TY - JOUR
T1 - Towards automatic classification of cardiovascular magnetic resonance Task Force Criteria for diagnosis of arrhythmogenic right ventricular cardiomyopathy
AU - Bourfiss, Mimount
AU - Sander, Jörg
AU - de Vos, Bob D.
AU - te Riele, Anneline S. J. M.
AU - Asselbergs, Folkert W.
AU - Išgum, Ivana
AU - Velthuis, Birgitta K.
N1 - Funding Information: Dr. Bourfiss is supported by the Alexandre Suerman Stipend of the UMC Utrecht (2017). J. Sander is supported by the Dutch Technology Foundation (DLMedIA program (P15-26)) with participation of Pie Medical Imaging. Dr. te Riele is supported by the Dutch Heart Foundation (grant no. 2015T058), the UMC Utrecht Fellowship Clinical Research Talent, and the CVON PREDICT Young Talent Program. Dr. Asselbergs is supported by UCL Hospitals NIHR Biomedical Research Center. The Netherlands ACM Registry ( www.acmregistry.nl ) is supported by the Netherlands Heart Institute (project 06901). Publisher Copyright: © 2022, The Author(s).
PY - 2023/3
Y1 - 2023/3
N2 - 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. Graphical abstract: [Figure not available: see fulltext.].
AB - 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. Graphical abstract: [Figure not available: see fulltext.].
KW - Arrhythmogenic right ventricular cardiomyopathy
KW - Automatic segmentation
KW - Cardiac magnetic resonance imaging
KW - Deep learning
UR - http://www.scopus.com/inward/record.url?scp=85137815007&partnerID=8YFLogxK
U2 - https://doi.org/10.1007/s00392-022-02088-x
DO - https://doi.org/10.1007/s00392-022-02088-x
M3 - Article
C2 - 36066609
SN - 1861-0684
VL - 112
SP - 363
EP - 378
JO - Clinical research in cardiology
JF - Clinical research in cardiology
IS - 3
ER -