Dataset Information

Toward Replacing Late Gadolinium Enhancement With Artificial Intelligence Virtual Native Enhancement for Gadolinium-Free Cardiovascular Magnetic Resonance Tissue Characterization in Hypertrophic Cardiomyopathy.

ABSTRACT:

Background

Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for noninvasive myocardial tissue characterization but requires intravenous contrast agent administration. It is highly desired to develop a contrast agent-free technology to replace LGE for faster and cheaper CMR scans.

Methods

A CMR virtual native enhancement (VNE) imaging technology was developed using artificial intelligence. The deep learning model for generating VNE uses multiple streams of convolutional neural networks to exploit and enhance the existing signals in native T1 maps (pixel-wise maps of tissue T1 relaxation times) and cine imaging of cardiac structure and function, presenting them as LGE-equivalent images. The VNE generator was trained using generative adversarial networks. This technology was first developed on CMR datasets from the multicenter Hypertrophic Cardiomyopathy Registry, using hypertrophic cardiomyopathy as an exemplar. The datasets were randomized into 2 independent groups for deep learning training and testing. The test data of VNE and LGE were scored and contoured by experienced human operators to assess image quality, visuospatial agreement, and myocardial lesion burden quantification. Image quality was compared using a nonparametric Wilcoxon test. Intra- and interobserver agreement was analyzed using intraclass correlation coefficients (ICC). Lesion quantification by VNE and LGE were compared using linear regression and ICC.

Results

A total of 1348 hypertrophic cardiomyopathy patients provided 4093 triplets of matched T1 maps, cines, and LGE datasets. After randomization and data quality control, 2695 datasets were used for VNE method development and 345 were used for independent testing. VNE had significantly better image quality than LGE, as assessed by 4 operators (n=345 datasets; P<0.001 [Wilcoxon test]). VNE revealed lesions characteristic of hypertrophic cardiomyopathy in high visuospatial agreement with LGE. In 121 patients (n=326 datasets), VNE correlated with LGE in detecting and quantifying both hyperintensity myocardial lesions (r=0.77-0.79; ICC=0.77-0.87; P<0.001) and intermediate-intensity lesions (r=0.70-0.76; ICC=0.82-0.85; P<0.001). The native CMR images (cine plus T1 map) required for VNE can be acquired within 15 minutes and producing a VNE image takes less than 1 second.

Conclusions

VNE is a new CMR technology that resembles conventional LGE but without the need for contrast administration. VNE achieved high agreement with LGE in the distribution and quantification of lesions, with significantly better image quality.

SUBMITTER: Zhang Q

PROVIDER: S-EPMC8378544 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundLate gadolinium enhancement (LGE) on cardiac magnetic resonance imaging (CMR) is believed to represent dense replacement fibrosis. It is seen in ≈60% of adult patients with hypertrophic cardiomyopathy (HCM). However, the prevalence of LGE in children and adolescents with HCM is not well established. In addition, longitudinal studies describing the development and evolution of LGE in pediatric HCM are lacking. This study assesses the prevalence, progression, and clinical correlations of LGE in children and adolescents with, or genetically predisposed to, HCM.MethodsCMR scans from 195 patients ≤21 years of age were analyzed in an observational, retrospective study, including 155 patients with overt HCM and 40 sarcomere mutation carriers without left ventricular (LV) hypertrophy. The extent of LGE was quantified by measuring regions with signal intensity >6 SD above nulled remote myocardium.ResultsPatients were 14.3±4.5 years of age at baseline and 68% were male. LGE was present in 70 (46%) patients with overt HCM (median extent, 3.3%; interquartile range, 0.8-7.1%), but absent in mutation carriers without LV hypertrophy. Thirty-one patients had >1 CMR (median interval between studies, 2.4 years; interquartile range, 1.5-3.2 years). LGE was detected in 13 patients (42%) at baseline and in 16 patients (52%) at follow-up CMR. The median extent of LGE increased by 2.4 g/y (range, 0-13.2 g/y) from 2.9% (interquartile range, 0.8-3.2%) of LV mass to 4.3% (interquartile range, 2.9-6.8%) ( P=0.02). In addition to LGE, LV mass and left atrial volume, indexed to body surface area, and z score for LV mass, as well, increased significantly from first to most recent CMR.ConclusionsLGE was present in 46% of children and adolescents with overt HCM, in contrast to ≈60% typically reported in adult HCM. In the subset of patients with serial imaging, statistically significant increases in LGE, LV mass, and left atrial size were detected over 2.5 years, indicating disease progression over time. Further prospective studies are required to confirm these findings and to better understand the clinical implications of LGE in pediatric HCM.

