ABSTRACT
OBJECTIVE: To evaluate an automatic correction method for velocity offset errors in cardiac 4D-flow acquisitions. MATERIALS AND METHODS: Velocity offset correction was done in a plane-by-plane scheme and compared to a volumetric approach. Stationary regions were automatically detected. In vitro experiments were conducted in a phantom using two orientations and two encoding velocities (Venc). First- to third-order models were fit to the time-averaged images of the three velocity components. In vivo experiments included realistic ROIs in a volunteer superimposed to a phantom. In 15 volunteers, blood flow volume of the proximal and distal descending aorta, of the pulmonary artery (Qp) and the ascending aorta (Qs) was compared. RESULTS: Offset errors were reduced after correction with a third-order model, yielding residual phantom velocities below 0.6 cm/s and 0.4% of Venc. The plane-by-plane correction method was more effective than the volumetric approach. Mean velocities through superimposed ROIs of a volunteer vs phantom were highly correlated (r2 = 0.96). The significant difference between proximal and distal descending aortic flows was decreased after correction from 8.1 to - 1.4 ml (p < 0.001) and Qp/Qs reduced from 1.08 ± 0.09 to 1.01 ± 0.05. DISCUSSION: An automatic third-order model corrected velocity offset errors in 4D-flow acquisitions, achieving acceptable levels for clinical applications.