Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation

2025-06-24

AI Summary

Medical image synthesis for vascular structure modeling faces two key challenges: pixel-level methods struggle to preserve geometric continuity (e.g., vessel discontinuities and unnatural curvatures), and the scarcity of paired X-ray angiography data hinders supervised learning. To address these, we propose the first geometry-aware diffusion framework for unpaired data, integrating a parametric vascular model with a mask-guided adversarial discriminator for non-contrast-to-contrast X-ray modality translation. Our method models the vascular distribution via diffusion, leveraging centerline topology and radius profiles as geometric priors to enforce structural fidelity in generated images. Evaluated on both public and private datasets, it achieves state-of-the-art performance—improving vessel connectivity by 23.6% and yielding significantly more natural curvature than GAN- and VAE-based baselines. We further release the first reproducible vascular synthesis benchmark dataset and open-source code.

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

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.

Problem

• Translate non-angiographic X-rays to angiographic X-rays
• Overcome lack of paired large-scale angiography datasets
• Improve geometric accuracy in vascular image synthesis

Innovation

• Self-supervised adversarial diffusion model for angiographic synthesis
• Parametric vascular model enhances geometric accuracy
• Mask-based adversarial module improves vessel synthesis