Deformation-encoding Deep Learning Transformer for High-Frame-Rate Cardiac Cine MRI.

Purpose To develop a deep learning model for increasing cardiac cine frame rate while maintaining spatial resolution and scan time. Materials and Methods A transformer-based model was trained and tested on a retrospective sample of cine images from 5840 patients (mean age, 55 years ± 19 [SD]; 3527 male patients) referred for clinical cardiac MRI from 2003 to 2021 at nine centers; images were acquired using 1.5- and 3-T scanners from three vendors. Data from three centers were used for training and testing (4:1 ratio). The remaining data were used for external testing. Cines with downsampled frame rates were restored using linear, bicubic, and model-based interpolation. The root mean square error between interpolated and original cine images was modeled using ordinary least squares regression. In a prospective study of 49 participants referred for clinical cardiac MRI (mean age, 56 years ± 13; 25 male participants) and 12 healthy participants (mean age, 51 years ± 16; eight male participants), the model was applied to cines acquired at 25 frames per second (fps), thereby doubling the frame rate, and these interpolated cines were compared with actual 50-fps cines. The preference of two readers based on perceived temporal smoothness and image quality was evaluated using a noninferiority margin of 10%. Results The model generated artifact-free interpolated images. Ordinary least squares regression analysis accounting for vendor and field strength showed lower error (P < .001) with model-based interpolation compared with linear and bicubic interpolation in internal and external test sets. The highest proportion of reader choices was "no preference" (84 of 122) between actual and interpolated 50-fps cines. The 90% CI for the difference between reader proportions favoring collected (15 of 122) and interpolated (23 of 122) high-frame-rate cines was -0.01 to 0.14, indicating noninferiority. Conclusion A transformer-based deep learning model increased cardiac cine frame rates while preserving both spatial resolution and scan time, resulting in images with quality comparable to that of images obtained at actual high frame rates. Keywords: Functional MRI, Heart, Cardiac, Deep Learning, High Frame Rate Supplemental material is available for this article. © RSNA, 2024.

The Paradigm of Sudden Death Prevention in Hypertrophic Cardiomyopathy.

Hypertrophic cardiomyopathy (HCM) is a relatively common and, often, inherited cardiac disease, once regarded as largely untreatable with ominous prognosis and, perhaps, most visibly as a common cause of sudden cardiac death (SCD) in the young. However, HCM is now more accurately considered a treatable disease with management options that significantly alter its clinical course. This is particularly true for SCD because the penetration of implantable cardioverter-defibrillators into HCM practice enables primary prevention device therapy that reliably terminates potentially lethal ventricular tachyarrhythmias (3% to 4%/year). This therapeutic advance is largely responsible for >10-fold decrease in the overall disease-related mortality to 0.5%/year, independent of patient age. A guideline-based clinical risk stratification algorithm has evolved, which included variables identifiable with cardiac magnetic resonance: ≥1 risk markers judged major within the clinical profile of an individual patient, associated with a measure of physician judgment and shared decision-making, can be sufficient to consider the recommendation of a prophylactic defibrillator implant. Implantable cardioverter-defibrillator decisions using the American College of Cardiology and the American Heart Association traditional major risk marker strategy are associated with a 95% sensitivity for identifying those patients who subsequently experience appropriate therapy, albeit often 5 to 10+ years after implant but without heart failure deterioration or death after a device intervention. A mathematical SCD risk score proposed by European Society of Cardiology is associated with a relatively low sensitivity (33%) for predicting and preventing SCD events but with potential for less device overtreatment.

Advances in the Management of Hypertrophic Cardiomyopathy Leading to Low Disease-Related Mortality in 2023.

Hypertrophic cardiomyopathy (HCM) is a relatively common often inherited heart disease encumbered throughout much of its almost 60-year history by the expectation of an unfavorable outcome with shortened longevity. However, it is notable that in 2023, most patients affected with HCM can now achieve normal or extended life expectancy without major disability because of a comprehensive constellation of management strategies that have evolved largely over the last 20 years. Distinct adverse disease pathways dictate high-benefit low-risk personalized treatments, without reliance on genomics and sarcomere mutations, including: primary prevention implantable defibrillators for sudden cardiac death prevention, surgical myectomy and percutaneous alcohol septal ablation to reverse heart failure symptoms, anticoagulation to prevent embolic stroke associated with concomitant atrial fibrillation, external defibrillation and hypothermia for out-of-hospital cardiac arrest, and heart transplant in a small patient subgroup with end-stage disease. Large cohort studies using these contemporary management strategies achieved remarkably low HCM-related mortality (0.5%/year) across all age groups, which is lower than in the other cardiac or noncardiac risks of living, and largely confined to nonobstructive patients with progressive heart failure, including those awaiting heart transplant.

