KR-20260066510-A - Method and system for blood vessel classification of coronary artery

Abstract

A method for classifying coronary artery vessels is disclosed. The method for classifying coronary artery vessels according to the present invention comprises: a step of dividing the aorta and the coronary artery from a computed tomography image; a step of determining two coronary arteries that are distinct from the aorta; a step of selecting one of the two coronary arteries and classifying it as the right coronary artery; a step of determining two branches for the other of the two coronary arteries and classifying the two branches as the left anterior descending artery and the left circumflex artery based on the branching direction of the branches.

Inventors

• 박지용
• 김영인
• 김판기

Assignees

• 주식회사 팬토믹스

Dates

Publication Date

20260512

Application Date

20241104

Claims (6)

1. In a method for classifying coronary artery vessels using at least one processor, Step of segmenting the aorta and coronary arteries from computed tomography images; Step of determining two coronary arteries distinct from the aorta; a) Step of selecting one of the two coronary arteries above and classifying it as the right coronary artery (RCA); A method for classifying coronary arteries, characterized by including: b) determining two branches for the other of the two coronary arteries and classifying the two branches into the left anterior descending artery (LAD) and the left circumflex artery (LCX) based on the branching direction of the branches.
2. In paragraph 1, Step a) above is, A step of determining the center of gravity of the two coronary arteries; and A method for classifying coronary arteries, characterized by including the step of classifying the right coronary artery based on the position of the center of gravity.
3. In paragraph 1, The above step b) is, c) Step for determining the branch point; A step of defining a first vector and a second vector, which are directions for each branch from the branch point; and A method for classifying coronary arteries, characterized by including the step of distinguishing the left anterior descending artery (LAD) and the left circumflex artery (LCX) based on the external product result of the first vector and the second vector.
4. In paragraph 3, The method further includes the step of determining the centerline of the coronary artery; The above step c) is, A step of searching for the existence of a branch along the above centerline; A step of determining the length of the branch if the above branch exists; and A method for classifying coronary artery blood vessels, characterized by including the step of determining whether there is a branch and the branch point by comparing the length of the branch above with a preset value.
5. In paragraph 3, A step of determining the first seed point of the above right coronary artery; A step of determining a second seed point of the left anterior descending artery and a third seed point of the left circumflex artery; and A method for classifying coronary arteries, further comprising the step of determining centerline information of the main blood vessel based on the first to third seed points, respectively.
6. processor; and Includes a storage unit in which computed tomography images are recorded; and The above processor is, Segment the aorta and coronary arteries from computed tomography images, Determine two coronary arteries distinct from the above aorta, and Select one of the two coronary arteries mentioned above and classify it as the right coronary artery (RCA), and A coronary artery vascular classification system characterized by determining two branches for one of the two coronary arteries and classifying the two branches into the left anterior descending artery (LAD) and the left circumflex artery (LCX) based on the branching direction of the branches.

Description

Method and system for blood vessel classification of coronary artery The present invention relates to a method and system for classifying coronary artery blood vessels. Since stenosis in the cardiovascular system can lead to fatal diseases such as angina and myocardial infarction, it is necessary to identify warning signs of stenosis and prepare in advance to prevent such diseases. The coronary arteries are connected to the aorta and consist of three major branches: the right coronary artery (RCA), the left anterior descending artery (LAD), and the left circumflex artery (LCX), which branch off from the left coronary artery. Since the treatment site varies depending on which of these three vessels the stenosis occurs in, distinguishing them is an important technical task. Extracting the centerline of the blood vessel is an important task in generating a 2D curved MPR (Multi Planar Reconstruction) based on 3D CT images. Curved MPR (Multi-Planar Reconstruction) is a two-dimensional planar image extracted from multiple angles of a three-dimensional computed tomography (CT) image (hereinafter also referred to as a ‘CT image’). Curved MPR is useful for diagnosing conditions such as stenosis of the heart blood vessels. In the observation of coronary arteries, the generation of high-quality curved MPR images is an important basis for determining the three-dimensional position of the coronary artery centerline. Figure 1 shows a coronary artery blood vessel classification system according to an embodiment of the present invention. Figure 2 shows a method for classifying coronary arteries according to an embodiment of the present invention. Figure 3 shows in detail a part of the configuration of a method for classifying coronary arteries according to an embodiment of the present invention. Figure 4 schematically shows the key points in the coronary artery blood vessel classification method. Figure 5 schematically shows the directions of the first vector and the second vector. The present invention is capable of various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. In describing the present invention, if it is determined that a detailed description of related known technology may obscure the essence of the present invention, such detailed description is omitted. Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. FIG. 1 shows a coronary artery blood vessel classification system (100) (hereinafter also briefly referred to as ‘system (100)’) according to one embodiment of the present invention. Referring to FIG. 1, the coronary artery blood vessel classification system (100) includes a processor (110), a memory (120), and a communication unit (130). The processor (110) is for performing information processing related to the classification of coronary arteries and may include at least one processor. The processor (110) may include at least one of a Central Processing Unit, a Graphic Processing Unit, a Micro Processor, and a processor dedicated to artificial intelligence, and the type and number of processors are not limited thereto as long as they perform the functions of the present invention. Memory (120) can have a program written to it, which is a set of data and executable instructions that can be read or written by the processor (110). The memory (120) includes non-volatile memory that can store data (information) regardless of whether power is provided, and volatile memory in which data to be processed by the processor (110) is loaded and data cannot be stored if power is not provided. Non-volatile memory includes flash memory, HDD (hard-disc drive), SSD (solid-state drive), ROM (Read Only Memory), etc., and volatile memory includes buffer, RAM (Random Access Memory), etc. The memory (120) may record a neural network model or an image processing algorithm for segmenting the aorta and coronary arteries from a CT image. The memory (120) can be programmed and recorded with an algorithm to distinguish between different blood vessels of the coronary artery. The different blood vessels of the coronary artery refer to the three vessels formed by the right coronary artery (RCA), the left anterior descending artery (LAD), and the left circumflex artery (LCX), which branch off from the left coronary artery. The memory (120) may record information regarding the first to third seed points for each different blood vessel. The information regarding the seed points may be information in three-dimensional coordinates. The communication unit (130) can operate under the control of the processor (110) to transmit and receive information with an ext