Mimount Bourfiss1, Jörg Sander2, Bob D de Vos2,3, Anneline S J M Te Riele4,5, Folkert W Asselbergs4,6,7, Ivana Išgum2,3,8, Birgitta K Velthuis9. 1. Department of Medicine, Division of Cardiology, University Medical Center Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands. m.bourfiss-2@umcutrecht.nl. 2. Department of Biomedical Engineering and Physics, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands. 3. Amsterdam Cardiovascular Sciences, Heart Failure & Arrhythmias, Amsterdam, The Netherlands. 4. Department of Medicine, Division of Cardiology, University Medical Center Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands. 5. Netherlands Heart Institute, Utrecht, The Netherlands. 6. Institute of Cardiovascular Science, Faculty of Population Health Sciences, University College London, London, UK. 7. Health Data Research UK and Institute of Health Informatics, University College London, London, UK. 8. Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands. 9. Department of Radiology, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
Abstract
BACKGROUND: Arrhythmogenic right ventricular cardiomyopathy (ARVC) is diagnosed according to the Task Force Criteria (TFC) in which cardiovascular magnetic resonance (CMR) imaging plays an important role. Our study aims to apply an automatic deep learning-based segmentation for right and left ventricular CMR assessment and evaluate this approach for classification of the CMR TFC. METHODS: We included 227 subjects suspected of ARVC who underwent CMR. Subjects were classified into (1) ARVC patients fulfilling TFC; (2) at-risk family members; and (3) controls. To perform automatic segmentation, a Bayesian Dilated Residual Neural Network was trained and tested. Performance of automatic versus manual segmentation was assessed using Dice-coefficient and Hausdorff distance. Since automatic segmentation is most challenging in basal slices, manual correction of the automatic segmentation in the most basal slice was simulated (automatic-basal). CMR TFC calculated using manual and automatic-basal segmentation were compared using Cohen's Kappa (κ). RESULTS: Automatic segmentation was trained on CMRs of 70 subjects (39.6 ± 18.1 years, 47% female) and tested on 157 subjects (36.9 ± 17.6 years, 59% female). Dice-coefficient and Hausdorff distance showed good agreement between manual and automatic segmentations (≥ 0.89 and ≤ 10.6 mm, respectively) which further improved after simulated correction of the most basal slice (≥ 0.92 and ≤ 9.2 mm, p < 0.001). Pearson correlation of volumetric and functional CMR measurements was good to excellent (automatic (r = 0.78-0.99, p < 0.001) and automatic-basal (r = 0.88-0.99, p < 0.001) measurements). CMR TFC classification using automatic-basal segmentations was comparable to manual segmentations (κ 0.98 ± 0.02) with comparable diagnostic performance. CONCLUSIONS: Combining automatic segmentation of CMRs with correction of the most basal slice results in accurate CMR TFC classification of subjects suspected of ARVC.
BACKGROUND: Arrhythmogenic right ventricular cardiomyopathy (ARVC) is diagnosed according to the Task Force Criteria (TFC) in which cardiovascular magnetic resonance (CMR) imaging plays an important role. Our study aims to apply an automatic deep learning-based segmentation for right and left ventricular CMR assessment and evaluate this approach for classification of the CMR TFC. METHODS: We included 227 subjects suspected of ARVC who underwent CMR. Subjects were classified into (1) ARVC patients fulfilling TFC; (2) at-risk family members; and (3) controls. To perform automatic segmentation, a Bayesian Dilated Residual Neural Network was trained and tested. Performance of automatic versus manual segmentation was assessed using Dice-coefficient and Hausdorff distance. Since automatic segmentation is most challenging in basal slices, manual correction of the automatic segmentation in the most basal slice was simulated (automatic-basal). CMR TFC calculated using manual and automatic-basal segmentation were compared using Cohen's Kappa (κ). RESULTS: Automatic segmentation was trained on CMRs of 70 subjects (39.6 ± 18.1 years, 47% female) and tested on 157 subjects (36.9 ± 17.6 years, 59% female). Dice-coefficient and Hausdorff distance showed good agreement between manual and automatic segmentations (≥ 0.89 and ≤ 10.6 mm, respectively) which further improved after simulated correction of the most basal slice (≥ 0.92 and ≤ 9.2 mm, p < 0.001). Pearson correlation of volumetric and functional CMR measurements was good to excellent (automatic (r = 0.78-0.99, p < 0.001) and automatic-basal (r = 0.88-0.99, p < 0.001) measurements). CMR TFC classification using automatic-basal segmentations was comparable to manual segmentations (κ 0.98 ± 0.02) with comparable diagnostic performance. CONCLUSIONS: Combining automatic segmentation of CMRs with correction of the most basal slice results in accurate CMR TFC classification of subjects suspected of ARVC.
Authors: James Clough; Nicholas Byrne; Ilkay Oksuz; Veronika A Zimmer; Julia A Schnabel; Andrew King Journal: IEEE Trans Pattern Anal Mach Intell Date: 2020-09-04 Impact factor: 6.226