KR-20260066511-A - Method and system for classifying the main vessels of the coronary artery

Abstract

A method for distinguishing the main blood vessels of a coronary artery is disclosed. The method for distinguishing the main blood vessels of a coronary artery according to the present invention comprises: a step of generating segmentation information by segmenting the aorta and the coronary artery from a computed tomography image; a step of generating first framework information by extracting a centerline from the segmentation information of the coronary artery; a step of determining a first seed point for the coronary artery; a step of determining all endpoints connected to the first seed point; a step of determining the shortest path for each endpoint connected to the first seed point; and a step of determining the centerline corresponding to the longest path among the shortest paths as the centerline for the main blood vessel.

Inventors

• 박지용
• 김영인
• 김판기

Assignees

• 주식회사 팬토믹스

Dates

Publication Date

20260512

Application Date

20241104

Claims (6)

1. In a method for at least one processor to distinguish the main vessels of the coronary arteries, A step of generating segmentation information for segmenting the aorta and coronary arteries from computed tomography images; A step of generating first skeletal information by extracting a centerline from the segmentation information of the coronary artery above; Step of determining a first seed point for the coronary artery; A step of determining all endpoints connected to the first seed point; A step of determining the shortest path for each endpoint connected to the first seed point; and The method includes the step of determining the centerline corresponding to the longest path among the shortest paths as the centerline for the main blood vessel; A method for distinguishing the main blood vessels of a coronary artery, characterized in that the above path is determined based on the centerline of the above first framework information.
2. In paragraph 1, The method further includes the step of determining a second seed point of the aorta and generating second framework information connected to the coronary artery; A method for distinguishing the main blood vessels of a coronary artery, characterized in that the determination of the shortest path above is for the path from the second seed point to the end point above.
3. In paragraph 1, A method for distinguishing the main blood vessels of coronary arteries, characterized in that the first seed point of the left anterior descending artery or the left circumflex artery is determined as a branch point of the coronary arteries or a point adjacent to a branch point.
4. In a method for at least one processor to distinguish the main vessels of the coronary arteries, A step of generating segmentation information for segmenting the aorta and coronary arteries from computed tomography images; A step of generating skeletal information by extracting a centerline from the segmentation information of the coronary artery above; Step to determine the seed point for the coronary artery; A step of searching for neighboring points while moving until there are no neighboring points, excluding the path traversed from the above seed point; and A method for distinguishing the main blood vessels of a coronary artery, characterized by including the step of selecting a point to move to based on the curvature calculation result and moving it when there are two or more adjacent points excluding the path traversed.
5. In paragraph 4, A method for distinguishing the main blood vessels of a coronary artery, characterized in that the above curvature is determined by three points: the average coordinate of n points passed, the current point, and the average coordinate of n points in the branched direction (where n≥2).
6. processor; and Includes a storage unit in which computed tomography images are recorded; and The above processor is, Generate segmentation information for segmenting the aorta and coronary arteries from computed tomography images, and A first skeletal information is generated by extracting a centerline from the above coronary artery segmentation information, and Determine the first seed point for the coronary artery, and Determine all endpoints connected to the above-mentioned first seed point, and Determine the shortest path for each endpoint connected to the first seed point, and The centerline corresponding to the longest path among the above shortest paths is determined as the centerline for the main blood vessel, A coronary artery main vessel classification system characterized in that the above path is determined based on the centerline of the above first skeletal information.

Description

Method and system for classifying the main vessels of the coronary artery The present invention relates to a method and system for distinguishing the main blood vessels of coronary arteries. 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. Coronary arteries can be divided into main vessels and several branches. The main vessels may include the right coronary artery (RCA), which is one of the three major branches of the coronary artery, and the left anterior descending artery (LAD) and left circumflex artery (LCX), which are formed by branching out from the left main coronary artery. First, distinguishing the major coronary arteries forms the basis for distinguishing the different coronary arteries and their branches in a three-dimensional image. FIG. 1 shows a main blood vessel classification system for coronary arteries according to an embodiment of the present invention. FIG. 2 shows a method for distinguishing the main blood vessels of a coronary artery according to the first embodiment of the present invention. Figure 3 shows a method for distinguishing the main blood vessels of a coronary artery according to a second embodiment of the present invention. FIG. 4 exemplarily shows seed points and endpoints selected on a centerline in the first embodiment of the present invention. Figure 5 shows an example to help understand the selection of the shortest path in the first embodiment. FIG. 6 exemplarily shows a point and a related vector for determining curvature in a second embodiment of the present invention. Figure 7 shows the centerline of the main blood vessel extracted according to an embodiment of the present invention, along with the outline of the aorta. 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 main blood vessel classification system (100) of a coronary artery according to one embodiment of the present invention (hereinafter also briefly referred to as ‘system (100)’). Referring to FIG. 1, the coronary artery main 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 main blood vessel classification 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 a processor 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) can be programmed and recorded with the algorithm of the present invention for searching for the main blood vessel. The memory (120) may record information regarding a skeletal structur