A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis

Implications of Bias in Artificial Intelligence: Considerations for Cardiovascular Imaging

PURPOSE OF REVIEW

Bias in artificial intelligence (AI) models can result in unintended consequences. In cardiovascular imaging, biased AI models used in clinical practice can negatively affect patient outcomes. Biased AI models result from decisions made when training and evaluating a model. This paper is a comprehensive guide for AI development teams to understand assumptions in datasets and chosen metrics for outcome/ground truth, and how this translates to real-world performance for cardiovascular disease (CVD).

RECENT FINDINGS

CVDs are the number one cause of mortality worldwide; however, the prevalence, burden, and outcomes of CVD vary across gender and race. Several biomarkers are also shown to vary among different populations and ethnic/racial groups. Inequalities in clinical trial inclusion, clinical presentation, diagnosis, and treatment are preserved in health data that is ultimately used to train AI algorithms, leading to potential biases in model performance. Despite the notion that AI models themselves are biased, AI can also help to mitigate bias (e.g., bias auditing tools). In this review paper, we describe in detail implicit and explicit biases in the care of cardiovascular disease that may be present in existing datasets but are not obvious to model developers. We review disparities in CVD outcomes across different genders and race groups, differences in treatment of historically marginalized groups, and disparities in clinical trials for various cardiovascular diseases and outcomes. Thereafter, we summarize some CVD AI literature that shows bias in CVD AI as well as approaches that AI is being used to mitigate CVD bias.

Device innovation in cardiovascular medicine: a report from the European Society of Cardiology Cardiovascular Round Table

Research performed in Europe has driven cardiovascular device innovation. This includes, but is not limited to, percutaneous coronary intervention, cardiac imaging, transcatheter heart valve implantation, and device therapy of cardiac arrhythmias and heart failure. An important part of future medical progress involves the evolution of medical technology and the ongoing development of artificial intelligence and machine learning. There is a need to foster an environment conducive to medical technology development and validation so that Europe can continue to play a major role in device innovation while providing high standards of safety. This paper summarizes viewpoints on the topic of device innovation in cardiovascular medicine at the European Society of Cardiology Cardiovascular Round Table, a strategic forum for high-level dialogue to discuss issues related to the future of cardiovascular health in Europe. Devices are developed and improved through an iterative process throughout their lifecycle. Early feasibility studies demonstrate proof of concept and help to optimize the design of a device. If successful, this should ideally be followed by randomized clinical trials comparing novel devices vs. accepted standards of care when available and the collection of post-market real-world evidence through registries. Unfortunately, standardized procedures for feasibility studies across various device categories have not yet been implemented in Europe. Cardiovascular imaging can be used to diagnose and characterize patients for interventions to improve procedural results and to monitor devices long term after implantation. Randomized clinical trials often use cardiac imaging-based inclusion criteria, while less frequently trials randomize patients to compare the diagnostic or prognostic value of different modalities. Applications using machine learning are increasingly important, but specific regulatory standards and pathways remain in development in both Europe and the USA. Standards are also needed for smart devices and digital technologies that support device-driven biomonitoring. Changes in device regulation introduced by the European Union aim to improve clinical evidence, transparency, and safety, but they may impact the speed of innovation, access, and availability. Device development programmes including dialogue on unmet needs and advice on study designs must be driven by a community of physicians, trialists, patients, regulators, payers, and industry to ensure that patients have access to innovative care.

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.

Anthracycline-induced cardiotoxicity: mechanisms, monitoring, and prevention

Anthracyclines are the most fundamental and important treatment of several cancers especially for lymphoma and breast cancer. However, their use is limited by a dose-dependent cardiotoxicity which may emerge early at the initiation of anthracycline administration or several years after termination of the therapy. A full comprehending of the mechanisms of anthracycline-induced cardiotoxicity, which has not been achieved and is currently under the efforts, is critical to the advance of developing effective methods to protect against the cardiotoxicity, as well as to early detect and treat it. Therefore, we review the recent progress of the mechanism underlying anthracycline-induced cardiotoxicity, as well as approaches to monitor and prevent this issue.

AI approach to biventricular function assessment in cine-MRI: an ultra-small training dataset and multivendor study

Objective. It was a great challenge to train an excellent and generalized model on an ultra-small data set composed of multi-orientation cardiac cine magnetic resonance imaging (MRI) images. We try to develop a 3D deep learning method based on an ultra-small training data set from muti-orientation cine MRI images and assess its performance of automated biventricular structure segmentation and function assessment in multivendor.Approach. We completed the training and testing of our deep learning networks using only heart datasets of 150 cases (90 cases for training and 60 cases for testing). This datasets were obtained from three different MRI vendors and each subject included two phases of the cardiac cycle and three cine sequences. A 3D deep learning algorithm combining Transformers and U-Net was trained. The performance of the segmentation was evaluated using the Dice metric and Hausdorff distance (HD). Based on this, the manual and automatic results of cardiac function parameters were compared with Pearson correlation, intraclass correlation coefficient (ICC) and Bland-Altman analysis in multivendor.Main results. The results show that the average Dice of 0.92, 0.92, 0.94 and HD95 of 2.50, 1.36, 1.37 for three sequences. The automatic and manual results of seven parameters were excellently correlated with the lowestr2 value of 0.824 and the highest of 0.983. The ICC (0.908-0.989,P< 0.001) showed that the results were highly consistent. Bland-Altman with a 95% limit of agreement showed there was no significant difference except for the difference in RVESV (P= 0.005) and LVM (P< 0.001).Significance. The model had high accuracy in segmentation and excellent correlation and consistency in function assessment. It provides a fast and effective method for studying cardiac MRI and heart disease.

Deep Learning for Cardiovascular Imaging: A Review

Importance

Artificial intelligence (AI), driven by advances in deep learning (DL), has the potential to reshape the field of cardiovascular imaging (CVI). While DL for CVI is still in its infancy, research is accelerating to aid in the acquisition, processing, and/or interpretation of CVI across various modalities, with several commercial products already in clinical use. It is imperative that cardiovascular imagers are familiar with DL systems, including a basic understanding of how they work, their relative strengths compared with other automated systems, and possible pitfalls in their implementation. The goal of this article is to review the methodology and application of DL to CVI in a simple, digestible fashion toward demystifying this emerging technology.

Observations

At its core, DL is simply the application of a series of tunable mathematical operations that translate input data into a desired output. Based on artificial neural networks that are inspired by the human nervous system, there are several types of DL architectures suited to different tasks; convolutional neural networks are particularly adept at extracting valuable information from CVI data. We survey some of the notable applications of DL to tasks across the spectrum of CVI modalities. We also discuss challenges in the development and implementation of DL systems, including avoiding overfitting, preventing systematic bias, improving explainability, and fostering a human-machine partnership. Finally, we conclude with a vision of the future of DL for CVI.

Conclusions and Relevance

Deep learning has the potential to meaningfully affect the field of CVI. Rather than a threat, DL could be seen as a partner to cardiovascular imagers in reducing technical burden and improving efficiency and quality of care. High-quality prospective evidence is still needed to demonstrate how the benefits of DL CVI systems may outweigh the risks.

Siamese pyramidal deep learning network for strain estimation in 3D cardiac cine-MR

Strain represents the quantification of regional tissue deformation within a given area. Myocardial strain has demonstrated considerable utility as an indicator for the assessment of cardiac function. Notably, it exhibits greater sensitivity in detecting subtle myocardial abnormalities compared to conventional cardiac function indices, like left ventricle ejection fraction (LVEF). Nonetheless, the estimation of strain poses considerable challenges due to the necessity for precise tracking of myocardial motion throughout the complete cardiac cycle. This study introduces a novel deep learning-based pipeline, designed to automatically and accurately estimate myocardial strain from three-dimensional (3D) cine-MR images. Consequently, our investigation presents a comprehensive pipeline for the precise quantification of local and global myocardial strain. This pipeline incorporates a supervised Convolutional Neural Network (CNN) for accurate segmentation of the cardiac muscle and an unsupervised CNN for robust left ventricle motion tracking, enabling the estimation of strain in both artificial phantoms and real cine-MR images. Our investigation involved a comprehensive comparison of our findings with those obtained from two commonly utilized commercial software in this field. This analysis encompassed the examination of both intra- and inter-user variability. The proposed pipeline exhibited demonstrable reliability and reduced divergence levels when compared to alternative systems. Additionally, our approach is entirely independent of previous user data, effectively eliminating any potential user bias that could influence the strain analyses.

The Role of Advanced Cardiovascular Imaging Modalities in Cardio-Oncology: From Early Detection to Unravelling Mechanisms of Cardiotoxicity

Advances in cancer therapies have led to a global improvement in patient survival rates. Nevertheless, the price to pay is a concomitant increase in cardiovascular (CV) morbidity and mortality in this population. Increased inflammation and disturbances of the immune system are shared by both cancer and CV diseases. Immunological effects of anti-cancer treatments occur with both conventional chemotherapy and, to a greater extent, with novel biological therapies such as immunotherapy. For these reasons, there is growing interest in the immune system and its potential role at the molecular level in determining cardiotoxicity. Early recognition of these detrimental effects could help in identifying patients at risk and improve their oncological management. Non-invasive imaging already plays a key role in evaluating baseline CV risk and in detecting even subclinical cardiac dysfunction during surveillance. The aim of this review is to highlight the role of advanced cardiovascular imaging techniques in the detection and management of cardiovascular complications related to cancer treatment.

Imaging Early Life Cardiovascular Phenotype

The growing epidemics of obesity, hypertension, and diabetes, in addition to worsening environmental factors such as air pollution, water scarcity, and climate change, have fueled the continuously increasing prevalence of cardiovascular diseases (CVDs). This has caused a markedly increasing burden of CVDs that includes mortality and morbidity worldwide. Identification of subclinical CVD before overt symptoms can lead to earlier deployment of preventative pharmacological and nonpharmacologic strategies. In this regard, noninvasive imaging techniques play a significant role in identifying early CVD phenotypes. An armamentarium of imaging techniques including vascular ultrasound, echocardiography, magnetic resonance imaging, computed tomography, noninvasive computed tomography angiography, positron emission tomography, and nuclear imaging, with intrinsic strengths and limitations can be utilized to delineate incipient CVD for both clinical and research purposes. In this article, we review the various imaging modalities used for the evaluation, characterization, and quantification of early subclinical cardiovascular diseases.

Single-Site Experience with an Automated Artificial Intelligence Application for Left Ventricular Ejection Fraction Measurement in Echocardiography

Left ventricular ejection fraction (LVEF) is a key parameter in evaluating left ventricular (LV) function using echocardiography (Echo), but its manual measurement by the modified biplane Simpson (MBS) method is time consuming and operator dependent. We investigated the feasibility of a server-based, commercially available and ready-to use-artificial intelligence (AI) application based on convolutional neural network methods that integrate fully automatic view selection and measurement of LVEF from an entire Echo exam into a single workflow. We prospectively enrolled 1083 consecutive patients who had been referred to Echo for diagnostic or therapeutic purposes. LVEF was measured independently using MBS and AI. Test–retest variability was assessed in 40 patients. The reliability, repeatability, and time efficiency of LVEF measurements were compared between the two methods. Overall, 889 Echos were analyzed by cardiologists with the MBS method and by the AI. Over the study period of 10 weeks, the feasibility of both automatic view classification and seamlessly measured LVEF rose to 81% without user involvement. LVEF, LV end-diastolic and end-systolic volumes correlated strongly between MBS and AI (R = 0.87, 0.89 and 0.93, p < 0.001 for all) with a mean bias of +4.5% EF, −12 mL and −11 mL, respectively, due to impaired image quality and the extent of LV function. Repeatability and reliability of LVEF measurement (n = 40, test–retest) by AI was excellent compared to MBS (coefficient of variation: 3.2% vs. 5.9%), although the median analysis time of the AI was longer than that of the operator-dependent MBS method (258 s vs. 171 s). This AI has succeeded in identifying apical LV views and measuring EF in one workflow with comparable results to the MBS method and shows excellent reproducibility. It offers realistic perspectives for fully automated AI-based measurement of LVEF in routine clinical settings.

Machine Learning Approaches in Diagnosis, Prognosis and Treatment Selection of Cardiac Amyloidosis

Cardiac amyloidosis is an uncommon restrictive cardiomyopathy featuring an unregulated amyloid protein deposition that impairs organic function. Early cardiac amyloidosis diagnosis is generally delayed by indistinguishable clinical findings of more frequent hypertrophic diseases. Furthermore, amyloidosis is divided into various groups, according to a generally accepted taxonomy, based on the proteins that make up the amyloid deposits; a careful differentiation between the various forms of amyloidosis is necessary to undertake an adequate therapeutic treatment. Thus, cardiac amyloidosis is thought to be underdiagnosed, which delays necessary therapeutic procedures, diminishing quality of life and impairing clinical prognosis. The diagnostic work-up for cardiac amyloidosis begins with the identification of clinical features, electrocardiographic and imaging findings suggestive or compatible with cardiac amyloidosis, and often requires the histological demonstration of amyloid deposition. One approach to overcome the difficulty of an early diagnosis is the use of automated diagnostic algorithms. Machine learning enables the automatic extraction of salient information from “raw data” without the need for pre-processing methods based on the a priori knowledge of the human operator. This review attempts to assess the various diagnostic approaches and artificial intelligence computational techniques in the detection of cardiac amyloidosis.

Deep Learning-Based Computed Tomography Image Standardization to Improve Generalizability of Deep Learning-Based Hepatic Segmentation

OBJECTIVE

We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods.

MATERIALS AND METHODS

We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume.

RESULTS

The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998).

CONCLUSION

Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

Towards automatic classification of cardiovascular magnetic resonance Task Force Criteria for diagnosis of arrhythmogenic right ventricular cardiomyopathy

BACKGROUND

Arrhythmogenic right ventricular cardiomyopathy (ARVC) is diagnosed according to the Task Force Criteria (TFC) in which cardiovascular magnetic resonance (CMR) imaging plays an important role. Our study aims to apply an automatic deep learning-based segmentation for right and left ventricular CMR assessment and evaluate this approach for classification of the CMR TFC.

METHODS

We included 227 subjects suspected of ARVC who underwent CMR. Subjects were classified into (1) ARVC patients fulfilling TFC; (2) at-risk family members; and (3) controls. To perform automatic segmentation, a Bayesian Dilated Residual Neural Network was trained and tested. Performance of automatic versus manual segmentation was assessed using Dice-coefficient and Hausdorff distance. Since automatic segmentation is most challenging in basal slices, manual correction of the automatic segmentation in the most basal slice was simulated (automatic^-basal). CMR TFC calculated using manual and automatic^-basal segmentation were compared using Cohen's Kappa (κ).

