CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy international registry: Design and rationale of the DERIVATE study

CarDiac magnEtic Resonance for prophylactic Implantable-cardioVerter defibrillAtor ThErapy in Non-Dilated Left Ventricular Cardiomyopathy: a sub-study from the DERIVATE Registry

BACKGROUND

Accurate risk stratification for patients with non-dilated left ventricular cardiomyopathy (NDLVC) remains challenging due to lack of dedicated clinical trials. This post-hoc analysis aims to delineate the arrhythmic risk and assess the incremental value of cardiac magnetic resonance (CMR) imaging in the DERIVATE (CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy) study cohort meeting the NDLVC diagnostic criteria.

METHODS

Patients with NDLVC from DERIVATE registry were identified in the absence of left ventricular (LV) dilatation and in the presence of non-ischaemic LV scarring ("fibrotic NDLVC") or isolated LV systolic dysfunction (LV ejection fraction <50%) without fibrosis ("hypokinetic NDLVC"). The primary endpoint was all-cause mortality. Major adverse arrhythmic cardiac events (MAACE) were the secondary endpoint and included sudden cardiac death (SCD) and aborted SCD.

RESULTS

One hundred ninety-seven NDLVC patients were identified from the cohort of the DERIVATE study (Mean age: 59±14 years; Male: 135). Over a median follow-up of 2.7 years, 15 (8%) patients died, and 8 (4%) experienced MAACE. Patients with "hypokinetic" NDLVC had significantly lower rates of MAACE than non-ischaemic dilated cardiomyopathy (NIDCM) (p=0.001), while patients with "fibrotic" NDLVC had same rate of both primary (p=0.48) and secondary endpoints (p= 0.616) compared to NIDMC patients. Multivariable analysis identified LGE with midwall distribution as an independent predictor of MAACE in NDLVC patients (Hazard Ratio 6.7, 95% Confidence Interval: 1.33-33.67; p=0.021).

CONCLUSIONS

NDLVC patients exhibit a heterogeneous risk profile for arrhythmic events. The presence of midwall LGE, similarly to NIDCM, is a significant predictor of MAACE, highlighting the importance of CMR imaging for risk stratification.

Clinical parameters of death and heart failure hospitalization in biventricular systolic dysfunction assessed via cardiac magnetic resonance

AIMS

While factors associated with adverse events are well elucidated in setting of isolated left ventricular dysfunction, clinical and imaging-based prognosticators of adverse outcomes are lacking in context of biventricular dysfunction. The purpose of this study was to establish role of clinical variables in prognosis of biventricular heart failure (HF), as assessed by cardiac magnetic resonance imaging.

METHODS

Study cohort consisted of 840 patients enrolled in DERIVATE registry with coexisting CMR-derived right ventricular (RV) and left ventricular (LV) dysfunction, as defined by RV and LV ejection fractions ≤45 % and ≤ 50 %, respectively. The primary objective was to identify factors associated with adverse long-term outcomes, defined as composite of all-cause death and HF hospitalizations (DHFH). Kaplan-Meir curves were plotted for survival analysis. Cox proportional hazard models were constructed to estimate adjusted hazard ratios (aHRs) and associated 95 % confidence intervals for clinical variables and their correlation with adverse events.

RESULTS

Mean age was 61.0 years; 83.1 % were male, 26.6 % had diabetes mellitus (DM), and 45.9 % had non-ischemic cardiomyopathy. At median follow-up of 2 years, DHFH occurred in 32.5 % of the cohort. Kaplan-Meir analysis showed higher rate of DHFH in patients with DM (35.2 % vs. 22.6 %, p < 0.001). Multivariate Cox regression analysis showed that DM was independently associated with DHFH (aHR 1.61 [95 % CI: 1.15-2.25]; p = 0.003). Importantly, ACE-inhibitor/ARB usage in patients with DM was associated with significant reduction in DHFH (aHR 0.53 [95 % CI: 0.31-0.90]; p = 0.02).

CONCLUSION

In patients with biventricular HF, DM was a strong predictor of DHFH, with ACE-inhibitor/ARB usage having cardioprotective effect.

Cardiac Magnetic Resonance for Prophylactic Implantable-Cardioverter Defibrillator Therapy in Ischemic Cardiomyopathy: The DERIVATE-ICM International Registry

BACKGROUND

Implantable cardioverter-defibrillator (ICD) therapy is the most effective prophylactic strategy against sudden cardiac death (SCD) in patients with ischemic cardiomyopathy (ICM) and left ventricle ejection fraction (LVEF) ≤35% as detected by transthoracic echocardiograpgy (TTE). This approach has been recently questioned because of the low rate of ICD interventions in patients who received implantation and the not-negligible percentage of patients who experienced SCD despite not fulfilling criteria for implantation.