Assessing the impact of atrial fibrillation on symptoms and quality of life in hypertrophic cardiomyopathy.

INTRODUCTION: In hypertrophic cardiomyopathy (HCM), atrial fibrillation (AF) has historically been regarded to have a deleterious impact on clinical course, strongly associated with progressive heart failure (HF) symptoms. However, there is a paucity of information regarding the impact of AF on HCM employing validated quality of life (QoL) surveys. Therefore, we evaluated the impact of AF on QoL utilizing patient reported outcome measures (PROMs). METHODS: 218 consecutive HCM patients with or without AF at the Lahey HCM center in 2022 completed PROMs at their most recent visit evaluating HF (Kansas City Cardiomyopathy Questionnaire [KCCQ]) and AF symptoms (AF Effect on QoL [AFEQT]). RESULTS: Among the 218 patients, 50 (23%) had a history of AF and comprise the primary study cohort. AF was diagnosed at 55 ± 10 years of age, median of 5.5 years before PROM, with 66% of patients treated with a rhythm control strategy with antiarrhythmic drug and/or AF ablation. AFEQT indicated that 52% of patients experienced no or minimal AF-related disability, mild to moderate in 22%, and severe in 26%. There was no substantial difference in HCM phenotype in patients with no or minimal AF disability compared to those with severe disability. HF symptoms for most HCM patients with prior AF history was consistent with no or minimal (59%) or only mild (27%) disability as measured by KCCQ overall summary scores. In addition, with multivariate analysis, AF history was associated with less HF symptoms and improved QoL (OR 0.4, p = 0.02). CONCLUSION: In contrast to prior perceptions, HCM patients with prior AF history were less likely to incur HF symptoms impairing QoL compared to HCM patients without AF. After treatment, prior history of AF did not substantially impact current QoL. These data provide a realistic appraisal for the impact that AF has on HCM patients and also offers a measure of reassurance for this patient subgroup.

Identification of high-risk imaging features in hypertrophic cardiomyopathy using electrocardiography: A deep-learning approach.

BACKGROUND: Patients with hypertrophic cardiomyopathy (HCM) are at risk of sudden death, and individuals with ≥1 major risk markers are considered for primary prevention implantable cardioverter-defibrillators. Guidelines recommend cardiac magnetic resonance (CMR) imaging to identify high-risk imaging features. However, CMR imaging is resource intensive and is not widely accessible worldwide. OBJECTIVE: The purpose of this study was to develop electrocardiogram (ECG) deep-learning (DL) models for the identification of patients with HCM and high-risk imaging features. METHODS: Patients with HCM evaluated at Tufts Medical Center (N = 1930; Boston, MA) were used to develop ECG-DL models for the prediction of high-risk imaging features: systolic dysfunction, massive hypertrophy (≥30 mm), apical aneurysm, and extensive late gadolinium enhancement. ECG-DL models were externally validated in a cohort of patients with HCM from the Amrita Hospital HCM Center (N = 233; Kochi, India). RESULTS: ECG-DL models reliably identified high-risk features (systolic dysfunction, massive hypertrophy, apical aneurysm, and extensive late gadolinium enhancement) during holdout testing (c-statistic 0.72, 0.83, 0.93, and 0.76) and external validation (c-statistic 0.71, 0.76, 0.91, and 0.68). A hypothetical screening strategy using echocardiography combined with ECG-DL-guided selective CMR use demonstrated a sensitivity of 97% for identifying patients with high-risk features while reducing the number of recommended CMRs by 61%. The negative predictive value with this screening strategy for the absence of high-risk features in patients without ECG-DL recommendation for CMR was 99.5%. CONCLUSION: In HCM, novel ECG-DL models reliably identified patients with high-risk imaging features while offering the potential to reduce CMR testing requirements in underresourced areas.

Radiomics of Late Gadolinium Enhancement Reveals Prognostic Value of Myocardial Scar Heterogeneity in Hypertrophic Cardiomyopathy.

