Dataset Information

Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study.

ABSTRACT: Background Cardiac MRI late gadolinium enhancement (LGE) scar volume is an important marker for outcome prediction in patients with hypertrophic cardiomyopathy (HCM); however, its clinical application is hindered by a lack of measurement standardization. Purpose To develop and evaluate a three-dimensional (3D) convolutional neural network (CNN)-based method for automated LGE scar quantification in patients with HCM. Materials and Methods We retrospectively identified LGE MRI data in a multicenter (n = 7) and multivendor (n = 3) HCM study obtained between November 2001 and November 2011. A deep 3D CNN based on U-Net architecture was used for LGE scar quantification. Independent CNN training and testing data sets were maintained with a 4:1 ratio. Stacks of short-axis MRI slices were split into overlapping substacks that were segmented and then merged into one volume. The 3D CNN per-site and per-vendor performances were evaluated with respect to manual scar quantification performed in a core laboratory setting using Dice similarity coefficient (DSC), Pearson correlation, and Bland-Altman analyses. Furthermore, the performance of 3D CNN was compared with that of two-dimensional (2D) CNN. Results This study included 1073 patients with HCM (733 men; mean age, 49 years ± 17 [standard deviation]). The 3D CNN-based quantification was fast (0.15 second per image) and demonstrated excellent correlation with manual scar volume quantification (r = 0.88, P < .001) and ratio of scar volume to total left ventricle myocardial volume (%LGE) (r = 0.91, P < .001). The 3D CNN-based quantification strongly correlated with manual quantification of scar volume (r = 0.82-0.99, P < .001) and %LGE (r = 0.90-0.97, P < .001) for all sites and vendors. The 3D CNN identified patients with a large scar burden (>15%) with 98% accuracy (202 of 207) (95% confidence interval [CI]: 95%, 99%). When compared with 3D CNN, 2D CNN underestimated scar volume (r = 0.85, P < .001) and %LGE (r = 0.83, P < .001). The DSC of 3D CNN segmentation was comparable among different vendors (P = .07) and higher than that of 2D CNN (DSC, 0.54 ± 0.26 vs 0.48 ± 0.29; P = .02). Conclusion In the hypertrophic cardiomyopathy population, a three-dimensional convolutional neural network enables fast and accurate quantification of myocardial scar volume, outperforms a two-dimensional convolutional neural network, and demonstrates comparable performance across different vendors. © RSNA, 2019 Online supplemental material is available for this article.

SUBMITTER: Fahmy AS

PROVIDER: S-EPMC6939743 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study.

Fahmy Ahmed S AS Neisius Ulf U Chan Raymond H RH Rowin Ethan J EJ Manning Warren J WJ Maron Martin S MS Nezafat Reza R

Radiology 20191112 1

Background Cardiac MRI late gadolinium enhancement (LGE) scar volume is an important marker for outcome prediction in patients with hypertrophic cardiomyopathy (HCM); however, its clinical application is hindered by a lack of measurement standardization. Purpose To develop and evaluate a three-dimensional (3D) convolutional neural network (CNN)-based method for automated LGE scar quantification in patients with HCM. Materials and Methods We retrospectively identified LGE MRI data in a multicente ...[more]

