Microvessel tree generation method based on conditional generative adversarial network and constraint rule

Abstract

The invention provides a capillary tree generation method based on a conditional generative adversarial network and a constraint rule. The method is based on the conditional generative adversarial network, wherein a capillary tree new model is established through the conditional generative adversarial network, and a next-level bifurcation is generated by using a previous-level bifurcation weakening condition. According to the mode, the microvascular tree can be generated only by forking the entrance and exit and growing step by step. Meanwhile, optimization conditions of the blood vessel density and the bifurcation angle are added in the growth process, the growth angle can be corrected carefully, the capillary tree with the more uniform blood vessel density can be obtained in the growth process, and the physiological requirements of the capillary network in the oxygen conveying and nutrient substance metabolism process are better met; thus, the generated capillary tree not only accords with morphological characteristics, but also indirectly accords with part of physiological characteristics.

Description

technical field [0001] The invention relates to a microvascular tree generation method based on conditional generation confrontation network and constraint rules, which belongs to the field of biomedicine. Background technique [0002] Angiogenesis is an important link in the development of vascular network. It is a process in which blood vessels grow and develop into vascular trees and vascular networks from scratch and even under the action of a series of physiological needs such as blood flow, metabolism, and material exchange. An important process of excreting metabolites. Studying the mechanism of vascular network neogenesis is of great significance to many research fields. However, vascular network neogenesis is a physiological process involving multiple time scales. It is difficult to observe short and long-term physiological processes at the same time by controlling experimental conditions in animal experiments, and the process of obtaining a real microvascular net...

AI Technical Summary

Problems solved by technology

However, vascular network neogenesis is a physiological process involving multiple time scales. It is difficult to observe short and long-term physiological processes at the same time by controlling experimental conditions in animal experiments, and the process of obtaining a real microvascular network is difficult and complicated.

Traditional methods are mostly based on statistics and fractal theory to generate microvascular trees. The generated microvascular trees have high homogeneity and cannot reflect the real microvascular tree structure with high heterogeneity.

Images