WO2025105671A1 - Blood vessel graph generation system and execution method thereof - Google Patents

Abstract

The present invention is characterized by comprising: a three-dimensional medical image processing apparatus which analyzes a three-dimensional medical image to extract a blood vessel pixel point coordinate corresponding to a blood vessel on the basis of a pixel value, removes noise around a main blood vessel, and generates a three-dimensional blood vessel model; and a blood vessel graph generation device which divides the three-dimensional blood vessel model into a plurality of layers, sets a blood vessel pixel point group for each layer as a blood vessel node, and generates connection information to generate a blood vessel graph.

Description

Vascular graph generation system and execution method thereof

The present invention relates to a vascular graph generation system and an execution method thereof, and more particularly, to a vascular graph generation system that generates a vascular graph including vascular location and structure information from a three-dimensional vascular image, and an execution method thereof.

In modern medicine, medical images are very important tools for effective disease diagnosis and patient treatment. In addition, with the development of imaging technology, more sophisticated medical image data has been generated. Accordingly, the amount of data is becoming increasingly large, making it difficult to analyze medical image data by relying on human vision. Accordingly, clinical decision support systems and computer-aided interpretation systems have played an essential role in automatic medical image analysis over the past decade.

Conventional clinical decision support systems or computer-aided interpretation systems perform the function of detecting and displaying lesion areas or providing interpretation information to medical staff or medical practitioners (hereinafter referred to as users).

For example, in the 'Method and device for generating disease diagnosis information based on medical images' disclosed in Korean Patent Publication No. 10-2017-0017614, the method includes detecting a region of interest in which an analysis target object is photographed, calculating a coefficient of variation, creating a coefficient of variation image, and comparing it with a reference sample, and mentions the effect of diagnosing the degree of a patient's disease by utilizing medical images acquired through CT, CTA, MRI, MRA, DSA, and ultrasound imaging devices.

Recently, artificial intelligence (AI) technology based on machine learning such as deep learning has made great strides in the field of analyzing and processing medical images. Deep learning technology in medical images is applied to various tasks such as image analysis, diagnosis, treatment, and prediction. For example, deep learning-based auxiliary diagnosis systems are being applied to diagnosing cerebrovascular diseases such as cerebral aneurysms.

In image interpretation using a deep learning-based learning model, a method of inputting coordinate values at each location in the image together has been proposed as one of the methods for improving interpretation accuracy. This is the principle that an artificial intelligence model that has learned an image with coordinate values receives an image to be interpreted with coordinate values and uses the coordinate values for interpretation to improve accuracy.

The purpose of the present invention is to provide a vascular graph generation system and an execution method thereof, which extracts pixel points corresponding to blood vessels from a three-dimensional medical image, removes noise and microvessels, and generates a blood vessel graph including blood vessel coordinates and structural information.

The purposes of the present invention are not limited to the purposes mentioned above, and other purposes and advantages of the present invention which are not mentioned can be understood by the following description, and will be more clearly understood by the embodiments of the present invention. In addition, it will be easily understood that the purposes and advantages of the present invention can be realized by the means and combinations thereof indicated in the claims.

A vascular graph generation system according to an embodiment of the present invention is characterized by including a 3D medical image processing device which analyzes a 3D medical image to extract vascular pixel point coordinates corresponding to a blood vessel based on pixel values, removes noise around a major blood vessel, and generates a 3D blood vessel model; and a vascular graph generation device which divides the 3D blood vessel model into a plurality of layers, sets a group of blood vessel pixel points for each layer as a blood vessel node, and generates connection information to generate a vascular graph.

According to the present invention as described above, a blood vessel graph including coordinates and structural information for major blood vessels can be generated from a three-dimensional blood vessel image. The blood vessel graph according to the present invention is a visual representation of a blood vessel structure, and information on characteristics such as branching, connection, size, and location of blood vessels is compressed, and has the effect of being able to provide parameters such as length, diameter, angle, branching pattern, and shape of blood vessels.

FIG. 1 is a drawing for explaining a vascular graph generation system according to one embodiment of the present invention.

FIG. 2 is a drawing for explaining a three-dimensional medical image processing device according to one embodiment of the present invention.

FIG. 3 is a flowchart illustrating one embodiment of a three-dimensional medical image processing method according to the present invention.

Figures 4 to 7 are exemplary diagrams for explaining the operation of a three-dimensional medical image processing device according to the present invention.

Figure 8 is a flowchart illustrating one embodiment of a method for generating a blood vessel graph according to the present invention.

Figures 9 to 13 are exemplary diagrams for explaining the operation of a blood vessel graph generation device according to the present invention.

FIG. 14 is a block diagram illustrating the configuration of a server that generates a blood vessel graph according to an embodiment of the present invention.

The above-mentioned objects, features and advantages will be described in detail below with reference to the attached drawings, so that those with ordinary skill in the art to which the present invention pertains can easily practice the technical idea of the present invention. In describing the present invention, if it is judged that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, a detailed description thereof will be omitted. Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components.

FIG. 1 is a drawing for explaining a vascular graph generation system according to one embodiment of the present invention.

Referring to FIG. 1, the vascular graph generation system includes a 3D medical image processing device (100) and a vascular graph generation device (200).

A 3D medical image processing device (100) can create a 3D blood vessel model for a major blood vessel from a 3D medical image.

First, when the 3D medical image processing device (100) receives a 3D medical image, it can analyze the pixel values of the 3D medical image to extract blood vessel pixel points and coordinates. For example, when any pixel value in the 3D medical image is greater than a preset threshold value, the 3D medical image processing device (100) can determine that it corresponds to a blood vessel, specify a blood vessel pixel point, and extract coordinate information of the blood vessel pixel point.

In the above embodiment, the 3D medical image processing device (100) can extract the coordinates of a pixel if the pixel value is greater than or equal to a predetermined threshold value, and can create a blood vessel pixel coordinate table using the pixel coordinates. Thereafter, the 3D medical image processing device (100) can display blood vessel points on a coordinate system based on the blood vessel pixel coordinate table to create a coordinate system of the entire blood vessel.

A 3D medical image processing device (100) can crop a major blood vessel portion from a blood vessel pixel point displayed on a coordinate system.

Thereafter, the 3D medical image processing device (100) can perform clustering on blood vessel pixel points and filter out noise and/or fine blood vessel pixels.

According to an embodiment of the present invention, a three-dimensional medical image processing device (100) can group blood vessel pixel points into clusters by performing clustering based on at least one of distance, density, and/or attribute information of blood vessel pixel points.

Thereafter, the 3D medical image processing device (100) can perform a first filtering operation to compare the number of blood vessel pixel points included in any cluster with a threshold value and delete clusters below the threshold value. The filtering operation can be performed by removing pixel points corresponding to clusters having a number of blood vessel points below the threshold value from the blood vessel coordinate system. This can remove noise around major blood vessels.

The 3D medical image processing device (100) can group the blood vessel pixel points into clusters by re-clustering the first filtered blood vessel pixel points based on at least one of their distance, density, and attribute information.

Thereafter, the 3D image processing device (100) can perform a second filtering operation to delete the remaining clusters except for the blood vessel pixel points included in any cluster. For example, the filtering operation can be performed by removing pixel points corresponding to clusters other than the largest cluster from the blood vessel coordinate system. This can remove microvessels.

According to another embodiment of the present invention, a three-dimensional medical image processing device (100) can perform clustering and/or filtering of blood vessel pixel points using various algorithms, and the present invention cannot be interpreted by limiting the clustering and/or filtering algorithms.

For example, clustering can be performed by grouping blood vessel pixel points into K clusters, calculating the center of each cluster, and assigning the blood vessel pixel points to the cluster with the closest center. Another example is to form clusters using a similarity matrix for blood vessel pixel points. Afterwards, filtering for noise and microvessels around blood vessels can be performed by modifying or removing clusters.

According to an embodiment of the present invention, when a 3D medical image processing device (100) performs filtering through clustering, blood vessel pixel points from which noise and fine blood vessels are removed are formed in a blood vessel coordinate system, and through this, the 3D medical image processing device (100) can generate a 3D blood vessel model.

A blood vessel graph generation device (200) can generate a blood vessel graph based on a three-dimensional blood vessel model generated by a three-dimensional medical image processing device (100).

The blood vessel graph generation device (200) can divide a three-dimensional blood vessel model into multiple layers and check the coordinate values of blood vessel pixel points for each layer. At this time, it is appropriate to generate the layers in two dimensions.

Thereafter, the blood vessel graph generation device (200) can group blood vessel pixel points for each layer. The blood vessel pixel point group of each layer can correspond to a cross-section of an actual blood vessel.

Thereafter, the blood vessel graph generation device (200) can calculate the center of gravity of each group. This is for generating nodes of the blood vessel graph, and the nodes of the blood vessel graph according to the embodiment of the present invention can be set as the center of gravity of the blood vessel pixel point group for each layer. In the blood vessel graph according to the embodiment of the present invention, the nodes can correspond to the centers of actual blood vessels, and it is appropriate to set the radius of the nodes of the blood vessel graph to the radius of the actual blood vessel.

Thereafter, the blood vessel graph generation device (200) can generate connection information (connectivity) of blood vessel graph nodes. More specifically, connection information can be generated for nodes for the first group and nodes for the second group based on whether there is an intersection between a first group of blood vessel pixel points of an arbitrary layer and a second group of blood vessel pixel points of another layer adjacent to the layer. The blood vessel pixel point group of each layer corresponds to a cross-section of an actual blood vessel, and if there is an intersection with an adjacent layer, it is because the actual blood vessel is connected.

Through this, the blood vessel graph generation device (200) can generate node and connection information from a three-dimensional blood vessel model and generate a blood vessel graph. Furthermore, the blood vessel graph generation device (200) can calculate an actual blood vessel radius from the blood vessel graph and set it as a node radius. Through this, a blood vessel graph created according to an embodiment of the present invention can reflect characteristics such as branching, connection, size, and location of blood vessels. A specific method for this will be described later in the description of the attached drawings.

FIG. 2 is a drawing for explaining the configuration of a three-dimensional medical image processing device according to one embodiment of the present invention.

Referring to FIG. 2, a 3D medical image processing device (100) includes a pixel coordinate extraction unit (110), a noise removal unit (120), and a 3D blood vessel model generation unit (130).

The pixel coordinate extraction unit (110) can analyze the pixel values of a 3D medical image to extract blood vessel pixel points and coordinates. For example, if any pixel value in a 3D medical image is greater than or equal to a preset threshold value, the pixel coordinate extraction unit (110) can determine that the pixel value corresponds to a blood vessel, specify the blood vessel pixel point, and extract coordinate information of the blood vessel pixel point. Thereafter, the pixel coordinate extraction unit (110) can display the blood vessel point on a coordinate system based on the coordinate information to generate a coordinate system of the entire blood vessel.

The noise removal unit (120) can remove noise and/or fine blood vessel pixels by filtering the blood vessel pixel points generated by the pixel coordinate extraction unit (110).

More specifically, the noise removal unit (120) can remove noise and/or fine blood vessel pixels by cropping the main blood vessel portion from the blood vessel pixel points displayed on the coordinate system in the pixel coordinate extraction unit (110) and performing clustering and filtering on the blood vessel pixel points in the crop area.

For example, the noise removal unit (120) may perform clustering based on at least one of distance, density, and/or attribute information of blood vessel pixel points to group blood vessel pixel points into clusters. Thereafter, filtering may be performed to compare the number of blood vessel points included in any cluster with a threshold value and delete clusters below the threshold value. Filtering may be performed by removing pixel points corresponding to clusters having a number of blood vessel points below the threshold value from the blood vessel coordinate system. Through this, noise around major blood vessels may be removed.

In addition, the noise removal unit (120) can perform clustering again based on at least one of the distance, density, and attribute information of the primary filtered blood vessel pixel points to group the blood vessel pixel points into clusters. Thereafter, filtering can be performed to delete the remaining clusters except for the blood vessel pixel points included in any cluster. For example, the filtering can be performed in a manner of removing pixel points corresponding to clusters other than the largest cluster from the blood vessel coordinate system. Through this, fine blood vessels can be removed.

