Takashi Fujiwara1, Haben Berhane2, Michael B Scott2,3, Erin K Englund1, Michal Schäfer4, Brian Fonseca5, Alexander Berthusen1, Joshua D Robinson3,6,7, Cynthia K Rigsby3,7,8, Lorna P Browne1, Michael Markl2,3, Alex J Barker1,9. 1. Department of Radiology, Section of Pediatric Radiology, Children's Hospital Colorado, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA. 2. Department of Biomedical Engineering, Northwestern University, Chicago, Illinois, USA. 3. Department of Radiology, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA. 4. Division of Cardiology, Heart Institute, Children's Hospital Colorado, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA. 5. Department of Pediatrics, Section of Pediatric Cardiology, Children's Hospital Colorado, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA. 6. Division of Pediatric Cardiology, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA. 7. Department of Pediatrics, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA. 8. Department of Medical Imaging, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Illinois, USA. 9. Department of Bioengineering, University of Colorado Anschutz Medical Campus, Aurora, Colorado, USA.
Abstract
BACKGROUND: Automated segmentation using convolutional neural networks (CNNs) have been developed using four-dimensional (4D) flow magnetic resonance imaging (MRI). To broaden usability for congenital heart disease (CHD), training with multi-institution data is necessary. However, the performance impact of heterogeneous multi-site and multi-vendor data on CNNs is unclear. PURPOSE: To investigate multi-site CNN segmentation of 4D flow MRI for pediatric blood flow measurement. STUDY TYPE: Retrospective. POPULATION: A total of 174 subjects across two sites (female: 46%; N = 38 healthy controls, N = 136 CHD patients). Participants from site 1 (N = 100), site 2 (N = 74), and both sites (N = 174) were divided into subgroups to conduct 10-fold cross validation (10% for testing, 90% for training). FIELD STRENGTH/SEQUENCE: 3 T/1.5 T; retrospectively gated gradient recalled echo-based 4D flow MRI. ASSESSMENT: Accuracy of the 3D CNN segmentations trained on data from single site (single-site CNNs) and data across both sites (multi-site CNN) were evaluated by geometrical similarity (Dice score, human segmentation as ground truth) and net flow quantification at the ascending aorta (Qs), main pulmonary artery (Qp), and their balance (Qp/Qs), between human observers, single-site and multi-site CNNs. STATISTICAL TESTS: Kruskal-Wallis test, Wilcoxon rank-sum test, and Bland-Altman analysis. A P-value <0.05 was considered statistically significant. RESULTS: No difference existed between single-site and multi-site CNNs for geometrical similarity in the aorta by Dice score (site 1: 0.916 vs. 0.915, P = 0.55; site 2: 0.906 vs. 0.904, P = 0.69) and for the pulmonary arteries (site 1: 0.894 vs. 0.895, P = 0.64; site 2: 0.870 vs. 0.869, P = 0.96). Qs site-1 medians were 51.0-51.3 mL/cycle (P = 0.81) and site-2 medians were 66.7-69.4 mL/cycle (P = 0.84). Qp site-1 medians were 46.8-48.0 mL/cycle (P = 0.97) and site-2 medians were 76.0-77.4 mL/cycle (P = 0.98). Qp/Qs site-1 medians were 0.87-0.88 (P = 0.97) and site-2 medians were 1.01-1.03 (P = 0.43). Bland-Altman analysis for flow quantification found equivalent performance. DATA CONCLUSION: Multi-site CNN-based segmentation and blood flow measurement are feasible for pediatric 4D flow MRI and maintain performance of single-site CNNs. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.
BACKGROUND: Automated segmentation using convolutional neural networks (CNNs) have been developed using four-dimensional (4D) flow magnetic resonance imaging (MRI). To broaden usability for congenital heart disease (CHD), training with multi-institution data is necessary. However, the performance impact of heterogeneous multi-site and multi-vendor data on CNNs is unclear. PURPOSE: To investigate multi-site CNN segmentation of 4D flow MRI for pediatric blood flow measurement. STUDY TYPE: Retrospective. POPULATION: A total of 174 subjects across two sites (female: 46%; N = 38 healthy controls, N = 136 CHD patients). Participants from site 1 (N = 100), site 2 (N = 74), and both sites (N = 174) were divided into subgroups to conduct 10-fold cross validation (10% for testing, 90% for training). FIELD STRENGTH/SEQUENCE: 3 T/1.5 T; retrospectively gated gradient recalled echo-based 4D flow MRI. ASSESSMENT: Accuracy of the 3D CNN segmentations trained on data from single site (single-site CNNs) and data across both sites (multi-site CNN) were evaluated by geometrical similarity (Dice score, human segmentation as ground truth) and net flow quantification at the ascending aorta (Qs), main pulmonary artery (Qp), and their balance (Qp/Qs), between human observers, single-site and multi-site CNNs. STATISTICAL TESTS: Kruskal-Wallis test, Wilcoxon rank-sum test, and Bland-Altman analysis. A P-value <0.05 was considered statistically significant. RESULTS: No difference existed between single-site and multi-site CNNs for geometrical similarity in the aorta by Dice score (site 1: 0.916 vs. 0.915, P = 0.55; site 2: 0.906 vs. 0.904, P = 0.69) and for the pulmonary arteries (site 1: 0.894 vs. 0.895, P = 0.64; site 2: 0.870 vs. 0.869, P = 0.96). Qs site-1 medians were 51.0-51.3 mL/cycle (P = 0.81) and site-2 medians were 66.7-69.4 mL/cycle (P = 0.84). Qp site-1 medians were 46.8-48.0 mL/cycle (P = 0.97) and site-2 medians were 76.0-77.4 mL/cycle (P = 0.98). Qp/Qs site-1 medians were 0.87-0.88 (P = 0.97) and site-2 medians were 1.01-1.03 (P = 0.43). Bland-Altman analysis for flow quantification found equivalent performance. DATA CONCLUSION: Multi-site CNN-based segmentation and blood flow measurement are feasible for pediatric 4D flow MRI and maintain performance of single-site CNNs. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.
Authors: Haben Berhane; Michael Scott; Mohammed Elbaz; Kelly Jarvis; Patrick McCarthy; James Carr; Chris Malaisrie; Ryan Avery; Alex J Barker; Joshua D Robinson; Cynthia K Rigsby; Michael Markl Journal: Magn Reson Med Date: 2020-03-13 Impact factor: 4.668
Authors: F Piatti; S Pirola; M Bissell; I Nesteruk; F Sturla; A Della Corte; A Redaelli; E Votta Journal: J Biomech Date: 2016-11-11 Impact factor: 2.712
Authors: Zahra Sedghi Gamechi; Lidia R Bons; Marco Giordano; Daniel Bos; Ricardo P J Budde; Klaus F Kofoed; Jesper Holst Pedersen; Jolien W Roos-Hesselink; Marleen de Bruijne Journal: Eur Radiol Date: 2019-01-23 Impact factor: 5.315