Related Experiment Video
Updated: Jun 27, 2025
10:53
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
Published on: January 3, 2017
9.9K
In Silico Design of Heterogeneous Microvascular Trees Using Generative Adversarial Networks and Constrained
Qing Pan1, Huanghui Shen1, Peilun Li2
1College of Information Engineering, Zhejiang University of Technology, Hangzhou, China.
Microcirculation (New York, N.Y. : 1994)
|May 1, 2024
Summary
This study introduces a novel method for generating realistic microvascular trees using a deep learning approach combined with fractal dimension optimization. The artificial trees accurately mimic the complexity of biological vascular networks for tissue engineering and simulations.
Area of Science:
- Bioengineering
- Computational Biology
- Biomedical Engineering
Background:
- Designing physiologically adequate microvascular trees is critical for bioengineering functional tissues and organs.
- Current methods struggle to replicate the heterogeneity of real microvascular trees due to simplistic control parameters.
Purpose of the Study:
- To develop a method for generating artificial microvascular trees that accurately mimic in vivo complexity.
- To overcome limitations of existing methods in replicating morphological and topological heterogeneity.
Main Methods:
- Integration of a conditional deep convolutional generative adversarial network (cDCGAN) with a local fractal dimension-oriented constrained constructive optimization (LFDO-CCO) strategy.
- The cDCGAN learns patterns of real microvascular bifurcations for artificial replication.
- LFDO-CCO connects generated bifurcations hierarchically to achieve realistic vessel density.
Main Results:
- Generated artificial microvascular trees exhibit consistency with real trees in fractal dimension and vascular density.
- Key characteristics like diameter, length, and tortuosity variation are accurately replicated.
- The method successfully generates microvascular trees with physiologically relevant parameters.
Conclusions:
- The proposed strategy effectively generates artificial microvascular trees mirroring biological complexity.
- This approach supports advancements in tissue engineering and computational modeling of microcirculation.
- The findings enable more accurate simulations of microcirculatory physiology.