The 3D blood vessel model generation unit (130) can form blood vessel pixel points with noise and fine blood vessels removed in a blood vessel coordinate system and generate a 3D blood vessel model.

Figures 3 to 6 are exemplary diagrams for explaining a three-dimensional medical image processing process according to the present invention.

Referring to FIG. 3, a 3D medical image processing device (100) can analyze a 3D medical image and extract pixel coordinates corresponding to a blood vessel based on pixel values (step S310).

In one embodiment of step S310, the 3D medical image processing device (100) can analyze the 3D medical image, determine that it is a blood vessel if any pixel value is greater than a predetermined threshold value, specify a blood vessel pixel point, and extract coordinate information of the blood vessel pixel point. Thereafter, based on the coordinate information, the blood vessel point can be displayed on a coordinate system to generate a coordinate system of the entire blood vessel.

For example, a 3D medical image processing device (100) can analyze a 3D medical image of (a) of FIG. 4, extract pixel coordinates corresponding to blood vessels based on pixel values as in (b) of FIG. 4, and then generate a pixel coordinate table as in (a) of FIG. 5. A coordinate system of the entire blood vessel can be generated based on the pixel coordinate table as in (b) of FIG. 5. That is, a coordinate system of the entire blood vessel can be generated by forming blood vessel pixel points on the coordinate system.

The 3D medical image processing device (100) can crop a major blood vessel portion from the blood vessel pixel points displayed on the coordinate system. (Step S320). For example, the 3D medical image processing device (100) can specify a major blood vessel portion to be the target of image processing, as in (b) of FIG. 6, from the pixel points of the entire blood vessel displayed on the coordinate system, as in (a) of FIG. 6.

Furthermore, the 3D medical image processing device (100) can perform clustering and filtering on blood vessel pixel points in the crop area to remove noise and/or fine blood vessel pixels. (Step S330)

For example, a 3D medical image processing device (100) can remove noise and fine blood vessel pixels from a blood vessel that is a target of image processing, as in (a) of FIG. 7, and generate a 3D blood vessel model, as in (b) of FIG. 7.

Fig. 8 is a flowchart for explaining one embodiment of a method for generating a blood vessel graph according to the present invention. Figs. 9 to 13 are exemplary diagrams for explaining the execution process of Fig. 8.

Referring to Fig. 8, the blood vessel graph generation device (200) can divide a three-dimensional blood vessel model into multiple layers and check the coordinate values of blood vessel pixel points for each layer. At this time, it is appropriate to generate the layers in two dimensions. (Step S810). For example, the blood vessel graph generation device (200) can divide a three-dimensional blood vessel model into multiple layers as in (a) of FIG. 9, and check the coordinate values of blood vessel pixel points for each layer as in (b) of FIG. 9.

Afterwards, the blood vessel graph generation device (200) can group blood vessel pixel points for each layer (step S820) and calculate the center of gravity of each group. This is for generating nodes of the blood vessel graph, and nodes of the blood vessel graph according to the embodiment of the present invention can be set as the center of gravity of blood vessel pixel point groups for each layer. (step S830)

For example, the blood vessel graph generation device (200) can group blood vessel pixel points in an arbitrary layer and form the center of gravity of the group as a node of the blood vessel graph, as shown in FIG. 10. In the example of FIG. 10, the blood vessel pixel point group corresponds to one section of an actual blood vessel, and the center of gravity of the group will correspond to the center of one section of the blood vessel. Therefore, it is appropriate to set the radius of the node of the blood vessel graph to the radius of the actual blood vessel.

Afterwards, the blood vessel graph generation device (200) can generate connection information (connectivity) of blood vessel graph nodes. (Step S840)

For example, the blood vessel graph generation device (200) can check the group of blood vessel pixel points of the i-th layer and the group of blood vessel pixel points of the i+1-th layer adjacent to the i-th layer as shown in FIG. 11, and if there is an intersection between the groups as shown in FIG. 12, connection information can be generated for the nodes. This is because the blood vessel pixel point group of each layer corresponds to a cross-section of an actual blood vessel, and if there is an intersection with an adjacent layer, it is interpreted that an actual blood vessel is connected.

Furthermore, the blood vessel graph generation device (200) can calculate the radius of an actual blood vessel in the blood vessel graph and set it as a node radius. (Step S850)

More specifically, this will be explained with reference to Fig. 13.

When a 3D blood vessel model is divided into 2D layers, the cross-sectional radius corresponds to the radius (R ₀ ) of the blood vessel pixel point group. That is, since it is not the actual radius of the blood vessel but the radius (R ₀ ) of the blood vessel pixel point group, it is necessary to calculate the actual radius (r) of the blood vessel. To this end, the radius (R ₀ ) of the blood vessel pixel point group can be converted by cosθ, and the actual radius (r) can be calculated by the following [Mathematical Formula 1].

[Mathematical Formula 1]

r = R ₀ Х cosθ

R ₀ : Radius of the blood vessel pixel point group,

r: actual radius of the vessel,

) 및 해당 레이어의 혈관 픽셀 포인트 그룹의 반경 방향 (

)을 이용하여 계산된다.cosθ: It is calculated by [Mathematical Formula 2], and θ is the direction of connection information of adjacent layers (

) and the radial direction of the blood vessel pixel point group of that layer (

) is calculated using .

[Mathematical formula 2]

: 연결 정보에서 계산된 길이 방향 ,

: 혈관 단면의 반지름 방향, 또는

: Length direction calculated from connection information,

: radial direction of the blood vessel cross-section, or

: 연결 정보에서 계산된 길이 방향의 수직 ,

: 혈관 픽셀 포인트 그룹의 수직

: Perpendicular to the length direction calculated from the connection information,

: Vertical of the blood vessel pixel point group

Returning to the description of FIG. 8, in step S860, the blood vessel graph generation device (200) can generate a blood vessel graph using nodes, connection information, and node radii. This is a visual representation of a blood vessel structure, and information on characteristics such as branching, connection, size, and location of blood vessels are compressed, and parameters such as length, diameter, angle, branching pattern, and shape of blood vessels are included.

FIG. 14 is a block diagram illustrating the configuration of a server that generates a blood vessel graph according to an embodiment of the present invention.

As illustrated in FIG. 14, a server (1400) according to an embodiment of the present invention may include a communication unit (1410), a storage unit (1430), and a control unit (1420), and may further include an input unit and a display unit, although not illustrated in FIG. 14. In FIG. 14, the server (1400) is illustrated as including a communication unit (1410), a storage unit (1430), and a control unit (1420), but each block may be physically separated. For example, the storage unit (1430) may exist in a virtualized data center and may be connected to the control unit (1420) of the server (1400) via the communication unit (1410).

The communication unit (1410) performs a data transmission and reception function for wired and wireless communication of the server (1400), receives data through a wired and wireless channel, outputs it to the control unit (1420), and transmits data output from the control unit (1420) through a wireless channel. In particular, the communication unit (1410) according to an embodiment of the present invention can perform a function of receiving a 3D medical image.

The storage unit (1430) serves to store programs and data required for the operation of the server (1400), and can be divided into a program area and a data area. The data area of the storage unit (1430) according to an embodiment of the present invention can store blood vessel pixel point coordinates, a three-dimensional blood vessel model, and a blood vessel graph.

Furthermore, the program area of the storage unit (1430) according to the embodiment of the present invention can store a computer program that executes a process of generating a blood vessel graph on a server. The computer program can perform a function of analyzing a three-dimensional medical image to extract blood vessel pixel point coordinates corresponding to blood vessels based on pixel values, removing noise around major blood vessels, generating a three-dimensional blood vessel model, and dividing the three-dimensional blood vessel model into a plurality of layers, setting a blood vessel pixel point group for each layer as a blood vessel node, and generating connection information to generate a blood vessel graph.

