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.

A universal biventricular coordinate system incorporating valve annuli: Validation in congenital heart disease.

Universal coordinate systems have been proposed to facilitate anatomic registration between three-dimensional images, data and models of the ventricles of the heart. However, current universal ventricular coordinate systems do not account for the outflow tracts and valve annuli where the anatomy is complex. Here we propose an extension to the 'Cobiveco' biventricular coordinate system that also accounts for the intervalvular bridges of the base and provides a tool for anatomically consistent registration between widely varying biventricular shapes. CobivecoX uses a novel algorithm to separate intervalvular bridges and assign new coordinates, including an inflow-outflow coordinate, to describe local positions in these regions uniquely and consistently. Anatomic consistency of registration was validated using curated three-dimensional biventricular shape models derived from cardiac MRI measurements in normal hearts and hearts from patients with congenital heart diseases. This new method allows the advantages of universal cardiac coordinates to be used for three-dimensional ventricular imaging data and models that include the left and right ventricular outflow tracts and valve annuli.

lGeneralized super-resolution 4D Flow MRI-using ensemble learning to extend across the cardiovascular system.

4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique capable of quantifying blood flow across the cardiovascular system. While practical use is limited by spatial resolution and image noise, incorporation of trained super-resolution (SR) networks has potential to enhance image quality post-scan. However, these efforts have predominantly been restricted to narrowly defined cardiovascular domains, with limited exploration of how SR performance extends across the cardiovascular system; a task aggravated by contrasting hemodynamic conditions apparent across the cardiovasculature. The aim of our study was to explore the generalizability of SR 4D Flow MRI using a combination of heterogeneous training sets and dedicated ensemble learning. With synthetic training data generated across three disparate domains (cardiac, aortic, cerebrovascular), varying convolutional base and ensemble learners were evaluated as a function of domain and architecture, quantifying performance on both in-silico and acquired in-vivo data from the same three domains. Results show that both bagging and stacking ensembling enhance SR performance across domains, accurately predicting high-resolution velocities from low-resolution input data in-silico. Likewise, optimized networks successfully recover native resolution velocities from downsampled in-vivo data, as well as show qualitative potential in generating denoised SR-images from clinicallevel input data. In conclusion, our work presents a viable approach for generalized SR 4D Flow MRI, with ensemble learning extending utility across various clinical areas of interest.

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

BACKGROUND: Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. METHODS: Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. RESULTS: The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. CONCLUSIONS: Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.

Quinapril treatment curtails decline of global longitudinal strain and mechanical function in hypertensive rats.

BACKGROUND: Left ventricular (LV) global longitudinal strain (GLS) has been proposed as an early imaging biomarker of cardiac mechanical dysfunction. OBJECTIVE: To assess the impact of angiotensin-converting enzyme (ACE) inhibitor treatment of hypertensive heart disease on LV GLS and mechanical function. METHODS: The spontaneously hypertensive rat (SHR) model of hypertensive heart disease ( n  = 38) was studied. A subset of SHRs received quinapril (TSHR, n  = 16) from 3 months (mo). Wistar Kyoto rats (WKY, n  = 13) were used as controls. Tagged cardiac MRI was performed using a 4.7 T Varian preclinical scanner. RESULTS: The SHRs had significantly lower LV ejection fraction (EF) than the WKYs at 3 mo (53.0 ±â€Š1.7% vs. 69.6 ±â€Š2.1%, P  < 0.05), 14 mo (57.0 ±â€Š2.5% vs. 74.4 ±â€Š2.9%, P  < 0.05) and 24 mo (50.1 ±â€Š2.4% vs. 67.0 ±â€Š2.0%, P  < 0.01). At 24 mo, ACE inhibitor treatment was associated with significantly greater LV EF in TSHRs compared to untreated SHRs (64.2 ±â€Š3.4% vs. 50.1 ±â€Š2.4%, P  < 0.01). Peak GLS magnitude was significantly lower in SHRs compared with WKYs at 14 months (7.5% ±â€Š0.4% vs. 9.9 ±â€Š0.8%, P  < 0.05). At 24 months, Peak GLS magnitude was significantly lower in SHRs compared with both WKYs (6.5 ±â€Š0.4% vs. 9.7 ±â€Š1.0%, P  < 0.01) and TSHRs (6.5 ±â€Š0.4% vs. 9.6 ±â€Š0.6%, P  < 0.05). CONCLUSIONS: ACE inhibitor treatment curtails the decline in global longitudinal strain in hypertensive rats, with the treatment group exhibiting significantly greater LV EF and GLS magnitude at 24 mo compared with untreated SHRs.