OBJECTIVES

The DERIVATE-ICM registry (CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy; NCT03352648) is an international, multicenter, and multivendor study to assess the net reclassification improvement (NRI) for the indication of ICD implantation by the use of cardiac magnetic resonance (CMR) as compared to TTE in patients with ICM.

METHODS

A total of 861 patients with ICM (mean age 65 ± 11 years, 86% male) with chronic heart failure and TTE-LVEF <50% participated. Major adverse arrhythmic cardiac events (MAACE) were the primary endpoints.

RESULTS

During a median follow-up of 1,054 days, MAACE occurred in 88 (10.2%). Left ventricular end-diastolic volume index (HR: 1.007 [95% CI: 1.000-1.011]; P = 0.05), CMR-LVEF (HR: 0.972 [95% CI: 0.945-0.999]; P = 0.045) and late gadolinium enhancement (LGE) mass (HR: 1.010 [95% CI: 1.002-1.018]; P = 0.015) were independent predictors of MAACE. A multiparametric CMR weighted predictive derived score identifies subjects at high risk for MAACE compared with TTE-LVEF cutoff of 35% with a NRI of 31.7% (P = 0.007).

CONCLUSIONS

The DERIVATE-ICM registry is a large multicenter registry showing the additional value of CMR to stratify the risk for MAACE in a large cohort of patients with ICM compared with standard of care.

Cardiac magnetic resonance for prophylactic implantable-cardioverter defibrillator therapy international study: prognostic value of cardiac magnetic resonance-derived right ventricular parameters substudy

AIMS

Right ventricular systolic dysfunction (RVSD) is an important determinant of outcomes in heart failure (HF) cohorts. While the quantitative assessment of RV function is challenging using 2D-echocardiography, cardiac magnetic resonance (CMR) is the gold standard with its high spatial resolution and precise anatomical definition. We sought to investigate the prognostic value of CMR-derived RV systolic function in a large cohort of HF with reduced ejection fraction (HFrEF).

METHODS AND RESULTS

Study cohort comprised of patients enrolled in the CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DefibrillAtor ThErapy registry who had HFrEF and had simultaneous baseline CMR and echocardiography (n = 2449). RVSD was defined as RV ejection fraction (RVEF) <45%. Kaplan-Meier curves and cox regression were used to investigate the association between RVSD and all-cause mortality (ACM). Mean age was 59.8 ± 14.0 years, 42.0% were female, and mean left ventricular ejection fraction (LVEF) was 34.0 ± 10.8. Median follow-up was 959 days (interquartile range: 560-1590). RVSD was present in 936 (38.2%) and was an independent predictor of ACM (adjusted hazard ratio = 1.44; 95% CI [1.09-1.91]; P = 0.01). On subgroup analyses, the prognostic value of RVSD was more pronounced in NYHA I/II than in NYHA III/IV, in LVEF <35% than in LVEF ≥35%, and in patients with renal dysfunction when compared to those with normal renal function.

CONCLUSION

RV systolic dysfunction is an independent predictor of ACM in HFrEF, with a more pronounced prognostic value in select subgroups, likely reflecting the importance of RVSD in the early stages of HF progression.

AI Cardiac MRI Scar Analysis Aids Prediction of Major Arrhythmic Events in the Multicenter DERIVATE Registry

