Shape Deformation Networks for Automated Aortic Valve Finite Element Meshing from 3D CT Images
Linchen Qian, Jiasong Chen, Ruonan Gong, Wei Sun, Minliang Liu, Liang Liang
TL;DR
This work tackles the challenge of producing patient-specific aortic valve meshes that are both high-quality and consistently correspondent across patients. It introduces a template-fitting, quad-mesh remeshing pipeline that preprocesses ground-truth surfaces to a common quad template, enabling a simplified two-term loss for neural networks to reconstruct valve geometries. Using UNet-GCN and UNet-Disp architectures, the approach achieves higher accuracy and more reliable mesh quality than traditional unstructured-tri-mesh methods, with APPD around $2.15$–$2.18$ mm and improved landmark localization for hinges and commissures. The resulting FE-ready quad meshes facilitate cross-patient comparisons and efficient biomechanical simulations, offering a practical path toward automated, clinical-grade aortic valve modeling.
Abstract
Accurate geometric modeling of the aortic valve from 3D CT images is essential for biomechanical analysis and patient-specific simulations to assess valve health or make a preoperative plan. However, it remains challenging to generate aortic valve meshes with both high-quality and consistency across different patients. Traditional approaches often produce triangular meshes with irregular topologies, which can result in poorly shaped elements and inconsistent correspondence due to inter-patient anatomical variation. In this work, we address these challenges by introducing a template-fitting pipeline with deep neural networks to generate structured quad (i.e., quadrilateral) meshes from 3D CT images to represent aortic valve geometries. By remeshing aortic valves of all patients with a common quad mesh template, we ensure a uniform mesh topology with consistent node-to-node and element-to-element correspondence across patients. This consistency enables us to simplify the learning objective of the deep neural networks, by employing a loss function with only two terms (i.e., a geometry reconstruction term and a smoothness regularization term), which is sufficient to preserve mesh smoothness and element quality. Our experiments demonstrate that the proposed approach produces high-quality aortic valve surface meshes with improved smoothness and shape quality, while requiring fewer explicit regularization terms compared to the traditional methods. These results highlight that using structured quad meshes for the template and neural network training not only ensures mesh correspondence and quality but also simplifies the training process, thus enhancing the effectiveness and efficiency of aortic valve modeling.