Fully Automated, Quality-Controlled Cardiac Analysis From CMR: Validation and Large-Scale Application to Characterize Cardiac Function

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

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

A Motion-Aware DNN Model with Edge Focus Loss and Quality Control for Short-Axis Left Ventricle Segmentation of Cine MR Sequences

Accurate segmentation of the left ventricle myocardium is the key step of automatic assessment of cardiac function. However, the current methods mainly focus on the end-diastolic and the end-systolic frames in cine MR sequences and lack the attention to myocardial motion in the cardiac cycle. Additionally, due to the lack of fine segmentation tools, the simplified approach, excluding papillary muscles and trabeculae from myocardium, is applied in clinical practice. To solve these problems, we propose a motion-aware DNN model with edge focus loss and quality control in this paper. Specifically, the bidirectional ConvLSTM layer and a new motion attention layer are proposed to encode motion-aware feature maps, and an edge focus loss function is proposed to train the model to generate the fine segmentation results. Additionally, a quality control method is proposed to filter out the abnormal segmentations before subsequent analyses. Compared with state-of-the-art segmentation models on the public dataset and the in-house dataset, the proposed method has obtained high segmentation accuracy. On the 17-segment model, the proposed method has obtained the highest Pearson correlation coefficient at 14 of 17 segments, and the mean PCC of 85%. The experimental results highlight the segmentation accuracy of the proposed method as well as its availability to substitute for the manually annotated boundaries for the automatic assessment of cardiac function.

Cardiac magnetic resonance in advanced heart failure

Heart failure (HF) is a chronic and progressive disease that often progresses to an advanced stage where conventional therapy is insufficient to relieve patients' symptoms. Despite the availability of advanced therapies such as mechanical circulatory support or heart transplantation, the complexity of defining advanced HF, which requires multiple parameters and multimodality assessment, often leads to delays in referral to dedicated specialists with the result of a worsening prognosis. In this review, we aim to explore the role of cardiac magnetic resonance (CMR) in advanced HF by showing how CMR is useful at every step in managing these patients: from diagnosis to prognostic stratification, hemodynamic evaluation, follow-up and advanced therapies such as heart transplantation. The technical challenges of scanning advanced HF patients, which often require troubleshooting of intracardiac devices and dedicated scans, will be also discussed.

The Role of Artificial Intelligence in Cardiac Imaging

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

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.

Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization

BACKGROUND

Late gadolinium enhancement (LGE) of the myocardium has significant diagnostic and prognostic implications, with even small areas of enhancement being important. Distinguishing between definitely normal and definitely abnormal LGE images is usually straightforward, but diagnostic uncertainty arises when reporters are not sure whether the observed LGE is genuine or not. This uncertainty might be resolved by repetition (to remove artifact) or further acquisition of intersecting images, but this must take place before the scan finishes. Real-time quality assurance by humans is a complex task requiring training and experience, so being able to identify which images have an intermediate likelihood of LGE while the scan is ongoing, without the presence of an expert is of high value. This decision-support could prompt immediate image optimization or acquisition of supplementary images to confirm or refute the presence of genuine LGE. This could reduce ambiguity in reports.

METHODS

Short-axis, phase-sensitive inversion recovery late gadolinium images were extracted from our clinical cardiac magnetic resonance (CMR) database and shuffled. Two, independent, blinded experts scored each individual slice for "LGE likelihood" on a visual analog scale, from 0 (absolute certainty of no LGE) to 100 (absolute certainty of LGE), with 50 representing clinical equipoise. The scored images were split into two classes-either "high certainty" of whether LGE was present or not, or "low certainty." The dataset was split into training, validation, and test sets (70:15:15). A deep learning binary classifier based on the EfficientNetV2 convolutional neural network architecture was trained to distinguish between these categories. Classifier performance on the test set was evaluated by calculating the accuracy, precision, recall, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Performance was also evaluated on an external test set of images from a different center.

RESULTS

One thousand six hundred and forty-five images (from 272 patients) were labeled and split at the patient level into training (1151 images), validation (247 images), and test (247 images) sets for the deep learning binary classifier. Of these, 1208 images were "high certainty" (255 for LGE, 953 for no LGE), and 437 were "low certainty". An external test comprising 247 images from 41 patients from another center was also employed. After 100 epochs, the performance on the internal test set was accuracy = 0.94, recall = 0.80, precision = 0.97, F1-score = 0.87, and ROC AUC = 0.94. The classifier also performed robustly on the external test set (accuracy = 0.91, recall = 0.73, precision = 0.93, F1-score = 0.82, and ROC AUC = 0.91). These results were benchmarked against a reference inter-expert accuracy of 0.86.

CONCLUSION

Deep learning shows potential to automate quality control of late gadolinium imaging in CMR. The ability to identify short-axis images with intermediate LGE likelihood in real-time may serve as a useful decision-support tool. This approach has the potential to guide immediate further imaging while the patient is still in the scanner, thereby reducing the frequency of recalls and inconclusive reports due to diagnostic indecision.

A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis

Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.

Assessment of deep learning segmentation for real-time free-breathing cardiac magnetic resonance imaging at rest and under exercise stress

In recent years, a variety of deep learning networks for cardiac MRI (CMR) segmentation have been developed and analyzed. However, nearly all of them are focused on cine CMR under breathold. In this work, accuracy of deep learning methods is assessed for volumetric analysis (via segmentation) of the left ventricle in real-time free-breathing CMR at rest and under exercise stress. Data from healthy volunteers (n = 15) for cine and real-time free-breathing CMR at rest and under exercise stress were analyzed retrospectively. Exercise stress was performed using an ergometer in the supine position. Segmentations of two deep learning methods, a commercially available technique (comDL) and an openly available network (nnU-Net), were compared to a reference model created via the manual correction of segmentations obtained with comDL. Segmentations of left ventricular endocardium (LV), left ventricular myocardium (MYO), and right ventricle (RV) are compared for both end-systolic and end-diastolic phases and analyzed with Dice's coefficient. The volumetric analysis includes the cardiac function parameters LV end-diastolic volume (EDV), LV end-systolic volume (ESV), and LV ejection fraction (EF), evaluated with respect to both absolute and relative differences. For cine CMR, nnU-Net and comDL achieve Dice's coefficients above 0.95 for LV and 0.9 for MYO, and RV. For real-time CMR, the accuracy of nnU-Net exceeds that of comDL overall. For real-time CMR at rest, nnU-Net achieves Dice's coefficients of 0.94 for LV, 0.89 for MYO, and 0.90 for RV and the mean absolute differences between nnU-Net and the reference are 2.9 mL for EDV, 3.5 mL for ESV, and 2.6% for EF. For real-time CMR under exercise stress, nnU-Net achieves Dice's coefficients of 0.92 for LV, 0.85 for MYO, and 0.83 for RV and the mean absolute differences between nnU-Net and reference are 11.4 mL for EDV, 2.9 mL for ESV, and 3.6% for EF. Deep learning methods designed or trained for cine CMR segmentation can perform well on real-time CMR. For real-time free-breathing CMR at rest, the performance of deep learning methods is comparable to inter-observer variability in cine CMR and is usable for fully automatic segmentation. For real-time CMR under exercise stress, the performance of nnU-Net could promise a higher degree of automation in the future.

Optimizing Deep Learning for Cardiac MRI Segmentation: The Impact of Automated Slice Range Classification

RATIONALE AND OBJECTIVES

Cardiac magnetic resonance imaging is crucial for diagnosing cardiovascular diseases, but lengthy postprocessing and manual segmentation can lead to observer bias. Deep learning (DL) has been proposed for automated cardiac segmentation; however, its effectiveness is limited by the slice range selection from base to apex.

MATERIALS AND METHODS

In this study, we integrated an automated slice range classification step to identify basal to apical short-axis slices before DL-based segmentation. We employed publicly available Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI data set with short-axis cine data from 160 training, 40 validation, and 160 testing cases. Three classification and seven segmentation DL models were studied. The top-performing segmentation model was assessed with and without the classification model. Model validation to compare automated and manual segmentation was performed using Dice score and Hausdorff distance and clinical indices (correlation score and Bland-Altman plots).

RESULTS

The combined classification (CBAM-integrated 2D-CNN) and segmentation model (2D-UNet with dilated convolution block) demonstrated superior performance, achieving Dice scores of 0.952 for left ventricle (LV), 0.933 for right ventricle (RV), and 0.875 for myocardium, compared to the stand-alone segmentation model (0.949 for LV, 0.925 for RV, and 0.867 for myocardium). Combined classification and segmentation model showed high correlation (0.92-0.99) with manual segmentation for biventricular volumes, ejection fraction, and myocardial mass. The mean absolute difference (2.8-8.3 mL) for clinical parameters between automated and manual segmentation was within the interobserver variability range, indicating comparable performance to manual annotation.

CONCLUSION

Integrating an initial automated slice range classification step into the segmentation process improves the performance of DL-based cardiac chamber segmentation.

Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking-a cardiovascular MR study in health and disease

OBJECTIVES

The analysis of myocardial deformation using feature tracking in cardiovascular MR allows for the assessment of global and segmental strain values. The aim of this study was to compare strain values derived from artificial intelligence (AI)-based contours with manually derived strain values in healthy volunteers and patients with cardiac pathologies.

MATERIALS AND METHODS

A cohort of 136 subjects (60 healthy volunteers and 76 patients; of those including 46 cases with left ventricular hypertrophy (LVH) of varying etiology and 30 cases with chronic myocardial infarction) was analyzed. Comparisons were based on quantitative strain analysis and on a geometric level by the Dice similarity coefficient (DSC) of the segmentations. Strain quantification was performed in 3 long-axis slices and short-axis (SAX) stack with epi- and endocardial contours in end-diastole. AI contours were checked for plausibility and potential errors in the tracking algorithm.

RESULTS

AI-derived strain values overestimated radial strain (+ 1.8 ± 1.7% (mean difference ± standard deviation); p = 0.03) and underestimated circumferential (- 0.8 ± 0.8%; p = 0.02) and longitudinal strain (- 0.1 ± 0.8%; p = 0.54). Pairwise group comparisons revealed no significant differences for global strain. The DSC showed good agreement for healthy volunteers (85.3 ± 10.3% for SAX) and patients (80.8 ± 9.6% for SAX). In 27 cases (27/76; 35.5%), a tracking error was found, predominantly (24/27; 88.9%) in the LVH group and 22 of those (22/27; 81.5%) at the insertion of the papillary muscle in lateral segments.

CONCLUSIONS

Strain analysis based on AI-segmented images shows good results in healthy volunteers and in most of the patient groups. Hypertrophied ventricles remain a challenge for contouring and feature tracking.

CLINICAL RELEVANCE STATEMENT

AI-based segmentations can help to streamline and standardize strain analysis by feature tracking.

KEY POINTS

• Assessment of strain in cardiovascular magnetic resonance by feature tracking can generate global and segmental strain values. • Commercially available artificial intelligence algorithms provide segmentation for strain analysis comparable to manual segmentation. • Hypertrophied ventricles are challenging in regards of strain analysis by feature tracking.

Systematic review and meta-analysis for the value of cardiac magnetic resonance strain to predict cardiac outcomes

Cardiac magnetic resonance (CMR) is the gold standard for the diagnostic classification and risk stratification in most patients with cardiac disorders. The aim of the present study was to investigate the ability of Strain-encoded MR (SENC) for the prediction of major adverse cardiovascular events (MACE). A systematic review and meta-analysis was performed according to the PRISMA Guidelines, including patients with or without cardiovascular disease and asymptomatic individuals. Myocardial strain by HARP were used as pulse sequences in 1.5 T scanners. Published literature in MEDLINE (PubMed) and Cochrane's databases were explored before February 2023 for studies assessing the clinical utility of myocardial strain by Harmonic Phase Magnetic Resonance Imaging (HARP), Strain-encoded MR (SENC) or fast-SENC. In total, 8 clinical trials (4 studies conducted in asymptomatic individuals and 4 in patients with suspected or known cardiac disease) were included in this systematic review, while 3 studies were used for our meta-analysis, based on individual patient level data. Kaplan-Meier analysis and Cox proportional hazard models were used, testing the ability of myocardial strain by HARP and SENC/fast-SENC for the prediction of MACE. Strain enabled risk stratification in asymptomatic individuals, predicting MACE and the development of incident heart failure. Of 1332 patients who underwent clinically indicated CMR, including SENC or fast-SENC acquisitions, 19 patients died, 28 experienced non-fatal infarctions, 52 underwent coronary revascularization and 86 were hospitalized due to heart failure during median 22.4 (17.2-28.5) months of follow-up. SENC/fast-SENC, predicted both all-cause mortality and MACE with high accuracy (HR = 3.0, 95% CI = 1.2-7.6, p = 0.02 and HR = 4.1, 95% CI = 3.0-5.5, respectively, p < 0.001). Using hierarchical Cox-proportional hazard regression models, SENC/fast-SENC exhibited incremental value to clinical data and conventional CMR parameters. Reduced myocardial strain predicts of all-cause mortality and cardiac outcomes in symptomatic patients with a wide range of ischemic or non-ischemic cardiac diseases, whereas in asymptomatic individuals, reduced strain was a precursor of incident heart failure.

Hemodynamic Determinants of Elevated Blood Pressure and Hypertension in the Middle to Older-Age UK Population: A UK Biobank Imaging Study

BACKGROUND

Increased systemic vascular resistance and, in older people, reduced aortic distensibility, are thought to be the hemodynamic determinants of primary hypertension but cardiac output could also be important. We examined the hemodynamics of elevated blood pressure and hypertension in the middle to older-aged UK population participating in the UK Biobank imaging studies.

METHODS

Cardiac output, systemic vascular resistance, and aortic distensibility were measured from cardiac magnetic resonance imaging in 31 112 (distensibility in 21 178) participants (46.3% male, mean age±SD 63±7 years). Body composition including visceral adipose tissue volume and abdominal subcutaneous adipose tissue volume were measured in 19 645 participants.

RESULTS

Participants with higher blood pressure had higher cardiac output (higher by 17.9±26.6% in hypertensive compared with those with optimal blood pressure) and higher systemic vascular resistance (higher by 11.4±27.9% in hypertensive compared with those with optimal blood pressure). These differences were little changed after adjustment for body size and adiposity. The contribution of cardiac output relative to systemic vascular resistance was more marked in younger compared with older subjects. Aortic distensibility decreased with age and was lower in participants with higher compared with lower blood pressure but with a greater difference in younger compared with older subjects.

CONCLUSIONS

In the middle to older-aged UK population, cardiac output plays an important role in contributing to elevated mean arterial blood pressure, particularly in younger compared with older subjects. Reduced aortic distensibility contributes to a rise in pulse pressure and systolic blood pressure at all ages.

An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases

Aims

Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases.

Methods and results

Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset (n = 414) and five external datasets (n = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups.

Conclusion

We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.

The application of radiology for dilated cardiomyopathy diagnosis, treatment, and prognosis prediction: a bibliometric analysis

Background

Radiology plays a highly crucial role in the diagnosis, treatment, and prognosis prediction of dilated cardiomyopathy (DCM). Related research has increased rapidly over the past few years, but systematic analyses are lacking. This study thus aimed to provide a reference for further research by analyzing the knowledge field, development trends, and research hotspots of radiology in DCM using bibliometric methods.

Methods

Articles on the radiology of DCM published between 2002 and 2021 in the Web of Science Core Collection database (WoSCCd) were searched and analyzed. Data were retrieved and analyzed using CiteSpace V, VOSviewer, and Scimago Graphic software, and included the name, research institution, and nationality of authors; journals of publication; and the number of citations.

Results

A total of 4,257 articles were identified on radiology of DCM from WoSCCd. The number of articles published in this field has grown steadily from 2002 to 2021 and is expected to reach 392 annually by 2024. According to subfields, the number of papers published in cardiac magnetic resonance field increased steadily. The authors from the United States published the most (1,364 articles, 32.04%) articles. The author with the most articles published was Bax JJ (54 articles, 1.27%) from Leiden University Medical Center. The most cited article was titled "2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure", with 138 citations. Citation-based clustering showed that arrhythmogenic cardiomyopathy, T1 mapping, and endomyocardial biopsy are the current hots pots for research in DCM radiology. The most frequently occurring keyword was "dilated cardiomyopathy". The keyword-based clusters mainly included "late gadolinium enhancement", "congestive heart failure", "cardiovascular magnetic resonance", "sudden cardiac death", "ventricular arrhythmia", and "cardiac resynchronization therapy".

Conclusions

The United States and Northern Europe are the most influential countries in research on DCM radiology, with many leading distinguished research institutions. The current research hots pots are myocardial fibrosis, risk stratification of ventricular arrhythmia, the prognosis of cardiac resynchronization therapy (CRT) treatment, and subtype classification of DCM.

Identification of novel genetic risk factors of dilated cardiomyopathy: from canine to human

BACKGROUND

Dilated cardiomyopathy (DCM) is a life-threatening heart disease and a common cause of heart failure due to systolic dysfunction and subsequent left or biventricular dilatation. A significant number of cases have a genetic etiology; however, as a complex disease, the exact genetic risk factors are largely unknown, and many patients remain without a molecular diagnosis.

METHODS

We performed GWAS followed by whole-genome, transcriptome, and immunohistochemical analyses in a spontaneously occurring canine model of DCM. Canine gene discovery was followed up in three human DCM cohorts.

RESULTS

Our results revealed two independent additive loci associated with the typical DCM phenotype comprising left ventricular systolic dysfunction and dilatation. We highlight two novel candidate genes, RNF207 and PRKAA2, known for their involvement in cardiac action potentials, energy homeostasis, and morphology. We further illustrate the distinct genetic etiologies underlying the typical DCM phenotype and ventricular premature contractions. Finally, we followed up on the canine discoveries in human DCM patients and discovered candidate variants in our two novel genes.

CONCLUSIONS

Collectively, our study yields insight into the molecular pathophysiology of DCM and provides a large animal model for preclinical studies.

Quality control-driven deep ensemble for accountable automated segmentation of cardiac magnetic resonance LGE and VNE images

Background

Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of the left ventricular (LV) myocardium remains a challenge due to limited training data and lack of quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native enhancement (VNE) images to expand the training set and incorporating an automated quality control-driven (QCD) framework to improve segmentation reliability.

Methods

A dataset comprising 4,716 LGE images (from 1,363 patients with hypertrophic cardiomyopathy and myocardial infarction) was used for development. To generate additional clinically validated data, LGE data were augmented with a GAN-based generator to produce VNE images. LV was contoured on these images manually by clinical observers. To create diverse candidate segmentations, the QCD framework involved multiple U-Nets, which were combined using statistical rank filters. The framework predicted the Dice Similarity Coefficient (DSC) for each candidate segmentation, with the highest predicted DSC indicating the most accurate and reliable result. The performance of the QCD ensemble framework was evaluated on both LGE and VNE test datasets (309 LGE/VNE images from 103 patients), assessing segmentation accuracy (DSC) and quality prediction (mean absolute error (MAE) and binary classification accuracy).

Results

The QCD framework effectively and rapidly segmented the LV myocardium (<1 s per image) on both LGE and VNE images, demonstrating robust performance on both test datasets with similar mean DSC (LGE: 0.845 ± 0.075 ; VNE: 0.845 ± 0.071 ; p = n s ). Incorporating GAN-generated VNE data into the training process consistently led to enhanced performance for both individual models and the overall framework. The quality control mechanism yielded a high performance (MAE = 0.043 , accuracy = 0.951 ) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference (p = n s ) was found when comparing the LGE and VNE test sets across all experiments.

Conclusions

The QCD ensemble framework, leveraging GAN-generated VNE data and an automated quality control mechanism, significantly improved the accuracy and reliability of LGE segmentation, paving the way for enhanced and accountable diagnostic imaging in routine clinical use.

Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study

OBJECTIVE

Convolutional neural networks (CNNs) have demonstrated promise in automated cardiac magnetic resonance image segmentation. However, when using CNNs in a large real-world dataset, it is important to quantify segmentation uncertainty and identify segmentations which could be problematic. In this work, we performed a systematic study of Bayesian and non-Bayesian methods for estimating uncertainty in segmentation neural networks.

METHODS

We evaluated Bayes by Backprop, Monte Carlo Dropout, Deep Ensembles, and Stochastic Segmentation Networks in terms of segmentation accuracy, probability calibration, uncertainty on out-of-distribution images, and segmentation quality control.

RESULTS

We observed that Deep Ensembles outperformed the other methods except for images with heavy noise and blurring distortions. We showed that Bayes by Backprop is more robust to noise distortions while Stochastic Segmentation Networks are more resistant to blurring distortions. For segmentation quality control, we showed that segmentation uncertainty is correlated with segmentation accuracy for all the methods. With the incorporation of uncertainty estimates, we were able to reduce the percentage of poor segmentation to 5% by flagging 31-48% of the most uncertain segmentations for manual review, substantially lower than random review without using neural network uncertainty (reviewing 75-78% of all images).

CONCLUSION

This work provides a comprehensive evaluation of uncertainty estimation methods and showed that Deep Ensembles outperformed other methods in most cases.

SIGNIFICANCE

Neural network uncertainty measures can help identify potentially inaccurate segmentations and alert users for manual review.

Druggable proteins influencing cardiac structure and function: Implications for heart failure therapies and cancer cardiotoxicity

Dysfunction of either the right or left ventricle can lead to heart failure (HF) and subsequent morbidity and mortality. We performed a genome-wide association study (GWAS) of 16 cardiac magnetic resonance (CMR) imaging measurements of biventricular function and structure. Cis-Mendelian randomization (MR) was used to identify plasma proteins associating with CMR traits as well as with any of the following cardiac outcomes: HF, non-ischemic cardiomyopathy, dilated cardiomyopathy (DCM), atrial fibrillation, or coronary heart disease. In total, 33 plasma proteins were prioritized, including repurposing candidates for DCM and/or HF: IL18R (providing indirect evidence for IL18), I17RA, GPC5, LAMC2, PA2GA, CD33, and SLAF7. In addition, 13 of the 25 druggable proteins (52%; 95% confidence interval, 0.31 to 0.72) could be mapped to compounds with known oncological indications or side effects. These findings provide leads to facilitate drug development for cardiac disease and suggest that cardiotoxicities of several cancer treatments might represent mechanism-based adverse effects.

