Multi-Ethnic Study of Atherosclerosis: Relationship between Left Ventricular Shape at Cardiac MRI and 10-year Outcomes.

Background Left ventricular (LV) subclinical remodeling is associated with adverse outcomes and indicates mechanisms of disease development. Standard metrics such as LV mass and volumes may not capture the full range of remodeling. Purpose To quantify the relationship between LV three-dimensional shape at MRI and incident cardiovascular events over 10 years. Materials and Methods In this retrospective study, 5098 participants from the Multi-Ethnic Study of Atherosclerosis who were free of clinical cardiovascular disease underwent cardiac MRI from 2000 to 2002. LV shape models were automatically generated using a machine learning workflow. Event-specific remodeling signatures were computed using partial least squares regression, and random survival forests were used to determine which features were most associated with incident heart failure (HF), coronary heart disease (CHD), and cardiovascular disease (CVD) events over a 10-year follow-up period. The discrimination improvement of adding LV shape to traditional cardiovascular risk factors, coronary artery calcium scores, and N-terminal pro-brain natriuretic peptide levels was assessed using the index of prediction accuracy and time-dependent area under the receiver operating characteristic curve (AUC). Kaplan-Meier survival curves were used to illustrate the ability of remodeling signatures to predict the end points. Results Overall, 4618 participants had sufficient three-dimensional MRI information to generate patient-specific LV models (mean age, 60.6 years ± 9.9 [SD]; 2540 women). Among these participants, 147 had HF, 317 had CHD, and 455 had CVD events. The addition of LV remodeling signatures to traditional cardiovascular risk factors improved the mean AUC for 10-year survival prediction and achieved better performance than LV mass and volumes; HF (AUC, 0.83 ± 0.01 and 0.81 ± 0.01, respectively; P < .05), CHD (AUC, 0.77 ± 0.01 and 0.75 ± 0.01, respectively; P < .05), and CVD (AUC, 0.78 ± 0.0 and 0.76 ± 0.0, respectively; P < .05). Kaplan-Meier analysis demonstrated that participants with high-risk HF remodeling signatures had a 10-year survival rate of 56% compared with 95% for those with low-risk scores. Conclusion Left ventricular event-specific remodeling signatures were more predictive of heart failure, coronary heart disease, and cardiovascular disease events over 10 years than standard mass and volume measures and enable an automatic personalized medicine approach to tracking remodeling. © RSNA, 2022 Online supplemental material is available for this article.

Emerging Techniques in Cardiac Magnetic Resonance Imaging.

Cardiovascular disease is the leading cause of death and a significant contributor of health care costs. Noninvasive imaging plays an essential role in the management of patients with cardiovascular disease. Cardiac magnetic resonance (MR) can noninvasively assess heart and vascular abnormalities, including biventricular structure/function, blood hemodynamics, myocardial tissue composition, microstructure, perfusion, metabolism, coronary microvascular function, and aortic distensibility/stiffness. Its ability to characterize myocardial tissue composition is unique among alternative imaging modalities in cardiovascular disease. Significant growth in cardiac MR utilization, particularly in Europe in the last decade, has laid the necessary clinical groundwork to position cardiac MR as an important imaging modality in the workup of patients with cardiovascular disease. Although lack of availability, limited training, physician hesitation, and reimbursement issues have hampered widespread clinical adoption of cardiac MR in the United States, growing clinical evidence will ultimately overcome these challenges. Advances in cardiac MR techniques, particularly faster image acquisition, quantitative myocardial tissue characterization, and image analysis have been critical to its growth. In this review article, we discuss recent advances in established and emerging cardiac MR techniques that are expected to strengthen its capability in managing patients with cardiovascular disease. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Right-left ventricular shape variations in tetralogy of Fallot: associations with pulmonary regurgitation.

BACKGROUND: Relationships between right ventricular (RV) and left ventricular (LV) shape and function may be useful in determining optimal timing for pulmonary valve replacement in patients with repaired tetralogy of Fallot (rTOF). However, these are multivariate and difficult to quantify. We aimed to quantify variations in biventricular shape associated with pulmonary regurgitant volume (PRV) in rTOF using a biventricular atlas. METHODS: In this cross-sectional retrospective study, a biventricular shape model was customized to cardiovascular magnetic resonance (CMR) images from 88 rTOF patients (median age 16, inter-quartile range 11.8-24.3 years). Morphometric scores quantifying biventricular shape at end-diastole and end-systole were computed using principal component analysis. Multivariate linear regression was used to quantify biventricular shape associations with PRV, corrected for age, sex, height, and weight. Regional associations were confirmed by univariate correlations with distances and angles computed from the models, as well as global systolic strains computed from changes in arc length from end-diastole to end-systole. RESULTS: PRV was significantly associated with 5 biventricular morphometric scores, independent of covariates, and accounted for 12.3% of total shape variation (p < 0.05). Increasing PRV was associated with RV dilation and basal bulging, in conjunction with decreased LV septal-lateral dimension (LV flattening) and systolic septal motion towards the RV (all p < 0.05). Increased global RV radial, longitudinal, circumferential and LV radial systolic strains were significantly associated with increased PRV (all p < 0.05). CONCLUSION: A biventricular atlas of rTOF patients quantified multivariate relationships between left-right ventricular morphometry and wall motion with pulmonary regurgitation. Regional RV dilation, LV reduction, LV septal-lateral flattening and increased RV strain were all associated with increased pulmonary regurgitant volume. Morphometric scores provide simple metrics linking mechanisms for structural and functional alteration with important clinical indices.

Machine learning in cardiovascular magnetic resonance: basic concepts and applications.

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

Right ventricular shape and function: cardiovascular magnetic resonance reference morphology and biventricular risk factor morphometrics in UK Biobank.

BACKGROUND: The associations between cardiovascular disease (CVD) risk factors and the biventricular geometry of the right ventricle (RV) and left ventricle (LV) have been difficult to assess, due to subtle and complex shape changes. We sought to quantify reference RV morphology as well as biventricular variations associated with common cardiovascular risk factors. METHODS: A biventricular shape atlas was automatically constructed using contours and landmarks from 4329 UK Biobank cardiovascular magnetic resonance (CMR) studies. A subdivision surface geometric mesh was customized to the contours using a diffeomorphic registration algorithm, with automatic correction of slice shifts due to differences in breath-hold position. A reference sub-cohort was identified consisting of 630 participants with no CVD risk factors. Morphometric scores were computed using linear regression to quantify shape variations associated with four risk factors (high cholesterol, high blood pressure, obesity and smoking) and three disease factors (diabetes, previous myocardial infarction and angina). RESULTS: The atlas construction led to an accurate representation of 3D shapes at end-diastole and end-systole, with acceptable fitting errors between surfaces and contours (average error less than 1.5 mm). Atlas shape features had stronger associations than traditional mass and volume measures for all factors (p < 0.005 for each). High blood pressure was associated with outward displacement of the LV free walls, but inward displacement of the RV free wall and thickening of the septum. Smoking was associated with a rounder RV with inward displacement of the RV free wall and increased relative wall thickness. CONCLUSION: Morphometric relationships between biventricular shape and cardiovascular risk factors in a large cohort show complex interactions between RV and LV morphology. These can be quantified by z-scores, which can be used to study the morphological correlates of disease.

Atlas-Based Ventricular Shape Analysis for Understanding Congenital Heart Disease.

