The role of cardiac imaging in clinical practice

Comprehensive characterization of cardiac contraction for improved post-infarction risk assessment

This study aims at identifying risk-related patterns of left ventricular contraction dynamics via novel volume transient characterization. A multicenter cohort of AMI survivors (n = 1021) who underwent Cardiac Magnetic Resonance (CMR) after infarction was considered for the study. The clinical endpoint was the 12-month rate of major adverse cardiac events (MACE, n = 73), consisting of all-cause death, reinfarction, and new congestive heart failure. Cardiac function was characterized from CMR in 3 potential directions: by (1) volume temporal transients (i.e. contraction dynamics); (2) feature tracking strain analysis (i.e. bulk tissue peak contraction); and (3) 3D shape analysis (i.e. 3D contraction morphology). A fully automated pipeline was developed to extract conventional and novel artificial-intelligence-derived metrics of cardiac contraction, and their relationship with MACE was investigated. Any of the 3 proposed directions demonstrated its additional prognostic value on top of established CMR indexes, myocardial injury markers, basic characteristics, and cardiovascular risk factors (P < 0.001). The combination of these 3 directions of enhancement towards a final CMR risk model improved MACE prediction by 13% compared to clinical baseline (0.774 (0.771-0.777) vs. 0.683 (0.681-0.685) cross-validated AUC, P < 0.001). The study evidences the contribution of the novel contraction characterization, enabled by a fully automated pipeline, to post-infarction assessment.

Recent Advances in Cardiac Magnetic Resonance for Imaging of Acute Myocardial Infarction

Acute myocardial infarction (AMI) is one of the primary causes of death worldwide, with a high incidence and mortality rate. Assessment of the infarcted and surviving myocardium, along with microvascular obstruction, is crucial for risk stratification, treatment, and prognosis in patients with AMI. Nonionizing radiation, excellent soft tissue contrast resolution, a large field of view, and multiplane imaging make cardiac magnetic resonance (CMR) a "one-stop" method for assessing cardiac structure, function, perfusion, and metabolism. Hence, this imaging technology is considered the "gold standard" for evaluating myocardial function and viability in AMI. This review critically compares the advantages and disadvantages of CMR with other cardiac imaging technologies, and relates the imaging findings to the underlying pathophysiological processes in AMI. A more thorough understanding of CMR technology will clarify their advanced clinical diagnosis and prognostic assessment applications, and assess the future approaches and challenges of CMR in the setting of AMI.

Factors influencing final year radiography students' intention to pursue postgraduate education in medical imaging

INTRODUCTION

Postgraduate education in medical imaging is an important platform that can support in preparing radiographers for the role extension and advancement in radiography. Thus, this study aims to identify the factors influencing final year radiography students' intention to pursue postgraduate education in medical imaging.

METHODS

An online cross-sectional survey was conducted among final year students in medical imaging programs from six institutions in Malaysia. Purposive convenience sampling has been employed. Data collection was related to students' interest in postgraduate study and possible factors that may affect students' intention to pursue postgraduate education after study degree completion. The questionnaire was a combination of a Likert Scale and open-ended question.

RESULTS

A total of 148 (female, n = 132 and male, n = 16) responses were included in the analysis. Among the participants, n = 93 (62.8 %) of students intended to pursue study. The highest choice of study was mixed mode (41.9 %) and cardiac imaging was the field of choice by the students (22.3 %). Five factors have been found to significantly correlate with the students' intention to pursue postgraduate study in medical imaging which were student attributes, being an academician, remuneration, finance, and social influences (p < 0.05). Two factors that did not significantly correlate with the students' intention were being an expert in the field and Covid-19 (p > 0.05).

CONCLUSION

Five out of seven factors tested were found to significantly influence students' decision to pursue postgraduate education in medical imaging. Effective strategies based on the influencing factors should be strategized to encourage more students to pursue postgraduate education in medical imaging.

IMPLICATIONS FOR PRACTICE

Implementation of effective strategies based on the influencing factors will improve access to education among radiography students, ultimately enhancing future radiographers' capability and competency.

Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation

BACKGROUND

Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data.

METHODS

Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark.

RESULTS

The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained.

CONCLUSIONS

Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.

Multi-class point cloud completion networks for 3D cardiac anatomy reconstruction from cine magnetic resonance images

Cine magnetic resonance imaging (MRI) is the current gold standard for the assessment of cardiac anatomy and function. However, it typically only acquires a set of two-dimensional (2D) slices of the underlying three-dimensional (3D) anatomy of the heart, thus limiting the understanding and analysis of both healthy and pathological cardiac morphology and physiology. In this paper, we propose a novel fully automatic surface reconstruction pipeline capable of reconstructing multi-class 3D cardiac anatomy meshes from raw cine MRI acquisitions. Its key component is a multi-class point cloud completion network (PCCN) capable of correcting both the sparsity and misalignment issues of the 3D reconstruction task in a unified model. We first evaluate the PCCN on a large synthetic dataset of biventricular anatomies and observe Chamfer distances between reconstructed and gold standard anatomies below or similar to the underlying image resolution for multiple levels of slice misalignment. Furthermore, we find a reduction in reconstruction error compared to a benchmark 3D U-Net by 32% and 24% in terms of Hausdorff distance and mean surface distance, respectively. We then apply the PCCN as part of our automated reconstruction pipeline to 1000 subjects from the UK Biobank study in a cross-domain transfer setting and demonstrate its ability to reconstruct accurate and topologically plausible biventricular heart meshes with clinical metrics comparable to the previous literature. Finally, we investigate the robustness of our proposed approach and observe its capacity to successfully handle multiple common outlier conditions.

Early transthoracic echocardiography and long-term mortality in moderate- to-severe acute respiratory distress syndrome: An analysis of the Medical Information Mart for Intensive Care database

BACKGROUND

The clinical use of transthoracic echocardiography (TTE) in patients with acute respiratory distress syndrome (ARDS) in the intensive care unit (ICU) has dramatically increased, its impact on long-term prognosis in these patients has not been studied. This study aimed to explore the effect of early-TTE on long-term mortality in patients with moderate-to-severe ARDS in ICU.

METHODS

A total of 2833 patients with moderate-to-severe ARDS who had or had not received early-TTE were obtained from the Medical Information Mart for Intensive Care (MIMIC-III) database after imputing missing values by a random forest model, patients were divided into early-TTE group and non-early-TTE group according to whether they received TTE examination in ICU. A variety of statistical methods were used to balance 41 covariates and increase the reliability of this study, including propensity score matching, inverse probability of treatment weight, covariate balancing propensity score, multivariable regression, and doubly robust estimation. Chi-Square test and t-tests were used to examine the differences between groups for categorical and continuous data, respectively.

RESULTS

There was a significant improvement in 90-day mortality in the early-TTE group compared to non-early-TTE group (odds ratio  =  0.79, 95% CI: 0.64-0.98, p-value  =  0.036), revealing a beneficial effect of early-TTE. Net-input was significantly decreased in the early-TTE group on the third day of ICU admission and throughout the ICU stay, compared with non-early-TTE group (838.57 vs. 1181.89 mL, p-value  =  0.014; 4542.54 vs. 8025.25 mL, p-value  =  0.05). There was a significant difference in the reduction of serum lactate between the two groups, revealing the beneficial effect of early-TTE (0.59 vs. 0.83, p-value  =  0.009). Furthermore, the reduction in the proportion of acute kidney injury demonstrated a correlation between early-TTE and kidney protection (33% vs. 40%, p-value < 0.001).

CONCLUSIONS

Early application of TTE is beneficial to improve the long-term mortality of patients with moderate-to-severe ARDS.

Indications for echocardiography and confirmation rates of cardiovascular diseases: experience of a specialist cardiac outpatient clinic in Kumasi, Ghana

Background

Transthoracic echocardiography is a very helpful noninvasive cardiovascular imaging technique for the diagnosis and risk stratification in the management of patients with cardiovascular diseases. We aimed to review the clinical indications for transthoracic echocardiography and the confirmation rate of cardiovascular diseases by echocardiography at a specialist cardiac clinic in Ghana.

