Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning

• Published in: Magnetic resonance in medicine Vol. 84; no. 4; pp. 2204 - 2218
• Main Authors: Berhane, Haben, Scott, Michael, Elbaz, Mohammed, Jarvis, Kelly, McCarthy, Patrick, Carr, James, Malaisrie, Chris, Avery, Ryan, Barker, Alex J., Robinson, Joshua D., Rigsby, Cynthia K., Markl, Michael
• Format: Journal Article
• Language: English
• Published: United States Wiley Subscription Services, Inc 01.10.2020
• Subjects: 4D flow MRI; Aorta; Aorta - diagnostic imaging; Aortic valve; Artificial neural networks; Automation; Coronary vessels; Deep Learning; Ground truth; Heart valves; Hemodynamics; Humans; Image processing; Image segmentation; Machine learning; Magnetic Resonance Imaging; Metric space; MRI; Neural networks; Reproducibility; Reproducibility of Results; thoracic aorta; Three dimensional flow; Velocity; 4D flow MRI; thoracic aorta; machine learning; MRI; hemodynamics

Purpose To generate fully automated and fast 4D‐flow MRI‐based 3D segmentations of the aorta using deep learning for reproducible quantification of aortic flow, peak velocity, and dimensions. Methods A total of 1018 subjects with aortic 4D‐flow MRI (528 with bicuspid aortic valve, 376 with tricuspid...