PMID: 31714190

Similar Datasets

Project description:Background Patients with hypertrophic cardiomyopathy (HCM) are at risk of ventricular arrhythmia (VA) attributed to abnormal electrical activation arising from myocardial fibrosis and myocyte disarray. We sought to quantify intra-QRS peaks (QRSp) in high-resolution ECGs as a measure of abnormal activation to predict late VA in patients with HCM. Methods and Results Prospectively enrolled patients with HCM (n=143, age 53±14 years) with prophylactic implantable cardioverter-defibrillators had 3-minute, high-resolution (1024 Hz), digital 12-lead ECGs recorded during intrinsic rhythm. For each precordial lead, QRSp was defined as the total number of peaks detected in the QRS complex that deviated from a smoothing filtered version of the QRS. The VA end point was appropriate implantable cardioverter-defibrillator therapy during 5-year prospective follow-up. After 5 years, 21 (16%) patients had VA. Patients who were VA positive had greater QRSp (6.0 [4.0-7.0] versus 4.0 [2.0-5.0]; P<0.01) and lower left ventricular ejection fraction (57±11 versus 62±9; P=0.038) compared with patients who were VA negative, but had similar established HCM risk metrics. Receiver operating characteristic analysis revealed that QRSp discriminated VA (area under the curve=0.76; P<0.001), with a QRSp ≥4 achieving 91% sensitivity and 39% specificity. The annual VA rate was greater in patients with QRSp ≥4 versus QRSp <4 (4.4% versus 0.98%; P=0.012). In multivariable Cox regression, age <50 years (hazard ratio [HR], 2.53; P=0.009) and QRSp (HR per QRS peak, 1.41; P=0.009) predicted VA after adjusting for established HCM risk metrics. In patients aged <50 years, the annual VA rate was 0.0% for QRSp <4 compared with 6.9% for QRSp ≥4 (P=0.012). Conclusions QRSp predicted VA in patients with HCM who were eligible for an implantable cardioverter-defibrillator after adjusting for established HCM risk metrics, such that each additional QRS peak increases VA risk by 40%. QRSp <4 was associated with a <1% annual VA risk in all patients, and no VA risk among those aged <50 years. This novel ECG metric may improve patient selection for prophylactic implantable cardioverter-defibrillator therapy by identifying those with low VA risk. These findings require further validation in a lower risk HCM cohort. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT02560844.

Project description:BackgroundIn patients with suspected or known hypertrophic cardiomyopathy (HCM), late gadolinium enhancement (LGE) provides diagnostic and prognostic value. However, contraindications and long-term retention of gadolinium have raised concern about repeated gadolinium administration in this population. Alternatively, native T1 -mapping enables identification of focal fibrosis, the substrate of LGE. However HCM-specific heterogeneous fibrosis distribution leads to subtle T1 -maps changes that are difficult to identify.PurposeTo apply radiomic texture analysis on native T1 -maps to identify patients with a low likelihood of LGE(+), thereby reducing the number of patients exposed to gadolinium administration.Study typeRetrospective interpretation of prospectively acquired data.SubjectsIn all, 188 (54.7 ± 14.4 years, 71% men) with suspected or known HCM.Field strength/sequenceA 1.5T scanner; slice-interleaved native T1 -mapping (STONE) sequence and 3D LGE after administration of 0.1 mmol/kg of gadobenate dimeglumine.AssessmentLeft ventricular LGE images were location-matched with native T1 -maps using anatomical landmarks. Using a split-sample validation approach, patients were randomly divided 3:1 (training/internal validation vs. test cohorts). To balance the data during training, 50% of LGE(-) slices were discarded.Statistical testsFour sets of texture descriptors were applied to the training dataset for capture of spatially dependent and independent pixel statistics. Five texture features were sequentially selected with the best discriminatory capacity between LGE(+) and LGE(-) T1 -maps and tested using a decision tree ensemble (DTE) classifier.ResultsThe selected texture features discriminated between LGE(+) and LGE(-) T1 -maps with a c-statistic of 0.75 (95% confidence interval [CI]: 0.70-0.80) using 10-fold cross-validation during internal validation in the training dataset and 0.74 (95% CI: 0.65-0.83) in the independent test dataset. The DTE classifier provided adequate labeling of all (100%) LGE(+) patients and 37% of LGE(-) patients during testing.Data conclusionRadiomic analysis of native T1 -images can identify ~1/3 of LGE(-) patients for whom gadolinium administration can be safely avoided.Level of evidence2 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2020. J. Magn. Reson. Imaging 2020;52:906-919.

Project description:Background Impaired myocardial blood flow (MBF) in the absence of epicardial coronary disease is a feature of hypertrophic cardiomyopathy (HCM). Although most evident in hypertrophied or scarred segments, reduced MBF can occur in apparently normal segments. We hypothesized that impaired MBF and myocardial perfusion reserve, quantified using perfusion mapping cardiac magnetic resonance, might occur in the absence of overt left ventricular hypertrophy (LVH) and late gadolinium enhancement, in mutation carriers without LVH criteria for HCM (genotype-positive, left ventricular hypertrophy-negative). Methods and Results A single center, case-control study investigated MBF and myocardial perfusion reserve (the ratio of MBF at stress:rest), along with other pre-phenotypic features of HCM. Individuals with genotype-positive, left ventricular hypertrophy-negative (n=50) with likely pathogenic/pathogenic variants and no evidence of LVH, and matched controls (n=28) underwent cardiac magnetic resonance. Cardiac magnetic resonance identified LVH-fulfilling criteria for HCM in 5 patients who were excluded. Individuals with genotype-positive, left ventricular hypertrophy-negative had longer indexed anterior mitral valve leaflet length (12.52±2.1 versus 11.55±1.6 mm/m2, P=0.03), lower left ventricular end-systolic volume (21.0±6.9 versus 26.7±6.2 mm/m2, P≤0.005) and higher left ventricular ejection fraction (71.9±5.5 versus 65.8±4.4%, P≤0.005). Maximum wall thickness was not significantly different (9.03±1.95 versus 8.37±1.2 mm, P=0.075), and no subject had significant late gadolinium enhancement (minor right ventricle‒insertion point late gadolinium enhancement only). Perfusion mapping demonstrated visual perfusion defects in 9 (20%) carriers versus 0 controls (P=0.011). These were almost all septal or near right ventricle insertion points. Globally, myocardial perfusion reserve was lower in carriers (2.77±0.83 versus 3.24±0.63, P=0.009), with a subendocardial:subepicardial myocardial perfusion reserve gradient (2.55±0.75 versus 3.2±0.65, P=<0.005; 3.01±0.96 versus 3.47±0.75, P=0.026) but equivalent MBF (2.75±0.82 versus 2.65±0.69 mL/g per min, P=0.826). Conclusions Regional and global impaired myocardial perfusion can occur in HCM mutation carriers, in the absence of significant hypertrophy or scarring.

Project description:BackgroundMyocardial scarring from infarction or nonischemic fibrosis forms an arrhythmogenic substrate. The Selvester QRS score has been extensively validated for estimating myocardial infarction scar size in the absence of ECG confounders, but has not been tested to quantify scar in patients with hypertrophy, bundle branch/fascicular blocks, or nonischemic cardiomyopathy. We assessed the hypotheses that (1) QRS scores (modified for each ECG confounder) correctly identify and quantify scar in ischemic and nonischemic patients when compared with the reference standard of cardiac magnetic resonance using late-gadolinium enhancement, and (2) QRS-estimated scar size predicts inducible sustained monomorphic ventricular tachycardia during electrophysiological testing.Methods and resultsOne hundred sixty-two patients with left ventricular ejection fraction < or =35% (95 ischemic, 67 nonischemic) received 12-lead ECG and cardiac magnetic resonance using late-gadolinium enhancement before implantable cardioverter defibrillator placement for primary prevention of sudden cardiac death. QRS scores correctly diagnosed cardiovascular magnetic resonance scar presence with receiver operating characteristics area under the curve of 0.91 and correlation for scar quantification of r=0.74 (P<0.0001) for all patients. Performance within hypertrophy, conduction defect, and nonischemic subgroups ranged from area under the curve of 0.81 to 0.94 and r=0.60 to 0.80 (P<0.001 for all). Among the 137 patients undergoing electrophysiological or device testing, each 3-point QRS-score increase (9% left ventricular scarring) was associated with an odds ratio for inducing monomorphic ventricular tachycardia of 2.2 (95% CI, 1.5 to 3.2; P<0.001) for all patients, 1.7 (1.0 to 2.7, P=0.04) for ischemics, and 2.2 (1.0 to 5.0, P=0.05) for nonischemics.ConclusionsQRS scores identify and quantify scar in ischemic and nonischemic cardiomyopathy patients despite ECG confounders. Higher QRS-estimated scar size is associated with increased arrhythmogenesis and warrants further study as a risk-stratifying tool.

Dataset Information

Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study.

Publications

Three-dimensional Deep Convolutional Neural Networks for Automated Myocardial Scar Quantification in Hypertrophic Cardiomyopathy: A Multicenter Multivendor Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets