Method for judging coronary artery branches in coronary artery segmentation of image and converting mask data into center line point set

A branch and coronary artery technology, which is applied in the field of coronary artery segmentation and the conversion of mask data into centerline point sets, can solve problems such as overgrowth, achieve accurate display, avoid overgrowth, and improve image processing. The effect of precision

Active Publication Date: 2019-11-15
心医国际数字医疗系统(大连)有限公司
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] 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 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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for judging coronary artery branches in coronary artery segmentation of image and converting mask data into center line point set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0017] Embodiment 1: a kind of heart coronary artery segmentation and centerline extraction method, comprises the following steps:

[0018] S1. Input cardiac CTA data.

[0019] S2, dividing the ascending aorta. In order to facilitate coronary artery positioning, the ascending aorta needs to be automatically segmented first, and then follow-up operations are performed based on the ascending aorta information.

[0020] Among them, the following methods are involved:

[0021] (1) The present invention proposes to automatically identify the region of interest for single-layer search of the ascending aorta. Choose a reasonable threshold, binarize the image, calculate the cumulative value of each row and each column image by row and column respectively, and find the region of interest for searching the ascending aorta through the inflection point of the histogram distribution.

[0022] (2) Find the first seed point of the ascending aorta and calculate the ascending aorta segmenta...

Embodiment 2

[0048] Embodiment 2: according to the technical scheme recorded in embodiment 1, the specific scheme is described as follows:

[0049] Step S1 is the CTA data body input from the outside.

[0050] In step S2, according to the characteristics of human tissue, the ascending aorta can assist in locating the coronary artery region, so the ascending aorta is segmented first, and this sum and step may not be required if there are other methods for positioning. In the present invention, the following two steps are used for the segmentation of the ascending aorta:

[0051](1) A method for automatically identifying the region of interest in the ascending aorta is proposed. Since the ascending aorta and the descending aorta are both circular in cross section, in order to remove the interference of the descending aorta and narrow the scope of the detection, the region of interest of the ascending aorta was identified first. Since the ascending aorta is generally located in the upper ha...

Embodiment 3

[0096] Embodiment 3: A kind of automatic coronary artery segmentation and centerline extraction method based on CTA image, including

[0097] S1. Input cardiac CTA data;

[0098] S2. Divide the ascending aorta;

[0099] S3. Coronary seed point search;

[0100] S4. Coronary segmentation;

[0101] S5. Coronary center point extraction.

[0102] Further, the step S2. dividing the ascending aorta includes:

[0103] S2.1 identifying the ascending aorta ROI;

[0104] S2.2 Find the ascending aorta seed point;

[0105] S2.3 Divide the ascending aorta.

[0106] The step S2.1 identifies the ascending aorta ROI:

[0107] Take the upper layer data of the CTA data, after confirming the selected layer, take out the two-dimensional data Img_Aorta corresponding to this layer;

[0108] Determine the segmentation threshold T_Ori according to the conventional range of CT values ​​of the ascending aorta, and apply the threshold T_Ori to segment the two-dimensional data Img_Aorta to obtain ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for judging coronary artery branches in coronary artery segmentation of an image and converting mask data into a center line point set. The invention discloses a coronary artery image segmentation method based on hierarchical clustering, belongs to the field of cardiac coronary artery image processing, and aims to solve the problem of coronary artery branches in coronary artery segmentation of an image, select seed points for interlayer region growth, use a hierarchical clustering method to take a set of points grown in each layer of region as a current point set in the growth process, and perform clustering under the condition that the Euclidean distance is smaller than a threshold; when the clustering number is greater than or equal to 2, the point set number n < um _ max > of the maximum cluster is taken, and the total number of the current point sets is n < um _ total >; whether the num _ max/num _ total ratio falls into the interval of (0.4, 0.75)or not serves as the condition for judging whether branches exist or not, the effect is that the branches can be recognized and judged in the image data, the branches grow in sequence, the overgrowthphenomenon can be avoided, and the image processing precision is improved.

Description

technical field [0001] 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 [0002] 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. [0003] Coronary angiography (CTA, CT angiography) is an important method for the diagnosis of heart diseases. Accurately segmenting coronary vessels from CTA data can not only provide a quantitative description of the vascular structure, but also observe and compare the geometric changes of the vessels, which is helpful for the diagnosis of diseases. Diagnosis and tre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/11G06T7/136G06T7/66G06K9/32G06K9/34G06K9/62
CPCG06T7/11G06T7/136G06T7/66G06T2207/10081G06T2207/30101G06T2207/30048G06T7/62G06T2207/20061G06T2207/20024G06V10/25G06F18/231
Inventor 王兴维邰从越刘龙王慧刘慧芳史黎鑫
Owner 心医国际数字医疗系统(大连)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap