WO2021097821A1

WO2021097821A1 - Method and device for extracting vascular centerline from two-dimensional coronary angiographic image

Info

Publication number: WO2021097821A1
Application number: PCT/CN2019/120343
Authority: WO
Inventors: 王之元; 刘广志; 曹文斌; 吴心娱
Original assignee: 苏州润迈德医疗科技有限公司
Priority date: 2019-11-19
Filing date: 2019-11-22
Publication date: 2021-05-27
Also published as: CN112132882A

Abstract

A method and device for extracting a vascular centerline from a two-dimensional coronary angiographic image, and a system. The method for extracting a vascular centerline from a two-dimensional coronary angiographic image comprises: extracting at least one vascular path line from a two-dimensional coronary angiographic image (S500); and selecting a vascular path line as a vascular centerline (S600). By first extracting at least one vascular path line from a two-dimensional coronary angiographic image and then obtaining a vascular centerline according to the vascular path line, the method has the advantages of rapid extraction, low difficulty, and high accuracy.

Description

Method and device for extracting blood vessel centerline from two-dimensional coronary angiography image

Technical field

The present invention relates to the technical field of coronary artery medicine, in particular to a method, a device, a coronary artery analysis system and a computer storage medium for extracting a blood vessel centerline from a two-dimensional coronary angiography image.

Background technique

The deposition of lipids and carbohydrates in human blood on the vascular wall will form plaques on the vascular wall, which will then cause vascular stenosis; especially the vascular stenosis that occurs near the coronary artery of the heart will cause insufficient blood supply to the myocardium and induce coronary heart disease Diseases such as angina and angina pectoris pose a serious threat to human health. According to statistics, there are currently about 11 million patients with coronary heart disease in my country, and the number of patients undergoing cardiovascular interventional surgery is increasing by more than 10% every year.

Although conventional medical detection methods such as coronary angiography CAG and computed tomography CT can show the severity of coronary artery stenosis, they cannot accurately evaluate coronary ischemia. In order to improve the accuracy of coronary vascular function evaluation, in 1993 Pijls proposed a new indicator of coronary vascular function through pressure measurement-Fractional Flow Reserve (FFR). After long-term basic and clinical research, FFR It has become the gold standard for functional evaluation of coronary stenosis.

Fractional flow reserve (FFR) usually refers to the myocardial blood flow reserve, which is defined as the ratio of the maximum blood flow that the diseased coronary artery can provide to the myocardium to the maximum blood flow when the coronary artery is completely normal. Studies have shown that the maximum congestion in the coronary artery In the state, the ratio of blood flow can be replaced by pressure. That is, the measurement of FFR value can be calculated by measuring the pressure at the distal end of coronary artery stenosis and the pressure at the proximal end of coronary artery stenosis through the pressure sensor under the state of maximum coronary congestion.

In the prior art, it is often necessary to extract the blood vessel centerline when calculating the blood vessel evaluation parameters through the blood vessel three-dimensional model. However, how to extract the blood vessel centerline, the extraction speed, and the accuracy have always been problems that technical personnel need to solve.

Summary of the invention

The present invention provides a method, device and system for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image, so as to solve how to extract the centerline of a blood vessel in the prior art. The speed and accuracy of extraction have always been the technical personnel need to solve problem.

In order to achieve the above objective, in the first aspect, the present application provides a method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image, which includes:

Extracting at least one blood vessel path line from the two-dimensional coronary angiography image;

One of the blood vessel path lines is selected as the blood vessel center line.

Optionally, the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, before the method for extracting at least one blood vessel path line from a two-dimensional coronary angiography image, further includes:

Read two-dimensional coronary angiography images;

Obtain the blood vessel segment of interest;

Pick the starting point and ending point of the blood vessel segment of interest;

The partial blood vessel area map corresponding to the start point and the end point is segmented from the two-dimensional coronary angiography image.

Optionally, the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, and the method for segmenting a local blood vessel area map corresponding to the starting point and ending point from the two-dimensional coronary angiography image Also includes:

Picking up at least one seed point of the blood vessel segment of interest;

Separate the two-dimensional contrast images between two adjacent points of the starting point, the seed point, and the end point to obtain at least two partial blood vessel region maps.

Optionally, the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the method for extracting at least one blood vessel path line from a two-dimensional coronary angiography image includes:

Extracting at least one local blood vessel path line from each of the local blood vessel area maps;

Connecting the corresponding local blood vessel path lines on each of the local blood vessel area maps to obtain at least one blood vessel path line.

Optionally, in the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the method for extracting at least one blood vessel local path line from the local blood vessel area map respectively includes:

Performing image enhancement processing on the local blood vessel region map to obtain a rough blood vessel map with strong contrast;

The rough blood vessel map is meshed, and at least one local path line of the blood vessel is extracted along the direction from the start point to the end point.

Optionally, the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the method of performing image enhancement processing on the partial blood vessel area map to obtain a rough blood vessel map with strong contrast includes:

In each local blood vessel region map, the blood vessel segment of interest is used as the foreground and other regions are used as the background to strengthen the foreground and weaken the background to obtain the rough blood vessel map with strong contrast.

Optionally, in the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the rough blood vessel map is meshed, and at least one line is extracted along the direction from the starting point to the ending point. The method of local route line of blood vessel includes:

Meshing the rough blood vessel diagram;

Along the blood vessel extending direction from the starting point to the ending point, search for the shortest time path between the starting point and the intersection on the surrounding n grids as the second point, and search for the second point and the surrounding The shortest time path of intersections on n grids is used as the third point, and the third point repeats the above steps until the shortest time path reaches the end point, where n is a positive integer greater than or equal to 1;

According to the search sequence, a line connecting the blood vessel extending direction from the starting point to the ending point is used to obtain at least one local path line of the blood vessel.

Optionally, in the above-mentioned method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the method for selecting one of the blood vessel path lines as the blood vessel centerline includes:

If there are two or more blood vessel path lines, the time taken for each blood vessel path line from the starting point to the ending point is summed;

The blood vessel path line with the least amount of time is taken as the blood vessel center line.

In a second aspect, the present application provides an apparatus for extracting a blood vessel centerline from a two-dimensional coronary angiography image, including: a blood vessel path unit and a blood vessel centerline extraction unit connected in sequence;

The blood vessel path unit is used to extract at least one blood vessel path line from a two-dimensional coronary angiography image;

The blood vessel centerline extraction unit is configured to select one of the blood vessel path lines sent by the blood vessel path module as the blood vessel centerline.

Optionally, the above-mentioned apparatus for extracting a blood vessel centerline from a two-dimensional coronary angiography image further includes: an image segmentation unit connected to the blood vessel path unit;

The image segmentation unit is used to segment the local blood vessel area map corresponding to the start point and the end point from the two-dimensional coronary angiography image, or to determine the start point, the seed point, and the two adjacent points of the end point. Segmentation of the two-dimensional angiographic image to obtain at least two partial blood vessel region maps.

The blood vessel path unit is configured to extract at least one blood vessel local path line from each of the local blood vessel area maps sent by the image segmentation unit.

Optionally, the above-mentioned apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image further includes: an image processing unit and a grid dividing unit connected in sequence, and the image processing unit is connected to the image dividing unit;

The image processing unit is configured to receive the partial blood vessel region map sent by the image segmentation unit, and use the blood vessel segment of interest as the foreground and other regions as the background to strengthen the foreground and weaken the background to obtain a comparison A strong picture of the rough blood vessel;

The grid division unit performs grid division on the rough blood vessel map sent by the image processing unit.

Optionally, in the above-mentioned apparatus for extracting a blood vessel centerline from a two-dimensional coronary angiography image, the blood vessel path unit includes: a search unit and a blood vessel partial path line extraction unit connected in sequence, and the search unit is connected to the network Grid division unit connection;

The searching unit is configured to search from the starting point of the grid division unit along the blood vessel extending direction from the starting point to the ending point, and search for the intersection of the starting point and the surrounding n grids The shortest time path is used as the second point, and the shortest time path between the intersection of the second point and the surrounding n grids is searched for as the third point, and the third point repeats the above steps until the shortest time path Reach the end point, where n is a positive integer greater than or equal to 1;

The blood vessel partial path line extraction unit is configured to obtain at least one blood vessel partial path line from the start point of the search unit to the end point of the blood vessel extension direction line according to the search order of the search unit.

In a third aspect, the present application provides a coronary artery analysis system, including: the above-mentioned device for extracting the centerline of the blood vessel from the two-dimensional coronary angiography image.

In a fourth aspect, the present application provides a computer storage medium. When the computer program is executed by a processor, the method for extracting the centerline of the blood vessel from the two-dimensional coronary angiography image is realized.

The beneficial effects brought about by the solutions provided in the embodiments of the present application include at least:

This application provides a method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image, by first extracting at least one blood vessel path line from the two-dimensional coronary angiography image, and then obtaining the blood vessel center line according to the blood vessel path line, providing technical personnel with A new idea, with the advantages of fast extraction and high accuracy.

Description of the drawings

The drawings described here are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and the description thereof are used to explain the present invention, and do not constitute an improper limitation of the present invention. In the attached picture:

FIG. 1 is a flowchart of Embodiment 1 of the method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image of this application;

2 is a flowchart of Embodiment 2 of the method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image of this application;

Figure 3 is a flow chart of S400 of this application;

Figure 4 is a flowchart of S500 of the application;

Figure 5 is a flowchart of S520 of the application;

Figure 6 is a flowchart of S600 of the application;

FIG. 7 is a structural block diagram of an embodiment of an apparatus for extracting a centerline of a blood vessel from a two-dimensional coronary angiography image of the present application;

FIG. 8 is a structural block diagram of another embodiment of the apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image of the present application;

9 is a structural block diagram of another embodiment of the apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image of the present application;

The reference signs are described below:

The blood vessel path unit 100, the search unit 110, the blood vessel local path line extraction unit 120, the blood vessel center line extraction unit 200, the image segmentation unit 300, the image processing unit 400, and the mesh division unit 500.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be described clearly and completely in conjunction with specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Hereinafter, multiple embodiments of the present invention will be disclosed in the form of drawings. For clear description, many practical details will be described in the following description. However, it should be understood that these practical details should not be used to limit the present invention. That is to say, in some embodiments of the present invention, these practical details are unnecessary. In addition, in order to simplify the drawings, some conventionally used structures and components will be shown in simple schematic ways in the drawings.

Example 1:

As shown in Fig. 1, in order to solve the above-mentioned problems, the present application provides a method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image, which includes:

S500: Extract at least one blood vessel path line from the two-dimensional coronary angiography image;

S600, selecting a blood vessel path line as the blood vessel center line.

Example 2:

As shown in Fig. 2, in order to solve the above problems, the present application provides a method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image, which includes:

S100, reading the two-dimensional coronary angiography image;

S200: Obtain a blood vessel segment of interest;

S300, pick up the start point and end point of the blood vessel segment of interest;

S400, segmenting a local blood vessel area map corresponding to the start point and the end point from the two-dimensional coronary angiography image, as shown in FIG. 3, including:

S410: Pick up at least one seed point of the blood vessel segment of interest;

S420: Separate the two-dimensional contrast images between two adjacent points of the start point, the seed point, and the end point to obtain at least two partial blood vessel area maps; since the two-dimensional contrast image is divided into the partial blood vessel area maps, it reduces The background data calculation is huge and tedious, and the calculation is faster.