Congenital heart disease is associated with abnormal ventricular shape that can affect wall mechanics and may be predictive of long-term adverse outcomes. Atlas-based parametric shape analysis was used to analyze ventricular geometries of eight adolescent or adult single-ventricle CHD patients with tricuspid atresia and Fontans. These patients were compared with an "atlas" of non-congenital asymptomatic volunteers, resulting in a set of z-scores which quantify deviations from the control population distribution on a patient-by-patient basis. We examined the potential of these scores to: (1) quantify abnormalities of ventricular geometry in single ventricle physiologies relative to the normal population; (2) comprehensively quantify wall motion in CHD patients; and (3) identify possible relationships between ventricular shape and wall motion that may reflect underlying functional defects or remodeling in CHD patients. CHD ventricular geometries at end-diastole and end-systole were individually compared with statistical shape properties of an asymptomatic population from the Cardiac Atlas Project. Shape analysis-derived model properties, and myocardial wall motions between end-diastole and end-systole, were compared with physician observations of clinical functional parameters. Relationships between altered shape and altered function were evaluated via correlations between atlas-based shape and wall motion scores. Atlas-based shape analysis identified a diverse set of specific quantifiable abnormalities in ventricular geometry or myocardial wall motion in all subjects. Moreover, this initial cohort displayed significant relationships between specific shape abnormalities such as increased ventricular sphericity and functional defects in myocardial deformation, such as decreased long-axis wall motion. These findings suggest that atlas-based ventricular shape analysis may be a useful new tool in the management of patients with CHD who are at risk of impaired ventricular wall mechanics and chamber remodeling.

Information maximizing component analysis of left ventricular remodeling due to myocardial infarction.

BACKGROUND: Although adverse left ventricular shape changes (remodeling) after myocardial infarction (MI) are predictive of morbidity and mortality, current clinical assessment is limited to simple mass and volume measures, or dimension ratios such as length to width ratio. We hypothesized that information maximizing component analysis (IMCA), a supervised feature extraction method, can provide more efficient and sensitive indices of overall remodeling. METHODS: IMCA was compared to linear discriminant analysis (LDA), both supervised methods, to extract the most discriminatory global shape changes associated with remodeling after MI. Finite element shape models from 300 patients with myocardial infarction from the DETERMINE study (age 31-86, mean age 63, 20 % women) were compared with 1991 asymptomatic cases from the MESA study (age 44-84, mean age 62, 52 % women) available from the Cardiac Atlas Project. IMCA and LDA were each used to identify a single mode of global remodeling best discriminating the two groups. Logistic regression was employed to determine the association between the remodeling index and MI. Goodness-of-fit results were compared against a baseline logistic model comprising standard clinical indices. RESULTS: A single IMCA mode simultaneously describing end-diastolic and end-systolic shapes achieved best results (lowest Deviance, Akaike information criterion and Bayesian information criterion, and the largest area under the receiver-operating-characteristic curve). This mode provided a continuous scale where remodeling can be quantified and visualized, showing that MI patients tend to present larger size and more spherical shape, more bulging of the apex, and thinner wall thickness. CONCLUSIONS: IMCA enables better characterization of global remodeling than LDA, and can be used to quantify progression of disease and the effect of treatment. These data and results are available from the Cardiac Atlas Project ( http://www.cardiacatlas.org ).

Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours.

BACKGROUND: High reproducibility of LV mass and volume measurement from cine cardiovascular magnetic resonance (CMR) has been shown within single centers. However, the extent to which contours may vary from center to center, due to different training protocols, is unknown. We aimed to quantify sources of variation between many centers, and provide a multi-center consensus ground truth dataset for benchmarking automated processing tools and facilitating training for new readers in CMR analysis. METHODS: Seven independent expert readers, representing seven experienced CMR core laboratories, analyzed fifteen cine CMR data sets in accordance with their standard operating protocols and SCMR guidelines. Consensus contours were generated for each image according to a statistical optimization scheme that maximized contour placement agreement between readers. RESULTS: Reader-consensus agreement was better than inter-reader agreement (end-diastolic volume 14.7 ml vs 15.2-28.4 ml; end-systolic volume 13.2 ml vs 14.0-21.5 ml; LV mass 17.5 g vs 20.2-34.5 g; ejection fraction 4.2 % vs 4.6-7.5 %). Compared with consensus contours, readers were very consistent (small variability across cases within each reader), but bias varied between readers due to differences in contouring protocols at each center. Although larger contour differences were found at the apex and base, the main effect on volume was due to small but consistent differences in the position of the contours in all regions of the LV. CONCLUSIONS: A multi-center consensus dataset was established for the purposes of benchmarking and training. Achieving consensus on contour drawing protocol between centers before analysis, or bias correction after analysis, is required when collating multi-center results.