Methods

Using a cross-sectional study design, the echocardiography reports of all patients above the age of 15 who were assessed at the clinic were analyzed. Data on patient demographics, clinical history, clinical indication for echocardiography, and the echocardiographic findings were analyzed using version 25.0 of the Statistical Package for Social Sciences (SPSS).

Results

A total of 594 participants were studied. The age range of participants was 15-96 years, with a mean (± standard deviation) age of 53.72 (± 17.25) years. There were more females (50.17%) than males (49.83%). Most (54.21%) of the participants had echocardiography for cardiac evaluation. Other indications included hypertension/hypertensive heart disease (HHD) (n = 131; 22.06%), heart failure (n = 69; 11.62%), chest pains (n = 12; 2.02%), and valvular heart disease (VHD) (n = 11; 1.85%). Three hundred and eight-nine (70.30%) of the participants had their clinical diagnoses confirmed by echocardiography; echocardiographic confirmation rates for heart failure, VHD, and HHD were 92.75%, 90.91%, and 88.54%, respectively.

Conclusion

Echocardiography showed high confirmation rates for our patients with heart failure, VHD, and HHD. Prompt usage of this noninvasive cardiovascular imaging for the initial evaluation of patients with cardiovascular diseases is highly recommended.

The Use of Artificial Intelligence for Detecting and Predicting Atrial Arrhythmias Post Catheter Ablation

Catheter ablation (CA) is considered as one of the most effective methods technique for eradicating persistent and abnormal cardiac arrhythmias. Nevertheless, in some cases, these arrhythmias are not treated properly, resulting in their recurrences. If left untreated, they may result in complications such as strokes, heart failure, or death. Until recently, the primary techniques for diagnosing recurrent arrhythmias following CA were the findings predisposing to the changes caused by the arrhythmias on cardiac imaging and electrocardiograms during follow-up visits, or if patients reported having palpitations or chest discomfort after the ablation. However, these follow-ups may be time-consuming and costly, and they may not always determine the root cause of the recurrences. With the introduction of artificial intelligence (AI), these follow-up visits can be effectively shortened, and improved methods for predicting the likelihood of recurring arrhythmias after their ablation procedures can be developed. AI can be divided into two categories: machine learning (ML) and deep learning (DL), the latter of which is a subset of ML. ML and DL models have been used in several studies to demonstrate their ability to predict and identify cardiac arrhythmias using clinical variables, electrophysiological characteristics, and trends extracted from imaging data. AI has proven to be a valuable aid for cardiologists due to its ability to compute massive amounts of data and detect subtle changes in electric signals and cardiac images, which may potentially increase the risk of recurrent arrhythmias after CA. Despite the fact that these studies involving AI have generated promising outcomes comparable to or superior to human intervention, they have primarily focused on atrial fibrillation while atrial flutter (AFL) and atrial tachycardia (AT) were the subjects of relatively few AI studies. Therefore, the aim of this review is to investigate the interaction of AI algorithms, electrophysiological characteristics, imaging data, risk score calculators, and clinical variables in predicting cardiac arrhythmias following an ablation procedure. This review will also discuss the implementation of these algorithms to enable the detection and prediction of AFL and AT recurrences following CA.