Quantitative CTA vascular calcification, atherosclerosis burden, and stroke mechanism in patients with ischemic stroke

BACKGROUND

Vascular calcification is recognized as the advanced stage of atherosclerosis burden. We hypothesized that vascular calcium quantification in CT angiography (CTA) would be helpful to differentiate large artery atherosclerosis (LAA) from other stroke etiology in patients with ischemic stroke.

METHODS

We studied 375 acute ischemic stroke patients (200 males, mean age 69.9 years) who underwent complete CTA images of the aortic arch, neck, and head. The automatic artery and calcification segmentation method measured calcification volumes in the intracranial internal carotid artery (ICA), cervical carotid artery, and aortic arch using deep-learning U-net model and region-grow algorithms. We investigated the correlations and patterns of vascular calcification in the different vessel beds among stroke etiology by age category (young: <65 years, intermediate: 65-74 years, older ≥75 years).

RESULTS

Ninety-five (25.3%) were diagnosed with LAA according to TOAST criteria. Median calcification volumes were higher by increasing the age category in each vessel bed. One-way ANOVA with Bonferroni correction showed calcification volumes in all vessel beds were significantly higher in LAA compared with other stroke subtypes in the younger subgroup. Calcification volumes were independently associated with LAA in intracranial ICA (OR; 2.89, 95% CI 1.56-5.34, P = .001), cervical carotid artery (OR; 3.40, 95% CI 1.94-5.94, P < .001) and aorta (OR; 1.69, 95%CI 1.01-2.80, P = .044) in younger subsets. By contrast, the intermediate and older subsets did not show a significant relationship between calcification volumes and stroke subtypes.

CONCLUSION

Atherosclerosis calcium volumes in major vessels were significantly higher in LAA compared to non-LAA stroke in younger age.

Cardiovascular magnetic resonance for evaluation of cardiac involvement in COVID-19: recommendations by the Society for Cardiovascular Magnetic Resonance

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has affected nearly 600 million people to date across the world. While COVID-19 is primarily a respiratory illness, cardiac injury is also known to occur. Cardiovascular magnetic resonance (CMR) imaging is uniquely capable of characterizing myocardial tissue properties in-vivo, enabling insights into the pattern and degree of cardiac injury. The reported prevalence of myocardial involvement identified by CMR in the context of COVID-19 infection among previously hospitalized patients ranges from 26 to 60%. Variations in the reported prevalence of myocardial involvement may result from differing patient populations (e.g. differences in severity of illness) and the varying intervals between acute infection and CMR evaluation. Standardized methodologies in image acquisition, analysis, interpretation, and reporting of CMR abnormalities across would likely improve concordance between studies. This consensus document by the Society for Cardiovascular Magnetic Resonance (SCMR) provides recommendations on CMR imaging and reporting metrics towards the goal of improved standardization and uniform data acquisition and analytic approaches when performing CMR in patients with COVID-19 infection.

Association of cardiovascular magnetic resonance diastolic indices with arrhythmia in repaired Tetralogy of Fallot

BACKGROUND

Patients with repaired Tetralogy of Fallot (rTOF) experience a high burden of long-term morbidity, particularly arrhythmias. Cardiovascular magnetic resonance (CMR) is routinely used to assess ventricular characteristics but the relationship between CMR diastolic function and arrhythmia has not been evaluated. We hypothesized in rTOF, left ventricular (LV) diastolic dysfunction on CMR would correlate with arrhythmias and mortality.

METHODS

Adolescents and adults with rTOF who underwent CMR were compared to healthy controls (n = 58). Standard ventricular parameters were assessed and manual planimetry was performed to generate filling curves and indices of diastolic function. Chart review was performed to collect outcomes. Univariate and multivariable logistic regression was performed to identify outcome associations.

RESULTS

One-hundred sixty-seven subjects with rTOF (mean age 32 years) and 58 healthy control subjects underwent CMR. Patients with rTOF had decreased LV volumes and increased right ventricular (RV) volumes, lower RV ejection fraction (RVEF), lower peak ejection rate (PER), peak filling rate (PFR) and PFR indexed to end-diastolic volume (PFR/EDV) compared to healthy controls. Eighty-three subjects with rTOF had arrhythmia (63 atrial, 47 ventricular) and 11 died. Left atrial (LA) volumes, time to peak filling rate (tPFR), and PFR/EDV were associated with arrhythmia on univariate analysis. PER/EDV was associated with ventricular (Odds ratio, OR 0.43 [0.24-0.80], p = 0.007) and total arrhythmia (OR 0.56 [0.37-0.92], p = 0.021) burden. A multivariable predictive model including diastolic covariates showed improved prediction for arrhythmia compared to clinical and conventional CMR measures (area under curve (AUC) 0.749 v. 0.685 for overall arrhythmia). PFR/EDV was decreased and tPFR was increased in rTOF subjects with mortality as compared to those without mortality.

CONCLUSIONS

Subjects with rTOF have abnormal LV diastolic function compared to healthy controls. Indices of LV diastolic function were associated with arrhythmia and mortality. CMR diastolic indices may be helpful in risk stratification for arrhythmia.

Translating principles of quality control to cardiovascular magnetic resonance: assessing quantitative parameters of the left ventricle in a large cohort

Cardiac magnetic resonance (CMR) examinations require standardization to achieve reproducible results. Therefore, quality control as known as in other industries such as in-vitro diagnostics, could be of essential value. One such method is the statistical detection of long-time drifts of clinically relevant measurements. Starting in 2010, reports from all CMR examinations of a high-volume center were stored in a hospital information system. Quantitative parameters of the left ventricle were analyzed over time with moving averages of different window sizes. Influencing factors on the acquisition and on the downstream analysis were captured. 26,902 patient examinations were exported from the clinical information system. The moving median was compared to predefined tolerance ranges, which revealed an overall of 50 potential quality relevant changes ("alerts") in SV, EDV and LVM. Potential causes such as change of staff, scanner relocation and software changes were found not to be causal of the alerts. No other influencing factors were identified retrospectively. Statistical quality assurance systems based on moving average control charts may provide an important step towards reliability of quantitative CMR. A prospective evaluation is needed for the effective root cause analysis of quality relevant alerts.

An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar

BACKGROUND AND OBJECTIVES

Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent.

METHODS

DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality.

RESULTS

The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction.

CONCLUSIONS

Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.

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.

A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR

Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. Therefore, whilst sharing a high spatial overlap with the ground truth, inferred CNN-based segmentations can lack coherence, including spurious connected components, holes and voids. Such results are implausible, violating anticipated anatomical topology. In response, (single-class) persistent homology-based loss functions have been proposed to capture global anatomical features. Our work extends these approaches to the task of multi-class segmentation. Building an enriched topological description of all class labels and class label pairs, our loss functions make predictable and statistically significant improvements in segmentation topology using a CNN-based post-processing framework. We also present (and make available) a highly efficient implementation based on cubical complexes and parallel execution, enabling practical application within high resolution 3D data for the first time. We demonstrate our approach on 2D short axis and 3D whole heart CMR segmentation, advancing a detailed and faithful analysis of performance on two publicly available datasets.