S500, extracting at least one blood vessel path line from the two-dimensional coronary angiography image, as shown in FIG. 4, includes:

S510: Perform image enhancement processing on the local blood vessel area map to obtain a rough blood vessel map with strong contrast, including: in each local blood vessel area map, take the blood vessel segment of interest as the foreground and other areas as the background, strengthen the foreground, and weaken the background , Get a rough blood vessel map with strong contrast;

S520: Perform grid division on the rough blood vessel map, and extract at least one local path line of the blood vessel along the direction from the start point to the end point, as shown in FIG. 5, including:

S521: Along the blood vessel extension direction from the start point to the end point, search for the shortest time path between the start point and the intersection on the surrounding n grids as the second point, and search for the second point and the surrounding n grids. The shortest time path at the intersection is the third point, and the third point repeats the above steps until the shortest time path reaches the end point, where n is a positive integer greater than or equal to 1; preferably, the starting point and the The end point, the extracted center line has high accuracy, and is not affected by artificial selection of the start point and end point.

S522: Obtain at least one local path line of the blood vessel according to the search order, from the start point to the end point of the blood vessel extension direction connection line;

S530: Connect the corresponding local blood vessel path lines on each local blood vessel area map to obtain at least one blood vessel path line.

S600, selecting a blood vessel path line as the blood vessel centerline, as shown in Fig. 6, including:

S610: If there are two or more blood vessel path lines, sum the time taken from the start point to the end point of each blood vessel path line;

In S620, the blood vessel path line with the least amount of time is taken as the blood vessel center line.

Example 3:

As shown in FIG. 7, the present application provides an apparatus for extracting a blood vessel centerline from a two-dimensional coronary angiography image, which includes: a blood vessel path unit 100 and a blood vessel centerline extraction unit 200 that are connected in sequence; a blood vessel path unit 100 with To extract at least one blood vessel path line from the two-dimensional coronary angiography image; the blood vessel center line extraction unit 200 is configured to select one of the blood vessel path lines sent by the blood vessel path unit 100 as the blood vessel center line.

As shown in FIG. 8, in an embodiment of the present application, it further includes: an image segmentation unit 300 connected to the blood vessel path unit 100; the image segmentation unit 300 is used to segment the start point and end point from the two-dimensional coronary angiography image. The local blood vessel area map corresponding to the point, or the two-dimensional contrast image between two adjacent points of the start point, the seed point, and the end point are segmented to obtain at least two local blood vessel area maps. The blood vessel path unit 100 is configured to extract at least one blood vessel local path line from each partial blood vessel area map sent by the image segmentation unit 300.

As shown in FIG. 9, an embodiment of the present application further includes: an image processing unit 400 and a grid division unit 500 connected in sequence, the image processing unit 400 is connected to the image segmentation unit 300; the image processing unit 400 is used to receive images The local blood vessel region map sent by the segmentation unit 300 uses the blood vessel segment of interest as the foreground and other regions as the background to strengthen the foreground and weaken the background to obtain a rough blood vessel map with strong contrast; the mesh division unit 500 sends to the image processing unit 400 The rough blood vessel diagram is meshed.

As shown in FIG. 9, in an embodiment of the present application, the blood vessel path unit 100 includes: a search unit 110 and a blood vessel local path line extraction unit 120 connected in sequence, the search unit 110 is connected to the mesh division unit 500; the search unit 110 , Used to search from the starting point of the grid division unit along the blood vessel extending direction from the starting point to the ending point, and search for the shortest time path between the starting point and the intersection on the surrounding n grids as the second point, search The shortest time path between the second point and the intersection on the surrounding n grids is taken as the third point. Repeat the above steps for the third point until the shortest time path reaches the end point, where n is a positive integer greater than or equal to 1. The blood vessel local path line extraction unit 120 is used to obtain at least one blood vessel local path line from the starting point to the end point of the search unit 110 in accordance with the search order of the search unit 110.

The present application provides a coronary artery analysis system, which includes: the above-mentioned device for extracting the centerline of the blood vessel from the two-dimensional angiographic image of the coronary artery.

The present application provides a computer storage medium. When the computer program is executed by a processor, the method for extracting the centerline of the blood vessel from the two-dimensional coronary angiography image is realized.