The control unit (1420) controls the overall operation of each component of the server (1400). In particular, the control unit (1420) according to the embodiment of the present invention analyzes a three-dimensional medical image to extract blood vessel pixel point coordinates corresponding to blood vessels based on pixel values, removes noise around major blood vessels, generates a three-dimensional blood vessel model, divides the three-dimensional blood vessel model into a plurality of layers, sets blood vessel pixel point groups for each layer as blood vessel nodes, and generates connection information to generate a blood vessel graph, and can control the communication unit (1410) to provide the blood vessel graph.

Although the invention has been described by way of limited embodiments and drawings, it is not limited to the above embodiments, and various modifications and variations are possible from this description by those skilled in the art to which the invention pertains. Accordingly, the spirit of the invention should be understood only by the scope of the claims set forth below, and all equivalent or equivalent variations thereof will be deemed to fall within the scope of the spirit of the invention.

Claims (9)

A 3D medical image processing device that analyzes a 3D medical image to extract blood vessel pixel point coordinates corresponding to blood vessels based on pixel values, removes noise around major blood vessels, and generates a 3D blood vessel model; and A blood vessel graph generating device characterized by comprising a device for generating a blood vessel graph by dividing the three-dimensional blood vessel model into a plurality of layers, setting a group of blood vessel pixel points for each layer as a blood vessel node, and generating connection information. Vascular graph generation system. In the first paragraph, The above 3D medical image processing device The method is characterized by analyzing the above 3D medical image, determining that it is a blood vessel if the pixel value is greater than a predetermined threshold value, specifying a blood vessel pixel point, and extracting the coordinates of the blood vessel pixel point. Vascular graph generation system. In the second paragraph, The above 3D medical image processing device A method characterized in that clustering is performed based on at least one of distance, density and/or attribute information of the blood vessel pixel points, and the noise is removed by filtering pixel points corresponding to clusters having a number of blood vessel points less than a threshold value. Vascular graph generation system. In the first paragraph, The above blood vessel graph generating device The above 3D blood vessel model is divided into multiple layers, the blood vessel pixel points are grouped for each layer, the center of gravity of each group is calculated, and the center of gravity is set to the blood vessel node of the corresponding layer. Vascular graph generation system. In paragraph 4, The above blood vessel graph generating device A method characterized in that connection information is generated for a node for a first group and a node for a second group based on whether there is an intersection between a first group of blood vessel pixel points of an arbitrary layer and a second group of blood vessel pixel points of another layer adjacent to the layer. Vascular graph generation system In paragraph 5, The above blood vessel graph generating device The method is characterized in that the actual blood vessel radius is calculated using the direction of the above connection information and the radius direction of the node, and the actual blood vessel radius is set as the node radius of the blood vessel graph. Vascular graph generation system. A step of analyzing a 3D medical image to extract blood vessel pixel point coordinates corresponding to blood vessels based on pixel values, removing noise around major blood vessels, and generating a 3D blood vessel model; and A method for generating a blood vessel graph, comprising: dividing the above 3D blood vessel model into multiple layers, setting a group of blood vessel pixel points for each layer as a blood vessel node, and generating connection information. How to create a blood vessel graph. A pixel coordinate extraction unit that analyzes a 3D medical image and extracts blood vessel pixel point coordinates corresponding to the blood vessel based on pixel values; A noise removal unit for removing noise and/or fine blood vessel pixels by filtering the above blood vessel pixel points; and It is characterized by including a 3D blood vessel model generation unit that forms blood vessel pixel points from which the noise and/or microvessels are removed in a blood vessel coordinate system and generates a 3D blood vessel model. 3D medical image processing device In a computer program stored in a medium for performing a process of generating a blood vessel graph, The function of analyzing a 3D medical image to extract the blood vessel pixel point coordinates corresponding to the blood vessel based on the pixel value, removing noise around the main blood vessel, and generating a 3D blood vessel model; and The above 3D blood vessel model is divided into multiple layers, and the blood vessel pixel point group for each layer is set as a blood vessel node and connection information is generated to perform the function of generating a blood vessel graph. A computer program for generating vascular graphs.

Images