RESULTS

Automatic segmentation was trained on CMRs of 70 subjects (39.6 ± 18.1 years, 47% female) and tested on 157 subjects (36.9 ± 17.6 years, 59% female). Dice-coefficient and Hausdorff distance showed good agreement between manual and automatic segmentations (≥ 0.89 and ≤ 10.6 mm, respectively) which further improved after simulated correction of the most basal slice (≥ 0.92 and ≤ 9.2 mm, p < 0.001). Pearson correlation of volumetric and functional CMR measurements was good to excellent (automatic (r = 0.78-0.99, p < 0.001) and automatic^-basal (r = 0.88-0.99, p < 0.001) measurements). CMR TFC classification using automatic^-basal segmentations was comparable to manual segmentations (κ 0.98 ± 0.02) with comparable diagnostic performance.

CONCLUSIONS

Combining automatic segmentation of CMRs with correction of the most basal slice results in accurate CMR TFC classification of subjects suspected of ARVC.

MITEA: A dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging

Segmentation of the left ventricle (LV) in echocardiography is an important task for the quantification of volume and mass in heart disease. Continuing advances in echocardiography have extended imaging capabilities into the 3D domain, subsequently overcoming the geometric assumptions associated with conventional 2D acquisitions. Nevertheless, the analysis of 3D echocardiography (3DE) poses several challenges associated with limited spatial resolution, poor contrast-to-noise ratio, complex noise characteristics, and image anisotropy. To develop automated methods for 3DE analysis, a sufficiently large, labeled dataset is typically required. However, ground truth segmentations have historically been difficult to obtain due to the high inter-observer variability associated with manual analysis. We address this lack of expert consensus by registering labels derived from higher-resolution subject-specific cardiac magnetic resonance (CMR) images, producing 536 annotated 3DE images from 143 human subjects (10 of which were excluded). This heterogeneous population consists of healthy controls and patients with cardiac disease, across a range of demographics. To demonstrate the utility of such a dataset, a state-of-the-art, self-configuring deep learning network for semantic segmentation was employed for automated 3DE analysis. Using the proposed dataset for training, the network produced measurement biases of -9 ± 16 ml, -1 ± 10 ml, -2 ± 5 %, and 5 ± 23 g, for end-diastolic volume, end-systolic volume, ejection fraction, and mass, respectively, outperforming an expert human observer in terms of accuracy as well as scan-rescan reproducibility. As part of the Cardiac Atlas Project, we present here a large, publicly available 3DE dataset with ground truth labels that leverage the higher resolution and contrast of CMR, to provide a new benchmark for automated 3DE analysis. Such an approach not only reduces the effect of observer-specific bias present in manual 3DE annotations, but also enables the development of analysis techniques which exhibit better agreement with CMR compared to conventional methods. This represents an important step for enabling more efficient and accurate diagnostic and prognostic information to be obtained from echocardiography.

Artificial intelligence in cardiology: Hope for the future and power for the present

Cardiovascular disease (CVD) is the principal cause of mortality and morbidity globally. With the pressures for improved care and translation of the latest medical advances and knowledge to an actionable plan, clinical decision-making for cardiologists is challenging. Artificial Intelligence (AI) is a field in computer science that studies the design of intelligent agents which take the best feasible action in a situation. It incorporates the use of computational algorithms which simulate and perform tasks that traditionally require human intelligence such as problem solving and learning. Whilst medicine is arguably the last to apply AI in its everyday routine, cardiology is at the forefront of AI revolution in the medical field. The development of AI methods for accurate prediction of CVD outcomes, non-invasive diagnosis of coronary artery disease (CAD), detection of malignant arrythmias through wearables, and diagnosis, treatment strategies and prediction of outcomes for heart failure (HF) patients, demonstrates the potential of AI in future cardiology. With the advancements of AI, Internet of Things (IoT) and the promotion of precision medicine, the future of cardiology will be heavily based on these innovative digital technologies. Despite this, ethical dilemmas regarding the implementation of AI technologies in real-world are still unaddressed.

Artificial intelligence and cardiovascular magnetic resonance imaging in myocardial infarction patients

Cardiovascular magnetic resonance (CMR) is an important cardiac imaging tool for assessing the prognostic extent of myocardial injury after myocardial infarction (MI). Within the context of clinical trials, CMR is also useful for assessing the efficacy of potential cardioprotective therapies in reducing MI size and preventing adverse left ventricular (LV) remodelling in reperfused MI. However, manual contouring and analysis can be time-consuming with interobserver and intraobserver variability, which can in turn lead to reduction in accuracy and precision of analysis. There is thus a need to automate CMR scan analysis in MI patients to save time, increase accuracy, increase reproducibility and increase precision. In this regard, automated imaging analysis techniques based on artificial intelligence (AI) that are developed with machine learning (ML), and more specifically deep learning (DL) strategies, can enable efficient, robust, accurate and clinician-friendly tools to be built so as to try and improve both clinician productivity and quality of patient care. In this review, we discuss basic concepts of ML in CMR, important prognostic CMR imaging biomarkers in MI and the utility of current ML applications in their analysis as assessed in research studies. We highlight potential barriers to the mainstream implementation of these automated strategies and discuss related governance and quality control issues. Lastly, we discuss the future role of ML applications in clinical trials and the need for global collaboration in growing this field.

The role of cardiac magnetic resonance imaging in the assessment of heart failure with preserved ejection fraction

Heart failure (HF) is a major cause of morbidity and mortality worldwide. Current classifications of HF categorize patients with a left ventricular ejection fraction of 50% or greater as HF with preserved ejection fraction or HFpEF. Echocardiography is the first line imaging modality in assessing diastolic function given its practicality, low cost and the utilization of Doppler imaging. However, the last decade has seen cardiac magnetic resonance (CMR) emerge as a valuable test for the sometimes challenging diagnosis of HFpEF. The unique ability of CMR for myocardial tissue characterization coupled with high resolution imaging provides additional information to echocardiography that may help in phenotyping HFpEF and provide prognostication for patients with HF. The precision and accuracy of CMR underlies its use in clinical trials for the assessment of novel and repurposed drugs in HFpEF. Importantly, CMR has powerful diagnostic utility in differentiating acquired and inherited heart muscle diseases presenting as HFpEF such as Fabry disease and amyloidosis with specific treatment options to reverse or halt disease progression. This state of the art review will outline established CMR techniques such as transmitral velocities and strain imaging of the left ventricle and left atrium in assessing diastolic function and their clinical application to HFpEF. Furthermore, it will include a discussion on novel methods and future developments such as stress CMR and MR spectroscopy to assess myocardial energetics, which show promise in unraveling the mechanisms behind HFpEF that may provide targets for much needed therapeutic interventions.

