WO2025087110A1 - Method and device for identifying plaque in blood vessel - Google Patents

Abstract

A method and device for identifying plaque in a blood vessel. The method comprises: when there is plaque in a target blood vessel to be identified, determining raw plaque medical image data corresponding to each plaque (S101); for each branch blood vessel, on the basis of pixel values and a region type division rule in the raw plaque medical image data, dividing each plaque region, and determining at least one plaque sub-region (S102); for each target branch blood vessel having target plaque sub-regions of any specified region type, on the basis of a high-risk plaque evaluation rule and corresponding image parameters, identifying a target plaque sub-region in the target branch blood vessel, and determining whether the target branch blood vessel has high-risk plaque (S103); and if yes, outputting a high-risk plaque identification result of the target branch blood vessel, the plaque identification result comprising the type of the high-risk plaque, the position of the plaque, and a blood vessel name (S104).

Description

Method and device for identifying plaque in blood vessel

This application claims priority to the Chinese patent application filed with the China Patent Office on October 24, 2023, with application number 202311385251.1, the entire contents of which are incorporated by reference into this application.

Technical Field

The present application relates to the field of medical technology, and for example, to a method and device for identifying plaque in a blood vessel.

Background Art

With the rapid development of social economy, vascular disease has become a topic of great concern. Among them, high-risk/vulnerable plaques in coronary atherosclerotic plaques usually exist in the early stage of coronary plaque formation and are the main cause of acute cardiovascular events. Therefore, the treatment technology and prevention level of vascular diseases are of paramount importance. However, whether it is treatment or prevention, it is inseparable from the study of vascular morphology. Therefore, the automated detection of vascular plaques has important research value, clinical value and practical significance.

Most of the related technical studies use traditional machine learning methods to detect high-risk plaques in the coronary arteries, that is, firstly, experienced experts manually design features, and then send the extracted features to the machine learning classifier to predict the plaque type. But this process is heavily dependent on the operator's experience and rich professional knowledge, and is time-consuming and laborious. However, given the diversity of coronary plaque sample characteristics, it is difficult for machine learning methods to design specific features for high-risk plaques when designing features, and it is heavily dependent on the operator's experience and rich professional knowledge, which is time-consuming and laborious. In addition, due to the characteristics of high-risk coronary plaques, a plaque usually spans multiple coronary CT angiography (CCTA) scans, and the deep learning training method of a single image corresponding to a single label has errors and is not suitable for high-risk plaque detection tasks.

Therefore, there are still certain limitations in using traditional machine learning methods to detect high-risk coronary artery plaques.

Summary of the invention

The present application provides a method and device for identifying plaques in blood vessels, which can effectively identify high-risk plaques in blood vessels.

The present application embodiment provides a method for identifying plaque in a blood vessel, the identification method comprising:

In response to the presence of plaques in the target blood vessel to be identified, original plaque medical image data corresponding to each plaque is determined according to an original total medical image of the target blood vessel; the target blood vessel includes at least one branch blood vessel;

For each branch blood vessel, according to the pixel value and region type division rule in the original plaque medical image data, the plaque region corresponding to each plaque in the branch blood vessel is divided to determine at least one plaque sub-region and the region type of each plaque sub-region;

For each target branch vessel having a target plaque sub-region of any specified region type, identifying the plaque region of the target branch vessel having the target plaque sub-region according to the high-risk plaque assessment rule and the corresponding imaging parameters, and determining whether the target branch vessel has a high-risk plaque;

In response to determining that a high-risk plaque exists in the target branch vessel, a high-risk plaque identification result of the target branch vessel is output; the plaque identification result includes the high-risk plaque type, the plaque location, and the vessel name of the target branch vessel.

In some embodiments, the presence of plaque in the target blood vessel to be identified is determined by:

Acquiring a three-dimensional reconstructed blood vessel model of the target blood vessel;

identifying, according to a morphological processing method, whether there is a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel;

In response to identifying the presence of a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel, it is determined that a plaque exists in the target blood vessel.