Interpretable cardiac anatomy modeling using variational mesh autoencoders

Cardiac anatomy and function vary considerably across the human population with important implications for clinical diagnosis and treatment planning. Consequently, many computer-based approaches have been developed to capture this variability for a wide range of applications, including explainable cardiac disease detection and prediction, dimensionality reduction, cardiac shape analysis, and the generation of virtual heart populations. In this work, we propose a variational mesh autoencoder (mesh VAE) as a novel geometric deep learning approach to model such population-wide variations in cardiac shapes. It embeds multi-scale graph convolutions and mesh pooling layers in a hierarchical VAE framework to enable direct processing of surface mesh representations of the cardiac anatomy in an efficient manner. The proposed mesh VAE achieves low reconstruction errors on a dataset of 3D cardiac meshes from over 1,000 patients with acute myocardial infarction, with mean surface distances between input and reconstructed meshes below the underlying image resolution. We also find that it outperforms a voxelgrid-based deep learning benchmark in terms of both mean surface distance and Hausdorff distance while requiring considerably less memory. Furthermore, we explore the quality and interpretability of the mesh VAE's latent space and showcase its ability to improve the prediction of major adverse cardiac events over a clinical benchmark. Finally, we investigate the method's ability to generate realistic virtual populations of cardiac anatomies and find good alignment between the synthesized and gold standard mesh populations in terms of multiple clinical metrics.

Multi-Domain Variational Autoencoders for Combined Modeling of MRI-Based Biventricular Anatomy and ECG-Based Cardiac Electrophysiology

Human cardiac function is characterized by a complex interplay of mechanical deformation and electrophysiological conduction. Similar to the underlying cardiac anatomy, these interconnected physiological patterns vary considerably across the human population with important implications for the effectiveness of clinical decision-making and the accuracy of computerized heart models. While many previous works have investigated this variability separately for either cardiac anatomy or physiology, this work aims to combine both aspects in a single data-driven approach and capture their intricate interdependencies in a multi-domain setting. To this end, we propose a novel multi-domain Variational Autoencoder (VAE) network to capture combined Electrocardiogram (ECG) and Magnetic Resonance Imaging (MRI)-based 3D anatomy information in a single model. Each VAE branch is specifically designed to address the particular challenges of the respective input domain, enabling efficient encoding, reconstruction, and synthesis of multi-domain cardiac signals. Our method achieves high reconstruction accuracy on a United Kingdom Biobank dataset, with Chamfer Distances between reconstructed and input anatomies below the underlying image resolution and ECG reconstructions outperforming multiple single-domain benchmarks by a considerable margin. The proposed VAE is capable of generating realistic virtual populations of arbitrary size with good alignment in clinical metrics between the synthesized and gold standard anatomies and Maximum Mean Discrepancy (MMD) scores of generated ECGs below those of comparable single-domain approaches. Furthermore, we observe the latent space of our VAE to be highly interpretable with separate components encoding different aspects of anatomical and ECG variability. Finally, we demonstrate that the combined anatomy and ECG representation improves the performance in a cardiac disease classification task by 3.9% in terms of Area Under the Receiver Operating Characteristic (AUROC) curve over the best corresponding single-domain modeling approach.

AI in Cardiovascular Imaging: "Unexplainable" Legal and Ethical Challenges?

Nowhere is the influence of artificial intelligence (AI) likely to be more profoundly felt than in healthcare, from patient triage and diagnosis to surgery and follow-up. Over the medium term, these impacts will be more acute in the cardiovascular imaging context, in which AI models are already successfully performing at roughly human levels of accuracy and efficiency in certain applications. Yet, the adoption of unexplainable AI systems for cardiovascular imaging still raises significant legal and ethical challenges. We focus in particular on challenges posed by the unexplainable character of deep learning and other forms of sophisticated AI modelling used for cardiovascular imaging by briefly outlining the systems being developed in this space, describing how they work, and considering how they might generate outputs that are not reviewable by physicians or system programmers. We suggest that an unexplainable tendency presents two specific ethico-legal concerns: (1) difficulty for health regulators and (2) confusion about the assignment of liability for error or fault in the use of AI systems. We suggest that addressing these concerns is critical for ensuring AI's successful implementation in cardiovascular imaging.

Non-18F-FDG/18F-NaF Radiotracers Proposed for the Diagnosis and Management of Diseases of the Heart and Vasculature

¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) and ¹⁸F-sodium fluoride (¹⁸F-NaF) are front-runners in PET. However, these tracers have limitations in the imaging of diseases in the heart. A multitude of other radiotracers have been identified as potentially useful PET agents in the identification of cardiovascular disease. This critical review examines recent studies with the use of non-¹⁸F-FDG/¹⁸F-NaF radiotracers in the identification and surveillance of cardiovascular diseases. We highlight the need for further investigation into alternative PET radiotracers to demonstrate their clinical value in the management of these pathologies.