Clinical Manifestations, Monitoring, and Prognosis: A Review of Cardiotoxicity After Antitumor Strategy

The development of various antitumor drugs has significantly improved the survival of patients with cancer. Many first-line chemotherapy drugs are cytotoxic and the cardiotoxicity is one of the most significant effects that could leads to poor prognosis and decreased survival rate. Cancer treatment include traditional anthracycline drugs, as well as some new targeted drugs such as trastuzumab and ICIs. These drugs may directly or indirectly cause cardiovascular injury through different mechanisms, and lead to increasing the risk of cardiovascular disease or accelerating the development of cardiovascular disease. Cardiotoxicity is clinically manifested by arrhythmia, decreased cardiac function, or even sudden death. The cardiotoxicity caused by traditional chemotherapy drugs such as anthracyclines are significantly known. The cardiotoxicity of some new antitumor drugs such like immune checkpoint inhibitors (ICIs) is also relatively clear and requiring further observation and verification. This review is focused on major three drugs with relatively high incidence of cardiotoxicity and poor prognosis and intended to provide an update on the clinical complications and outcomes of these drugs, and we innovatively summarize the monitoring status of survivors using these drugs and discuss the biomarkers and non-invasive imaging features to identify early cardiotoxicity. Finally, we summarize the prevention that decreasing antitumor drugs-induced cardiotoxicity.

Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning

BACKGROUND

Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis.

METHODS

A fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm ('machine') performance was compared to three clinicians ('human') and a commercial tool (cvi42, Circle Cardiovascular Imaging).

FINDINGS

Machine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint.

CONCLUSION

We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.

AI Based CMR Assessment of Biventricular Function: Clinical Significance of Intervendor Variability and Measurement Errors

OBJECTIVES

The aim of this study was to determine whether left ventricular ejection fraction (LVEF) and right ventricular ejection fraction (RVEF) and left ventricular mass (LVM) measurements made using 3 fully automated deep learning (DL) algorithms are accurate and interchangeable and can be used to classify ventricular function and risk-stratify patients as accurately as an expert.

BACKGROUND

Artificial intelligence is increasingly used to assess cardiac function and LVM from cardiac magnetic resonance images.

METHODS

Two hundred patients were identified from a registry of individuals who underwent vasodilator stress cardiac magnetic resonance. LVEF, LVM, and RVEF were determined using 3 fully automated commercial DL algorithms and by a clinical expert (CLIN) using conventional methodology. Additionally, LVEF values were classified according to clinically important ranges: <35%, 35% to 50%, and ≥50%. Both ejection fraction values and classifications made by the DL ejection fraction approaches were compared against CLIN ejection fraction reference. Receiver-operating characteristic curve analysis was performed to evaluate the ability of CLIN and each of the DL classifications to predict major adverse cardiovascular events.

RESULTS

Excellent correlations were seen for each DL-LVEF compared with CLIN-LVEF (r = 0.83-0.93). Good correlations were present between DL-LVM and CLIN-LVM (r = 0.75-0.85). Modest correlations were observed between DL-RVEF and CLIN-RVEF (r = 0.59-0.68). A >10% error between CLIN and DL ejection fraction was present in 5% to 18% of cases for the left ventricle and 23% to 43% for the right ventricle. LVEF classification agreed with CLIN-LVEF classification in 86%, 80%, and 85% cases for the 3 DL-LVEF approaches. There were no differences among the 4 approaches in associations with major adverse cardiovascular events for LVEF, LVM, and RVEF.

CONCLUSIONS

This study revealed good agreement between automated and expert-derived LVEF and similarly strong associations with outcomes, compared with an expert. However, the ability of these automated measurements to accurately classify left ventricular function for treatment decision remains limited. DL-LVM showed good agreement with CLIN-LVM. DL-RVEF approaches need further refinements.

Automated In-Line Artificial Intelligence Measured Global Longitudinal Shortening and Mitral Annular Plane Systolic Excursion: Reproducibility and Prognostic Significance

Background Global longitudinal shortening (GL-Shortening) and the mitral annular plane systolic excursion (MAPSE) are known markers in heart failure patients, but measurement may be subjective and less frequently reported because of the lack of automated analysis. Therefore, a validated, automated artificial intelligence (AI) solution can be of strong clinical interest. Methods and Results The model was implemented on cardiac magnetic resonance scanners with automated in-line processing. Reproducibility was evaluated in a scan-rescan data set (n=160 patients). The prognostic association with adverse events (death or hospitalization for heart failure) was evaluated in a large patient cohort (n=1572) and compared with feature tracking global longitudinal strain measured manually by experts. Automated processing took ≈1.1 seconds for a typical case. On the scan-rescan data set, the model exceeded the precision of human expert (coefficient of variation 7.2% versus 11.1% for GL-Shortening, P=0.0024; 6.5% versus 9.1% for MAPSE, P=0.0124). The minimal detectable change at 90% power was 2.53 percentage points for GL-Shortening and 1.84 mm for MAPSE. AI GL-Shortening correlated well with manual global longitudinal strain (R2=0.85). AI MAPSE had the strongest association with outcomes (χ2, 255; hazard ratio [HR], 2.5 [95% CI, 2.2-2.8]), compared with AI GL-Shortening (χ2, 197; HR, 2.1 [95% CI,1.9-2.4]), manual global longitudinal strain (χ2, 192; HR, 2.1 [95% CI, 1.9-2.3]), and left ventricular ejection fraction (χ2, 147; HR, 1.8 [95% CI, 1.6-1.9]), with P<0.001 for all. Conclusions Automated in-line AI-measured MAPSE and GL-Shortening can deliver immediate and highly reproducible results during cardiac magnetic resonance scanning. These results have strong associations with adverse outcomes that exceed those of global longitudinal strain and left ventricular ejection fraction.

Deep Learning Analysis of Cardiac MRI in Legacy Datasets: Multi-Ethnic Study of Atherosclerosis

The Multi-Ethnic Study of Atherosclerosis (MESA), begun in 2000, was the first large cohort study to incorporate cardiovascular magnetic resonance (CMR) to study the mechanisms of cardiovascular disease in over 5,000 initially asymptomatic participants, and there is now a wealth of follow-up data over 20 years. However, the imaging technology used to generate the CMR images is no longer in routine use, and methods trained on modern data fail when applied to such legacy datasets. This study aimed to develop a fully automated CMR analysis pipeline that leverages the ability of machine learning algorithms to enable extraction of additional information from such a large-scale legacy dataset, expanding on the original manual analyses. We combined the original study analyses with new annotations to develop a set of automated methods for customizing 3D left ventricular (LV) shape models to each CMR exam and build a statistical shape atlas. We trained VGGNet convolutional neural networks using a transfer learning sequence between two-chamber, four-chamber, and short-axis MRI views to detect landmarks. A U-Net architecture was used to detect the endocardial and epicardial boundaries in short-axis images. The landmark detection network accurately predicted mitral valve and right ventricular insertion points with average error distance &lt;2.5 mm. The agreement of the network with two observers was excellent (intraclass correlation coefficient &gt;0.9). The segmentation network produced average Dice score of 0.9 for both myocardium and LV cavity. Differences between the manual and automated analyses were small, i.e., &lt;1.0 ± 2.6 mL/m2 for indexed LV volume, 3.0 ± 6.4 g/m2 for indexed LV mass, and 0.6 ± 3.3% for ejection fraction. In an independent atlas validation dataset, the LV atlas built from the fully automated pipeline showed similar statistical relationships to an atlas built from the manual analysis. Hence, the proposed pipeline is not only a promising framework to automatically assess additional measures of ventricular function, but also to study relationships between cardiac morphologies and future cardiac events, in a large-scale population study.