Background Scar burden with late gadolinium enhancement (LGE) cardiac MRI (CMR) predicts arrhythmic events in patients with postinfarction in single-center studies. However, LGE analysis requires experienced human observers, is time consuming, and introduces variability. Purpose To test whether postinfarct scar with LGE CMR can be quantified fully automatically by machines and to compare the ability of LGE CMR scar analyzed by humans and machines to predict arrhythmic events. Materials and Methods This study is a retrospective analysis of the multicenter, multivendor CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry. Patients with chronic heart failure, echocardiographic left ventricular ejection fraction (LVEF) of less than 50%, and LGE CMR were recruited (from January 2015 through December 2020). In the current study, only patients with ischemic cardiomyopathy were included. Quantification of total, dense, and nondense scars was carried out by two experienced readers or a Ternaus network, trained and tested with LGE images of 515 and 246 patients, respectively. Univariable and multivariable Cox analyses were used to assess patient and cardiac characteristics associated with a major adverse cardiac event (MACE). Area under the receiver operating characteristic curve (AUC) was used to compare model performances. Results In 761 patients (mean age, 65 years ± 11, 671 men), 83 MACEs occurred. With use of the testing group, univariable Cox-analysis found New York Heart Association class, left ventricle volume and/or function parameters (by echocardiography or CMR), guideline criterion (LVEF of ≤35% and New York Heart Association class II or III), and LGE scar analyzed by humans or the machine-learning algorithm as predictors of MACE. Machine-based dense or total scar conferred incremental value over the guideline criterion for the association with MACE (AUC: 0.68 vs 0.63, P = .02 and AUC: 0.67 vs 0.63, P = .01, respectively). Modeling with competing risks yielded for dense and total scar (AUC: 0.67 vs 0.61, P = .01 and AUC: 0.66 vs 0.61, P = .005, respectively). Conclusion In this analysis of the multicenter CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry, fully automatic machine learning-based late gadolinium enhancement analysis reliably quantifies myocardial scar mass and improves the current prediction model that uses guideline-based risk criteria for implantable cardioverter defibrillator implantation. ClinicalTrials.gov registration no.: NCT03352648 Published under a CC BY 4.0 license. Supplemental material is available for this article.

Artificial Intelligence for Cardiothoracic Imaging: Overview of Current and Emerging Applications

Artificial intelligence algorithms can learn by assimilating information from large datasets in order to decipher complex associations, identify previously undiscovered pathophysiological states, and construct prediction models. There has been tremendous interest and increased incorporation of artificial intelligence into various industries, including healthcare. As a result, there has been an exponential rise in the number of research articles and industry participants producing models intended for a variety of applications in medical imaging, which can be challenging to navigate for radiologists. In thoracic imaging, multiple applications are being evaluated for chest radiography and computed tomography and include applications for lung nodule evaluation and cancer imaging, quantifying diffuse lung disorders, and cardiac imaging, to name a few. This review aims to provide an overview of current clinical AI models, focusing on the most common clinical applications of AI in cardiothoracic imaging.

Application of AI in cardiovascular multimodality imaging

Technical advances in artificial intelligence (AI) in cardiac imaging are rapidly improving the reproducibility of this approach and the possibility to reduce time necessary to generate a report. In cardiac computed tomography angiography (CCTA) the main application of AI in clinical practice is focused on detection of stenosis, characterization of coronary plaques, and detection of myocardial ischemia. In cardiac magnetic resonance (CMR) the application of AI is focused on post-processing and particularly on the segmentation of cardiac chambers during late gadolinium enhancement. In echocardiography, the application of AI is focused on segmentation of cardiac chambers and is helpful for valvular function and wall motion abnormalities. The common thread represented by all of these techniques aims to shorten the time of interpretation without loss of information compared to the standard approach. In this review we provide an overview of AI applications in multimodality cardiac imaging.

The Applications of Artificial Intelligence in Cardiovascular Magnetic Resonance-A Comprehensive Review

Cardiovascular disease remains an integral field on which new research in both the biomedical and technological fields is based, as it remains the leading cause of mortality and morbidity worldwide. However, despite the progress of cardiac imaging techniques, the heart remains a challenging organ to study. Artificial intelligence (AI) has emerged as one of the major innovations in the field of diagnostic imaging, with a dramatic impact on cardiovascular magnetic resonance imaging (CMR). AI will be increasingly present in the medical world, with strong potential for greater diagnostic efficiency and accuracy. Regarding the use of AI in image acquisition and reconstruction, the main role was to reduce the time of image acquisition and analysis, one of the biggest challenges concerning magnetic resonance; moreover, it has been seen to play a role in the automatic correction of artifacts. The use of these techniques in image segmentation has allowed automatic and accurate quantification of the volumes and masses of the left and right ventricles, with occasional need for manual correction. Furthermore, AI can be a useful tool to directly help the clinician in the diagnosis and derivation of prognostic information of cardiovascular diseases. This review addresses the applications and future prospects of AI in CMR imaging, from image acquisition and reconstruction to image segmentation, tissue characterization, diagnostic evaluation, and prognostication.

CarDiac magnEtic Resonance for prophylactic Implantable-cardioVerter defibrillAtor ThErapy in Non-Ischaemic dilated CardioMyopathy: an international Registry

AIMS

The aim of this registry was to evaluate the additional prognostic value of a composite cardiac magnetic resonance (CMR)-based risk score over standard-of-care (SOC) evaluation in a large cohort of consecutive unselected non-ischaemic cardiomyopathy (NICM) patients.