Cardiac multi-scale investigation of the right and left ventricle ex vivo: a review

The heart is a complex multi-scale system composed of components integrated at the subcellular, cellular, tissue and organ levels. The myocytes, the contractile elements of the heart, form a complex three-dimensional (3D) network which enables propagation of the electrical signal that triggers the contraction to efficiently pump blood towards the whole body. Cardiovascular diseases (CVDs), a major cause of mortality in developed countries, often lead to cardiovascular remodeling affecting cardiac structure and function at all scales, from myocytes and their surrounding collagen matrix to the 3D organization of the whole heart. As yet, there is no consensus as to how the myocytes are arranged and packed within their connective tissue matrix, nor how best to image them at multiple scales. Cardiovascular imaging is routinely used to investigate cardiac structure and function as well as for the evaluation of cardiac remodeling in CVDs. For a complete understanding of the relationship between structural remodeling and cardiac dysfunction in CVDs, multi-scale imaging approaches are necessary to achieve a detailed description of ventricular architecture along with cardiac function. In this context, ventricular architecture has been extensively studied using a wide variety of imaging techniques: ultrasound (US), optical coherence tomography (OCT), microscopy (confocal, episcopic, light sheet, polarized light), magnetic resonance imaging (MRI), micro-computed tomography (micro-CT) and, more recently, synchrotron X-ray phase contrast imaging (SR X-PCI). Each of these techniques have their own set of strengths and weaknesses, relating to sample size, preparation, resolution, 2D/3D capabilities, use of contrast agents and possibility of performing together with in vivo studies. Therefore, the combination of different imaging techniques to investigate the same sample, thus taking advantage of the strengths of each method, could help us to extract the maximum information about ventricular architecture and function. In this review, we provide an overview of available and emerging cardiovascular imaging techniques for assessing myocardial architecture ex vivo and discuss their utility in being able to quantify cardiac remodeling, in CVDs, from myocyte to whole organ.

Deep Learning-based Prescription of Cardiac MRI Planes

PURPOSE

To develop and evaluate a system to prescribe imaging planes for cardiac MRI based on deep learning (DL)-based localization of key anatomic landmarks.

MATERIALS AND METHODS

Annotated landmarks on 892 long-axis (LAX) and 493 short-axis (SAX) cine steady-state free precession series from cardiac MR images were retrospectively collected between February 2012 and June 2017. U-Net-based heatmap regression was used for localization of cardiac landmarks, which were used to compute cardiac MRI planes. Performance was evaluated by comparing localization distances and plane angle differences between DL predictions and ground truth. The plane angulations from DL were compared with those prescribed by the technologist at the original time of acquisition. Data were split into 80% for training and 20% for testing, and results confirmed with fivefold cross-validation.

RESULTS

On LAX images, DL localized the apex within mean 12.56 mm ± 19.11 (standard deviation) and the mitral valve (MV) within 7.68 mm ± 6.91. On SAX images, DL localized the aortic valve within 5.78 mm ± 5.68, MV within 5.90 mm ± 5.24, pulmonary valve within 6.55 mm ± 6.39, and tricuspid valve within 6.39 mm ± 5.89. On the basis of these localizations, average angle bias and mean error of DL-predicted imaging planes relative to ground truth annotations were as follows: SAX, -1.27° ± 6.81 and 4.93° ± 4.86; four chambers, 0.38° ± 6.45 and 5.16° ± 3.80; three chambers, 0.13° ± 12.70 and 9.02° ± 8.83; and two chamber, 0.25° ± 9.08 and 6.53° ± 6.28, respectively.

CONCLUSION

DL-based anatomic localization is a feasible strategy for planning cardiac MRI planes. This approach can produce imaging planes comparable to those defined by ground truth landmarks.© RSNA, 2019 Supplemental material is available for this article.