Performance of artificial intelligence for biventricular cardiovascular magnetic resonance volumetric analysis in the clinical setting

Cardiovascular magnetic resonance (CMR) derived ventricular volumes and function guide clinical decision-making for various cardiac pathologies. We aimed to evaluate the efficiency and clinical applicability of a commercially available artificial intelligence (AI) method for performing biventricular volumetric analysis. Three-hundred CMR studies (100 with normal CMR findings, 50 dilated cardiomyopathy, 50 hypertrophic cardiomyopathy, 50 ischaemic heart disease and 50 congenital or valvular heart disease) were randomly selected from database. Manual biventricular volumetric analysis (CMRtools) results were derived from clinical reports and automated volumetric analyses were performed using short axis volumetry AI function of CircleCVI⁴² v5.12 software. For 20 studies, a combined method of manually adjusted AI contours was tested and all three methods were timed. Clinicians` confidence in AI method was assessed using an online survey. Although agreement was better for left ventricle than right ventricle, AI analysis results were comparable to manual method. Manual adjustment of AI contours further improved agreement: within subject coefficient of variation decreased from 5.0% to 4.5% for left ventricular ejection fraction (EF) and from 9.9% to 7.1% for right ventricular EF. Twenty manual analyses were performed in 250 min 12 s whereas same task took 5 min 48 s using AI method. Clinicians were open to adopt AI but concerns about accuracy and validity were raised. The AI method provides clinically valid outcomes and saves significant time. To address concerns raised by survey participants and overcome shortcomings of the automated myocardial segmentation, visual assessment of contours and performing manual corrections where necessary appears to be a practical approach.

Interinstitutional Portability of a Deep Learning Brain MRI Lesion Segmentation Algorithm

PURPOSE

To assess how well a brain MRI lesion segmentation algorithm trained at one institution performed at another institution, and to assess the effect of multi-institutional training datasets for mitigating performance loss.

MATERIALS AND METHODS

In this retrospective study, a three-dimensional U-Net for brain MRI abnormality segmentation was trained on data from 293 patients from one institution (IN1) (median age, 54 years; 165 women; patients treated between 2008 and 2018) and tested on data from 51 patients from a second institution (IN2) (median age, 46 years; 27 women; patients treated between 2003 and 2019). The model was then trained on additional data from various sources: (a) 285 multi-institution brain tumor segmentations, (b) 198 IN2 brain tumor segmentations, and (c) 34 IN2 lesion segmentations from various brain pathologic conditions. All trained models were tested on IN1 and external IN2 test datasets, assessing segmentation performance using Dice coefficients.

RESULTS

The U-Net accurately segmented brain MRI lesions across various pathologic conditions. Performance was lower when tested at an external institution (median Dice score, 0.70 [IN2] vs 0.76 [IN1]). Addition of 483 training cases of a single pathologic condition, including from IN2, did not raise performance (median Dice score, 0.72; P = .10). Addition of IN2 training data with heterogeneous pathologic features, representing only 10% (34 of 329) of total training data, increased performance to baseline (Dice score, 0.77; P < .001). This final model produced total lesion volumes with a high correlation to the reference standard (Spearman r = 0.98).

CONCLUSION

For brain MRI lesion segmentation, adding a modest amount of relevant training data from an external institution to a previously trained model supported successful application of the model to this external institution.Keywords: Neural Networks, Brain/Brain Stem, Segmentation Supplemental material is available for this article. © RSNA, 2021.

Genomic insights in ascending aortic size and distensibility

Background

Alterations in the anatomic and biomechanical properties of the ascending aorta (AAo) can give rise to various vascular pathologies. The aim of the current study is to gain additional insights in the biology of the AAo size and function.

Methods

We developed an AI based analysis pipeline for the segmentation of the AAo, and the extraction of AAO parameters. We then performed genome-wide association studies of AAo maximum area, AAo minimum area and AAo distensibility in up to 37,910 individuals from the UK Biobank. Variants that were significantly associated with AAo phenotypes were used as instrumental variables in Mendelian randomization analyses to investigate potential causal relationships with coronary artery disease, myocardial infarction, stroke and aneurysms.

Findings

Genome-wide association studies revealed a total of 107 SNPs in 78 loci. We annotated 101 candidate genes involved in various biological processes, including connective tissue development (THSD4 and COL6A3). Mendelian randomization analyses showed a causal association with aneurysm development, but not with other vascular diseases.

Interpretation

We identified 78 loci that provide insights into mechanisms underlying AAo size and function in the general population and provide genetic evidence for their role in aortic aneurysm development.

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

The future of healthcare is an organic blend of technology, innovation, and human connection. As artificial intelligence (AI) is gradually becoming a go-to technology in healthcare to improve efficiency and outcomes, we must understand our limitations. We should realize that our goal is not only to provide faster and more efficient care, but also to deliver an integrated solution to ensure that the care is fair and not biased to a group of sub-population. In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions-from heart failure to stroke-has made some advances to provide assistive tools to care providers. This article aimed to provide an overall thematic review of recent development focusing on various AI applications in cardio-cerebrovascular diseases to identify gaps and potential areas of improvement. If well designed, technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for efficiency.

Artificial intelligence in cardiology: the debate continues

In 1955, when John McCarthy and his colleagues proposed their first study of artificial intelligence, they suggested that 'every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it'. Whether that might ever be possible would depend on how we define intelligence, but what is indisputable is that new methods are needed to analyse and interpret the copious information provided by digital medical images, genomic databases, and biobanks. Technological advances have enabled applications of artificial intelligence (AI) including machine learning (ML) to be implemented into clinical practice, and their related scientific literature is exploding. Advocates argue enthusiastically that AI will transform many aspects of clinical cardiovascular medicine, while sceptics stress the importance of caution and the need for more evidence. This report summarizes the main opposing arguments that were presented in a debate at the 2021 Congress of the European Society of Cardiology. Artificial intelligence is an advanced analytical technique that should be considered when conventional statistical methods are insufficient, but testing a hypothesis or solving a clinical problem-not finding another application for AI-remains the most important objective. Artificial intelligence and ML methods should be transparent and interpretable, if they are to be approved by regulators and trusted to provide support for clinical decisions. Physicians need to understand AI methods and collaborate with engineers. Few applications have yet been shown to have a positive impact on clinical outcomes, so investment in research is essential.

Systematic Comparison of Left Ventricular Geometry Between 3D-Echocardiography and Cardiac Magnetic Resonance Imaging

Aims: Left ventricular (LV) volumes estimated using three-dimensional echocardiography (3D-echo) have been reported to be smaller than those measured using cardiac magnetic resonance (CMR) imaging, but the underlying causes are not well-understood. We investigated differences in regional LV anatomy derived from these modalities and related subsequent findings to image characteristics.

Methods and Results: Seventy participants (18 patients and 52 healthy participants) were imaged with 3D-echo and CMR (<1 h apart). Three-dimensional left ventricular models were constructed at end-diastole (ED) and end-systole (ES) from both modalities using previously validated software, enabling the fusion of CMR with 3D-echo by rigid registration. Regional differences were evaluated as mean surface distances for each of the 17 American Heart Association segments, and by comparing contours superimposed on images from each modality. In comparison to CMR-derived models, 3D-echo models underestimated LV end-diastolic volume (EDV) by −16 ± 22, −1 ± 25, and −18 ± 24 ml across three independent analysis methods. Average surface distance errors were largest in the basal-anterolateral segment (11–15 mm) and smallest in the mid-inferoseptal segment (6 mm). Larger errors were associated with signal dropout in anterior regions and the appearance of trabeculae at the lateral wall.