BACKGROUND: Late gadolinium enhancement (LGE) scar burden by cardiac magnetic resonance is a major risk factor for sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM). However, there is currently limited data on the incremental prognostic value of integrating myocardial LGE radiomics (ie, shape and texture features) into SCD risk stratification models. OBJECTIVES: The purpose of this study was to investigate the incremental prognostic value of myocardial LGE radiomics beyond current European Society of Cardiology (ESC) and American College of Cardiology (ACC)/American Heart Association (AHA) models for SCD risk prediction in HCM. METHODS: A total of 1,229 HCM patients (62% men; age 52 ± 16 years) from 3 medical centers were included. Left ventricular myocardial radiomic features were calculated from LGE images. Principal component analysis was used to reduce the radiomic features and calculate 3 principal radiomics (PrinRads). Cox and logistic regression analyses were then used to evaluate the significance of the extracted PrinRads of LGE images, alone or in combination with ESC or ACC/AHA models, to predict SCD risk. The ACC/AHA risk markers include LGE burden using a dichotomized 15% threshold of LV scar. RESULTS: SCD events occurred in 30 (2.4%) patients over a follow-up period of 49 ± 28 months. Risk prediction using PrinRads resulted in higher c-statistics than the ESC (0.69 vs 0.57; P = 0.02) and the ACC/AHA (0.69 vs 0.67; P = 0.75) models. Risk predictions were improved by combining the 3 PrinRads with ESC (0.73 vs 0.57; P < 0.01) or ACC/AHA (0.76 vs 0.67; P < 0.01) risk scores. The net reclassification index was improved by combining the PrinRads with ESC (0.25 [95% CI: 0.08-0.43]; P = 0.005) or ACC/AHA (0.05 [95% CI: -0.07 to 0.16]; P = 0.42) models. One PrinRad was a significant predictor of SCD risk (HR: 0.57 [95% CI: 0.39-0.84]; P = 0.01). LGE heterogeneity was a major component of PrinRads and a significant predictor of SCD risk (HR: 0.07 [95% CI: 0.01-0.75]; P = 0.03). CONCLUSIONS: Myocardial LGE radiomics are strongly associated with SCD risk in HCM and provide incremental risk stratification beyond current ESC or AHA/ACC risk models. Our proof-of-concept study warrants further validation.

Evolving Contemporary Management of Atrial Fibrillation in Hypertrophic Cardiomyopathy.

Atrial fibrillation (AF) is the most common sustained arrhythmia in hypertrophic cardiomyopathy (HCM) with clinical and subclinical episodes occurring in nearly one-half of patients. AF in HCM historically has been characterized as a decisive disease complication associated with substantial risk for thromboembolic stroke and increased morbidity and mortality. However, there have been many advances in treatment strategy resulting in improved outcomes for this patient group. For example, stroke risk in HCM has been greatly reduced by using systemic oral anticoagulation initiated after the first clinical (symptomatic) AF episode, usually with preference given to direct anticoagulants over warfarin. In contrast, stroke risk scoring systems (such as CHA2DS2-VASc score) are not informative in HCM given the substantial potential for stroke events in patients with low scores, and therefore should not be used for anticoagulation decisions in this disease. A novel risk score specifically designed for HCM (HCM-AF score) can reliably identify most patients with HCM at risk for future AF. Although a strategy focused on controlling ventricular rate is effective in asymptomatic (or minimally symptomatic) patients with AF, restoring and maintaining sinus rhythm is required for most patients with marked AF symptom burden and impaired quality of life. Several antiarrhythmic drugs such as sotalol, disopyramide, and amiodarone, can be effective in suppressing AF episodes; albeit safe, long-term efficacy is supported by only limited data. Catheter AF ablation has emerged as an important treatment option for some patients, although freedom from AF after a single ablation is relatively low (35% at 3 years), multiple ablations and the concomitant use of antiarrhythmic drugs can control AF with more than two-thirds of patients maintaining sinus rhythm at 5 years. Surgical AF ablation with biatrial Cox-Maze IV performed as an adjunctive procedure during myectomy can reduce symptomatic AF episodes (70% of patients free from AF at 5 years). For the vast majority of patients who have HCM with AF, the implementation of contemporary therapies has allowed for improved quality of life and low HCM-related mortality.

Analysis of risk stratification and prevention of sudden death in pediatric patients with hypertrophic cardiomyopathy: Dilemmas and clarity.

