Hierarchical Part-based Generative Model for Realistic 3D Blood Vessel

2025-07-20

AI Summary

Existing methods struggle to accurately model complex 3D vascular geometries—particularly multi-level branching, pronounced curvatures, and local irregularities—due to coupled topological and geometric constraints. To address this, we propose the first hierarchical part-based generative framework for 3D vascular modeling. Our approach decouples global tree-like topology from local geometric details: (1) a topology-critical graph is generated first; (2) high-fidelity vascular segments are then synthesized conditionally on geometric attributes; and (3) segments are hierarchically assembled into a complete reconstruction. Technically, the framework integrates graph generation models, conditional GANs, and geometry-guided segment modeling. Extensive experiments on real vascular datasets demonstrate that our method significantly outperforms state-of-the-art approaches in topological consistency, geometric accuracy, and structural diversity. It establishes a new benchmark for medical image synthesis and computational angiology.

Technology Category

• Computer Vision: Segmentation
• 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: Web data generation and simulation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Advancements in 3D vision have increased the impact of blood vessel modeling on medical applications. However, accurately representing the complex geometry and topology of blood vessels remains a challenge due to their intricate branching patterns, curvatures, and irregular shapes. In this study, we propose a hierarchical part-based frame work for 3D vessel generation that separates the global binary tree-like topology from local geometric details. Our approach proceeds in three stages: (1) key graph generation to model the overall hierarchical struc ture, (2) vessel segment generation conditioned on geometric properties, and (3) hierarchical vessel assembly by integrating the local segments according to the global key graph. We validate our framework on real world datasets, demonstrating superior performance over existing methods in modeling complex vascular networks. This work marks the first successful application of a part-based generative approach for 3D vessel modeling, setting a new benchmark for vascular data generation. The code is available at: https://github.com/CybercatChen/PartVessel.git.

Problem

• Modeling complex 3D blood vessel geometry and topology
• Separating global binary tree-like structure from local details
• Generating realistic hierarchical vascular networks efficiently

Innovation

• Hierarchical part-based framework for 3D vessels
• Separates global topology from local geometry
• Three-stage generation: graph, segments, assembly