Challenges of cardiac image analysis in large-scale population-based studies.

Large-scale population-based imaging studies of preclinical and clinical heart disease are becoming possible due to the advent of standardized robust non-invasive imaging methods and infrastructure for big data analysis. This gives an exciting opportunity to gain new information about the development and progression of heart disease across population groups. However, the large amount of image data and prohibitive time required for image analysis present challenges for obtaining useful derived data from the images. Automated analysis tools for cardiac image analysis are only now becoming available. This paper reviews the challenges and possible solutions to the analysis of big imaging data in population studies. We also highlight the potential of recent large epidemiological studies using cardiac imaging to discover new knowledge on heart health and well-being.

Left ventricular shape variation in asymptomatic populations: the Multi-Ethnic Study of Atherosclerosis.

BACKGROUND: Although left ventricular cardiac geometric indices such as size and sphericity characterize adverse remodeling and have prognostic value in symptomatic patients, little is known of shape distributions in subclinical populations. We sought to quantify shape variation across a large number of asymptomatic volunteers, and examine differences among sub-cohorts. METHODS: An atlas was constructed comprising 1,991 cardiovascular magnetic resonance (CMR) cases contributed from the Multi-Ethnic Study of Atherosclerosis baseline examination. A mathematical model describing regional wall motion and shape was used to establish a coordinate map registered to the cardiac anatomy. The model was automatically customized to left ventricular contours and anatomical landmarks, corrected for breath-hold mis-registration between image slices. Mathematical techniques were used to characterize global shape distributions, after removal of translations, rotations, and scale due to height. Differences were quantified among ethnicity, sex, smoking, hypertension and diabetes sub-cohorts. RESULTS: The atlas construction process yielded accurate representations of global shape (errors between manual and automatic surface points in 244 validation cases were less than the image pixel size). After correction for height, the dominant shape component was associated with heart size, explaining 32% of the total shape variance at end-diastole and 29% at end-systole. After size, the second dominant shape component was sphericity at end-diastole (13%), and concentricity at end-systole (10%). The resulting shape components distinguished differences due to ethnicity and risk factors with greater statistical power than traditional mass and volume indices. CONCLUSIONS: We have quantified the dominant components of global shape variation in the adult asymptomatic population. The data and results are available at cardiacatlas.org. Shape distributions were principally explained by size, sphericity and concentricity, which are known correlates of adverse outcomes. Atlas-based global shape analysis provides a powerful method for quantifying left ventricular shape differences in asymptomatic populations. TRIAL REGISTRATION: ClinicalTrials.gov NCT00005487.

Atlas-based Anatomical Modeling and Analysis of Heart Disease.

Heart shape and function are major determinants of disease severity and predictors of future morbidity and mortality. Many studies now rely on non-invasive cardiac imaging techniques to quantify structural and functional changes. Statistical anatomical modeling of heart shape and motion provides a new tool for the quantification and evaluation of heart disease. This review surveys recent progress in the evaluation of statistical shape measures across populations and sub-cohorts, and highlights collaborative efforts to facilitate data sharing and atlas-based shape analysis.

Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

Evaluation of Deep Learning Estimation of Whole Heart Anatomy from Automated Cardiovascular Magnetic Resonance Short- and Long-Axis Analyses in UK Biobank.

