A machine-learning-based method to predict adverse events in patients with dilated cardiomyopathy and severely reduced ejection fractions

Improving the efficiency and accuracy of CMR with AI - review of evidence and proposition of a roadmap to clinical translation

Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR. Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis. These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives. Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.

Current Insights and Novel Cardiovascular Magnetic Resonance-Based Techniques in the Prognosis of Non-Ischemic Dilated Cardiomyopathy

Cardiac magnetic resonance (CMR) imaging has an important emerging role in the evaluation and management of patients with cardiomyopathies, especially in patients with dilated cardiomyopathy (DCM). It allows a non-invasive characterization of myocardial tissue, thus assisting early diagnosis and precise phenotyping of the different cardiomyopathies, which is an essential step for early and individualized treatment of patients. Using imaging techniques such as late gadolinium enhancement (LGE), standard and advanced quantification as well as quantitative mapping parameters, CMR-based tissue characterization is useful in the differential diagnosis of DCM and risk stratification. The purpose of this article is to review the utility of CMR in the diagnosis and management of idiopathic DCM, as well as risk prediction and prognosis based on standard and emerging CMR contrast and non-contrast techniques. This is consistent with current evidence and guidance moving beyond traditional prognostic markers such as ejection fraction.

Deep learning-based prognostic model using non-enhanced cardiac cine MRI for outcome prediction in patients with heart failure

OBJECTIVES

To evaluate the performance of a deep learning-based multi-source model for survival prediction and risk stratification in patients with heart failure.

METHODS

Patients with heart failure with reduced ejection fraction (HFrEF) who underwent cardiac magnetic resonance between January 2015 and April 2020 were retrospectively included in this study. Baseline electronic health record data, including clinical demographic information, laboratory data, and electrocardiographic information, were collected. Short-axis non-contrast cine images of the whole heart were acquired to estimate the cardiac function parameters and the motion features of the left ventricle. Model accuracy was evaluated using the Harrell's concordance index. All patients were followed up for major adverse cardiac events (MACEs), and survival prediction was assessed using Kaplan-Meier curves.

RESULTS

A total of 329 patients were evaluated (age 54 ± 14 years; men, 254) in this study. During a median follow-up period of 1041 days, 62 patients experienced MACEs and their median survival time was 495 days. When compared with conventional Cox hazard prediction models, deep learning models showed better survival prediction performance. Multi-data denoising autoencoder (DAE) model reached the concordance index of 0.8546 (95% CI: 0.7902-0.8883). Furthermore, when divided into phenogroups, the multi-data DAE model could significantly discriminate between the survival outcomes of the high-risk and low-risk groups compared with other models (p < 0.001).

CONCLUSIONS

The proposed deep learning (DL) model based on non-contrast cardiac cine magnetic resonance imaging could independently predict the outcome of patients with HFrEF and showed better prediction efficiency than conventional methods.

CLINICAL RELEVANCE STATEMENT

The proposed multi-source deep learning model based on cardiac magnetic resonance enables survival prediction in patients with heart failure.

KEY POINTS

• A multi-source deep learning model based on non-contrast cardiovascular magnetic resonance (CMR) cine images was built to make robust survival prediction in patients with heart failure. • The ground truth definition contains electronic health record data as well as DL-based motion data, and cardiac motion information is extracted by optical flow method from non-contrast CMR cine images. • The DL-based model exhibits better prognostic value and stratification performance when compared with conventional prediction models and could aid in the risk stratification in patients with HF.

Primer on Machine Learning in Electrophysiology

Artificial intelligence has become ubiquitous. Machine learning, a branch of artificial intelligence, leads the current technological revolution through its remarkable ability to learn and perform on data sets of varying types. Machine learning applications are expected to change contemporary medicine as they are brought into mainstream clinical practice. In the field of cardiac arrhythmia and electrophysiology, machine learning applications have enjoyed rapid growth and popularity. To facilitate clinical acceptance of these methodologies, it is important to promote general knowledge of machine learning in the wider community and continue to highlight the areas of successful application. The authors present a primer to provide an overview of common supervised (least squares, support vector machine, neural networks and random forest) and unsupervised (k-means and principal component analysis) machine learning models. The authors also provide explanations as to how and why the specific machine learning models have been used in arrhythmia and electrophysiology studies.

Machine learning to predict left ventricular reverse remodeling by guideline-directed medical therapy by utilizing texture feature of extracellular volume fraction in patients with non-ischemic dilated cardiomyopathy

Extracellular volume fraction (ECV) by cardiac magnetic resonance (CMR) allows for the non-invasive quantification of diffuse myocardial fibrosis. Texture analysis and machine learning are now gathering attention in the medical field to exploit the ability of diagnostic imaging for various diseases. This study aimed to investigate the predictive value of texture analysis of ECV and machine learning for predicting response to guideline-directed medical therapy (GDMT) for patients with non-ischemic dilated cardiomyopathy (NIDCM). A total of one-hundred and fourteen NIDCM patients [age: 63 ± 12 years, 91 (81%) males] were retrospectively analyzed. We performed texture analysis of ECV mapping of LV myocardium using dedicated software. We calculated nine histogram-based features (mean, standard deviation, maximum, minimum, etc.) and five gray-level co-occurrence matrices. Five machine learning techniques and the fivefold cross-validation method were used to develop prediction models for LVRR by GDMT based on 14 texture parameters on ECV mapping. We defined the LVRR as follows: LVEF increased ≥ 10% points and decreased LVEDV ≥ 10% on echocardiography after GDMT > 12 months. Fifty (44%) patients were classified as non-responders. The area under the receiver operating characteristics curve for predicting non-responder was 0.82 for eXtreme Gradient Boosting, 0.85 for support vector machine, 0.76 for multi-layer perception, 0.81 for Naïve Bayes, 0.77 for logistic regression, respectively. Mean ECV value was the most critical factor among texture features for differentiating NIDCM patients with LVRR and those without (0.28 ± 0.03 vs. 0.36 ± 0.06, p < 0.001). Machine learning analysis using the support vector machine may be helpful in detecting high-risk NIDCM patients resistant to GDMT. Mean ECV is the most crucial feature among texture features.

Predictive value of electrocardiographic markers in children with dilated cardiomyopathy

Dilated cardiomyopathy (DCM) refers to a heterogeneous group of cardiomyopathies characterized by ventricular dilatation and myocardial systolic dysfunction, which can lead to serious consequences such as malign arrhythmia, sudden death, heart failure, and thromboembolism. With its economical, non-invasive, simple and reproducible advantages, electrocardiogram (ECG) has become an important indicator for assessing the prognosis of cardiovascular diseases. In recent years, more and more studies of electrocardiography on DCM have been carried out, but there is still a lack of a comprehensive summary of its prognostic value. This article reviews the prognostic value of electrocardiographic markers in children with DCM.