Method for converting extracted mask data containing coronary artery center line into center line point set

Abstract

A method for converting extracted mask data containing a coronary artery center line into a center line point set comprises the steps that a root node is recognized, only one connected point exists in multiple neighborhoods, and a first point located at the highest point in the vertical direction serves as the root node and serves as a first determination point after conversion; multiple neighborhood connection points are sequentially tracked, a sampling rule that two points are spaced by a certain distance D is set and when the distance between the connection point to be judged and the previous determined point is smaller than D, the point is not put into the determined point list and directly jumps to the next connection point; when it is judged that the distance between the connection point and the previous determined point is larger than D, the point is put into a determined point list, and the father node relation of the point is recorded; when the connection points are judged to have branches, putting the branches into a determined point list no matter whether the distance requirement is met or not; when it is judged that only one connection point in front of the connection point exists, the connection point is a termination point of the branch; according to a conversion method, the logic relation between the points is defined, classification and judgment are carried out, and therefore accurate display of the image is achieved.

Description

[0001] This application is a divisional application with the application number 2019106025823, the application date is July 5, 2019, and the title of the invention is "Method for Converting Coronary Branches and Mask Data into Centerline Point Sets in Judging Image Coronary Segmentation". technical field [0002] The invention belongs to the field of cardiac coronary image processing, and relates to a method for automatic coronary segmentation and central line extraction based on CTA images, and a method for converting coronary branch and mask data into a central line point set in the coronary segmentation of judging images. Background technique [0003] Cardiovascular disease has become an important disease that threatens human life. How to quickly and accurately diagnose cardiovascular disease has become the key to treatment. Cardiovascular disease is mostly caused by coronary artery disease. [0004] Coronary angiography (CTA, CT angiography) is an important method for th...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the problem of judging the coronary artery branch in the coronary artery segmentation of the image and avoid the overgrowth phenomenon, the present invention proposes a method for judging the coronary artery branch in the coronary artery segmentation of the image. In , use the hierarchical clustering method to use the set of points grown in each layer of the region as the current point set, and cluster with the condition that the Euclidean distance is less than the threshold; when the number of clusters is greater than or equal to 2, take the number of point sets in the largest cluster num_max, the total number of the current point set is num_total; whether the ratio of num_max / num_total falls into the interval of (0.4,0.75) is used as the condition for judging whether there is a branch. If the ratio falls into this interval, it is considered that there is a branch, and the largest cluster is one of the branches , other point sets are branches on the other side, if the ratio does not fall into this interval, it is considered that there is no branch, and all current points are set as one cluster

Images