AIMS: Standard methods of heart chamber volume estimation in cardiovascular magnetic resonance (CMR) typically utilize simple geometric formulae based on a limited number of slices. We aimed to evaluate whether an automated deep learning neural network prediction of 3D anatomy of all four chambers would show stronger associations with cardiovascular risk factors and disease than standard volume estimation methods in the UK Biobank. METHODS: A deep learning network was adapted to predict 3D segmentations of left and right ventricles (LV, RV) and atria (LA, RA) at ∼1mm isotropic resolution from CMR short and long axis 2D segmentations obtained from a fully automated machine learning pipeline in 4723 individuals with cardiovascular disease (CVD) and 5733 without in the UK Biobank. Relationships between volumes at end-diastole (ED) and end-systole (ES) and risk/disease factors were quantified using univariate, multivariate and logistic regression analyses. Strength of association between deep learning volumes and standard volumes was compared using the area under the receiving operator characteristic curve (AUC). RESULTS: Univariate and multivariate associations between deep learning volumes and most risk and disease factors were stronger than for standard volumes (higher R2 and more significant P values), particularly for sex, age, and body mass index. AUC for all logistic regressions were higher for deep learning volumes than standard volumes (p<0.001 for all four chambers at ED and ES). CONCLUSIONS: Neural network reconstructions of whole heart volumes had significantly stronger associations with cardiovascular disease and risk factors than standard volume estimation methods in an automatic processing pipeline.

Atlas-based analysis of cardiac shape and function: correction of regional shape bias due to imaging protocol for population studies.

BACKGROUND: Cardiovascular imaging studies generate a wealth of data which is typically used only for individual study endpoints. By pooling data from multiple sources, quantitative comparisons can be made of regional wall motion abnormalities between different cohorts, enabling reuse of valuable data. Atlas-based analysis provides precise quantification of shape and motion differences between disease groups and normal subjects. However, subtle shape differences may arise due to differences in imaging protocol between studies. METHODS: A mathematical model describing regional wall motion and shape was used to establish a coordinate system registered to the cardiac anatomy. The atlas was applied to data contributed to the Cardiac Atlas Project from two independent studies which used different imaging protocols: steady state free precession (SSFP) and gradient recalled echo (GRE) cardiovascular magnetic resonance (CMR). Shape bias due to imaging protocol was corrected using an atlas-based transformation which was generated from a set of 46 volunteers who were imaged with both protocols. RESULTS: Shape bias between GRE and SSFP was regionally variable, and was effectively removed using the atlas-based transformation. Global mass and volume bias was also corrected by this method. Regional shape differences between cohorts were more statistically significant after removing regional artifacts due to imaging protocol bias. CONCLUSIONS: Bias arising from imaging protocol can be both global and regional in nature, and is effectively corrected using an atlas-based transformation, enabling direct comparison of regional wall motion abnormalities between cohorts acquired in separate studies.

The Cardiac Atlas Project--an imaging database for computational modeling and statistical atlases of the heart.

MOTIVATION: Integrative mathematical and statistical models of cardiac anatomy and physiology can play a vital role in understanding cardiac disease phenotype and planning therapeutic strategies. However, the accuracy and predictive power of such models is dependent upon the breadth and depth of noninvasive imaging datasets. The Cardiac Atlas Project (CAP) has established a large-scale database of cardiac imaging examinations and associated clinical data in order to develop a shareable, web-accessible, structural and functional atlas of the normal and pathological heart for clinical, research and educational purposes. A goal of CAP is to facilitate collaborative statistical analysis of regional heart shape and wall motion and characterize cardiac function among and within population groups. RESULTS: Three main open-source software components were developed: (i) a database with web-interface; (ii) a modeling client for 3D + time visualization and parametric description of shape and motion; and (iii) open data formats for semantic characterization of models and annotations. The database was implemented using a three-tier architecture utilizing MySQL, JBoss and Dcm4chee, in compliance with the DICOM standard to provide compatibility with existing clinical networks and devices. Parts of Dcm4chee were extended to access image specific attributes as search parameters. To date, approximately 3000 de-identified cardiac imaging examinations are available in the database. All software components developed by the CAP are open source and are freely available under the Mozilla Public License Version 1.1 (http://www.mozilla.org/MPL/MPL-1.1.txt). AVAILABILITY: http://www.cardiacatlas.org CONTACT: a.young@auckland.ac.nz SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Automated regional wall motion abnormality detection by combining rest and stress cardiac MRI: correlation with contrast-enhanced MRI.