Aortic Distensibility Measured by Automated Analysis of Magnetic Resonance Imaging Predicts Adverse Cardiovascular Events in UK Biobank

Background Automated analysis of cardiovascular magnetic resonance images provides the potential to assess aortic distensibility in large populations. The aim of this study was to compare the prediction of cardiovascular events by automated cardiovascular magnetic resonance with those of other simple measures of aortic stiffness suitable for population screening. Methods and Results Aortic distensibility was measured from automated segmentation of aortic cine cardiovascular magnetic resonance using artificial intelligence in 8435 participants. The associations of distensibility, brachial pulse pressure, and stiffness index (obtained by finger photoplethysmography) with conventional risk factors was examined by multivariable regression and incident cardiovascular events by Cox proportional-hazards regression. Mean (±SD) distensibility values for men and women were 1.77±1.15 and 2.10±1.45 (P<0.0001) 10-3 mm Hg-1, respectively. There was a good correlation between automatically and manually obtained systolic and diastolic aortic areas (r=0.980 and r=0.985, respectively). In regression analysis, distensibility associated with age, mean arterial pressure, heart rate, weight, and plasma glucose but not male sex, cholesterol or current smoking. During an average follow-up of 2.8±1.3 years, 86 participants experienced cardiovascular events 6 of whom died. Higher distensibility was associated with reduced risk of cardiovascular events (adjusted hazard ratio [HR], 0.61 per log unit of distensibility; P=0.016). There was no evidence of an association between pulse pressure (adjusted HR 1.00; P=0.715) or stiffness index (adjusted HR, 1.02; P=0.535) and risk of cardiovascular events. Conclusions Automated cardiovascular magnetic resonance-derived aortic distensibility may be incorporated into routine clinical imaging. It shows a similar association to cardiovascular risk factors as other measures of arterial stiffness and predicts new-onset cardiovascular events, making it a useful tool for the measurement of vascular aging and associated cardiovascular risk.

Prevalence and Disease Expression of Pathogenic and Likely Pathogenic Variants Associated With Inherited Cardiomyopathies in the General Population

BACKGROUND

Pathogenic and likely pathogenic variants associated with arrhythmogenic right ventricular cardiomyopathy (ARVC), dilated cardiomyopathy (DCM), and hypertrophic cardiomyopathy (HCM) are recommended to be reported as secondary findings in genome sequencing studies. This provides opportunities for early diagnosis, but also fuels uncertainty in variant carriers (G+), since disease penetrance is incomplete. We assessed the prevalence and disease expression of G+ in the general population.

METHODS

We identified pathogenic and likely pathogenic variants associated with ARVC, DCM and/or HCM in 200 643 UK Biobank individuals, who underwent whole exome sequencing. We calculated the prevalence of G+ and analyzed the frequency of cardiomyopathy/heart failure diagnosis. In undiagnosed individuals, we analyzed early signs of disease expression using available electrocardiography and cardiac magnetic resonance imaging data.

RESULTS

We found a prevalence of 1:578, 1:251, and 1:149 for pathogenic and likely pathogenic variants associated with ARVC, DCM and HCM respectively. Compared with controls, cardiovascular mortality was higher in DCM G+ (odds ratio 1.67 [95% CI 1.04; 2.59], P=0.030), but similar in ARVC and HCM G+ (P≥0.100). Cardiomyopathy or heart failure diagnosis were more frequent in DCM G+ (odds ratio 3.66 [95% CI 2.24; 5.81], P=4.9×10^-7) and HCM G+ (odds ratio 3.03 [95% CI 1.98; 4.56], P=5.8×10^-7), but comparable in ARVC G+ (P=0.172). In contrast, ARVC G+ had more ventricular arrhythmias (P=3.3×10^-4). In undiagnosed individuals, left ventricular ejection fraction was reduced in DCM G+ (P=0.009).

CONCLUSIONS

In the general population, pathogenic and likely pathogenic variants associated with ARVC, DCM, or HCM are not uncommon. Although G+ have increased mortality and morbidity, disease penetrance in these carriers from the general population remains low (1.2-3.1%). Follow-up decisions in case of incidental findings should not be based solely on a variant, but on multiple factors, including family history and disease expression.

Beyond Simpson's Rule: Accounting for Orientation and Ellipticity Assumptions

Simpson's biplane rule (SBR) is considered the gold standard method for left ventricle (LV) volume quantification from echocardiography but relies on a summation-of-disks approach that makes assumptions about LV orientation and cross-sectional shape. We aim to identify key limiting factors in SBR and to develop a new robust standard for volume quantification. Three methods for computing LV volume were studied: (i) SBR, (ii) addition of a truncated basal cone (TBC) to SBR and (iii) a novel method of basal-oriented disks (BODs). Three retrospective cohorts representative of the young, adult healthy and heart failure populations were used to study the impact of anatomical variations in volume computations. Results reveal how basal slanting can cause over- and underestimation of volume, with errors by SBR and TBC >10 mL for slanting angles >6°. Only the BOD method correctly accounted for basal slanting, reducing relative volume errors by SBR from -2.23 ± 2.21% to -0.70 ± 1.91% in the adult population and similar qualitative performance in the other two cohorts. In conclusion, the summation of basal oriented disks, a novel interpretation of SBR, is a more accurate and precise method for estimating LV volume.

'The Digital Cardiologist': How Technology Is Changing the Paradigm of Cardiology Training

In the same way that the practice of cardiology has evolved over the years, so too has the way cardiology fellows in training (FITs) are trained. Propelled by recent advances in technology-catalyzed by COVID-19-and the requirement to adapt age-old methods of both teaching and health care delivery, many aspects, or 'domains', of learning have changed. These include the environments in which FITs work (outpatient clinics, 'on-call' inpatient service) and procedures in which they need clinical competency. Further advances in virtual reality are also changing the way FITs learn and interact. The proliferation of technology into the cardiology curriculum has led to some describing the need for FITs to develop into 'digital cardiologists', namely those who comfortably use digital tools to aid clinical practice, teaching, and training whilst, at the same time, retain the ability for human analysis and nuanced assessment so important to patient-centred training and clinical care.

Optimized automated cardiac MR scar quantification with GAN-based data augmentation

BACKGROUND

The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification.

METHODS

A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN.

RESULTS

The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively.

CONCLUSION

A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.

Artificial intelligence in cardiac magnetic resonance fingerprinting

Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T₁ and T₂ mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.

Artificial intelligence fully automated myocardial strain quantification for risk stratification following acute myocardial infarction

Feasibility of automated volume-derived cardiac functional evaluation has successfully been demonstrated using cardiovascular magnetic resonance (CMR) imaging. Notwithstanding, strain assessment has proven incremental value for cardiovascular risk stratification. Since introduction of deformation imaging to clinical practice has been complicated by time-consuming post-processing, we sought to investigate automation respectively. CMR data (n = 1095 patients) from two prospectively recruited acute myocardial infarction (AMI) populations with ST-elevation (STEMI) (AIDA STEMI n = 759) and non-STEMI (TATORT-NSTEMI n = 336) were analysed fully automated and manually on conventional cine sequences. LV function assessment included global longitudinal, circumferential, and radial strains (GLS/GCS/GRS). Agreements were assessed between automated and manual strain assessments. The former were assessed for major adverse cardiac event (MACE) prediction within 12 months following AMI. Manually and automated derived GLS showed the best and excellent agreement with an intraclass correlation coefficient (ICC) of 0.81. Agreement was good for GCS and poor for GRS. Amongst automated analyses, GLS (HR 1.12, 95% CI 1.08-1.16, p < 0.001) and GCS (HR 1.07, 95% CI 1.05-1.10, p < 0.001) best predicted MACE with similar diagnostic accuracy compared to manual analyses; area under the curve (AUC) for GLS (auto 0.691 vs. manual 0.693, p = 0.801) and GCS (auto 0.668 vs. manual 0.686, p = 0.425). Amongst automated functional analyses, GLS was the only independent predictor of MACE in multivariate analyses (HR 1.10, 95% CI 1.04-1.15, p < 0.001). Considering high agreement of automated GLS and equally high accuracy for risk prediction compared to the reference standard of manual analyses, automation may improve efficiency and aid in clinical routine implementation.Trial registration: ClinicalTrials.gov, NCT00712101 and NCT01612312.

Cardiac MRI segmentation with sparse annotations: Ensembling deep learning uncertainty and shape priors

The performance of deep learning for cardiac magnetic resonance imaging (MRI) segmentation is oftentimes degraded when using small datasets and sparse annotations for training or adapting a pre-trained model to previously unseen datasets. Here, we developed and evaluated an approach to addressing some of these issues to facilitate broader use of deep learning for short-axis cardiac MRI segmentation. We developed a globally optimal label fusion (GOLF) algorithm that enforced spatial smoothness to generate consensus segmentation from segmentation predictions provided by a deep learning ensemble algorithm. The GOLF consensus was entered into an uncertainty-guided coupled continuous kernel cut (ugCCKC) algorithm that employed normalized cut, image-grid continuous regularization, and "nesting" and circular shape priors of the left ventricular myocardium (LVM) and cavity (LVC). In addition, the uncertainty measurements derived from the segmentation predictions were used to constrain the similarity of GOLF and final segmentation. We optimized ugCCKC through upper bound relaxation, for which we developed an efficient coupled continuous max-flow algorithm implemented in an iterative manner. We showed that GOLF yielded average symmetric surface distance (ASSD) 0.2-0.8 mm lower than an averaging method with higher or similar Dice similarity coefficient (DSC). We also demonstrated that ugCCKC incorporating the shape priors improved DSC by 0.01-0.05 and reduced ASSD by 0.1-0.9 mm. In addition, we integrated GOLF and ugCCKC into a deep learning ensemble algorithm by refining the segmentation of an unannotated dataset and using the refined segmentation to update the trained models. With the proposed framework, we demonstrated the capability of using relatively small datasets (5-10 subjects) with sparse (5-25% slices labeled) annotations to train a deep learning algorithm, while achieving DSC of 0.871-0.893 for LVM and 0.933-0.959 for LVC on the LVQuan dataset, and these were 0.844-0.871 for LVM and 0.923-0.931 for LVC on the ACDC dataset. Furthermore, we showed that the proposed approach can be adapted to substantially alleviate the domain shift issue. Moreover, we calculated a number of commonly used LV function measurements using the derived segmentation and observed strong correlations (Pearson r=0.77-1.00, p<0.001) between algorithm and manual LV function analyses. These results suggest that the developed approaches can be used to facilitate broader application of deep learning in research and clinical cardiac MR imaging workflow.

Applications of Machine Learning in Cardiology

In this digital era, artificial intelligence (AI) is establishing a strong foothold in commercial industry and the field of technology. These effects are trickling into the healthcare industry, especially in the clinical arena of cardiology. Machine learning (ML) algorithms are making substantial progress in various subspecialties of cardiology. This will have a positive impact on patient care and move the field towards precision medicine. In this review article, we explore the progress of ML in cardiovascular imaging, electrophysiology, heart failure, and interventional cardiology.

Towards fully automated segmentation of rat cardiac MRI by leveraging deep learning frameworks

Automated segmentation of human cardiac magnetic resonance datasets has been steadily improving during recent years. Similar applications would be highly useful to improve and speed up the studies of cardiac function in rodents in the preclinical context. However, the transfer of such segmentation methods to the preclinical research is compounded by the limited number of datasets and lower image resolution. In this paper we present a successful application of deep architectures 3D cardiac segmentation for rats in preclinical contexts which to our knowledge has not yet been reported. We developed segmentation models that expand on the standard U-Net architecture and evaluated models separately trained for systole and diastole phases (2MSA) and a single model trained for all phases (1MSA). Furthermore, we calibrated model outputs using a Gaussian process (GP)-based prior to improve phase selection. The resulting models approach human performance in terms of left ventricular segmentation quality and ejection fraction (EF) estimation in both 1MSA and 2MSA settings (Sørensen-Dice score 0.91 ± 0.072 and 0.93 ± 0.032, respectively). 2MSA achieved a mean absolute difference between estimated and reference EF of 3.5 ± 2.5%, while 1MSA resulted in 4.1 ± 3.0%. Applying GPs to 1MSA enabled automating systole and diastole phase selection. Both segmentation approaches (1MSA and 2MSA) were statistically equivalent. Combined with a proposed cardiac phase selection strategy, our work presents an important first step towards a fully automated segmentation pipeline in the context of rat cardiac analysis.

Application of machine learning in screening for congenital heart diseases using fetal echocardiography

There is a growing body of literature supporting the utilization of machine learning (ML) to improve diagnosis and prognosis tools of cardiovascular disease. The current study was to investigate the impact that the ML framework may have on the sensitivity of predicting the presence or absence of congenital heart disease (CHD) using fetal echocardiography. A comprehensive fetal echocardiogram including 2D cardiac chamber quantification, valvar assessments, assessment of great vessel morphology, and Doppler-derived blood flow interrogation was recorded. The postnatal echocardiogram was used to ascertain the diagnosis of CHD. A random forest (RF) algorithm with a nested tenfold cross-validation was used to train models for assessing the presence of CHD. The study population was derived from a database of 3910 singleton fetuses with maternal age of 28.8 ± 5.2 years and gestational age at the time of fetal echocardiography of 22.0 weeks (IQR 21-24). The proportion of CHD was 14.1% for the studied cohort confirmed by post-natal echocardiograms. Our proposed RF-based framework provided a sensitivity of 0.85, a specificity of 0.88, a positive predictive value of 0.55 and a negative predictive value of 0.97 to detect the CHD with the mean of mean ROC curves of 0.94 and the mean of mean PR curves of 0.84. Additionally, six first features, including cardiac axis, peak velocity of blood flow across the pulmonic valve, cardiothoracic ratio, pulmonary valvar annulus diameter, right ventricular end-diastolic diameter, and aortic valvar annulus diameter, are essential features that play crucial roles in adding more predictive values to the model in detecting patients with CHD. ML using RF can provide increased sensitivity in prenatal CHD screening with very good performance. The incorporation of ML algorithms into fetal echocardiography may further standardize the assessment for CHD.

From Accuracy to Reliability and Robustness in Cardiac Magnetic Resonance Image Segmentation: A Review

Since the rise of deep learning (DL) in the mid-2010s, cardiac magnetic resonance (CMR) image segmentation has achieved state-of-the-art performance. Despite achieving inter-observer variability in terms of different accuracy performance measures, visual inspections reveal errors in most segmentation results, indicating a lack of reliability and robustness of DL segmentation models, which can be critical if a model was to be deployed into clinical practice. In this work, we aim to bring attention to reliability and robustness, two unmet needs of cardiac image segmentation methods, which are hampering their translation into practice. To this end, we first study the performance accuracy evolution of CMR segmentation, illustrate the improvements brought by DL algorithms and highlight the symptoms of performance stagnation. Afterwards, we provide formal definitions of reliability and robustness. Based on the two definitions, we identify the factors that limit the reliability and robustness of state-of-the-art deep learning CMR segmentation techniques. Finally, we give an overview of the current set of works that focus on improving the reliability and robustness of CMR segmentation, and we categorize them into two families of methods: quality control methods and model improvement techniques. The first category corresponds to simpler strategies that only aim to flag situations where a model may be incurring poor reliability or robustness. The second one, instead, directly tackles the problem by bringing improvements into different aspects of the CMR segmentation model development process. We aim to bring the attention of more researchers towards these emerging trends regarding the development of reliable and robust CMR segmentation frameworks, which can guarantee the safe use of DL in clinical routines and studies.

