AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface Generation

2025-07-16

AI Summary

Existing methods rely heavily on large-scale annotated datasets and manual intervention, hindering the generation of geometrically consistent, structurally complete, and CFD-compatible 3D aortic surface models. To address this, we propose AortaDiff: an end-to-end framework based on a volume-guided conditional diffusion model that directly synthesizes smooth, high-fidelity triangular meshes of the aorta from CT or MRI volumetric data. Its core innovation lies in jointly learning centerline extraction and cross-sectional contour prompting, followed by 3D surface fitting to produce CFD-ready meshes—significantly reducing dependence on labeled data. Under few-shot settings, AortaDiff robustly reconstructs both normal and pathological aortic morphologies (e.g., aneurysms, coarctation), achieving superior geometric consistency. The resulting models support high-quality visualization and accurate hemodynamic simulation, establishing a novel paradigm for clinical diagnosis, preoperative planning, and computational medicine.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate 3D aortic construction is crucial for clinical diagnosis, preoperative planning, and computational fluid dynamics (CFD) simulations, as it enables the estimation of critical hemodynamic parameters such as blood flow velocity, pressure distribution, and wall shear stress. Existing construction methods often rely on large annotated training datasets and extensive manual intervention. While the resulting meshes can serve for visualization purposes, they struggle to produce geometrically consistent, well-constructed surfaces suitable for downstream CFD analysis. To address these challenges, we introduce AortaDiff, a diffusion-based framework that generates smooth aortic surfaces directly from CT/MRI volumes. AortaDiff first employs a volume-guided conditional diffusion model (CDM) to iteratively generate aortic centerlines conditioned on volumetric medical images. Each centerline point is then automatically used as a prompt to extract the corresponding vessel contour, ensuring accurate boundary delineation. Finally, the extracted contours are fitted into a smooth 3D surface, yielding a continuous, CFD-compatible mesh representation. AortaDiff offers distinct advantages over existing methods, including an end-to-end workflow, minimal dependency on large labeled datasets, and the ability to generate CFD-compatible aorta meshes with high geometric fidelity. Experimental results demonstrate that AortaDiff performs effectively even with limited training data, successfully constructing both normal and pathologically altered aorta meshes, including cases with aneurysms or coarctation. This capability enables the generation of high-quality visualizations and positions AortaDiff as a practical solution for cardiovascular research.

Problem

• Generates 3D aortic surfaces from CT/MRI volumes
• Reduces dependency on large annotated datasets
• Produces CFD-compatible meshes with high fidelity

Innovation

• Volume-guided conditional diffusion model for aortic centerlines
• Automatic contour extraction from centerline points
• Smooth 3D surface fitting for CFD-compatible meshes