In some embodiments, the three-dimensional reconstructed blood vessel model of the target blood vessel is constructed by:

Performing centerline extraction processing on the original total medical image of the target blood vessel to determine the centerline of the target blood vessel;

Performing contour recognition according to the centerline of the target blood vessel and the original total medical image to determine the intima contour and the adventitia contour of the target blood vessel;

Performing lofting processing on the intima contour and the adventitia contour of the target blood vessel respectively to obtain an intima curved surface model and an adventitia curved surface model of the target blood vessel;

According to the intima curved surface model and the adventitia curved surface model of the target blood vessel, volume filling processing is performed to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel; the three-dimensional reconstructed blood vessel model of the target blood vessel includes an intima three-dimensional model and an adventitia three-dimensional model.

In some embodiments, determining the original plaque medical image data corresponding to each plaque includes:

Determine a three-dimensional reconstruction result of all plaques in the target blood vessel using a result obtained by subtracting a three-dimensional model of the inner membrane from a three-dimensional model of the outer membrane of the target blood vessel;

According to the three-dimensional reconstruction results of all plaques, the medical image at the corresponding position is extracted from the original total medical image of the target blood vessel to determine the original plaque medical image data corresponding to each plaque.

In some embodiments, the region type division rule is to set different pixels for different region types. Threshold ranges to establish rules for plaque quantification analysis.

In some embodiments, for each target branch vessel having a target plaque sub-region of any specified region type, identifying the plaque region having the target plaque sub-region in the target branch vessel according to a high-risk plaque assessment rule and corresponding image parameters, and determining whether the target branch vessel has a high-risk plaque, comprises:

For each plaque region in each target branch blood vessel where a target plaque sub-region exists, determining an identification order of high-risk plaques according to a region type of the target plaque sub-region in the plaque region;

According to the determined recognition order of high-risk plaques, imaging parameters required for identifying each high-risk plaque are sequentially acquired;

Identify the high-risk plaque according to the high-risk plaque assessment rules and the image parameters corresponding to the high-risk plaque, until all high-risk plaques in the identification sequence are identified, and obtain the high-risk plaque identification result corresponding to the plaque area;

In response to the high-risk plaque identification result corresponding to any plaque area in the target branch blood vessel indicating the existence of a high-risk plaque, it is determined that the target branch blood vessel has a high-risk plaque.

In some embodiments, the plaque location includes the plaque location of each high-risk plaque, and the plaque location of each high-risk plaque is determined by:

In response to identifying the presence of a high-risk plaque in the target branch vessel, determining the plaque region to which the high-risk plaque belongs;

According to the determined plaque area and the original total medical image, the plaque position of the high-risk plaque is determined by adopting the shortest distance mapping processing method.

The present application also provides a device for identifying plaque in a blood vessel, the device comprising:

A first determination module is configured to determine original plaque medical image data corresponding to each plaque according to an original total medical image of the target blood vessel in response to the presence of plaque in the target blood vessel to be identified; the target blood vessel includes at least one branch blood vessel;

a division module, configured to divide the plaque area corresponding to each plaque in the branch blood vessel according to the pixel value and area type division rule in the original plaque medical image data, and determine at least one plaque sub-area and the area type of each plaque sub-area;

an identification module configured to identify, for each target branch vessel having a target plaque sub-region of any specified region type, a plaque region in the target branch vessel having a target plaque sub-region according to a high-risk plaque assessment rule and corresponding imaging parameters, to determine whether the target branch vessel has a high-risk plaque;

The output module is configured to output the target branch vessel in response to determining that the target branch vessel has a high-risk plaque. The high-risk plaque identification result of the target branch blood vessel includes the high-risk plaque type, plaque location and the blood vessel name of the target branch blood vessel.

In some embodiments, the identification device further includes a second determination module, and the second determination module is configured to:

Acquiring a three-dimensional reconstructed blood vessel model of the target blood vessel;

identifying, according to a morphological processing method, whether there is a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel;

In response to identifying the presence of a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel, it is determined that a plaque exists in the target blood vessel.

In some embodiments, the identification device further includes a building module, and the building module is configured to:

Performing centerline extraction processing on the original total medical image of the target blood vessel to determine the centerline of the target blood vessel;

Performing contour recognition according to the centerline of the target blood vessel and the original total medical image to determine the intima contour and the adventitia contour of the target blood vessel;

Performing lofting processing on the intima contour and the adventitia contour of the target blood vessel respectively to obtain an intima curved surface model and an adventitia curved surface model of the target blood vessel;

According to the intima curved surface model and the adventitia curved surface model of the target blood vessel, volume filling processing is performed to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel; the three-dimensional reconstructed blood vessel model of the target blood vessel includes an intima three-dimensional model and an adventitia three-dimensional model.

In some embodiments, when the first determining module is configured to determine the original plaque medical image data corresponding to each plaque in the following manner, the first determining module is configured to:

Determine a three-dimensional reconstruction result of all plaques in the target blood vessel using a result obtained by subtracting a three-dimensional model of the inner membrane from a three-dimensional model of the outer membrane of the target blood vessel;

According to the three-dimensional reconstruction results of all plaques, the medical image at the corresponding position is extracted from the original total medical image of the target blood vessel to determine the original plaque medical image data corresponding to each plaque.

In some embodiments, the region type division rule is a rule for setting different pixel threshold ranges for different region types to perform plaque quantitative analysis.

In some embodiments, when the identification module is configured to identify the plaque area in the target branch vessel where the target plaque sub-area exists according to the high-risk plaque assessment rule and the corresponding image parameters for each target branch vessel where the target plaque sub-area of any specified area type exists, and to determine whether the target branch vessel has a high-risk plaque, the identification module is configured to:

For each plaque region in each target branch vessel where a target plaque sub-region exists, according to the The area type of the target plaque sub-area in the plaque area determines the identification order of high-risk plaques;

According to the determined recognition order of high-risk plaques, imaging parameters required for identifying each high-risk plaque are sequentially acquired;

Identify the high-risk plaque according to the high-risk plaque assessment rules and the image parameters corresponding to the high-risk plaque, until all high-risk plaques in the identification sequence are identified, and obtain the high-risk plaque identification result corresponding to the plaque area;

In response to the high-risk plaque identification result corresponding to any plaque area in the target branch blood vessel indicating the existence of a high-risk plaque, it is determined that the target branch blood vessel has a high-risk plaque.

In some embodiments, the identification module is further configured to:

In response to identifying the presence of a high-risk plaque in the target branch vessel, determining the plaque region to which the high-risk plaque belongs;

According to the determined plaque area and the original total medical image, the plaque position of the high-risk plaque is determined by adopting the shortest distance mapping processing method.

An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the identification method as described above is performed.

An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the identification method as described above is executed.

BRIEF DESCRIPTION OF THE DRAWINGS

The following are the drawings required for use in the embodiments. The following drawings only show some drawings of the embodiments related to the present application. For ordinary technicians in this field, other related drawings can also be obtained based on these drawings without creative work.

FIG1 is a flow chart of a method for identifying plaque in a blood vessel provided in an embodiment of the present application;

FIG2 is a schematic structural diagram of a blood vessel centerline provided in an embodiment of the present application;

FIG3 is a schematic structural diagram of a vascular adventitia profile provided in an embodiment of the present application;

FIG4 is a schematic diagram of the structure of a branch blood vessel with plaque provided by the present application;

FIG5 is a schematic diagram of the data results of the positive reconstruction high-risk plaque identification process provided by the present application;

FIG6 is a schematic diagram of a structure of a device for identifying plaque in a blood vessel provided in an embodiment of the present application;

FIG. 7 is a second schematic diagram of the structure of a device for identifying plaque in a blood vessel provided in an embodiment of the present application;

FIG8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

DETAILED DESCRIPTION

The following will describe the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application, and the described embodiments are some embodiments related to the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various configurations. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

The embodiments of the present application provide a method and device for identifying plaques in blood vessels, which can effectively identify high-risk plaques in blood vessels and improve the speed and accuracy of high-risk plaque identification.

Please refer to Figure 1, which is a flow chart of a method for identifying a plaque in a blood vessel provided by an embodiment of the present application. As shown in Figure 1, the identification method provided by the embodiment of the present application includes:

S101. When plaques exist in a target blood vessel to be identified, original plaque medical image data corresponding to each plaque is determined according to an original total medical image of the target blood vessel.

The target blood vessel includes at least one branch blood vessel. For example, when the target blood vessel is a coronary artery, the target blood vessel includes the branch blood vessels of the left main trunk, the left anterior descending branch, the left circumflex branch, and the right coronary artery, or can be further divided into the sharp edge branch, the sinoatrial node branch, the atrioventricular node branch, the posterior descending branch, the left posterior ventricular branch, and other branch blood vessels.

The type of branch blood vessels included in the target blood vessel may be set in advance by relevant personnel.

In one embodiment provided in the present application, the presence of plaque in the target blood vessel to be identified is determined by the following steps:

S201: Acquire a three-dimensional reconstructed blood vessel model of the target blood vessel.

S202: Identify whether there is a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel according to a morphological processing method.

S203: In response to identifying that a mutation region exists in the three-dimensional reconstructed blood vessel model of the target blood vessel, determine that a plaque exists in the target blood vessel.

With respect to step S201, in one embodiment provided in the present application, a three-dimensional reconstructed blood vessel model of the target blood vessel is constructed by the following steps:

S301 , performing centerline extraction processing on the original total medical image of the target blood vessel to determine the centerline of the target blood vessel.

S302: Perform contour recognition according to the center line of the target blood vessel and the original total medical image to determine the intima contour and adventitia contour of the target blood vessel.

S303 , performing lofting processing on the intima contour and the adventitia contour of the target blood vessel respectively to obtain an intima curved surface model and an adventitia curved surface model of the target blood vessel.

S304, performing volume filling processing according to the intima curved surface model and the adventitia curved surface model of the target blood vessel to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel; the three-dimensional reconstructed blood vessel model of the target blood vessel includes an intima three-dimensional model and an adventitia three-dimensional model.

For step S301, please refer to FIG2 for example, which is a schematic diagram of the structure of a blood vessel centerline provided in an embodiment of the present application. As shown in FIG2, when extracting the centerline, the center target points of multiple locations of the target blood vessel can be first determined to obtain multiple center target points, and then the multiple center target points can be connected in sequence according to the blood vessel direction and structural characteristics of the target blood vessel to determine the centerline of the target blood vessel.

Regarding step S302, it should be noted that the blood vessel wall tissue has an intima and an adventitia, and the inner edge of the intima and the outer edge of the adventitia are used as the intima contour and the adventitia contour, respectively.

The characteristics of the contour are: a closed curve formed by a series of spatial points on the same spatial plane, and the normal vector of the contour plane is parallel to the tangent direction of the center line where the point is located. For example, please refer to Figure 3, which is a structural schematic diagram of a vascular adventitia contour provided in an embodiment of the present application. As shown in Figure 3, the adventitia contour of the target blood vessel determined here is actually composed of contour lines of multiple positions of the target blood vessel arranged in sequence. Among them, each central target point on the center line of the target blood vessel corresponds to a contour (contour curve).

With respect to step S303, the lofting process is a method of generating a smooth and continuous shape by gradually transitioning or interpolating a plurality of curves or surfaces of different cross sections.

The lofting process includes steps such as contour preparation, interpolation, smoothing and adjustment, connection and supplementation, and shape output. When performing interpolation processing: adjacent contours are interpolated to generate an intermediate shape (contour), which can be achieved by interpolating contour points, adjusting control points, parameterizing curves, and other methods. When performing smoothing and adjustment processing: during the interpolation and fusion process, problems such as uneven shapes and unnatural corner transitions may occur. In this step, curve fitting, smoothing algorithms, and other techniques can be used to adjust the shape to make it smoother and more continuous in the transition area. When performing connection and supplementation processing: during the lofting process, some discontinuously connected parts may appear, or the shape needs to be supplemented in some places. This can be solved by curve and surface connection algorithms, or additional interpolation operations.

For step S304, performing volume filling processing on the intimal surface model and the adventitia surface model of the target blood vessel to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel includes: performing volume filling processing on the intimal surface model and the adventitia surface model of the target blood vessel to obtain a three-dimensional intimal model and a three-dimensional adventitia model of the target blood vessel, and reconstructing the three-dimensional intimal model and the adventitia surface model of the target blood vessel according to the three-dimensional intimal model and the adventitia surface model of the target blood vessel. A three-dimensional reconstructed blood vessel model of the target blood vessel is determined based on the three-dimensional model.

With respect to the determination of the original plaque medical image data corresponding to each plaque in step S101, in one embodiment provided in the present application, the original plaque medical image data corresponding to each plaque is determined by the following steps:

S1011. Determine a three-dimensional reconstruction result of all plaques in the target blood vessel by using a result obtained by subtracting the three-dimensional model of the inner membrane from the three-dimensional model of the outer membrane of the target blood vessel.

S1012: extracting medical images at corresponding positions from the original total medical image of the target blood vessel according to the three-dimensional reconstruction results of all plaques, and determining original plaque medical image data corresponding to each plaque.

Regarding step S1011, it should be noted that the inner membrane and the outer membrane of a normal plaque-free blood vessel are basically overlapped.

When the three-dimensional reconstruction results of all plaques in the target blood vessel are determined, the position of each plaque in the target blood vessel is also determined, so that step S1012 can be executed.

S102. For each branch blood vessel, divide the plaque region corresponding to each plaque in the branch blood vessel according to the pixel values and region type division rules in the original plaque medical image data, and determine at least one plaque sub-region and the region type of each plaque sub-region.

In step S102, the plaque area in the blood vessel is divided based on the blood vessel.

The pixel value in the original plaque medical imaging data may be, for example, a computed tomography (CT) value, the unit of which is Hounsfield unit (HU).

The region type division rule is a rule for setting different pixel threshold ranges for different region types to perform plaque quantitative analysis.

For example, the regional type classification rule may be: for the plaque area, the area with a CT value ≥ 350HU is determined as a calcified plaque area, and the area with a CT value < 350HU is determined as a non-calcified plaque area. The non-calcified plaque area may also include: determining the area with a CT value in the range of -30 to 30HU as a non-calcified plaque area with a necrotic core, determining the area with a CT value in the range of 31 to 130HU as a non-calcified plaque area with fiber fat, and determining the area with a CT value in the range of 131 to 350HU as a non-calcified plaque area with fiber.

In this way, the corresponding area type can be determined for each divided patch sub-area.

For example, please refer to Figure 4, which is a schematic diagram of the structure of a branch blood vessel with plaque provided by the present application. The plaque area can be divided to determine at least one plaque sub-area.

S103, for each target branch vessel in a target plaque sub-region of any specified region type, according to a high-risk plaque assessment rule and corresponding imaging parameters, The plaque sub-area is identified to determine whether the target branch vessel has a high-risk plaque.

High-risk plaques are determined according to the coronary CT image interpretation and reporting guidelines (such as the Society of Cardiovascular Computed Tomography (SCCT) guidelines). The SCCT guidelines stipulate that high-risk plaques include: positive remodeling, "napkin ring" sign, punctate calcification, and low-density plaques.

Positive remodelling refers to the ratio of the maximum vessel diameter (including plaque and lumen) of the diseased segment to the normal average lumen diameter proximal and distal to the plaque, which is ