Related Experiment Video
Updated: Jun 25, 2025
06:36
An In Vitro 3D Model and Computational Pipeline to Quantify the Vasculogenic Potential of iPSC-Derived Endothelial Progenitors
Published on: May 13, 2019
6.1K
3DVascNet: An Automated Software for Segmentation and Quantification of Mouse Vascular Networks in 3D
Hemaxi Narotamo1,2,3, Margarida Silveira1, Cláudio A Franco2,3
1Instituto de Sistemas e Robótica, LARSyS, Instituto Superior Técnico (H.N., M.S.), Universidade de Lisboa, Lisbon, Portugal.
Arteriosclerosis, Thrombosis, and Vascular Biology
|May 23, 2024
Summary
3DVascNet is a new deep learning software that automates the analysis of 3D vascular networks, overcoming limitations of 2D methods. This tool enables efficient and accurate quantification of blood vessel structures in health and disease.
Area of Science:
- Biomedical Engineering
- Computational Biology
- Image Analysis
Background:
- Analysis of vascular networks is crucial for understanding blood vessel physiology and pathology.
- Current methods rely on 2D projections of 3D networks, which distort geometry and connectivity.
- Manual 3D analysis is time-consuming and impractical for large datasets.
Purpose of the Study:
- To develop an automated software solution for 3D vascular network analysis.
- To overcome the limitations of existing 2D projection and manual analysis methods.
- To provide a user-friendly tool for researchers studying vascular networks.
Main Methods:
- Developed 3DVascNet, a deep learning-based software for automated segmentation and quantification.
- Utilized a deep learning model for segmenting 3D retinal vascular networks.
- Quantified morphometric parameters including vessel density, branch length, radius, and branching points.
Main Results:
- 3DVascNet efficiently segments 3D vascular networks.
- Quantified parameters accurately reflect phenotypes identified by manual 2D analysis.
- The software demonstrates high generalization capability across different datasets and organs.
Conclusions:
- 3DVascNet is a freely available, user-friendly software for 3D vascular network analysis.
- It facilitates the study of vascular networks in both health and disease.
- The open-source nature allows for extension to other 3D vascular network analyses.
