An official website of the United States government
Faithful, accurate, and successful cardiac biomechanics and electrophysiological simulations require patient-specific geometric models of the heart. Since the cardiac geometry consists of highly-curved boundaries, the use of high-order meshes with curved elements would ensure that the various curves and features present in the cardiac geometry are well-captured and preserved in the corresponding mesh. Most other existing mesh generation techniques require computer-aided design files to represent the geometric boundary, which are often not available for biomedical applications. Unlike such methods, our technique takes a high-order surface mesh, generated from patient medical images, as input and generates a high-order volume mesh directly from the curved surface mesh. In this paper, we use our direct high-order curvilinear tetrahedral mesh generation method [1] to generate several second-order cardiac meshes. Our meshes include the left ventricle myocardia of a healthy heart and hearts with dilated and hypertrophic cardiomyopathy. We show that our high-order cardiac meshes do not contain inverted elements and are of sufficiently high quality for use in cardiac finite element simulations.
more »
« less
Motion Extraction of the Right Ventricle from 4D Cardiac Cine MRI Using A Deep Learning-Based Deformable Registration Framework
Cardiac Cine Magnetic Resonance (CMR) Imaging has made a significant paradigm shift in medical imaging technology, thanks to its capability of acquiring high spatial and temporal resolution images of different structures within the heart that can be used for reconstructing patient-specific ventricular computational models. In this work, we describe the development of dynamic patient-specific right ventricle (RV) models associated with normal subjects and abnormal RV patients to be subsequently used to assess RV function based on motion and kinematic analysis. We first constructed static RV models using segmentation masks of cardiac chambers generated from our accurate, memory-efficient deep neural architecture - CondenseUNet - featuring both a learned group structure and a regularized weight-pruner to estimate the motion of the right ventricle. In our study, we use a deep learning-based deformable network that takes 3D input volumes and outputs a motion field which is then used to generate isosurface meshes of the cardiac geometry at all cardiac frames by propagating the end-diastole (ED) isosurface mesh using the reconstructed motion field. The proposed model was trained and tested on the Automated Cardiac Diagnosis Challenge (ACDC) dataset featuring 150 cine cardiac MRI patient datasets. The isosurface meshes generated using the proposed pipeline were compared to those obtained using motion propagation via traditional non-rigid registration based on several performance metrics, including Dice score and mean absolute distance (MAD).
more »
« less
- PAR ID:
- 10357908
- Date Published:
- Journal Name:
- Proc. of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (EMBC 2021)
- Page Range / eLocation ID:
- 3795 to 3799
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Bernard, O.; Clarysse, P.; Duchateau, N.; Ohayon, J.; Viallon, M (Ed.)Increased passive myocardial stiffness is implicated in the pathophysiology of many cardiac diseases, and its in vivo estimation can improve management of heart disease. MRI-driven computational constitutive modeling has been used extensively to evaluate passive myocardial stiffness. This approach requires subject-specific data that is best acquired with different MRI sequences: conventional cine (e.g. bSSFP), tagged MRI (or DENSE), and cardiac diffusion tensor imaging. However, due to the lack of comprehensive datasets and the challenge of incorporating multi-phase and single-phase disparate MRI data, no studies have combined in vivo cine bSSFP, tagged MRI, and cardiac diffusion tensor imaging to estimate passive myocardial stiffness. The objective of this work was to develop a personalized in silico left ventricular model to evaluate passive myocardial stiffness by integrating subject-specific geometric data derived from cine bSSFP, regional kinematics extracted from tagged MRI, and myocardial microstructure measured using in vivo cardiac diffusion tensor imaging. To demonstrate the feasibility of using a complete subject-specific imaging dataset for passive myocardial stiffness estimation, we calibrated a bulk stiffness parameter of a transversely isotropic exponential constitutive relation to match the local kinematic field extracted from tagged MRI. This work establishes a pipeline for developing subject-specific biomechanical ventricular models to probe passive myocardial mechanical behavior, using comprehensive cardiac imaging data from multiple in vivo MRI sequences.more » « less
-
Abstract Computational fluid dynamics (CFD) modeling of left ventricle (LV) flow combined with patient medical imaging data has shown great potential in obtaining patient-specific hemodynamics information for functional assessment of the heart. A typical model construction pipeline usually starts with segmentation of the LV by manual delineation followed by mesh generation and registration techniques using separate software tools. However, such approaches usually require significant time and human efforts in the model generation process, limiting large-scale analysis. In this study, we propose an approach toward fully automating the model generation process for CFD simulation of LV flow to significantly reduce LV CFD model generation time. Our modeling framework leverages a novel combination of techniques including deep-learning based segmentation, geometry processing, and image registration to reliably reconstruct CFD-suitable LV models with little-to-no user intervention.1 We utilized an ensemble of two-dimensional (2D) convolutional neural networks (CNNs) for automatic segmentation of cardiac structures from three-dimensional (3D) patient images and our segmentation approach outperformed recent state-of-the-art segmentation techniques when evaluated on benchmark data containing both magnetic resonance (MR) and computed tomography(CT) cardiac scans. We demonstrate that through a combination of segmentation and geometry processing, we were able to robustly create CFD-suitable LV meshes from segmentations for 78 out of 80 test cases. Although the focus on this study is on image-to-mesh generation, we demonstrate the feasibility of this framework in supporting LV hemodynamics modeling by performing CFD simulations from two representative time-resolved patient-specific image datasets.more » « less
-
Abstract The increasing recognition of the right ventricle (RV) necessitates the development of RV-focused interventions, devices and testbeds. In this study, we developed a soft robotic model of the right heart that accurately mimics RV biomechanics and hemodynamics, including free wall, septal and valve motion. This model uses a biohybrid approach, combining a chemically treated endocardial scaffold with a soft robotic synthetic myocardium. When connected to a circulatory flow loop, the robotic right ventricle (RRV) replicates real-time hemodynamic changes in healthy and pathological conditions, including volume overload, RV systolic failure and pressure overload. The RRV also mimics clinical markers of RV dysfunction and is validated using an in vivo porcine model. Additionally, the RRV recreates chordae tension, simulating papillary muscle motion, and shows the potential for tricuspid valve repair and replacement in vitro. This work aims to provide a platform for developing tools for research and treatment for RV pathophysiology.more » « less
-
This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains; and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/EMBC46164.2021.9630586
