Synthetic Data for Blood Vessel Network Extraction

2025-04-16

AI Summary

In stroke research, microvascular network topology extraction from microscopy images faces two key challenges: scarcity of annotated data and low topological accuracy. To address these, this paper proposes a synthetic-data-driven method for automatic graph-structured vascular extraction. We introduce a novel three-stage biologically constrained synthetic pipeline—comprising graph generation, vessel mask synthesis, and medical image synthesis—that integrates imaging artifact modeling with volumetric image synthesis. Additionally, we design a 3D U-Net-based two-stage model to separately perform node detection and edge prediction. With only five real annotated samples, our approach boosts edge prediction F1-score from 0.496 to 0.626—a statistically significant improvement—enabling high-fidelity topological reconstruction of vascular graphs. This facilitates large-scale structural and functional analysis of cerebral vasculature, substantially advancing quantitative neurovascular phenotyping.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

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

Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential for analyzing blood flow dynamics. However, extracting detailed topological vessel network information from microscopy data remains a significant challenge, mainly due to the scarcity of labeled training data and the need for high topological accuracy. This work combines synthetic data generation with deep learning to automatically extract vessel networks as graphs from volumetric microscopy data. To combat data scarcity, we introduce a comprehensive pipeline for generating large-scale synthetic datasets that mirror the characteristics of real vessel networks. Our three-stage approach progresses from abstract graph generation through vessel mask creation to realistic medical image synthesis, incorporating biological constraints and imaging artifacts at each stage. Using this synthetic data, we develop a two-stage deep learning pipeline of 3D U-Net-based models for node detection and edge prediction. Fine-tuning on real microscopy data shows promising adaptation, improving edge prediction F1 scores from 0.496 to 0.626 by training on merely 5 manually labeled samples. These results suggest that automated vessel network extraction is becoming practically feasible, opening new possibilities for large-scale vascular analysis in stroke research.

Problem

• Extracting topological vessel networks from microscopy data
• Overcoming scarcity of labeled training data for vessel analysis
• Improving accuracy in blood flow dynamics research

Innovation

• Synthetic data generation mimics real vessel networks
• Three-stage pipeline creates realistic medical images
• Two-stage 3D U-Net models detect nodes and edges