Training and clinical testing of artificial intelligence derived right atrial cardiovascular magnetic resonance measurements

BACKGROUND

Right atrial (RA) area predicts mortality in patients with pulmonary hypertension, and is recommended by the European Society of Cardiology/European Respiratory Society pulmonary hypertension guidelines. The advent of deep learning may allow more reliable measurement of RA areas to improve clinical assessments. The aim of this study was to automate cardiovascular magnetic resonance (CMR) RA area measurements and evaluate the clinical utility by assessing repeatability, correlation with invasive haemodynamics and prognostic value.

METHODS

A deep learning RA area CMR contouring model was trained in a multicentre cohort of 365 patients with pulmonary hypertension, left ventricular pathology and healthy subjects. Inter-study repeatability (intraclass correlation coefficient (ICC)) and agreement of contours (DICE similarity coefficient (DSC)) were assessed in a prospective cohort (n = 36). Clinical testing and mortality prediction was performed in n = 400 patients that were not used in the training nor prospective cohort, and the correlation of automatic and manual RA measurements with invasive haemodynamics assessed in n = 212/400. Radiologist quality control (QC) was performed in the ASPIRE registry, n = 3795 patients. The primary QC observer evaluated all the segmentations and recorded them as satisfactory, suboptimal or failure. A second QC observer analysed a random subcohort to assess QC agreement (n = 1018).

RESULTS

All deep learning RA measurements showed higher interstudy repeatability (ICC 0.91 to 0.95) compared to manual RA measurements (1st observer ICC 0.82 to 0.88, 2nd observer ICC 0.88 to 0.91). DSC showed high agreement comparing automatic artificial intelligence and manual CMR readers. Maximal RA area mean and standard deviation (SD) DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 is 92.4 ± 3.5 cm2, 91.2 ± 4.5 cm2 and 93.2 ± 3.2 cm2, respectively. Minimal RA area mean and SD DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 was 89.8 ± 3.9 cm2, 87.0 ± 5.8 cm2 and 91.8 ± 4.8 cm2. Automatic RA area measurements all showed moderate correlation with invasive parameters (r = 0.45 to 0.66), manual (r = 0.36 to 0.57). Maximal RA area could accurately predict elevated mean RA pressure low and high-risk thresholds (area under the receiver operating characteristic curve artificial intelligence = 0.82/0.87 vs manual = 0.78/0.83), and predicted mortality similar to manual measurements, both p < 0.01. In the QC evaluation, artificial intelligence segmentations were suboptimal at 108/3795 and a low failure rate of 16/3795. In a subcohort (n = 1018), agreement by two QC observers was excellent, kappa 0.84.

CONCLUSION

Automatic artificial intelligence CMR derived RA size and function are accurate, have excellent repeatability, moderate associations with invasive haemodynamics and predict mortality.

Fairness in Cardiac Magnetic Resonance Imaging: Assessing Sex and Racial Bias in Deep Learning-Based Segmentation

Background

Artificial intelligence (AI) techniques have been proposed for automation of cine CMR segmentation for functional quantification. However, in other applications AI models have been shown to have potential for sex and/or racial bias. The objective of this paper is to perform the first analysis of sex/racial bias in AI-based cine CMR segmentation using a large-scale database.

Methods

A state-of-the-art deep learning (DL) model was used for automatic segmentation of both ventricles and the myocardium from cine short-axis CMR. The dataset consisted of end-diastole and end-systole short-axis cine CMR images of 5,903 subjects from the UK Biobank database (61.5 ± 7.1 years, 52% male, 81% white). To assess sex and racial bias, we compared Dice scores and errors in measurements of biventricular volumes and function between patients grouped by race and sex. To investigate whether segmentation bias could be explained by potential confounders, a multivariate linear regression and ANCOVA were performed.

Results

Results on the overall population showed an excellent agreement between the manual and automatic segmentations. We found statistically significant differences in Dice scores between races (white ∼94% vs. minority ethnic groups 86-89%) as well as in absolute/relative errors in volumetric and functional measures, showing that the AI model was biased against minority racial groups, even after correction for possible confounders. The results of a multivariate linear regression analysis showed that no covariate could explain the Dice score bias between racial groups. However, for the Mixed and Black race groups, sex showed a weak positive association with the Dice score. The results of an ANCOVA analysis showed that race was the main factor that can explain the overall difference in Dice scores between racial groups.

Conclusion

We have shown that racial bias can exist in DL-based cine CMR segmentation models when training with a database that is sex-balanced but not race-balanced such as the UK Biobank.

Cardiac MR: From Theory to Practice

Cardiovascular disease (CVD) is the leading single cause of morbidity and mortality, causing over 17. 9 million deaths worldwide per year with associated costs of over $800 billion. Improving prevention, diagnosis, and treatment of CVD is therefore a global priority. Cardiovascular magnetic resonance (CMR) has emerged as a clinically important technique for the assessment of cardiovascular anatomy, function, perfusion, and viability. However, diversity and complexity of imaging, reconstruction and analysis methods pose some limitations to the widespread use of CMR. Especially in view of recent developments in the field of machine learning that provide novel solutions to address existing problems, it is necessary to bridge the gap between the clinical and scientific communities. This review covers five essential aspects of CMR to provide a comprehensive overview ranging from CVDs to CMR pulse sequence design, acquisition protocols, motion handling, image reconstruction and quantitative analysis of the obtained data. (1) The basic MR physics of CMR is introduced. Basic pulse sequence building blocks that are commonly used in CMR imaging are presented. Sequences containing these building blocks are formed for parametric mapping and functional imaging techniques. Commonly perceived artifacts and potential countermeasures are discussed for these methods. (2) CMR methods for identifying CVDs are illustrated. Basic anatomy and functional processes are described to understand the cardiac pathologies and how they can be captured by CMR imaging. (3) The planning and conduct of a complete CMR exam which is targeted for the respective pathology is shown. Building blocks are illustrated to create an efficient and patient-centered workflow. Further strategies to cope with challenging patients are discussed. (4) Imaging acceleration and reconstruction techniques are presented that enable acquisition of spatial, temporal, and parametric dynamics of the cardiac cycle. The handling of respiratory and cardiac motion strategies as well as their integration into the reconstruction processes is showcased. (5) Recent advances on deep learning-based reconstructions for this purpose are summarized. Furthermore, an overview of novel deep learning image segmentation and analysis methods is provided with a focus on automatic, fast and reliable extraction of biomarkers and parameters of clinical relevance.

Artificial Intelligence to Improve Risk Prediction with Nuclear Cardiac Studies

Purpose of Review

As machine learning-based artificial intelligence (AI) continues to revolutionize the way in which we analyze data, the field of nuclear cardiology provides fertile ground for the implementation of these complex analytics. This review summarizes and discusses the principles regarding nuclear cardiology techniques and AI, and the current evidence regarding its performance and contribution to the improvement of risk prediction in cardiovascular disease.

Recent Findings and Summary

There is a growing body of evidence on the experimentation with and implementation of machine learning-based AI on nuclear cardiology studies both concerning SPECT and PET technology for the improvement of risk-of-disease (classification of disease) and risk-of-events (prediction of adverse events) estimations. These publications still report objective divergence in methods either utilizing statistical machine learning approaches or deep learning with varying architectures, dataset sizes, and performance. Recent efforts have been placed into bringing standardization and quality to the experimentation and application of machine learning-based AI in cardiovascular imaging to generate standards in data harmonization and analysis through AI. Machine learning-based AI offers the possibility to improve risk evaluation in cardiovascular disease through its implementation on cardiac nuclear studies.

