Abstract
Bioprosthetic heart valves (BHVs) are commonly used as heart valve replacements but they are prone to fatigue failure; estimating their remaining life directly from medical images is difficult. Analyzing the valve performance can provide better guidance for personalized valve design. However, such analyses are often computationally intensive. In this work, we introduce the concept of deep learning (DL) based finite element analysis (DLFEA) to learn the deformation biomechanics of bioprosthetic aortic valves directly from simulations. The proposed DL framework can eliminate the time-consuming biomechanics simulations, while predicting valve deformations with the same fidelity. We present statistical results that demonstrate the high performance of the DLFEA framework and the applicability of the framework to predict bioprosthetic aortic valve deformations. With further development, such a tool can provide fast decision support for designing surgical bioprosthetic aortic valves. Ultimately, this framework could be extended to other BHVs and improve patient care.
Highlights
Semilunar valves are structures that permit blood to be pumped into the aorta and pulmonary artery from the ventricles during systole, and prevent backflow into the ventricles during diastole[1]
The Deep-Learning for finite element analysis (DLFEA) framework predicts the final deformations of the aortic valve and the valve coaptation area using the original undeformed geometry of the valve, the aortic pressure, and the material properties of the valve as input
We compare the performance of DLFEA framework on a test dataset, which were not used for training
Summary
Semilunar valves (i.e. the aortic and pulmonary valves) are structures that permit blood to be pumped into the aorta and pulmonary artery from the ventricles during systole, and prevent backflow into the ventricles during diastole[1]. Computational analysis of the heart valve can be an important tool in understanding the etiology of valvular diseases and can help clinicians in obtaining additional information that aid in therapeutic or valve replacement decisions. Current state-of-the-art valve analysis approaches reconstruct the aortic heart valve geometry from computed tomography (CT) images using NURBS5,10. Current BHVs are designed only for certain discrete population-averaged sizes These geometries are analyzed using shell formulations of finite element analysis after meshing to assess the valve performance[5]. While these analysis frameworks have proven to be useful, they often involve large computational overhead. Deep learning can provide a viable fast alternative to computational analysis, IGA, to accelerate the design and analysis process for bioprosthetic valves. Along with recent algorithmic advances, the success of deep learning as a powerful function approximator could be attributed to the availability of large volume of data and advances in high-performance computing such as the Graphics Processing Units (GPUs)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
