Multi-Modality Deep Infarct: Non-invasive identification of infarcted myocardium using composite in-silico-human data learning.

Myocardial infarction (MI) continues to be a leading cause of death worldwide. The precise quantification of infarcted tissue is crucial to diagnosis, therapeutic management, and post-MI care. Late gadolinium enhancement-cardiac magnetic resonance (LGE-CMR) is regarded as the gold standard for precise infarct tissue localization in MI patients. A fundamental limitation of LGE-CMR is the invasive intravenous introduction of gadolinium-based contrast agents that present potential high-risk toxicity, particularly for individuals with underlying chronic kidney diseases. Herein, we develop a completely non-invasive methodology that identifies the location and extent of an infarct region in the left ventricle via a machine learning (ML) model using only cardiac strains as inputs. In this transformative approach, we demonstrate the remarkable performance of a multi-fidelity ML model that combines rodent-based in-silico-generated training data (low-fidelity) with very limited patient-specific human data (high-fidelity) in predicting LGE ground truth. Our results offer a new paradigm for developing feasible prognostic tools by augmenting synthetic simulation-based data with very small amounts of in-vivo human data. More broadly, the proposed approach can significantly assist with addressing biomedical challenges in healthcare where human data are limited.

Multi-Modality Deep Infarct: Non-invasive identification of infarcted myocardium using composite in-silico-human data learning.

Myocardial infarction (MI) continues to be a leading cause of death worldwide. The precise quantification of infarcted tissue is crucial to diagnosis, therapeutic management, and post-MI care. Late gadolinium enhancement-cardiac magnetic resonance (LGE-CMR) is regarded as the gold standard for precise infarct tissue localization in MI patients. A fundamental limitation of LGE-CMR is the invasive intravenous introduction of gadolinium-based contrast agents that present potential high-risk toxicity, particularly for individuals with underlying chronic kidney diseases. Herein, we develop a completely non-invasive methodology that identifies the location and extent of an infarct region in the left ventricle via a machine learning (ML) model using only cardiac strains as inputs. In this transformative approach, we demonstrate the remarkable performance of a multi-fidelity ML model that combines rodent-based in-silico-generated training data (low-fidelity) with very limited patient-specific human data (high-fidelity) in predicting LGE ground truth. Our results offer a new paradigm for developing feasible prognostic tools by augmenting synthetic simulation-based data with very small amounts of in-vivo human data. More broadly, the proposed approach can significantly assist with addressing biomedical challenges in healthcare where human data are limited.

Right ventricular stiffening and anisotropy alterations in pulmonary hypertension: Mechanisms and relations to function.

Aims: Pulmonary hypertension (PH) results in an increase in RV afterload, leading to RV dysfunction and failure. The mechanisms underlying maladaptive RV remodeling are poorly understood. In this study, we investigated the multiscale and mechanistic nature of RV free wall (RVFW) biomechanical remodeling and its correlations with RV function adaptations. Methods and Results: Mild and severe models of PH, consisting of hypoxia (Hx) model in Sprague-Dawley (SD) rats (n=6 each, Control and PH) and Sugen-hypoxia (SuHx) model in Fischer (CDF) rats (n=6 each, Control and PH), were used. Organ-level function and tissue-level stiffness and microstructure were quantified through in-vivo and ex-vivo measures, respectively. Multiscale analysis was used to determine the association between fiber-level remodeling, tissue-level stiffening, and organ-level dysfunction. Animal models with different PH severity provided a wide range of RVFW stiffening and anisotropy alterations in PH. Decreased RV-pulmonary artery (PA) coupling correlated strongly with stiffening but showed a weaker association with the loss of RVFW anisotropy. Machine learning classification identified the range of adaptive and maladaptive RVFW stiffening. Multiscale modeling revealed that increased collagen fiber tautness was a key remodeling mechanism that differentiated severe from mild stiffening. Myofiber orientation analysis indicated a shift away from the predominantly circumferential fibers observed in healthy RVFW specimens, leading to a significant loss of tissue anisotropy. Conclusion: Multiscale biomechanical analysis indicated that although hypertrophy and fibrosis occur in both mild and severe PH, certain fiber-level remodeling events, including increased tautness in the newly deposited collagen fibers and significant reorientations of myofibers, contributed to excessive biomechanical maladaptation of the RVFW leading to severe RV-PA uncoupling. Collagen fiber remodeling and the loss of tissue anisotropy can provide an improved understanding of the transition from adaptive to maladaptive remodeling. Translational perspective: Right ventricular (RV) failure is a leading cause of mortality in patients with pulmonary hypertension (PH). RV diastolic and systolic impairments are evident in PH patients. Stiffening of the RV wall tissue and changes in the wall anisotropy are expected to be major contributors to both impairments. Global assessments of the RV function remain inadequate in identifying patients with maladaptive RV wall remodeling primarily due to their confounded and weak representation of RV fiber and tissue remodeling events. This study provides novel insights into the underlying mechanisms of RV biomechanical remodeling and identifies the adaptive-to-maladaptive transition across the RV biomechanics-function spectrum. Our analysis dissecting the contribution of different RV wall remodeling events to RV dysfunction determines the most adverse fiber-level remodeling to RV dysfunction as new therapeutic targets to curtail RV maladaptation and, in turn, RV failure in PH.