Project description:BackgroundArtificial intelligence (AI) applied to 12-lead electrocardiographs (ECGs) can detect hypertrophic cardiomyopathy (HCM).ObjectivesThe purpose of this study was to determine if AI-enhanced ECG (AI-ECG) can track longitudinal therapeutic response and changes in cardiac structure, function, or hemodynamics in obstructive HCM during mavacamten treatment.MethodsWe applied 2 independently developed AI-ECG algorithms (University of California-San Francisco and Mayo Clinic) to serial ECGs (n = 216) from the phase 2 PIONEER-OLE trial of mavacamten for symptomatic obstructive HCM (n = 13 patients, mean age 57.8 years, 69.2% male). Control ECGs from 2,600 age- and sex-matched individuals without HCM were obtained. AI-ECG output was correlated longitudinally to echocardiographic and laboratory metrics of mavacamten treatment response.ResultsIn the validation cohorts, both algorithms exhibited similar performance for HCM diagnosis, and exhibited mean HCM score decreases during mavacamten treatment: patient-level score reduction ranged from approximately 0.80 to 0.45 for Mayo and 0.70 to 0.35 for USCF algorithms; 11 of 13 patients demonstrated absolute score reduction from start to end of follow-up for both algorithms. HCM scores were significantly associated with other HCM-relevant parameters, including left ventricular outflow tract gradient at rest, postexercise, and with Valsalva, and NT-proBNP level, independent of age and sex (all P < 0.01). For both algorithms, the strongest longitudinal correlation was between AI-ECG HCM score and left ventricular outflow tract gradient postexercise (slope estimate: University of California-San Francisco 0.70 [95% CI: 0.45-0.96], P < 0.0001; Mayo 0.40 [95% CI: 0.11-0.68], P = 0.007).ConclusionsAI-ECG analysis longitudinally correlated with changes in echocardiographic and laboratory markers during mavacamten treatment in obstructive HCM. These results provide early evidence for a potential paradigm for monitoring HCM therapeutic response.

Project description:ObjectivesEntropy is a new late gadolinium enhanced (LGE) cardiac magnetic resonance (CMR)-derived parameter that is independent of signal intensity thresholds. Entropy can be used to measure myocardial tissue heterogeneity by comparing full pixel points of tissue images. This study investigated the incremental prognostic value of left ventricular (LV) entropy in patients with hypertrophic cardiomyopathy (HCM).MethodsThis study enrolled 337 participants with HCM who underwent 3.0-T CMR. The LV entropy was obtained by calculating the probability distribution of the LV myocardial pixel signal intensities of the LGE sequence. Patients who underwent CMR imaging were followed up for endpoints. The primary endpoint was defined as readmission to the hospital owing to heart failure. The secondary endpoint was the composite of the primary endpoint, sudden cardiac death and non-cardiovascular death.ResultsDuring the median follow-up of 24 months ± 13 (standard deviation), 43 patients who reached the primary and secondary endpoints had a higher entropy (6.20 ± 0.45, p < 0.001). The patients with increased entropy (≥ 5.587) had a higher risk of the primary and secondary endpoints, compared with HCM patients with low entropy (p < 0.001 for both). In addition, Cox analysis showed that LV entropy provided significant prognostic value for predicting both primary and secondary endpoints (HR: 1.291 and 1.273, all p < 0.001). Addition of LV entropy to the multivariable model improved model performance and risk reclassification (p < 0.05).ConclusionLV entropy assessed by CMR was an independent predictor of primary and secondary endpoints. LV entropy assessment contributes to improved risk stratification in patients with HCM.Critical relevance statementMyocardial heterogeneity reflected by entropy the derived parameter of LGE has prognostic value for adverse events in HCM. The measurement of LV entropy helped to identify patients with HCM who were at risk for heart failure and sudden cardiac death.Key points• Left ventricular entropy can reflect myocardial heterogeneity in HCM patients. • Left ventricular entropy was significantly higher in HCM patients who reached endpoint events. • Left ventricular entropy helps to predict the occurrence of heart failure and death in HCM patients.

Project description:BackgroundIdentifying the patients with hypertrophic cardiomyopathy (HCM) in whom the risk of sudden cardiac death (SCD) justifies the implantation of a cardioverter-defibrillator (ICD) in primary prevention remains challenging. Different risk stratification and criteria are used by the European and American guidelines in this setting. We sought to evaluate the role of cardiovascular magnetic resonance (CMR) late gadolinium enhancement (LGE) in improving these risk stratification strategies.MethodsWe conducted a multicentric retrospective analysis of HCM patients who underwent CMR for diagnostic confirmation and/or risk stratification. Eligibility for ICD was assessed according to the HCM Risk-SCD score and the American College of Cardiology Foundation/American Heart Association (ACCF/AHA) algorithm. The amount of LGE was quantified (LGE%) and categorized as 0%, 0.1-10%, 10.1-19.9% and ≥ 20%. The primary endpoint was a composite of SCD, aborted SCD, sustained ventricular tachycardia (VT), or appropriate ICD discharge.ResultsA total of 493 patients were available for analysis (58% male, median age 46 years). LGE was present in 79% of patients, with a median LGE% of 2.9% (IQR 0.4-8.4%). The concordance between risk assessment by the HCM Risk-SCD, ACCF/AHA and LGE was relatively weak. During a median follow-up of 3.4 years (IQR 1.5-6.8 years), 23 patients experienced an event (12 SCDs, 6 appropriate ICD discharges and 5 sustained VTs). The amount of LGE was the only independent predictor of outcome (adjusted HR: 1.08; 95% CI: 1.04-1.12; p < 0.001) after adjustment for the HCM Risk-SCD and ACCF/AHA criteria. The amount of LGE showed greater discriminative power (C-statistic 0.84; 95% CI: 0.76-0.91) than the ACCF/AHA (C-statistic 0.61; 95% CI: 0.49-0.72; p for comparison < 0.001) and the HCM Risk-SCD (C-statistic 0.68; 95% CI: 0.59-0.78; p for comparison = 0.006). LGE was able to increase the discriminative power of the ACCF/AHA and HCM Risk-SCD criteria, with net reclassification improvements of 0.36 (p = 0.021) and 0.43 (p = 0.011), respectively.ConclusionsThe amount of LGE seems to outperform the HCM Risk-SCD score and the ACCF/AHA algorithm in the identification of HCM patients at increased risk of SCD and reclassifies a relevant proportion of patients.