METHODS AND RESULTS

In the DERIVATE registry (www.clinicaltrials.gov/registration: RCT#NCT03352648), 1000 (derivation cohort) and 508 (validation cohort) NICM patients with chronic heart failure (HF) and left ventricular ejection fraction <50% were included. All-cause mortality and major adverse arrhythmic cardiac events (MAACE) were the primary and secondary endpoints, respectively. During a median follow-up of 959 days, all-cause mortality and MAACE occurred in 72 (7%) and 93 (9%) patients, respectively. Age and >3 segments with midwall fibrosis on late gadolinium enhancement (LGE) were the only independent predictors of all-cause mortality (HR: 1.036, 95% CI: 1.0117-1.056, P < 0.001 and HR: 2.077, 95% CI: 1.211-3.562, P = 0.008, respectively). For MAACE, the independent predictors were male gender, left ventricular end-diastolic volume index by CMR (CMR-LVEDVi), and >3 segments with midwall fibrosis on LGE (HR: 2.131, 95% CI: 1.231-3.690, P = 0.007; HR: 3.161, 95% CI: 1.750-5.709, P < 0.001; and HR: 1.693, 95% CI: 1.084-2.644, P = 0.021, respectively). A composite clinical and CMR-based risk score provided a net reclassification improvement of 63.7% (P < 0.001) for MAACE occurrence when added to the model based on SOC evaluation. These findings were confirmed in the validation cohort.

CONCLUSION

In a large multicentre, multivendor cohort registry reflecting daily clinical practice in NICM work-up, a composite clinical and CMR-based risk score provides incremental prognostic value beyond SOC evaluation, which may have impact on the indication of implantable cardioverter-defibrillator implantation.

Artificial intelligence in cardiac radiology

Artificial intelligence (AI) is entering the clinical arena, and in the early stage, its implementation will be focused on the automatization tasks, improving diagnostic accuracy and reducing reading time. Many studies investigate the potential role of AI to support cardiac radiologist in their day-to-day tasks, assisting in segmentation, quantification, and reporting tasks. In addition, AI algorithms can be also utilized to optimize image reconstruction and image quality. Since these algorithms will play an important role in the field of cardiac radiology, it is increasingly important for radiologists to be familiar with the potential applications of AI. The main focus of this article is to provide an overview of cardiac-related AI applications for CT and MRI studies, as well as non-imaging-based applications for reporting and image optimization.

Artificial Intelligence and Texture Analysis in Cardiac Imaging

PURPOSE OF REVIEW

The aim of this structured review is to summarize the current research applications and opportunities arising from artificial intelligence (AI) and texture analysis with regard to cardiac imaging.

RECENT FINDINGS

Current research findings suggest tremendous potential for AI in cardiac imaging, especially with regard to objective image analyses, overcoming the limitations of an observer-dependent subjective image interpretation. Researchers have used this technique across multiple imaging modalities, for instance to detect myocardial scars in cardiac MR imaging, to predict contrast enhancement in non-contrast studies, and to improve image acquisition and reconstruction. AI in medical imaging has the potential to provide novel, much-needed applications for improving patient care pertaining to the cardiovascular system. While several shortcomings are still present in the current methodology, AI may serve as a resourceful assistant to radiologists and clinicians alike.

Machine learning in cardiovascular magnetic resonance: basic concepts and applications

Machine learning (ML) is making a dramatic impact on cardiovascular magnetic resonance (CMR) in many ways. This review seeks to highlight the major areas in CMR where ML, and deep learning in particular, can assist clinicians and engineers in improving imaging efficiency, quality, image analysis and interpretation, as well as patient evaluation. We discuss recent developments in the field of ML relevant to CMR in the areas of image acquisition & reconstruction, image analysis, diagnostic evaluation and derivation of prognostic information. To date, the main impact of ML in CMR has been to significantly reduce the time required for image segmentation and analysis. Accurate and reproducible fully automated quantification of left and right ventricular mass and volume is now available in commercial products. Active research areas include reduction of image acquisition and reconstruction time, improving spatial and temporal resolution, and analysis of perfusion and myocardial mapping. Although large cohort studies are providing valuable data sets for ML training, care must be taken in extending applications to specific patient groups. Since ML algorithms can fail in unpredictable ways, it is important to mitigate this by open source publication of computational processes and datasets. Furthermore, controlled trials are needed to evaluate methods across multiple centers and patient groups.