Machine learning-based classification of cardiac relaxation impairment using sarcomere length and intracellular calcium transients.

Impaired relaxation of cardiomyocytes leads to diastolic dysfunction in the left ventricle. Relaxation velocity is regulated in part by intracellular calcium (Ca2+) cycling, and slower outflux of Ca2+ during diastole translates to reduced relaxation velocity of sarcomeres. Sarcomere length transient and intracellular calcium kinetics are integral parts of characterizing the relaxation behavior of the myocardium. However, a classifier tool that can separate normal cells from cells with impaired relaxation using sarcomere length transient and/or calcium kinetics remains to be developed. In this work, we employed nine different classifiers to classify normal and impaired cells, using ex-vivo measurements of sarcomere kinematics and intracellular calcium kinetics data. The cells were isolated from wild-type mice (referred to as normal) and transgenic mice expressing impaired left ventricular relaxation (referred to as impaired). We utilized sarcomere length transient data with a total of n = 126 cells (n = 60 normal cells and n = 66 impaired cells) and intracellular calcium cycling measurements with a total of n = 116 cells (n = 57 normal cells and n = 59 impaired cells) from normal and impaired cardiomyocytes as inputs to machine learning (ML) models for classification. We trained all ML classifiers with cross-validation method separately using both sets of input features, and compared their performance metrics. The performance of classifiers on test data showed that our soft voting classifier outperformed all other individual classifiers on both sets of input features, with 0.94 and 0.95 area under the receiver operating characteristic curves for sarcomere length transient and calcium transient, respectively, while multilayer perceptron achieved comparable scores of 0.93 and 0.95, respectively. However, the performance of decision tree, and extreme gradient boosting was found to be dependent on the set of input features used for training. Our findings highlight the importance of selecting appropriate input features and classifiers for the accurate classification of normal and impaired cells. Layer-wise relevance propagation (LRP) analysis demonstrated that the time to 50% contraction of the sarcomere had the highest relevance score for sarcomere length transient, whereas time to 50% decay of calcium had the highest relevance score for calcium transient input features. Despite the limited dataset, our study demonstrated satisfactory accuracy, suggesting that the algorithm can be used to classify relaxation behavior in cardiomyocytes when the potential relaxation impairment of the cells is unknown.

On the possibility of estimating myocardial fiber architecture from cardiac strains.

The myocardium is composed of a complex network of contractile myofibers that are organized in such a way as to produce efficient contraction and relaxation of the heart. The myofiber architecture in the myocardium is a key determinant of cardiac motion and the global or organ-level function of the heart. Reports of architectural remodeling in cardiac diseases, such as pulmonary hypertension and myocardial infarction, potentially contributing to cardiac dysfunction call for the inclusion of an architectural marker for an improved assessment of cardiac function. However, the in-vivo quantification of three-dimensional myo-architecture has proven challenging. In this work, we examine the sensitivity of cardiac strains to varying myofiber orientation using a multiscale finite-element model of the LV. Additionally, we present an inverse modeling approach to predict the myocardium fiber structure from cardiac strains. Our results indicate a strong correlation between fiber orientation and LV kinematics, corroborating that the fiber structure is a principal determinant of LV contractile behavior. Our inverse model was capable of accurately predicting the myocardial fiber range and regional fiber angles from strain measures. A concrete understanding of the link between LV myofiber structure and motion, and the development of non-invasive and feasible means of characterizing the myocardium architecture is expected to lead to advanced LV functional metrics and improved prognostic assessment of structural heart disease.