Coronary artery center line generation method and device based on bidirectional coronary artery blood vessel tracking

Abstract

The invention provides a coronary artery center line generation method and device based on bidirectional coronary artery blood vessel tracking. The method comprises the steps that according to an input coronary artery mask, blood vessel starting points, located at the aortic sinus, of coronary artery blood vessels and all tail end points in a connected domain in the mask where all the starting points are located are extracted; coronary artery center lines are extracted by tracking coronary artery blood vessels from top to bottom from a starting point, and a coronary artery center line tree isconstructed; coronary vessels are tracked from bottom to top from the tail end point, and a coronary center line tree is complemented; removing blood vessel adhesion and vein center lines, and combining all extracted coronary artery center line trees to obtain a complete coronary artery center line.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for generating a coronary centerline based on bidirectional coronary vessel tracking. Background technique [0002] Coronary artery centerline extraction in cardiac CT (CCTA) images is a prerequisite for the assessment of stenosis and atherosclerotic plaque. The existing methods can be roughly divided into two categories: predictive tracking algorithm based on deep network; 3D skeleton extraction algorithm based on coronary mask. However, both methods have obvious deficiencies. Coronary tracking based on deep network prediction will lead to the loss of entire vessel branches due to incorrect prediction of coronary bifurcation points; 3D skeletons based on coronary mask extraction are often overly dependent on Accuracy of coronary artery segmentation, centerline extraction is not reliable in the presence of vascular adhesions or when veins are misidentified ...

AI Technical Summary

Problems solved by technology

However, both methods have obvious deficiencies. Coronary tracking based on deep network prediction will cause the entire vessel branch to be lost due to incorrect prediction of coronary bifurcation points; 3D skeletons based on coronary mask extraction often rely too much on Accuracy of coronary artery segmentation, unreliable centerline extraction in the presence of vascular adhesions or when veins are misidentified as coronary arteries

These unstable factors may affect the follow-up doctor's diagnosis of the disease

Images