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