Hypertrophic cardiomyopathy (HCM) has been considered the most common cause of sudden death (SD) in the young. However, introduction of implantable cardioverter-defibrillators (ICDs) in HCM has proved highly effective and the mainstay of preventing SD in children, adolescents, and adults by terminating malignant ventricular tachyarrhythmias. Nevertheless, ICD decision making is generally regarded as more difficult in pediatrics, and the strategy for selecting ICD patients from this population remains without consensus. Prospective studies in HCM children and adolescents have shown the American Heart Association/American College of Cardiology traditional major risk marker strategy to be reliable with >90% sensitivity in selecting patients for SD prevention. International data in >2000 young HCM patients assembled over 20 years who were stratified by major risk markers showed ICDs effectively prevented SD in 20%. Alternatively, novel quantitative risk scoring initiatives provide 5-year risk estimates that are potentially useful as adjunctive tools to facilitate discussion of prophylactic ICD risks vs benefit but are as yet unsupported by prospective outcome studies. Risk scoring strategies are characterized by reasonable discriminatory statistical power (C-statistic 0.69-0.76) for identifying patients with SD events but with relatively low sensitivity, albeit with specificity comparable with the risk marker strategy. While some reticence for obligating healthy-appearing young patients to lifelong device implants is understandable, underutilization of the ICD in high-risk children and adolescents can represent a lost opportunity for fulfilling the long-standing aspiration of SD prevention. This review provides a critical assessment of the current strengths and weaknesses of SD risk stratification strategies in young HCM patients in an effort to clarify clinical decision making in this challenging subpopulation.

Do Implantable Cardioverter-Defibrillators Really Belong on the Athlete Field?

High-risk athletes with implanted cardioverter-defibrillators who are competing in intense sports represent a controversial issue in cardiovascular medicine. Such devices have the capability to protect patients with a variety of cardiovascular diseases from sudden death and have aborted potentially lethal events during competitive sports but they can also lead to adverse clinical consequences for athletes with implants and other participants. In conclusion, clinicians and athletes should consider the data presented here in making prudent and informed recommendations regarding the eligibility of this patient group with implanted cardioverter-defibrillators for intense competitive sports.

Development of the Implantable Cardioverter-Defibrillator: JACC Historical Breakthroughs in Perspective.

Implantable cardioverter-defibrillators (ICDs) represent transformational technology, arguably the most significant advance in cardiovascular medicine in 50 years. The vision and determination of pioneers Mirowski and Mower was fundamental to this monumental achievement, working with limited resources and confronted by skepticism/criticism from medical establishment. The inventors were followed >35 years in which a multitude of innovative clinical scientists and engineers introduced technological advances leading to the sophisticated devices in practice today. A pivotal patient experiment with automated termination of ventricular fibrillation (1980) led to U.S. Food and Drug Administration approval. Transvenous lead systems converted ICDs from thoracotomy-based secondary prevention to primary prevention of sudden death devices in countless patients worldwide. ICD acceptance was solidified by prospective randomized controlled trials showing reduced mortality superior to antiarrhythmic drugs. ICDs eventually expanded from coronary disease to inherited arrhythmia conditions (eg, hypertrophic cardiomyopathy). The ICD breakthrough story demonstrates how significant progress is possible in medicine against all odds, given fearless imagination to pursue novel ideas that conflict with accepted wisdom.

How common is hypertrophic cardiomyopathy really?: Disease prevalence revisited 27 years after CARDIA.

Hypertrophic cardiomyopathy (HCM) is a heterogeneous albeit treatable cardiac disease of variable severity, with the potential for heart failure, atrial fibrillation and arrhythmic sudden death, characterized by otherwise unexplained left ventricular (LV) hypertrophy and affecting all ages and races. Over the last 30 years, several studies have estimated the prevalence of HCM in the general population, employing echocardiography and cardiac magnetic resonance imaging (CMR), as well electronic health records and billing databases for clinical diagnosis. The estimated prevalence in the general population based on the disease phenotype of LV hypertrophy by imaging is 1:500 (0.2%). This prevalence was initially proposed in 1995 in the population-based CARDIA study employing echocardiography, and more recently confirmed by automated CMR analysis in the large UK Biobank cohort. The 1:500 prevalence appears most relevant to clinical assessment and management of HCM. These available data suggest that HCM is not a rare condition but likely underdiagnosed clinically and by extrapolation potentially affects about 700,000 Americans and possibly 15 million people worldwide.

Exercise-Induced Left Atrial Hypertension in Heart Failure With Preserved Ejection Fraction.