PURPOSE: To correlate an automated regional wall motion abnormality (RWMA) detection method based on combined rest and dobutamine-stress cardiac MRI with the assessment of myocardial infarction from contrast-enhanced MRI (CE-MRI), and to demonstrate that adding stress data improves the detection of scar segments compared with rest data alone. MATERIALS AND METHODS: An automated RWMA detection method was built based on a statistical model of normokinetic myocardium from 41 healthy volunteers. The method was adapted to detect changes in RWMA from rest to stress. Twelve patients with myocardial infarction were included in the experiment. The correlation with CE-MRI was performed on two measurements: infarct transmurality and scar detection. RESULTS: Compared with infarct transmurality, the probability of normokinetic motion decreased progressively as infarct transmurality increased. These probability values were 0.59 for non-scar segments, for <25% transmurality was 0.4 (SE=0.04), for 25-50% was 0.33 (SE=0.03), for 50-75% was 0.21 (SE=0.03) and for ≥75% was 0.10 (SE=0.03). For scar tissue detection, adding stress data significantly improved the performance (P<0.001, confidence interval=99.9%). The sensitivity, specificity, and accuracy increased by 34%, 30%, and 32%, respectively. The area under the receiver operating characteristics curve was 0.63 when rest-only data was used, but it was improved to 0.87 when stress data was added. CONCLUSION: The presented automated RWMA assessment was capable of detecting wall motion improvements from rest to stress. The method correlated well with infarct transmurality from CE-MRI. Detection of scar regions was more accurate when rest and stress data were combined compared with rest data alone.

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 <2.5 mm. The agreement of the network with two observers was excellent (intraclass correlation coefficient >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., <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.

Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy.

In many cardiovascular pathologies, the shape and motion of the heart provide important clues to understanding the mechanisms of the disease and how it progresses over time. With the advent of large-scale cardiac data, statistical modeling of cardiac anatomy has become a powerful tool to provide automated, precise quantification of the status of patient-specific heart geometry with respect to reference populations. Powered by supervised or unsupervised machine learning algorithms, statistical cardiac shape analysis can be used to automatically identify and quantify the severity of heart diseases, to provide morphometric indices that are optimally associated with clinical factors, and to evaluate the likelihood of adverse outcomes. Recently, statistical cardiac atlases have been integrated with deep neural networks to enable anatomical consistency of cardiac segmentation, registration, and automated quality control. These combinations have already shown significant improvements in performance and avoid gross anatomical errors that could make the results unusable. This current trend is expected to grow in the near future. Here, we aim to provide a mini review highlighting recent advances in statistical atlasing of cardiac function in the context of artificial intelligence in cardiac imaging.

Fully Automated Myocardial Strain Estimation from Cardiovascular MRI-tagged Images Using a Deep Learning Framework in the UK Biobank.

PURPOSE: To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac MRI-tagged images. MATERIALS AND METHODS: In this retrospective cross-sectional study, 4508 cases from the U.K. Biobank were split randomly into 3244 training cases, 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of (a) a convolutional neural network (CNN) for localization and (b) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis. RESULTS: Within the test set, myocardial end-systolic circumferential Green strain errors were -0.001 ± 0.025, -0.001 ± 0.021, and 0.004 ± 0.035 in the basal, mid-, and apical slices, respectively (mean ± standard deviation of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in participants with diabetes, hypertensive participants, and participants with a previous heart attack. Typical processing time was approximately 260 frames (approximately 13 slices) per second on a GPU with 12 GB RAM compared with 6-8 minutes per slice for the manual analysis. CONCLUSION: The fully automated combined RNN and CNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack.Published under a CC BY 4.0 license. Supplemental material is available for this article.