Correcting bias in cardiac geometries derived from multimodal images using spatiotemporal mapping.

Cardiovascular imaging studies provide a multitude of structural and functional data to better understand disease mechanisms. While pooling data across studies enables more powerful and broader applications, performing quantitative comparisons across datasets with varying acquisition or analysis methods is problematic due to inherent measurement biases specific to each protocol. We show how dynamic time warping and partial least squares regression can be applied to effectively map between left ventricular geometries derived from different imaging modalities and analysis protocols to account for such differences. To demonstrate this method, paired real-time 3D echocardiography (3DE) and cardiac magnetic resonance (CMR) sequences from 138 subjects were used to construct a mapping function between the two modalities to correct for biases in left ventricular clinical cardiac indices, as well as regional shape. Leave-one-out cross-validation revealed a significant reduction in mean bias, narrower limits of agreement, and higher intraclass correlation coefficients for all functional indices between CMR and 3DE geometries after spatiotemporal mapping. Meanwhile, average root mean squared errors between surface coordinates of 3DE and CMR geometries across the cardiac cycle decreased from 7 ± 1 to 4 ± 1 mm for the total study population. Our generalised method for mapping between time-varying cardiac geometries obtained using different acquisition and analysis protocols enables the pooling of data between modalities and the potential for smaller studies to leverage large population databases for quantitative comparisons.

Automated segmentation of long and short axis DENSE cardiovascular magnetic resonance for myocardial strain analysis using spatio-temporal convolutional neural networks.

BACKGROUND: Cine Displacement Encoding with Stimulated Echoes (DENSE) facilitates the quantification of myocardial deformation, by encoding tissue displacements in the cardiovascular magnetic resonance (CMR) image phase, from which myocardial strain can be estimated with high accuracy and reproducibility. Current methods for analyzing DENSE images still heavily rely on user input, making this process time-consuming and subject to inter-observer variability. The present study sought to develop a spatio-temporal deep learning model for segmentation of the left-ventricular (LV) myocardium, as spatial networks often fail due to contrast-related properties of DENSE images. METHODS: 2D + time nnU-Net-based models have been trained to segment the LV myocardium from DENSE magnitude data in short- and long-axis images. A dataset of 360 short-axis and 124 long-axis slices was used to train the networks, from a combination of healthy subjects and patients with various conditions (hypertrophic and dilated cardiomyopathy, myocardial infarction, myocarditis). Segmentation performance was evaluated using ground-truth manual labels, and a strain analysis using conventional methods was performed to assess strain agreement with manual segmentation. Additional validation was performed using an externally acquired dataset to compare the inter- and intra-scanner reproducibility with respect to conventional methods. RESULTS: Spatio-temporal models gave consistent segmentation performance throughout the cine sequence, while 2D architectures often failed to segment end-diastolic frames due to the limited blood-to-myocardium contrast. Our models achieved a DICE score of 0.83 ± 0.05 and a Hausdorff distance of 4.0 ± 1.1 mm for short-axis segmentation, and 0.82 ± 0.03 and 7.9 ± 3.9 mm respectively for long-axis segmentations. Strain measurements obtained from automatically estimated myocardial contours showed good to excellent agreement with manual pipelines, and remained within the limits of inter-user variability estimated in previous studies. CONCLUSION: Spatio-temporal deep learning shows increased robustness for the segmentation of cine DENSE images. It provides excellent agreement with manual segmentation for strain extraction. Deep learning will facilitate the analysis of DENSE data, bringing it one step closer to clinical routine.