Those skilled in the art know that various aspects of the present invention can be implemented as a system, a method, or a computer program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, resident software, microcode, etc.), or a combination of hardware and software implementations, Here can be collectively referred to as "circuit", "module" or "system". In addition, in some embodiments, various aspects of the present invention may also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium contains computer-readable program code. The implementation of the method and/or system of the embodiments of the present invention may involve performing or completing selected tasks manually, automatically, or a combination thereof.

For example, hardware for performing selected tasks according to an embodiment of the present invention may be implemented as a chip or a circuit. As software, selected tasks according to embodiments of the present invention can be implemented as a plurality of software instructions executed by a computer using any suitable operating system. In an exemplary embodiment of the present invention, one or more tasks according to the exemplary embodiment of the method and/or system as described herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes a volatile memory for storing instructions and/or data and/or a non-volatile memory for storing instructions and/or data, for example, a magnetic hard disk and/or a Move the media. Optionally, a network connection is also provided. Optionally, a display and/or user input device, such as a keyboard or mouse, is also provided.

Any combination of one or more computer readable can be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer-readable storage media would include the following:

Electrical connection with one or more wires, portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk Read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .

The program code contained on the computer-readable medium can be transmitted by any suitable medium, including (but not limited to) wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

For example, any combination of one or more programming languages can be used to write computer program codes for performing operations for various aspects of the present invention, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional process programming languages, such as "C" programming language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network-including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).

It should be understood that each block of the flowchart and/or block diagram and the combination of each block in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, or other programmable data processing devices, thereby producing a machine that makes these computer program instructions when executed by the processors of the computer or other programmable data processing devices , A device that implements the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams is produced.

These computer program instructions can also be stored in a computer-readable medium. These instructions make computers, other programmable data processing devices, or other devices work in a specific manner, so that the instructions stored in the computer-readable medium generate An article of manufacture that implements instructions for the functions/actions specified in one or more blocks in the flowchart and/or block diagram.

Computer program instructions can also be loaded onto a computer (for example, a coronary artery analysis system) or other programmable data processing equipment to cause a series of operation steps to be executed on the computer, other programmable data processing equipment or other equipment to produce a computer-implemented process , Causing instructions executed on a computer, other programmable device or other equipment to provide a process for implementing the functions/actions specified in the flowchart and/or one or more block diagrams.

The above specific examples of the present invention further describe the purpose, technical solutions and beneficial effects of the present invention in further detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

A method for extracting a blood vessel centerline from a two-dimensional coronary angiography image, which is characterized in that it comprises:

Extracting at least one blood vessel path line from the two-dimensional coronary angiography image;

One of the blood vessel path lines is selected as the blood vessel center line.
The method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to claim 1, wherein before the method for extracting at least one blood vessel path line from the two-dimensional coronary angiography image, the method further comprises:

Read two-dimensional coronary angiography images;

Obtain the blood vessel segment of interest;

Pick the starting point and ending point of the blood vessel segment of interest;

The partial blood vessel area map corresponding to the start point and the end point is segmented from the two-dimensional coronary angiography image.
The method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image according to claim 2, wherein said segmenting the part corresponding to the start point and the end point from the two-dimensional coronary angiography image The method of vascular area map also includes:

Picking up at least one seed point of the blood vessel segment of interest;

Separate the two-dimensional contrast images between two adjacent points of the starting point, the seed point, and the end point to obtain at least two partial blood vessel region maps.
The method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to claim 2, wherein the method for extracting at least one blood vessel path line from a two-dimensional coronary angiography image comprises:

Extracting at least one local blood vessel path line from each of the local blood vessel area maps;

Connecting the corresponding local blood vessel path lines on each of the local blood vessel area maps to obtain at least one blood vessel path line.
The method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to claim 4, wherein the method of extracting at least one blood vessel local path line from the local blood vessel area map respectively comprises:

Performing image enhancement processing on the local blood vessel region map to obtain a rough blood vessel map with strong contrast;