Conclusions: Fusion of CMR and 3D-echo provides insight into the causes of volume underestimation by 3D-echo. Systematic signal dropout and differences in appearances of trabeculae lead to discrepancies in the delineation of LV geometry at anterior and lateral regions. A better understanding of error sources across modalities may improve correlation of clinical indices between 3D-echo and CMR.

Effects of Spironolactone and Chlorthalidone on Cardiovascular Structure and Function in Chronic Kidney Disease: A Randomized, Open-Label Trial

BACKGROUND AND OBJECTIVES

In a randomized double-blind, placebo-controlled trial, treatment with spironolactone in early-stage CKD reduced left ventricular mass and arterial stiffness compared with placebo. It is not known if these effects were due to BP reduction or specific vascular and myocardial effects of spironolactone.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

A prospective, randomized, open-label, blinded end point study conducted in four UK centers (Birmingham, Cambridge, Edinburgh, and London) comparing spironolactone 25 mg to chlorthalidone 25 mg once daily for 40 weeks in 154 participants with nondiabetic stage 2 and 3 CKD (eGFR 30-89 ml/min per 1.73 m²). The primary end point was change in left ventricular mass on cardiac magnetic resonance imaging. Participants were on treatment with an angiotensin-converting enzyme inhibitor or angiotensin receptor blocker and had controlled BP (target ≤130/80 mm Hg).

RESULTS

There was no significant difference in left ventricular mass regression; at week 40, the adjusted mean difference for spironolactone compared with chlorthalidone was -3.8 g (95% confidence interval, -8.1 to 0.5 g, P=0.08). Office and 24-hour ambulatory BPs fell in response to both drugs with no significant differences between treatment. Pulse wave velocity was not significantly different between groups; at week 40, the adjusted mean difference for spironolactone compared with chlorthalidone was 0.04 m/s (-0.4 m/s, 0.5 m/s, P=0.90). Hyperkalemia (defined ≥5.4 mEq/L) occurred more frequently with spironolactone (12 versus two participants, adjusted relative risk was 5.5, 95% confidence interval, 1.4 to 22.1, P=0.02), but there were no patients with severe hyperkalemia (defined ≥6.5 mEq/L). A decline in eGFR >30% occurred in eight participants treated with chlorthalidone compared with two participants with spironolactone (adjusted relative risk was 0.2, 95% confidence interval, 0.05 to 1.1, P=0.07).

CONCLUSIONS

Spironolactone was not superior to chlorthalidone in reducing left ventricular mass, BP, or arterial stiffness in nondiabetic CKD.

Balancing Speed and Accuracy in Cardiac Magnetic Resonance Function Post-Processing: Comparing 2 Levels of Automation in 3 Vendors to Manual Assessment

Automating cardiac function assessment on cardiac magnetic resonance short-axis cines is faster and more reproducible than manual contour-tracing; however, accurately tracing basal contours remains challenging. Three automated post-processing software packages (Level 1) were compared to manual assessment. Subsequently, automated basal tracings were manually adjusted using a standardized protocol combined with software package-specific relative-to-manual standard error correction (Level 2). All post-processing was performed in 65 healthy subjects. Manual contour-tracing was performed separately from Level 1 and 2 automated analysis. Automated measurements were considered accurate when the difference was equal or less than the maximum manual inter-observer disagreement percentage. Level 1 (2.1 ± 1.0 min) and Level 2 automated (5.2 ± 1.3 min) were faster and more reproducible than manual (21.1 ± 2.9 min) post-processing, the maximum inter-observer disagreement was 6%. Compared to manual, Level 1 automation had wide limits of agreement. The most reliable software package obtained more accurate measurements in Level 2 compared to Level 1 automation: left ventricular end-diastolic volume, 98% and 53%; ejection fraction, 98% and 60%; mass, 70% and 3%; right ventricular end-diastolic volume, 98% and 28%; ejection fraction, 80% and 40%, respectively. Level 1 automated cardiac function post-processing is fast and highly reproducible with varying accuracy. Level 2 automation balances speed and accuracy.

Landmark Detection in Cardiac MRI by Using a Convolutional Neural Network

PURPOSE

To develop a convolutional neural network (CNN) solution for landmark detection in cardiac MRI (CMR).

MATERIALS AND METHODS

This retrospective study included cine, late gadolinium enhancement (LGE), and T1 mapping examinations from two hospitals. The training set included 2329 patients (34 089 images; mean age, 54.1 years; 1471 men; December 2017 to March 2020). A hold-out test set included 531 patients (7723 images; mean age, 51.5 years; 323 men; May 2020 to July 2020). CNN models were developed to detect two mitral valve plane and apical points on long-axis images. On short-axis images, anterior and posterior right ventricular (RV) insertion points and left ventricular (LV) center points were detected. Model outputs were compared with manual labels assigned by two readers. The trained model was deployed to MRI scanners.

RESULTS

For the long-axis images, successful detection of cardiac landmarks ranged from 99.7% to 100% for cine images and from 99.2% to 99.5% for LGE images. For the short-axis images, detection rates were 96.6% for cine, 97.6% for LGE, and 98.7% for T1 mapping. The Euclidean distances between model-assigned and manually assigned labels ranged from 2 to 3.5 mm for different landmarks, indicating close agreement between model-derived landmarks and manually assigned labels. For all views and imaging sequences, no differences between the models' assessment of images and the readers' assessment of images were found for the anterior RV insertion angle or LV length. Model inference for a typical cardiac cine series took 610 msec with the graphics processing unit and 5.6 seconds with central processing unit.

CONCLUSION

A CNN was developed for landmark detection on both long- and short-axis CMR images acquired with cine, LGE, and T1 mapping sequences, and the accuracy of the CNN was comparable with the interreader variation.Keywords: Cardiac, Heart, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection, Quantification, Supervised Learning, MR Imaging Supplemental material is available for this article. Published under a CC BY 4.0 license.

Artificial intelligence in the diagnosis and management of arrhythmias

The field of cardiac electrophysiology (EP) had adopted simple artificial intelligence (AI) methodologies for decades. Recent renewed interest in deep learning techniques has opened new frontiers in electrocardiography analysis including signature identification of diseased states. Artificial intelligence advances coupled with simultaneous rapid growth in computational power, sensor technology, and availability of web-based platforms have seen the rapid growth of AI-aided applications and big data research. Changing lifestyles with an expansion of the concept of internet of things and advancements in telecommunication technology have opened doors to population-based detection of atrial fibrillation in ways, which were previously unimaginable. Artificial intelligence-aided advances in 3D cardiac imaging heralded the concept of virtual hearts and the simulation of cardiac arrhythmias. Robotics, completely non-invasive ablation therapy, and the concept of extended realities show promise to revolutionize the future of EP. In this review, we discuss the impact of AI and recent technological advances in all aspects of arrhythmia care.

Applications of artificial intelligence in cardiovascular imaging

Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome.