Graphical Abstract

AI in improving risk evaluation in nuclear cardiology. * Based on the 2019 ESC guidelines

Assessment of Bi-Ventricular and Bi-Atrial Areas Using Four-Chamber Cine Cardiovascular Magnetic Resonance Imaging: Fully Automated Segmentation with a U-Net Convolutional Neural Network

Four-chamber (4CH) cine cardiovascular magnetic resonance imaging (CMR) facilitates simultaneous evaluation of cardiac chambers; however, manual segmentation is time-consuming and subjective in practice. We evaluated deep learning based on a U-Net convolutional neural network (CNN) for fully automated segmentation of the four cardiac chambers using 4CH cine CMR. Cine CMR datasets from patients were randomly assigned for training (1400 images from 70 patients), validation (600 images from 30 patients), and testing (1000 images from 50 patients). We validated manual and automated segmentation based on the U-Net CNN using the dice similarity coefficient (DSC) and Spearman’s rank correlation coefficient (ρ); p < 0.05 was statistically significant. The overall median DSC showed high similarity (0.89). Automated segmentation correlated strongly with manual segmentation in all chambers—the left and right ventricles, and the left and right atria (end-diastolic area: ρ = 0.88, 0.76, 0.92, and 0.87; end-systolic area: ρ = 0.81, 0.81, 0.92, and 0.83, respectively; p < 0.01). The area under the curve for the left ventricle, left atrium, right ventricle, and right atrium showed high scores (0.96, 0.99, 0.88, and 0.96, respectively). Fully automated segmentation could facilitate simultaneous evaluation and detection of enlargement of the four cardiac chambers without any time-consuming analysis.

Artificial Intelligence in Cardiac MRI: Is Clinical Adoption Forthcoming?

Artificial intelligence (AI) refers to the area of knowledge that develops computerised models to perform tasks that typically require human intelligence. These algorithms are programmed to learn and identify patterns from "training data," that can be subsequently applied to new datasets, without being explicitly programmed to do so. AI is revolutionising the field of medical imaging and in particular of Cardiovascular Magnetic Resonance (CMR) by providing deep learning solutions for image acquisition, reconstruction and analysis, ultimately supporting the clinical decision making. Numerous methods have been developed over recent years to enhance and expedite CMR data acquisition, image reconstruction, post-processing and analysis; along with the development of promising AI-based biomarkers for a wide spectrum of cardiac conditions. The exponential rise in the availability and complexity of CMR data has fostered the development of different AI models. Integration in clinical routine in a meaningful way remains a challenge. Currently, innovations in this field are still mostly presented in proof-of-concept studies with emphasis on the engineering solutions; often recruiting small patient cohorts or relying on standardised databases such as Multi-ethnic Study on atherosclerosis (MESA), UK Biobank and others. The wider incorporation of clinically valid endpoints such as symptoms, survival, need and response to treatment remains to be seen. This review briefly summarises the current principles of AI employed in CMR and explores the relevant prospective observational studies in cardiology patient cohorts. It provides an overview of clinical studies employing undersampled reconstruction techniques to speed up the scan encompassing cine imaging, whole-heart imaging, multi-parametric mapping and magnetic resonance fingerprinting along with the clinical utility of AI applications in image post-processing, and analysis. Specific focus is given to studies that have incorporated CMR-derived prediction models for prognostication in cardiac disease. It also discusses current limitations and proposes potential developments to enable multi-disciplinary collaboration for improved evidence-based medicine. AI is an extremely promising field and the timely integration of clinician's input in the ingenious technical investigator's paradigm holds promise for a bright future in the medical field.

The role of artificial intelligence in paediatric cardiovascular magnetic resonance imaging

Artificial intelligence (AI) offers the potential to change many aspects of paediatric cardiac imaging. At present, there are only a few clinically validated examples of AI applications in this field. This review focuses on the use of AI in paediatric cardiovascular MRI, using examples from paediatric cardiovascular MRI, adult cardiovascular MRI and other radiologic experience.

The Role of AI in Characterizing the DCM Phenotype

Dilated Cardiomyopathy is conventionally defined by left ventricular dilatation and dysfunction in the absence of coronary disease. Emerging evidence suggests many patients remain vulnerable to major adverse outcomes despite clear therapeutic success of modern evidence-based heart failure therapy. In this era of personalized medical care, the conventional assessment of left ventricular ejection fraction falls short in fully predicting evolution and risk of outcomes in this heterogenous group of heart muscle disease, as such, a more refined means of phenotyping this disease appears essential. Cardiac MRI (CMR) is well-placed in this respect, not only for its diagnostic utility, but the wealth of information captured in global and regional function assessment with the addition of unique tissue characterization across different disease states and patient cohorts. Advanced tools are needed to leverage these sensitive metrics and integrate with clinical, genetic and biochemical information for personalized, and more clinically useful characterization of the dilated cardiomyopathy phenotype. Recent advances in artificial intelligence offers the unique opportunity to impact clinical decision making through enhanced precision image-analysis tasks, multi-source extraction of relevant features and seamless integration to enhance understanding, improve diagnosis, and subsequently clinical outcomes. Focusing particularly on deep learning, a subfield of artificial intelligence, that has garnered significant interest in the imaging community, this paper reviews the main developments that could offer more robust disease characterization and risk stratification in the Dilated Cardiomyopathy phenotype. Given its promising utility in the non-invasive assessment of cardiac diseases, we firstly highlight the key applications in CMR, set to enable comprehensive quantitative measures of function beyond the standard of care assessment. Concurrently, we revisit the added value of tissue characterization techniques for risk stratification, showcasing the deep learning platforms that overcome limitations in current clinical workflows and discuss how they could be utilized to better differentiate at-risk subgroups of this phenotype. The final section of this paper is dedicated to the allied clinical applications to imaging, that incorporate artificial intelligence and have harnessed the comprehensive abundance of data from genetics and relevant clinical variables to facilitate better classification and enable enhanced risk prediction for relevant outcomes.

Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review

The risk of coronary heart disease (CHD) clinical manifestations and patient management is estimated according to risk scores accounting multifactorial risk factors, thus failing to cover the individual cardiovascular risk. Technological improvements in the field of medical imaging, in particular, in cardiac computed tomography angiography and cardiac magnetic resonance protocols, laid the development of radiogenomics. Radiogenomics aims to integrate a huge number of imaging features and molecular profiles to identify optimal radiomic/biomarker signatures. In addition, supervised and unsupervised artificial intelligence algorithms have the potential to combine different layers of data (imaging parameters and features, clinical variables and biomarkers) and elaborate complex and specific CHD risk models allowing more accurate diagnosis and reliable prognosis prediction. Literature from the past 5 years was systematically collected from PubMed and Scopus databases, and 60 studies were selected. We speculated the applicability of radiogenomics and artificial intelligence through the application of machine learning algorithms to identify CHD and characterize atherosclerotic lesions and myocardial abnormalities. Radiomic features extracted by cardiac computed tomography angiography and cardiac magnetic resonance showed good diagnostic accuracy for the identification of coronary plaques and myocardium structure; on the other hand, few studies exploited radiogenomics integration, thus suggesting further research efforts in this field. Cardiac computed tomography angiography resulted the most used noninvasive imaging modality for artificial intelligence applications. Several studies provided high performance for CHD diagnosis, classification, and prognostic assessment even though several efforts are still needed to validate and standardize algorithms for CHD patient routine according to good medical practice.