The rough blood vessel map is meshed, and at least one local path line of the blood vessel is extracted along the direction from the start point to the end point.
The method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to claim 5, wherein the method of performing image enhancement processing on the local blood vessel area map to obtain a rough blood vessel map with strong contrast, include:

In each local blood vessel region map, the blood vessel segment of interest is used as the foreground and other regions are used as the background to strengthen the foreground and weaken the background to obtain the rough blood vessel map with strong contrast.
The method for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image according to claim 5, wherein the grid division of the rough blood vessel map is performed along the starting point to the ending point Direction, the method of extracting at least one local path line of a blood vessel includes:

Meshing the rough blood vessel diagram;

Along the blood vessel extending direction from the starting point to the ending point, search for the shortest time path between the starting point and the intersection on the surrounding n grids as the second point, and search for the second point and the surrounding The shortest time path of intersections on n grids is used as the third point, and the third point repeats the above steps until the shortest time path reaches the end point, where n is a positive integer greater than or equal to 1;

According to the search sequence, a line connecting the blood vessel extending direction from the starting point to the ending point is used to obtain at least one local path line of the blood vessel.
8. The method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to claim 7, wherein the method of selecting one of the blood vessel path lines as the blood vessel centerline comprises:

If there are two or more blood vessel path lines, the time taken for each blood vessel path line from the starting point to the ending point is summed;

The blood vessel path line with the least amount of time is taken as the blood vessel center line.
An apparatus for extracting a blood vessel centerline from a two-dimensional coronary angiography image, used in the method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to any one of claims 1 to 8, characterized in that it comprises : The blood vessel path unit and the blood vessel centerline extraction unit connected in sequence;

The blood vessel path unit is used to extract at least one blood vessel path line from a two-dimensional coronary angiography image;

The blood vessel centerline extraction unit is configured to select one of the blood vessel path lines sent by the blood vessel path module as the blood vessel centerline.
The apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image according to claim 9, further comprising: an image segmentation unit connected to the blood vessel path unit;

The image segmentation unit is used to segment the local blood vessel area map corresponding to the start point and the end point from the two-dimensional coronary angiography image, or to determine the start point, the seed point, and the two adjacent points of the end point. Segmentation of the two-dimensional angiographic image to obtain at least two partial blood vessel region maps.

The blood vessel path unit is configured to extract at least one blood vessel local path line from each of the local blood vessel area maps sent by the image segmentation unit.
The apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image according to claim 10, further comprising: an image processing unit and a grid division unit connected in sequence, the image processing unit and the image segmentation unit connection;

The image processing unit is configured to receive the partial blood vessel region map sent by the image segmentation unit, and use the blood vessel segment of interest as the foreground and other regions as the background to strengthen the foreground and weaken the background to obtain a comparison A strong picture of the rough blood vessel;

The grid division unit performs grid division on the rough blood vessel map sent by the image processing unit.
The apparatus for extracting the centerline of a blood vessel from a two-dimensional coronary angiography image according to claim 11, wherein the blood vessel path unit comprises: a search unit and a blood vessel partial path line extraction unit connected in sequence, and the search The unit is connected to the grid division unit;

The searching unit is configured to search from the starting point of the grid division unit along the blood vessel extending direction from the starting point to the ending point, and search for the intersection of the starting point and the surrounding n grids The shortest time path is used as the second point, and the shortest time path between the intersection of the second point and the surrounding n grids is searched for as the third point, and the third point repeats the above steps until the shortest time path Reach the end point, where n is a positive integer greater than or equal to 1;

The blood vessel partial path line extraction unit is configured to obtain at least one blood vessel partial path line from the start point of the search unit to the end point of the blood vessel extension direction line according to the search order of the search unit.
A coronary artery analysis system, characterized by comprising: the device for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to any one of claims 9-12.
A computer storage medium, characterized in that, when a computer program is executed by a processor, the method for extracting a blood vessel centerline from a two-dimensional coronary angiography image according to any one of claims 1 to 8 is realized.