Automated biventricular quantification in patients with repaired tetralogy of Fallot using a three-dimensional deep learning segmentation model.

Deep learning is the state-of-the-art approach for automated segmentation of the left ventricle (LV) and right ventricle (RV) in cardiovascular magnetic resonance (CMR) images. However, these models have been mostly trained and validated using CMR datasets of structurally normal hearts or cases with acquired cardiac disease, and are therefore not well-suited to handle cases with congenital cardiac disease such as tetralogy of Fallot (TOF). We aimed to develop and validate a dedicated model with improved performance for LV and RV cavity and myocardium quantification in patients with repaired TOF. We trained a three-dimensional (3D) convolutional neural network (CNN) with 5-fold cross-validation using manually delineated end-diastolic (ED) and end-systolic (ES) short-axis image stacks obtained from either a public dataset containing patients with no or acquired cardiac pathology (n = 100), an institutional dataset of TOF patients (n = 96), or both datasets mixed. Our method allows for missing labels in the training images to accommodate for different ED and ES phases for LV and RV as is commonly the case in TOF. The best performing model was applied to all frames of a separate test set of TOF cases (n = 36) and ED and ES phases were automatically determined for LV and RV separately. The model was evaluated against the performance of a commercial software (suiteHEART®, NeoSoft, Pewaukee, Wisconsin, US). Training on the mixture of both datasets yielded the best agreement with the manual ground truth for the TOF cases, achieving a median Dice similarity coefficient of (93.8%, 89.8%) for LV cavity and of (92.9%, 90.9%) for RV cavity at (ED, ES) respectively, and of 80.9% and 61.8% for LV and RV myocardium at ED. The offset in automated ED and ES frame selection was 0.56 and 0.89 frames on average for LV and RV respectively. No statistically significant differences were found between our model and the commercial software for LV quantification (two-sided Wilcoxon signed rank test, p<5%), while RV quantification was significantly improved with our model achieving a mean absolute error of 12 ml for RV cavity compared to 36 ml for the commercial software. We developed and validated a fully automatic segmentation and quantification approach for LV and RV, including RV mass, in patients with repaired TOF. Compared to a commercial software, our approach is superior for RV quantification indicating its potential in clinical practice.

Tilborghs S ，Liang T ，Raptis S ，Ishikita A ，Budts W ，Dresselaers T ，Bogaert J ，Maes F ，Wald RM ，Van De Bruaene A ... -  《-》

Growth of the right ventricular outflow tract in repaired tetralogy of Fallot: A longitudinal CMR study.

Jurow K ，Gauvreau K ，Maschietto N ，Prakash A ... -  《-》

Deep learning based automated left ventricle segmentation and flow quantification in 4D flow cardiac MRI.

Sun X ，Cheng LH ，Plein S ，Garg P ，van der Geest RJ ... -  《-》

Cardiovascular magnetic resonance semi-automated threshold-based post-processing of right ventricular volumes in repaired tetralogy of Fallot.

Cardiovascular magnetic resonance (CMR) is the gold-standard to estimate right ventricular (RV) volumes, which are key for clinical management of patients with repaired tetralogy of Fallot (rTOF). Semi-automated threshold-based methods (SAT) have been proposed for CMR post-processing as alternatives to fully manual standard tracing. We investigated the impact of SAT on RV analysis using different thresholds in rTOF patients. RV volumes and mass were estimated using SAT and standard fully manual tracing methods in rTOF patients. Two threshold levels were set for SAT, i.e., default 50 (SAT-50) and 30 (SAT-30). RV stroke volumes (SV) were compared to main pulmonary artery forward flow (MPA-FF). Post-processing time, intra- and interobserver variabilities were compared across methods. Sixty-two CMRs of rTOF patients were analyzed. Compared to the standard fully manual tracing, no significant differences in RV mass, volumes and ejection fraction were observed using SAT-30, whereas SAT-50 significantly underestimated RV end-diastolic-volume index (EDVi) by 10.4% (mean difference of - 11.8 ± 6.2 ml/m2, p 0.03) and overestimated RV mass index by 21.8% (mean difference of 14.2 ± 11.9 g/m2, p 0.002). Compared to MPA-FF, RVSV by standard fully manual method and SAT-30 showed minor biases, respectively, 0.03 ml/m2 and 0.7 ml/m2, while SAT-50 underestimated RVSV by 6.86 ml/m2 (p < 0.001). In six patients, the degree of RV EDVi underestimation by SAT-50 determined a change of category from dilated to non-dilated RV. Intra- and interobserver variabilities were good to excellent for all methods. Post-processing duration was shorter for SAT compared to standard manual segmentation (5.5 ± 1.7 min vs. 19.5 ± 4.4 min, p < 0.001). CMR SAT-30 post-processing is a precise, accurate and time-saving method for biventricular assessment of volumes, ejection fraction and mass in rTOF.

Tondi L ，Figliozzi S ，Boveri S ，Sturla F ，Pasqualin G ，Camporeale A ，Disabato G ，Attanasio A ，Carrafiello G ，Spagnolo P ，Lombardi M ... -  《-》

Prognostic value of myocardial deformation parameters for outcome prediction in tetralogy of Fallot.

The prognostic value of myocardial deformation parameters in adults with repaired tetralogy of Fallot (rTOF) has not been well-elucidated. We therefore aimed to explore myocardial deformation parameters for outcome prediction in adults with rTOF using cardiovascular magnetic resonance imaging (CMR). Adults with rTOF and at least moderate pulmonary regurgitation were identified from an institutional prospective CMR registry. Left ventricular (LV) and right ventricular (RV) global strains were recorded in longitudinal (GLS), circumferential (GCS), and radial (GRS) directions. Major adverse cardiovascular events (MACE) were defined as a composite of mortality, resuscitated sudden death, sustained ventricular tachycardia (>30 seconds), or heart failure (hospital admission >24 hours). In patients with pulmonary valve replacement (PVR), pre- and post-PVR CMR studies were analyzed to assess for predictors of complete RV reverse remodeling, defined as indexed RV end-diastolic volume (RVEDVi) <110 mL/m2. Logistic regression models were used to estimate the odds ratio (OR) per unit change in absolute strain value associated with clinical outcomes and receiver operator characteristic curves were constructed with area under the curve (AUC) for select CMR variables. We included 307 patients (age 35 ± 13 years, 59% (180/307) male). During 6.1 years (3.3-8.8) of follow-up, PVR was performed in 142 (46%) and MACE occurred in 31 (10%). On univariate analysis, baseline biventricular ejection fraction (EF), mass, and all strain parameters were associated with MACE. After adjustment for LVEF, only LV-GLS remained independently predictive of MACE (OR 0.822 [0.693-0.976] p = 0.025). Receiver operator curves identified an absolute LV-GLS value less than 15 and LVEF less than 51% as thresholds for MACE prediction (AUC 0.759 [0.655-0.840] and 0.720 [0.608-0.810]). After adjusting for baseline RVEDVi, RV-GCS (OR 1.323 [1.094-1.600] p = 0.004), LV-GCS (OR 1.276 [1.029-1.582] p = 0.027) and LV-GRS (OR 1.101 [1.0210-1.200], p = 0.028) were independent predictors of complete remodeling post-PVR remodeling. Biventricular strain parameters predict clinical outcomes and post-PVR remodeling in rTOF. Further study will be necessary to establish the role of myocardial deformation parameters in clinical practice.

Thomas SK ，DSouza R ，Hanneman K ，Karur GR ，Houbois C ，Ishikita A ，D'Errico L ，Begun I ，Ng MY ，Wald RM ... -  《-》