A coronary blood vessel segmentation method and system

Abstract

The invention discloses a coronary blood vessel segmentation method and system. The method comprises the following steps of: acquiring coronary vessel data; using coronary artery segmentation model and vein segmentation model to segment and extract the coronary artery data, and obtaining the results of coronary artery segmentation and vein segmentation; determining bifurcation branches in the segmentation results of coronary arteries and venous branches in the segmentation results of veins; detecting whether there are bifurcation branches in the coronary artery segmentation results matching the vein branches in the vein segmentation results; if there is a bifurcation branch in the coronary artery segmentation result that matches the vein branch in the vein segmentation result, the bifurcation branch is deleted. Thus, when coronary artery segmentation is performed, by matching and sharing the coronary artery segmentation result and the vein segmentation result at the interference position of the vein image, the corresponding vein branches in the coronary artery segmentation result can be deleted, accurate coronary artery map can be obtained, and better coronary artery segmentation can be realized.

Description

technical field [0001] The invention relates to the technical field of medical imaging, in particular to a coronary vessel segmentation method and system. Background technique [0002] In recent years, the global incidence of coronary heart disease has continued to rise, and interventional therapy, surgery and drug therapy for coronary heart disease have developed rapidly. Both doctors and patients have a dependence and expectation on the surgical treatment of coronary heart disease, which can be seen from the increasing number of patients with coronary artery revascularization around the world, and this technology has been widely accepted and recognized. Therefore, coronary artery reconstruction has become the most commonly used and most important method in the treatment of coronary artery disease, which has important clinical value and practical significance. [0003] However, the problem of venous image interference (that is, entanglement of veins) in coronary artery seg...

AI Technical Summary

Problems solved by technology

[0003] However, the problem of venous image interference (i.e. venous entanglement) in coronary artery segmentation has always troubled doctors and patients

Especially when the separability of the arteries and veins is poor, it is difficult to directly separate the arteries and veins at the place where the image interferes, regardless of the traditional method or the neural network method, which will bring great difficulties to the segmentation and reconstruction of the coronary arteries.

Images