Applications of artificial intelligence/machine learning approaches in cardiovascular medicine: a systematic review with recommendations

Aims

Artificial intelligence (AI) and machine learning (ML) promise vast advances in medicine. The current state of AI/ML applications in cardiovascular medicine is largely unknown. This systematic review aims to close this gap and provides recommendations for future applications.

Methods and results

Pubmed and EMBASE were searched for applied publications using AI/ML approaches in cardiovascular medicine without limitations regarding study design or study population. The PRISMA statement was followed in this review. A total of 215 studies were identified and included in the final analysis. The majority (87%) of methods applied belong to the context of supervised learning. Within this group, tree-based methods were most commonly used, followed by network and regression analyses as well as boosting approaches. Concerning the areas of application, the most common disease context was coronary artery disease followed by heart failure and heart rhythm disorders. Often, different input types such as electronic health records and images were combined in one AI/ML application. Only a minority of publications investigated reproducibility and generalizability or provided a clinical trial registration.

Conclusions

A major finding is that methodology may overlap even with similar data. Since we observed marked variation in quality, reporting of the evaluation and transparency of data and methods urgently need to be improved.

Noninvasive rapid cardiac magnetic resonance for the assessment of cardiomyopathies in low-middle income countries

Introduction: Cardiac Magnetic Resonance (CMR) is a crucial diagnostic imaging test that redefines diagnosis and enables targeted therapies, but the access to CMR is limited in low-middle Income Countries (LMICs) even though cardiovascular disease is an emergent primary cause of mortality in LMICs. New abbreviated CMR protocols can be less expensive, faster, whilst maintaining accuracy, potentially leading to a higher utilization in LMICs.Areas covered: This article will review cardiovascular disease in LMICs and the current role of CMR in cardiac diagnosis and enable targeted therapy, discussing the main obstacles to prevent the adoption of CMR in LMICs. We will then review the potential utility of abbreviated, cost-effective CMR protocols to improve cardiac diagnosis and care, the clinical indications of the exam, current evidence and future directions.Expert opinion: Rapid CMR protocols, provided that they are utilized in potentially high yield cases, could reduce cost and increase effectiveness. The adoption of these protocols, their integration into care pathways, and prioritizing key treatable diagnoses can potentially improve patient care. Several LMIC countries are now pioneering these approaches and the application of rapid CMR protocols appears to have a bright future if delivered effectively.

Computational analysis of cardiac structure and function in congenital heart disease: Translating discoveries to clinical strategies

Increased availability and access to medical image data has enabled more quantitative approaches to clinical diagnosis, prognosis, and treatment planning for congenital heart disease. Here we present an overview of long-term clinical management of tetralogy of Fallot (TOF) and its intersection with novel computational and data science approaches to discovering biomarkers of functional and prognostic importance. Efforts in translational medicine that seek to address the clinical challenges associated with cardiovascular diseases using personalized and precision-based approaches are then discussed. The considerations and challenges of translational cardiovascular medicine are reviewed, and examples of digital platforms with collaborative, cloud-based, and scalable design are provided.

Development, validation, and implementation of biomarker testing in cardiovascular medicine state-of-the-art: proceedings of the European Society of Cardiology-Cardiovascular Round Table

Many biomarkers that could be used to assess ejection fraction, heart failure, or myocardial infarction fail to translate into clinical practice because they lack essential performance characteristics or fail to meet regulatory standards for approval. Despite their potential, new technologies have added to the complexities of successful translation into clinical practice. Biomarker discovery and implementation require a standardized approach that includes: identification of a clinical need; identification of a valid surrogate biomarker; stepwise assay refinement, demonstration of superiority over current standard-of-care; development and understanding of a clinical pathway; and demonstration of real-world performance. Successful biomarkers should improve efficacy or safety of treatment, while being practical at a realistic cost. Everyone involved in cardiovascular healthcare, including researchers, clinicians, and industry partners, are important stakeholders in facilitating the development and implementation of biomarkers. This article provides suggestions for a development pathway for new biomarkers, discusses regulatory issues and challenges, and suggestions for accelerating the pathway to improve patient outcomes. Real-life examples of successful biomarkers-high-sensitivity cardiac troponin, T2* cardiovascular magnetic resonance imaging, and echocardiography-are used to illustrate the value of a standardized development pathway in the translation of concepts into routine clinical practice.

Role of cardiovascular magnetic resonance imaging in cardio-oncology

Advances in cancer therapy have led to significantly longer cancer-free survival times over the last 40 years. Improved survivorship coupled with increasing recognition of an expanding range of adverse cardiovascular effects of many established and novel cancer therapies has highlighted the impact of cardiovascular disease in this population. This has led to the emergence of dedicated cardio-oncology services that can provide pre-treatment risk stratification, surveillance, diagnosis, and monitoring of cardiotoxicity during cancer therapies, and late effects screening following completion of treatment. Cardiovascular imaging and the development of imaging biomarkers that can accurately and reliably detect pre-clinical disease and enhance our understanding of the underlying pathophysiology of cancer treatment-related cardiotoxicity are becoming increasingly important. Multi-parametric cardiovascular magnetic resonance (CMR) is able to assess cardiac structure, function, and provide myocardial tissue characterization, and hence can be used to address a variety of important clinical questions in the emerging field of cardio-oncology. In this review, we discuss the current and potential future applications of CMR in the investigation and management of cancer patients.

Left atrial 4D flow cardiovascular magnetic resonance: a reproducibility study in sinus rhythm and atrial fibrillation

BACKGROUND

Four-dimensional (4D) flow cardiovascular magnetic resonance (CMR) allows sophisticated quantification of left atrial (LA) blood flow, and could yield novel biomarkers of propensity for intra-cardiac thrombus formation and embolic stroke. As reproducibility is critically important to diagnostic performance, we systematically investigated technical and temporal variation of LA 4D flow in atrial fibrillation (AF) and sinus rhythm (SR).

METHODS

Eighty-six subjects (SR, n = 64; AF, n = 22) with wide-ranging stroke risk (CHA2DS2VASc 0-6) underwent LA 4D flow assessment of peak and mean velocity, vorticity, vortex volume, and stasis. Eighty-five (99%) underwent a second acquisition within the same session, and 74 (86%) also returned at 30 (27-35) days for an interval scan. We assessed variability attributable to manual contouring (intra- and inter-observer), and subject repositioning and reacquisition of data, both within the same session (same-day scan-rescan), and over time (interval scan). Within-subject coefficients of variation (CV) and bootstrapped 95% CIs were calculated and compared.

RESULTS

Same-day scan-rescan CVs were 6% for peak velocity, 5% for mean velocity, 7% for vorticity, 9% for vortex volume, and 10% for stasis, and were similar between SR and AF subjects (all p > 0.05). Interval-scan variability was similar to same-day scan-rescan variability for peak velocity, vorticity, and vortex volume (all p > 0.05), and higher for stasis and mean velocity (interval scan CVs of 14% and 8%, respectively, both p < 0.05). Longitudinal changes in heart rate and blood pressure at the interval scan in the same subjects were associated with significantly higher variability for LA stasis (p = 0.024), but not for the remaining flow parameters (all p > 0.05). SR subjects showed significantly greater interval-scan variability than AF patients for mean velocity, vortex volume, and stasis (all p < 0.05), but not peak velocity or vorticity (both p > 0.05).

CONCLUSIONS

LA peak velocity and vorticity are the most reproducible and temporally stable novel LA 4D flow biomarkers, and are robust to changes in heart rate, blood pressure, and differences in heart rhythm.