Super-resolution 4D flow MRI to quantify aortic regurgitation using computational fluid dynamics and deep learning.

Changes in cardiovascular hemodynamics are closely related to the development of aortic regurgitation (AR), a type of valvular heart disease. Metrics derived from blood flows are used to indicate AR onset and evaluate its severity. These metrics can be non-invasively obtained using four-dimensional (4D) flow magnetic resonance imaging (MRI), where accuracy is primarily dependent on spatial resolution. However, insufficient resolution often results from limitations in 4D flow MRI and complex aortic regurgitation hemodynamics. To address this, computational fluid dynamics simulations were transformed into synthetic 4D flow MRI data and used to train a variety of neural networks. These networks generated super-resolution, full-field phase images with an upsample factor of 4. Results showed decreased velocity error, high structural similarity scores, and improved learning capabilities from previous work. Further validation was performed on two sets of in vivo 4D flow MRI data and demonstrated success in de-noising flow images. This approach presents an opportunity to comprehensively analyse AR hemodynamics in a non-invasive manner.

AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance.

Aims: One of the major challenges in the quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) is the estimation of the arterial input function (AIF). This is due to the non-linear relationship between the concentration of gadolinium and the MR signal, which leads to signal saturation. In this work, we show that a deep learning model can be trained to predict the unsaturated AIF from standard images, using the reference dual-sequence acquisition AIFs (DS-AIFs) for training. Methods and results: A 1D U-Net was trained, to take the saturated AIF from the standard images as input and predict the unsaturated AIF, using the data from 201 patients from centre 1 and a test set comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n = 44). Fully-automated MBF was compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis. There was no statistical difference between the MBF quantified with the DS-AIF [2.77 mL/min/g (1.08)] and predicted with the AI-AIF (2.79 mL/min/g (1.08), P = 0.33. Bland-Altman analysis shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF (bias of -0.11 mL/min/g). Additionally, the MBF diagnosis classification of the AI-AIF matched the DS-AIF in 669/704 (95%) of myocardial segments. Conclusion: Quantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF.

Biventricular shape modes discriminate pulmonary valve replacement in tetralogy of Fallot better than imaging indices.

Current indications for pulmonary valve replacement (PVR) in repaired tetralogy of Fallot (rTOF) rely on cardiovascular magnetic resonance (CMR) image-based indices but are inconsistently applied, lead to mixed outcomes, and remain debated. This study aimed to test the hypothesis that specific markers of biventricular shape may discriminate differences between rTOF patients who did and did not require subsequent PVR better than standard imaging indices. In this cross-sectional retrospective study, biventricular shape models were customized to CMR images from 84 rTOF patients. A statistical atlas of end-diastolic shape was constructed using principal component analysis. Multivariate regression was used to quantify shape mode and imaging index associations with subsequent intervention status (PVR, n = 48 vs. No-PVR, n = 36), while accounting for confounders. Clustering analysis was used to test the ability of the most significant shape modes and imaging indices to discriminate PVR status as evaluated by a Matthews correlation coefficient (MCC). Geometric strain analysis was also conducted to assess shape mode associations with systolic function. PVR status correlated significantly with shape modes associated with right ventricular (RV) apical dilation and left ventricular (LV) dilation (p < 0.01), RV basal bulging and LV conicity (p < 0.05), and pulmonary valve dilation (p < 0.01). PVR status also correlated significantly with RV ejection fraction (p < 0.05) and correlated marginally with LV end-systolic volume index (p < 0.07). Shape modes discriminated subsequent PVR better than standard imaging indices (MCC = 0.49 and MCC = 0.28, respectively) and were significantly associated with RV and LV radial systolic strain. Biventricular shape modes discriminated differences between patients who did and did not require subsequent PVR better than standard imaging indices in current use. These regional features of cardiac morphology may provide insight into adaptive vs. maladaptive types of structural remodeling and point toward an improved quantitative, patient-specific assessment tool for clinical use.

A deep learning approach for fully automated cardiac shape modeling in tetralogy of Fallot.

BACKGROUND: Cardiac shape modeling is a useful computational tool that has provided quantitative insights into the mechanisms underlying dysfunction in heart disease. The manual input and time required to make cardiac shape models, however, limits their clinical utility. Here we present an end-to-end pipeline that uses deep learning for automated view classification, slice selection, phase selection, anatomical landmark localization, and myocardial image segmentation for the automated generation of three-dimensional, biventricular shape models. With this approach, we aim to make cardiac shape modeling a more robust and broadly applicable tool that has processing times consistent with clinical workflows. METHODS: Cardiovascular magnetic resonance (CMR) images from a cohort of 123 patients with repaired tetralogy of Fallot (rTOF) from two internal sites were used to train and validate each step in the automated pipeline. The complete automated pipeline was tested using CMR images from a cohort of 12 rTOF patients from an internal site and 18 rTOF patients from an external site. Manually and automatically generated shape models from the test set were compared using Euclidean projection distances, global ventricular measurements, and atlas-based shape mode scores. RESULTS: The mean absolute error (MAE) between manually and automatically generated shape models in the test set was similar to the voxel resolution of the original CMR images for end-diastolic models (MAE = 1.9 ± 0.5 mm) and end-systolic models (MAE = 2.1 ± 0.7 mm). Global ventricular measurements computed from automated models were in good agreement with those computed from manual models. The average mean absolute difference in shape mode Z-score between manually and automatically generated models was 0.5 standard deviations for the first 20 modes of a reference statistical shape atlas. CONCLUSIONS: Using deep learning, accurate three-dimensional, biventricular shape models can be reliably created. This fully automated end-to-end approach dramatically reduces the manual input required to create shape models, thereby enabling the rapid analysis of large-scale datasets and the potential to deploy statistical atlas-based analyses in point-of-care clinical settings. Training data and networks are available from cardiacatlas.org.

Deep learning estimation of three-dimensional left atrial shape from two-chamber and four-chamber cardiac long axis views.

AIMS: Left atrial volume is commonly estimated using the bi-plane area-length method from two-chamber (2CH) and four-chamber (4CH) long axes views. However, this can be inaccurate due to a violation of geometric assumptions. We aimed to develop a deep learning neural network to infer 3D left atrial shape, volume and surface area from 2CH and 4CH views. METHODS AND RESULTS: A 3D UNet was trained and tested using 2CH and 4CH segmentations generated from 3D coronary computed tomography angiography (CCTA) segmentations (n = 1700, with 1400/100/200 cases for training/validating/testing). An independent test dataset from another institution was also evaluated, using cardiac magnetic resonance (CMR) 2CH and 4CH segmentations as input and 3D CCTA segmentations as the ground truth (n = 20). For the 200 test cases generated from CCTA, the network achieved a mean Dice score value of 93.7%, showing excellent 3D shape reconstruction from two views compared with the 3D segmentation Dice of 97.4%. The network also showed significantly lower mean absolute error values of 3.5 mL/4.9 cm2 for LA volume/surface area respectively compared to the area-length method errors of 13.0 mL/34.1 cm2 respectively (P < 0.05 for both). For the independent CMR test set, the network achieved accurate 3D shape estimation (mean Dice score value of 87.4%), and a mean absolute error values of 6.0 mL/5.7 cm2 for left atrial volume/surface area respectively, significantly less than the area-length method errors of 14.2 mL/19.3 cm2 respectively (P < 0.05 for both). CONCLUSIONS: Compared to the bi-plane area-length method, the network showed higher accuracy and robustness for both volume and surface area.

Left ventricular anatomy in obstructive hypertrophic cardiomyopathy: beyond basal septal hypertrophy.

AIMS: Obstructive hypertrophic cardiomyopathy (oHCM) is characterized by dynamic obstruction of the left ventricular (LV) outflow tract (LVOT). Although this may be mediated by interplay between the hypertrophied septal wall, systolic anterior motion of the mitral valve, and papillary muscle abnormalities, the mechanistic role of LV shape is still not fully understood. This study sought to identify the LV end-diastolic morphology underpinning oHCM. METHODS AND RESULTS: Cardiovascular magnetic resonance images from 2398 HCM individuals were obtained as part of the NHLBI HCM Registry. Three-dimensional LV models were constructed and used, together with a principal component analysis, to build a statistical shape model capturing shape variations. A set of linear discriminant axes were built to define and quantify (Z-scores) the characteristic LV morphology associated with LVOT obstruction (LVOTO) under different physiological conditions and the relationship between LV phenotype and genotype. The LV remodelling pattern in oHCM consisted not only of basal septal hypertrophy but a combination with LV lengthening, apical dilatation, and LVOT inward remodelling. Salient differences were observed between obstructive cases at rest and stress. Genotype negative cases showed a tendency towards more obstructive phenotypes both at rest and stress. CONCLUSIONS: LV anatomy underpinning oHCM consists of basal septal hypertrophy, apical dilatation, LV lengthening, and LVOT inward remodelling. Differences between oHCM cases at rest and stress, as well as the relationship between LV phenotype and genotype, suggest different mechanisms for LVOTO. Proposed Z-scores render an opportunity of redefining management strategies based on the relationship between LV anatomy and LVOTO.

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.

Machine learning evaluation of LV outflow obstruction in hypertrophic cardiomyopathy using three-chamber cardiovascular magnetic resonance.

Left ventricular outflow tract obstruction (LVOTO) is common in hypertrophic cardiomyopathy (HCM), but relationships between anatomical metrics and obstruction are poorly understood. We aimed to develop machine learning methods to evaluate LVOTO in HCM patients and quantify relationships between anatomical metrics and obstruction. This retrospective analysis of 1905 participants of the HCM Registry quantified 11 anatomical metrics derived from 14 landmarks automatically detected on the three-chamber long axis cine CMR images. Linear and logistic regression was used to quantify strengths of relationships with the presence of LVOTO (defined by resting Doppler pressure drop of > 30 mmHg), using the area under the receiver operating characteristic (AUC). Intraclass correlation coefficients between the network predictions and three independent observers showed similar agreement to that between observers. The distance from anterior mitral valve leaflet tip to basal septum (AML-BS) was most highly correlated with Doppler pressure drop (R2 = 0.19, p < 10-5). Multivariate stepwise regression found the best predictive model included AML-BS, AML length to aortic valve diameter ratio, AML length to LV width ratio, and midventricular septal thickness metrics (AUC 0.84). Excluding AML-BS, metrics grouped according to septal hypertrophy, LV geometry, and AML anatomy each had similar associations with LVOTO (AUC 0.71, 0.71, 0.68 respectively, p = ns), significantly less than their combination (AUC 0.77, p < 0.05 for each). Anatomical metrics derived from a standard three-chamber CMR cine acquisition can be used to highlight risk of LVOTO, and suggest further investigation if necessary. A combination of geometric factors is required to provide the best risk prediction.

Predicting post-contrast information from contrast agent free cardiac MRI using machine learning: Challenges and methods.

Objectives: Currently, administering contrast agents is necessary for accurately visualizing and quantifying presence, location, and extent of myocardial infarction (MI) with cardiac magnetic resonance (CMR). In this study, our objective is to investigate and analyze pre- and post-contrast CMR images with the goal of predicting post-contrast information using pre-contrast information only. We propose methods and identify challenges. Methods: The study population consists of 272 retrospectively selected CMR studies with diagnoses of MI (n = 108) and healthy controls (n = 164). We describe a pipeline for pre-processing this dataset for analysis. After data feature engineering, 722 cine short-axis (SAX) images and segmentation mask pairs were used for experimentation. This constitutes 506, 108, and 108 pairs for the training, validation, and testing sets, respectively. We use deep learning (DL) segmentation (UNet) and classification (ResNet50) models to discover the extent and location of the scar and classify between the ischemic cases and healthy cases (i.e., cases with no regional myocardial scar) from the pre-contrast cine SAX image frames, respectively. We then capture complex data patterns that represent subtle signal and functional changes in the cine SAX images due to MI using optical flow, rate of change of myocardial area, and radiomics data. We apply this dataset to explore two supervised learning methods, namely, the support vector machines (SVM) and the decision tree (DT) methods, to develop predictive models for classifying pre-contrast cine SAX images as being a case of MI or healthy. Results: Overall, for the UNet segmentation model, the performance based on the mean Dice score for the test set (n = 108) is 0.75 (±0.20) for the endocardium, 0.51 (±0.21) for the epicardium and 0.20 (±0.17) for the scar. For the classification task, the accuracy, F1 and precision scores of 0.68, 0.69, and 0.64, respectively, were achieved with the SVM model, and of 0.62, 0.63, and 0.72, respectively, with the DT model. Conclusion: We have presented some promising approaches involving DL, SVM, and DT methods in an attempt to accurately predict contrast information from non-contrast images. While our initial results are modest for this challenging task, this area of research still poses several open problems.

Le Cœur en Sabot: shape associations with adverse events in repaired tetralogy of Fallot.

BACKGROUND: Maladaptive remodelling mechanisms occur in patients with repaired tetralogy of Fallot (rToF) resulting in a cycle of metabolic and structural changes. Biventricular shape analysis may indicate mechanisms associated with adverse events independent of pulmonary regurgitant volume index (PRVI). We aimed to determine novel remodelling patterns associated with adverse events in patients with rToF using shape and function analysis. METHODS: Biventricular shape and function were studied in 192 patients with rToF (median time from TOF repair to baseline evaluation 13.5 years). Linear discriminant analysis (LDA) and principal component analysis (PCA) were used to identify shape differences between patients with and without adverse events. Adverse events included death, arrhythmias, and cardiac arrest with median follow-up of 10 years. RESULTS: LDA and PCA showed that shape characteristics pertaining to adverse events included a more circular left ventricle (LV) (decreased eccentricity), dilated (increased sphericity) LV base, increased right ventricular (RV) apical sphericity, and decreased RV basal sphericity. Multivariate LDA showed that the optimal discriminative model included only RV apical ejection fraction and one PCA mode associated with a more circular and dilated LV base (AUC = 0.77). PRVI did not add value, and shape changes associated with increased PRVI were not predictive of adverse outcomes. CONCLUSION: Pathological remodelling patterns in patients with rToF are significantly associated with adverse events, independent of PRVI. Mechanisms related to incident events include LV basal dilation with a reduced RV apical ejection fraction.

Myocardial mesostructure and mesofunction.

The complex and highly organized structural arrangement of some five billion cardiomyocytes directs the coordinated electrical activity and mechanical contraction of the human heart. The characteristic transmural change in cardiomyocyte orientation underlies base-to-apex shortening, circumferential shortening, and left ventricular torsion during contraction. Individual cardiomyocytes shorten ∼15% and increase in diameter ∼8%. Remarkably, however, the left ventricular wall thickens by up to 30-40%. To accommodate this, the myocardium must undergo significant structural rearrangement during contraction. At the mesoscale, collections of cardiomyocytes are organized into sheetlets, and sheetlet shear is the fundamental mechanism of rearrangement that produces wall thickening. Herein, we review the histological and physiological studies of myocardial mesostructure that have established the sheetlet shear model of wall thickening. Recent developments in tissue clearing techniques allow for imaging of whole hearts at the cellular scale, whereas magnetic resonance imaging (MRI) and computed tomography (CT) can image the myocardium at the mesoscale (100 µm to 1 mm) to resolve cardiomyocyte orientation and organization. Through histology, cardiac diffusion tensor imaging (DTI), and other modalities, mesostructural sheetlets have been confirmed in both animal and human hearts. Recent in vivo cardiac DTI methods have measured reorientation of sheetlets during the cardiac cycle. We also examine the role of pathological cardiac remodeling on sheetlet organization and reorientation, and the impact this has on ventricular function and dysfunction. We also review the unresolved mesostructural questions and challenges that may direct future work in the field.