Key result
Deep learning CMR segmentation with manual basal correction achieves ~98% agreement for ARVC classification.
Why the study?
CMR plays an important role in ARVC Task Force Criteria, and the study aimed to evaluate automatic deep learning-based ventricular segmentation for CMR TFC classification.
Does automatic deep learning-based segmentation with basal slice correction provide comparable accuracy to manual segmentation for CMR TFC classification in subjects suspected of ARVC?
Cross-Sectional (n=227)
No
Does automatic deep learning-based segmentation with basal slice correction provide comparable accuracy to manual segmentation for CMR TFC classification in subjects suspected of ARVC?
Answers are grounded in this paper and cite their sources.
Combining automatic deep learning segmentation of CMRs with manual correction of the most basal slice provides accurate CMR TFC classification for ARVC that is comparable to fully manual segmentation.
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.
No takes yet. Share an insight, caveat, or question.
Bourfiss et al. (2022) conducted a cross-sectional in Arrhythmogenic right ventricular cardiomyopathy (ARVC) (n=227). Automatic deep learning-based segmentation with manual correction of the most basal slice vs. Manual segmentation was evaluated on Agreement of CMR Task Force Criteria classification between manual and automatic-basal segmentations (κ 0.98). Combining automatic deep learning-based segmentation of cardiovascular magnetic resonance images with manual correction of the most basal slice resulted in accurate Task Force Criteria classification for ARVC.
Synapse has enriched 10 related papers. Consider them for comparative context: