Deep learning–based velocity antialiasing of 4D‐flow MRI

• Published in: Magnetic resonance in medicine 2022-07, Vol.88 (1), p.449-463
• Main Authors: Berhane, Haben, Scott, Michael B., Barker, Alex J., McCarthy, Patrick, Avery, Ryan, Allen, Brad, Malaisrie, Chris, Robinson, Joshua D., Rigsby, Cynthia K., Markl, Michael
• Format: Article
• Language: English
• Subjects: 4D flow; Adult; Algorithms; Aliasing; Aorta; Artificial neural networks; Blood Flow Velocity; Computer simulation; Datasets; Deep Learning; hemodynamics; Humans; Imaging, Three-Dimensional; Machine learning; Magnetic Resonance Imaging; MRI; Neural networks; Phantoms, Imaging; Reproducibility of Results; Robustness; thoracic aorta; Velocity
• ISSN: 0740-3194; 1522-2594
• DOI: 10.1002/mrm.29205

Purpose To develop a convolutional neural network (CNN) for the robust and fast correction of velocity aliasing in 4D‐flow MRI. Methods This study included 667 adult subjects with aortic 4D‐flow MRI data with existing velocity aliasing (n = 362) and no velocity aliasing (n = 305). Additionally, 10 controls received back‐to‐back 4D‐flow scans with systemically varied velocity‐encoding sensitivity (vencs) at 60, 100, and 175 cm/s. The no‐aliasing data sets were used to simulate velocity aliasing by reducing the venc to 40%–70% of the original, alongside a ground truth locating all aliased voxels (153 training, 152 testing). The 152 simulated and 362 existing aliasing data sets were used for testing and compared with a conventional velocity antialiasing algorithm. Dice scores were calculated to quantify CNN performance. For controls, the venc 175‐cm/s scans were used as the ground truth and compared with the CNN‐corrected venc 60 and 100 cm/s data sets Results The CNN required 176 ± 30 s to perform compared with 162 ± 14 s for the conventional algorithm. The CNN showed excellent performance for the simulated data compared with the conventional algorithm (median range of Dice scores CNN: [0.89–0.99], conventional algorithm: [0.84–0.94], p