Shape Deformation Networks for Automated Aortic Valve Finite Element Meshing from 3D CT Images

2025-11-05

AI Summary

To address inter-subject inconsistencies in aortic valve finite element modeling—including irregular mesh topology, poor element quality, and lack of anatomical correspondence—this paper proposes a deep neural network-based template-fitting framework. The method employs a unified parameterized quadrilateral mesh template and leverages a shape-deformation network to achieve end-to-end generation of structured meshes directly from 3D CT images, ensuring strict node- and element-wise correspondence across subjects. A composite loss function integrating geometric reconstruction fidelity and smoothness regularization enables joint optimization, eliminating the need for complex post-processing. Experimental results demonstrate that the generated meshes exhibit superior element quality and surface smoothness, significantly improved modeling consistency across patients, and complete automation—requiring neither manual intervention nor iterative optimization—thereby substantially enhancing modeling efficiency.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Generating high-quality aortic valve meshes from 3D CT images
• Ensuring consistent mesh correspondence across different patients
• Overcoming irregular topologies in traditional triangular mesh approaches

Innovation

• Template-fitting pipeline with deep neural networks
• Structured quad meshes from 3D CT images
• Simplified loss function with two regularization terms