovascular hemodynamics.</div><div>Some improvements were made to the original 4DFlowNet.</div><div>The network was trained with cerebrovascular dataset with multiple resolution and more realistic synthetic magnitude image.</div><div><br></div><div>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</div><div><br></div><div>You can download the pre-trained cerebrovascular 4DFlowNet on this site.</div><div>Usage on other vascular anatomy has not been tested yet, however we argue the network can generalize well to other vasculature.</div>