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 aortic valve and aortic dilation, 114 healthy controls) comprised the data set. A convolutional neural network was trained to generate 3D aortic segmentations from 4D-flow data. Manual segmentations served as the ground truth (N = 499 training, N = 101 validation, N = 418 testing). Dice scores, Hausdorff distance, and average symmetrical surface distance were calculated to assess performance. Aortic flow, peak velocity, and lumen dimensions were quantified at the ascending, arch, and descending aorta and compared using Bland-Altman analysis. Interobserver variability of manual analysis was assessed on a subset of 40. RESULTS: Convolutional neural network segmentation required 0.438 ± 0.355 seconds versus 630 ± 254 seconds for manual analysis and demonstrated excellent performance with a median Dice score of 0.951 (0.930-0.966), Hausdorff distance of 2.80 (2.13-4.35), and average symmetrical surface distance of 0.176 (0.119-0.290). Excellent agreement was found for flow, peak velocity, and dimensions with low bias and limits of agreement less than 10% difference versus manual analysis. For aortic volume, limits of agreement were moderate within 16.3%. Interobserver variability (median Dice score: 0.950; Hausdorff distance: 2.45; and average symmetrical surface distance: 0.145) and convolutional neural network-based analysis (median Dice score: 0.953-0.959; Hausdorff distance: 2.24-2.91; and average symmetrical surface distance: 0.145-1.98 to observers) demonstrated similar reproducibility. CONCLUSIONS: Deep learning enabled fast and automated 3D aortic segmentation from 4D-flow MRI, demonstrating its potential for efficient clinical workflows. Future studies should investigate its utility for other vasculature and multivendor applications.
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 aortic valve and aortic dilation, 114 healthy controls) comprised the data set. A convolutional neural network was trained to generate 3D aortic segmentations from 4D-flow data. Manual segmentations served as the ground truth (N = 499 training, N = 101 validation, N = 418 testing). Dice scores, Hausdorff distance, and average symmetrical surface distance were calculated to assess performance. Aortic flow, peak velocity, and lumen dimensions were quantified at the ascending, arch, and descending aorta and compared using Bland-Altman analysis. Interobserver variability of manual analysis was assessed on a subset of 40. RESULTS: Convolutional neural network segmentation required 0.438 ± 0.355 seconds versus 630 ± 254 seconds for manual analysis and demonstrated excellent performance with a median Dice score of 0.951 (0.930-0.966), Hausdorff distance of 2.80 (2.13-4.35), and average symmetrical surface distance of 0.176 (0.119-0.290). Excellent agreement was found for flow, peak velocity, and dimensions with low bias and limits of agreement less than 10% difference versus manual analysis. For aortic volume, limits of agreement were moderate within 16.3%. Interobserver variability (median Dice score: 0.950; Hausdorff distance: 2.45; and average symmetrical surface distance: 0.145) and convolutional neural network-based analysis (median Dice score: 0.953-0.959; Hausdorff distance: 2.24-2.91; and average symmetrical surface distance: 0.145-1.98 to observers) demonstrated similar reproducibility. CONCLUSIONS: Deep learning enabled fast and automated 3D aortic segmentation from 4D-flow MRI, demonstrating its potential for efficient clinical workflows. Future studies should investigate its utility for other vasculature and multivendor applications.
Authors: F M Callaghan; J Karkouri; K Broadhouse; M Evin; D F Fletcher; S M Grieve Journal: Comput Methods Biomech Biomed Engin Date: 2015-08-03 Impact factor: 1.763
Authors: Luca Antiga; Marina Piccinelli; Lorenzo Botti; Bogdan Ene-Iordache; Andrea Remuzzi; David A Steinman Journal: Med Biol Eng Comput Date: 2008-11-11 Impact factor: 2.602
Authors: Ramona Lorenz; Jelena Bock; Jeff Snyder; Jan G Korvink; Bernd A Jung; Michael Markl Journal: Magn Reson Med Date: 2013-09-04 Impact factor: 4.668
Authors: Gilles Soulat; Michael B Scott; Bradley D Allen; Ryan Avery; Robert O Bonow; S Chris Malaisrie; Patrick McCarthy; Paul W M Fedak; Alex J Barker; Michael Markl Journal: JACC Cardiovasc Imaging Date: 2021-08-18
Authors: Vineeta Ojha; Omar K Khalique; Rishabh Khurana; Daniel Lorenzatti; Steve W Leung; Benny Lawton; Timothy C Slesnick; Joao C Cavalcante; Chiara-Bucciarelli Ducci; Amit R Patel; Claudia C Prieto; Sven Plein; Subha V Raman; Michael Salerno; Purvi Parwani Journal: J Cardiovasc Magn Reson Date: 2022-06-20 Impact factor: 6.903
Authors: Takashi Fujiwara; Haben Berhane; Michael B Scott; Erin K Englund; Michal Schäfer; Brian Fonseca; Alexander Berthusen; Joshua D Robinson; Cynthia K Rigsby; Lorna P Browne; Michael Markl; Alex J Barker Journal: J Magn Reson Imaging Date: 2021-11-18 Impact factor: 5.119
Authors: Ashitha Pathrose; Liliana Ma; Haben Berhane; Michael B Scott; Kelvin Chow; Christoph Forman; Ning Jin; Ali Serhal; Ryan Avery; James Carr; Michael Markl Journal: Magn Reson Med Date: 2020-10-26 Impact factor: 4.668
Authors: Jiacheng Zhang; Sean M Rothenberger; Melissa C Brindise; Michael B Scott; Haben Berhane; Justin J Baraboo; Michael Markl; Vitaliy L Rayz; Pavlos P Vlachos Journal: IEEE Trans Med Imaging Date: 2021-11-30 Impact factor: 10.048
Authors: Zahra Sedghi Gamechi; Andres M Arias-Lorza; Zaigham Saghir; Daniel Bos; Marleen de Bruijne Journal: Med Phys Date: 2021-10-29 Impact factor: 4.506