Purpose To develop a prospective motion correction (MC) method for phase contrast (PC) MRI of penetrating arteries (PAs) in centrum semiovale at 7 T and to evaluate its performance using automatic PA segmentation. Methods Head motion was monitored and corrected during the scan based on fat navigator images. Two convolutional neural networks (CNN) were developed to automatically segment PAs and exclude surface vessels. Real‐life scans with MC and without MC (NoMC) were performed to evaluate the MC performance. Motion score was calculated from the ranges of translational and rotational motion parameters. MC versus NoMC pairs with similar motion scores during MC and NoMC scans were compared. Data corrupted by motion were reacquired to further improve PA visualization. Results PA counts (NPA) and PC and magnitude contrasts (MgC) relative to neighboring tissue were significantly correlated with motion score and were higher in MC than NoMC images at motion scores above 0.5–0.8 mm. Data reacquisition further increased PC but had no significant effect on NPA and MgC. CNNs had higher sensitivity and Dice similarity coefficient for detecting PAs than a threshold‐based method. Conclusions Prospective MC can improve the count and contrast of segmented PAs in the presence of severe motion. CNN‐based PA segmentation has improved performance in delineating PAs than the threshold‐based method.

No abstract

Purpose: To develop a prospective motion correction (MC) method for phase contrast (PC) MRI of penetrating arteries (PA) in centrum semiovale at 7 T and evaluate its performance using automatic PA segmentation. Methods: Head motion was monitored and corrected during the scan based on fat navigator images. Two convolutional neural networks (CNN) were developed to automatically segment PAs and exclude surface vessels. Real-life scans with MC and without MC (NoMC) were performed to evaluate the MC performance. Motion score was calculated from the range of translational and rotational motion parameters. MC vs NoMC pairs were divided according to their score differences into groups with similar, less, or more motions during MC. Data reacquisition was also performed to evaluate whether it can further improve PA visualization. Results: In the group with similar motion, more PA counts (NPA) were obtained with MC in 9 (60%) cases, significantly more than the number of cases (1) with less PAs (p = 0.011; binomial test). In the group with less motion during MC, MC images had more or similar NPA in all cases, while in the group with more motion during MC, the numbers of cases with less and more NPA during MC were not significantly different (3 vs 0). Data reacquisition did not further increase NPA. CNNs had higher sensitivity (0.85) and accuracy (Dice coefficient 0.85) of detecting PAs than a threshold based method. Conclusions: Prospective MC and CNN based segmentation improved the visualization and delineation of PAs in PC MRI at 7 T.

No abstract