Atlas-based Anatomical Modeling and Analysis of Heart Disease

Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks

Cardiac magnetic resonance (CMR) imaging is used widely for morphological assessment and diagnosis of various cardiovascular diseases. Deep learning approaches based on 3D fully convolutional networks (FCNs), have improved state-of-the-art segmentation performance in CMR images. However, previous methods have employed several pre-processing steps and have focused primarily on segmenting low-resolutions images. A crucial step in any automatic segmentation approach is to first localize the cardiac structure of interest within the MRI volume, to reduce false positives and computational complexity. In this paper, we propose two strategies for localizing and segmenting the heart ventricles and myocardium, termed multi-stage and end-to-end, using a 3D convolutional neural network. Our method consists of an encoder–decoder network that is first trained to predict a coarse localized density map of the target structure at a low resolution. Subsequently, a second similar network employs this coarse density map to crop the image at a higher resolution, and consequently, segment the target structure. For the latter, the same two-stage architecture is trained end-to-end. The 3D U-Net with some architectural changes (referred to as 3D DR-UNet) was used as the base architecture in this framework for both the multi-stage and end-to-end strategies. Moreover, we investigate whether the incorporation of coarse features improves the segmentation. We evaluate the two proposed segmentation strategies on two cardiac MRI datasets, namely, the Automatic Cardiac Segmentation Challenge (ACDC) STACOM 2017, and Left Atrium Segmentation Challenge (LASC) STACOM 2018. Extensive experiments and comparisons with other state-of-the-art methods indicate that the proposed multi-stage framework consistently outperforms the rest in terms of several segmentation metrics. The experimental results highlight the robustness of the proposed approach, and its ability to generate accurate high-resolution segmentations, despite the presence of varying degrees of pathology-induced changes to cardiac morphology and image appearance, low contrast, and noise in the CMR volumes.

Research Priorities for Heart Failure With Preserved Ejection Fraction: National Heart, Lung, and Blood Institute Working Group Summary

Heart failure with preserved ejection fraction (HFpEF), a major public health problem that is rising in prevalence, is associated with high morbidity and mortality and is considered to be the greatest unmet need in cardiovascular medicine today because of a general lack of effective treatments. To address this challenging syndrome, the National Heart, Lung, and Blood Institute convened a working group made up of experts in HFpEF and novel research methodologies to discuss research gaps and to prioritize research directions over the next decade. Here, we summarize the discussion of the working group, followed by key recommendations for future research priorities. There was uniform recognition that HFpEF is a highly integrated, multiorgan, systemic disorder requiring a multipronged investigative approach in both humans and animal models to improve understanding of mechanisms and treatment of HFpEF. It was recognized that advances in the understanding of basic mechanisms and the roles of inflammation, macrovascular and microvascular dysfunction, fibrosis, and tissue remodeling are needed and ideally would be obtained from (1) improved animal models, including large animal models, which incorporate the effects of aging and associated comorbid conditions; (2) repositories of deeply phenotyped physiological data and human tissue, made accessible to researchers to enhance collaboration and research advances; and (3) novel research methods that take advantage of computational advances and multiscale modeling for the analysis of complex, high-density data across multiple domains. The working group emphasized the need for interactions among basic, translational, clinical, and epidemiological scientists and across organ systems and cell types, leveraging different areas or research focus, and between research centers. A network of collaborative centers to accelerate basic, translational, and clinical research of pathobiological mechanisms and treatment strategies in HFpEF was discussed as an example of a strategy to advance research progress. This resource would facilitate comprehensive, deep phenotyping of a multicenter HFpEF patient cohort with standardized protocols and a robust biorepository. The research priorities outlined in this document are meant to stimulate scientific advances in HFpEF by providing a road map for future collaborative investigations among a diverse group of scientists across multiple domains.

Cardiac Motion Evolution Model for Analysis of Functional Changes Using Tensor Decomposition and Cross-Sectional Data

Cardiac disease can reduce the ability of the ventricles to function well enough to sustain long-term pumping efficiency. Recent advances in cardiac motion tracking have led to improvements in the analysis of cardiac function. We propose a method to study cohort effects related to age with respect to cardiac function. The proposed approach makes use of a recent method for describing cardiac motion of a given subject using a polyaffine model, which gives a compact parameterization that reliably and accurately describes the cardiac motion across populations. Using this method, a data tensor of motion parameters is extracted for a given population. The partial least squares method for higher order arrays is used to build a model to describe the motion parameters with respect to age, from which a model of motion given age is derived. Based on the cross-sectional statistical analysis with the data tensor of each subject treated as an observation along time, the left ventricular motion over time of Tetralogy of Fallot patients is analysed to understand the temporal evolution of functional abnormalities in this population compared to healthy motion dynamics.