arXiv subjects

Shawn Shadden

Publications and source records attributed to Shawn Shadden.

4 recordsLinked to original sources

arXiv2026

Bayesian finite element regression for vascular flow reconstruction with quantified uncertainty

Reconstructing accurate velocity and pressure fields from under-resolved noisy measurements of blood flow is an ill-posed inverse problem due to unknown inlet and outlet boundary conditions. We present a Bayesian finite element regression framework that reconstructs steady three-dimensional velocity and pressure fields, with quantified uncertainty, from noisy velocity observations without offline training data. We represent velocity and pressure fields in Taylor-Hood finite element basis functions, and construct physics-informed priors on the nodal degrees of freedom from maximum-entropy principles. Combined with a likelihood specified by a noise-model, this yields a posterior whose maximum-a-posteriori estimate (MAP) gives velocity and pressure reconstructions. The MAP estimate is computed by solving a large-scale sparse nonlinear least-squares problem where pressure is eliminated analytically, no-slip walls are enforced exactly, and gradient is computed without forward/adjoint solves or automatic differentiation. A Laplace approximation of the posterior quantifies the uncertainties in our reconstructions and propagates them to clinically relevant quantities of interest including, pressure drop, flow rates, and wall shear stress. On patient-specific cerebral aneurysm, aortic aneurysm, and aortic coarctation geometries, the method reconstructs velocity and pressure more accurately than tricubic interpolation and comparably to a PINN, while recovering region-of-interest wall shear stress more accurately than both.

physics.flu-dyn↗

arXiv2023

LinFlo-Net: A two-stage deep learning method to generate simulation ready meshes of the heart

We present a deep learning model to automatically generate computer models of the human heart from patient imaging data with an emphasis on its capability to generate thin-walled cardiac structures. Our method works by deforming a template mesh to fit the cardiac structures to the given image. Compared with prior deep learning methods that adopted this approach, our framework is designed to minimize mesh self-penetration, which typically arises when deforming surface meshes separated by small distances. We achieve this by using a two-stage diffeomorphic deformation process along with a novel loss function derived from the kinematics of motion that penalizes surface contact and interpenetration. Our model demonstrates comparable accuracy with state-of-the-art methods while additionally producing meshes free of self-intersections. The resultant meshes are readily usable in physics based simulation, minimizing the need for post-processing and cleanup.

cs.CV↗

arXiv2022

Learning Whole Heart Mesh Generation From Patient Images For Computational Simulations

Patient-specific cardiac modeling combines geometries of the heart derived from medical images and biophysical simulations to predict various aspects of cardiac function. However, generating simulation-suitable models of the heart from patient image data often requires complicated procedures and significant human effort. We present a fast and automated deep-learning method to construct simulation-suitable models of the heart from medical images. The approach constructs meshes from 3D patient images by learning to deform a small set of deformation handles on a whole heart template. For both 3D CT and MR data, this method achieves promising accuracy for whole heart reconstruction, consistently outperforming prior methods in constructing simulation-suitable meshes of the heart. When evaluated on time-series CT data, this method produced more anatomically and temporally consistent geometries than prior methods, and was able to produce geometries that better satisfy modeling requirements for cardiac flow simulations. Our source code and pretrained networks are available at https://github.com/fkong7/HeartDeformNets.

eess.IV↗

arXiv2019

Simulation of Cardiac Flow: Analysis of Geometry Simplification

Cardiovascular diseases (CVDs) are the leading causes of mortality worldwide. The contraction and relaxation of left ventricle (LV) is the main driving force of blood circulation. Altered LV hemodynamics is believed to be associated with the initiation and progression of many CVDs. Thus, understanding and evaluating the flow pattern inside a patient LV is thought to be essential to capture, and subsequently treat, cardiovascular dysfunction at early stages to reduce the mortality and morbidity rates. Computational fluid dynamics (CFD) models, often derived from patient-specific medical imaging, have been used to provide a more fundamental understanding of individual LV flow patterns and pressure fields. Such image-based modeling may advance diagnostic capabilities, treatment protocols and help guide clinicians to choose the most effective therapy of CVDs. Most prior ventricular flow studies obtained LV wall geometries from in vivo ultrasound-based or cardiac magnetic resonance imaging (MRI) images with limited resolution. The model geometries were often highly simplified and usually lacked the papillary muscles (PM) and the corrugated trabecular structures of the LV. Since the LV flow pattern is sensitive to geometry, it is important to understand the effect of this simplification on modeling intraventricular flow and pressure. Here we apply CFD modeling to a subject-specific porcine LV model with detailed ventricular structures and motion obtained from previous solid mechanics finite-element (FE) simulations based on high-resolution image data. We simplified the detailed LV endocardial surfaces to remove PM and trabecular structures and built a smoothed model that resembles the resolution of in vivo MRI images. We then compare the simulated LV flow pattern and pressure of the simplified models to those of the complex model.

physics.med-ph↗