Automated analysis and detection of abnormalities in transaxial anatomical cardiovascular magnetic resonance images: a proof of concept study with potential to optimize image acquisition

The large number of available MRI sequences means patients cannot realistically undergo them all, so the range of sequences to be acquired during a scan are protocolled based on clinical details. Adapting this to unexpected findings identified early on in the scan requires experience and vigilance. We investigated whether deep learning of the images acquired in the first few minutes of a scan could provide an automated early alert of abnormal features. Anatomy sequences from 375 CMR scans were used as a training set. From these, we annotated 1500 individual slices and used these to train a convolutional neural network to perform automatic segmentation of the cardiac chambers, great vessels and any pleural effusions. 200 scans were used as a testing set. The system then assembled a 3D model of the thorax from which it made clinical measurements to identify important abnormalities. The system was successful in segmenting the anatomy slices (Dice 0.910) and identified multiple features which may guide further image acquisition. Diagnostic accuracy was 90.5% and 85.5% for left and right ventricular dilatation, 85% for left ventricular hypertrophy and 94.4% for ascending aorta dilatation. The area under ROC curve for diagnosing pleural effusions was 0.91. We present proof-of-concept that a neural network can segment and derive accurate clinical measurements from a 3D model of the thorax made from transaxial anatomy images acquired in the first few minutes of a scan. This early information could lead to dynamic adaptive scanning protocols, and by focusing scanner time appropriately and prioritizing cases for supervision and early reporting, improve patient experience and efficiency.

Entwicklung kardiovaskuläre Medizin 2020: Kardiale Magnetresonanztomographie

Die kardiale Magnetresonanztomographie (MRT) hat sich als wichtiges nicht-invasives Diagnostikverfahren innerhalb der Kardiologie etabliert und entwickelt sich stetig weiter. Dieser Beitrag stellt beispielhaft drei interessante MRT-Studien der letzten Monate vor, die die Themen „MRT und COVID-19“, „Fibrose bei Aortenklappenstenose“ und „MRT und künstliche Intelligenz“ behandeln. Außerdem werden neue MRT-Positionspapiere zu den Bereichen „MRT-Indikationen“, „MRT-Protokolle“, „MRT-Postprocessing“ und „MRT-Normwerte“ beschrieben. Darüber hinaus wird die Rolle der kardialen MRT in den 2020 erschienenen kardiologischen Leitlinien der European Society of Cardiology und der American Heart Association dargestellt. Schließlich folgt eine aktuelle Bilanz der MRT-Zertifizierung durch die Deutsche Gesellschaft für Kardiologie.

Cardiac MRI-Update 2020

PURPOSE

To review emerging techniques in cardiac magnetic resonance imaging (CMR) and their clinical applications with a special emphasis on new technologies, recent trials, and updated guidelines.

TECHNOLOGICAL INNOVATIONS

The utility of CMR has expanded with the development of new MR sequences, postprocessing techniques, and artificial intelligence-based technologies, which have substantially increased the spectrum, quality, and reliability of information that can be obtained by CMR.

ESTABLISHED AND EMERGING INDICATIONS

The CMR modality has become an irreplaceable tool for diagnosis, treatment guidance and follow-up of patients with ischemic heart disease, myocarditis, and cardiomyopathies. Its role has been further strengthened by recent trials and guidelines. Quantitative mapping techniques are increasingly used for tissue characterization and detection of diffuse myocardial changes including myocardial storage diseases.

PRACTICAL RECOMMENDATIONS

With state-of-the-art CMR sequences, postprocessing techniques and understanding of their interpretation, CMR makes invaluable contributions to provide state-of-the-art diagnostics and care for cardiac patients in a multidisciplinary team.

Diagnosis and risk stratification in hypertrophic cardiomyopathy using machine learning wall thickness measurement: a comparison with human test-retest performance

BACKGROUND

Left ventricular maximum wall thickness (MWT) is central to diagnosis and risk stratification of hypertrophic cardiomyopathy, but human measurement is prone to variability. We developed an automated machine learning algorithm for MWT measurement and compared precision (reproducibility) with that of 11 international experts, using a dataset of patients with hypertrophic cardiomyopathy.

METHODS

60 adult patients with hypertrophic cardiomyopathy, including those carrying hypertrophic cardiomyopathy gene mutations, were recruited at three institutes in the UK from August, 2018, to September, 2019: Barts Heart Centre, University College London Hospital (The Heart Hospital), and Leeds Teaching Hospitals NHS Trust. Participants had two cardiovascular magnetic resonance scans (test and retest) on the same day, ensuring no biological variability, using four cardiac MRI scanner models represented across two manufacturers and two field strengths. End-diastolic short-axis MWT was measured in test and retest by 11 international experts (from nine centres in six countries) and an automated machine learning method, which was trained to segment endocardial and epicardial contours on an independent, multicentre, multidisease dataset of 1923 patients. Machine learning MWT measurement was done with a method based on solving Laplace's equation. To assess test-retest reproducibility, we estimated the absolute test-retest MWT difference (precision), the coefficient of variation (CoV) for duplicate measurements, and the number of patients reclassified between test and retest according to different thresholds (MWT >15 mm and >30 mm). We calculated the sample size required to detect a prespecified MWT change between pairs of scans for machine learning and each expert.

FINDINGS

1440 MWT measurements were analysed, corresponding to two scans from 60 participants by 12 observers (11 experts and machine learning). Experts differed in the MWT they measured, ranging from 14·9 mm (SD 4·2) to 19·0 mm (4·7; p<0·0001 for trend). Machine learning-measured mean MWT was 16·8 mm (4·1). Machine learning precision was superior, with a test-retest difference of 0·7 mm (0·6) compared with experts, who ranged from 1·1 mm (0·9) to 3·7 mm (2·0; p values for machine learning vs expert comparison ranging from <0·0001 to 0·0073) and a significantly lower CoV than for all experts (4·3% [95% CI 3·3-5·1] vs 5·7-12·1% across experts). On average, 38 (64%) patients were designated as having MWT greater than 15 mm by machine learning compared with 27 (45%) to 50 (83%) patients by experts; five (8%) patients were reclassified in test-retest by machine learning compared with four (7%) to 12 (20%) by experts. With a cutoff point of more than 30 mm for implantable cardioverter-defibrillator, three experts would have changed recommendations between tests a total of four times, but machine learning was consistent. Using machine learning, a clinical trial to detect a 2 mm MWT change would need 2·3 times (range 1·6-4·6) fewer patients.

INTERPRETATION

In this preliminary study, machine learning MWT measurement in hypertrophic cardiomyopathy is superior to human experts with potential implications for diagnosis, risk stratification, and clinical trials.

FUNDING

European Regional Development Fund and Barts Charity.

The Role of Artificial Intelligence in Cardiovascular Imaging: State of the Art Review

In this current digital landscape, artificial intelligence (AI) has established itself as a powerful tool in the commercial industry and is an evolving technology in healthcare. Cutting-edge imaging modalities outputting multi-dimensional data are becoming increasingly complex. In this era of data explosion, the field of cardiovascular imaging is undergoing a paradigm shift toward machine learning (ML) driven platforms. These diverse algorithms can seamlessly analyze information and automate a range of tasks. In this review article, we explore the role of ML in the field of cardiovascular imaging.