BACKGROUND: Many patients with heart failure and preserved ejection fraction have no overt volume overload and normal resting left atrial (LA) pressure. OBJECTIVES: This study sought to characterize patients with normal resting LA pressure (pulmonary capillary wedge pressure [PCWP] <15 mm Hg) but exercise-induced left atrial hypertension (EILAH). METHODS: The REDUCE LAP-HF II (A Study to Evaluate the Corvia Medical, Inc. IASD System II to Reduce Elevated Left Atrial Pressure in Patients With Heart Failure) trial randomized 626 patients with ejection fraction ≥40% and exercise PCWP ≥25 mm Hg to atrial shunt or sham procedure. The primary trial outcome, a hierarchical composite of death, heart failure hospitalization, intensification of diuretics, and change in health status was compared between patients with EILAH and those with heart failure and resting left atrial hypertension (RELAH). RESULTS: Patients with EILAH (29%) had similar symptom severity, but lower natriuretic peptide levels, higher 6-minute walk distance, less atrial fibrillation, lower left ventricular mass, smaller LA volumes, lower E/e', and better LA strain. PCWP was lower at rest, but had a larger increase with exercise in EILAH. Neither group as a whole had a significant effect from shunt therapy vs sham. Patients with EILAH were more likely to have characteristics associated with atrial shunt responsiveness (peak exercise pulmonary vascular resistance <1.74 WU) and no pacemaker (63% vs 46%; P < 0.001). The win ratio for the primary outcome was 1.56 (P = 0.08) in patients with EILAH and 1.51 (P = 0.04) in those with RELAH when responder characteristics were present. CONCLUSIONS: Patients with EILAH had similar symptom severity but less advanced myocardial and pulmonary vascular disease. This important subgroup may be difficult to diagnose without invasive exercise hemodynamics, but it has characteristics associated with favorable response to atrial shunt therapy. (A Study to Evaluate the Corvia Medical, Inc. IASD System II to Reduce Elevated Left Atrial Pressure in Patients With Heart Failure [REDUCE LAP-HF TRIAL II]; NCT03088033).

Evidence of Advanced Pulmonary Vascular Remodeling in Obstructive Hypertrophic Cardiomyopathy With Pulmonary Hypertension.

BACKGROUND: Elevated mean pulmonary artery pressure (mPAP) is common in patients with hypertrophic cardiomyopathy (HCM) and heart failure symptoms. However, dynamic left ventricular (LV) outflow tract obstruction may confound interpretation of pulmonary hypertension (PH) pathophysiologic features in HCM when relying on resting invasive hemodynamic data alone. RESEARCH QUESTION: Do structural changes to the lung vasculature clarify PH pathophysiologic features in patients with HCM with progressive heart failure? STUDY DESIGN AND METHODS: Clinical data and ultrarare lung autopsy specimens were acquired retrospectively from the National Institutes of Health (1975-1992). Patients were included based on the availability of lung tissue and recorded mPAP. Discarded tissue from rejected lung donors served as control specimens. Histomorphology was performed on pulmonary arterioles and veins. Comparisons were calculated using the Student t test and Mann-Whitney U test; Pearson correlation was used to assess association between morphometric measurements and HCM cardiac and hemodynamic measurements. RESULTS: The HCM cohort (n = 7; mean ± SD age, 43 ± 18 years; 71% men) showed maximum mean ± SD LV wall thickness of 25 ± 2.8 mm, mean ± SD outflow tract gradient of 90 ± 30 mm Hg, median mPAP of 25 mm Hg (interquartile range [IQR], 6 mm Hg), median pulmonary artery wedge pressure (PAWP) of 16 mm Hg (IQR, 4 mm Hg), and median pulmonary vascular resistance of 1.8 Wood units (WU; IQR, 2.4 WU). Compared with control samples (n = 5), patients with HCM showed greater indexed pulmonary arterial hypertrophy (20.7 ± 7.2% vs 49.7 ± 12%; P < .001) and arterial wall fibrosis (11.5 ± 3.4 mm vs 21.0 ± 4.7 mm; P < .0001), which correlated with mPAP (r = 0.84; P = .018), PAWP (r = 0.74; P = .05), and LV outflow tract gradient (r = 0.78; P = .035). Compared with control samples, pulmonary vein thickness was increased by 2.9-fold (P = .008) in the HCM group, which correlated with mPAP (r = 0.81; P = .03) and LV outflow tract gradient (r = 0.83; P = .02). INTERPRETATION: To the best of our knowledge, these data demonstrate for the first time that in patients with obstructive HCM, heart failure is associated with pathogenic pulmonary vascular remodeling even when mPAP is elevated only mildly. These observations clarify PH pathophysiologic features in HCM, with future implications for clinical strategies that mitigate outflow tract obstruction.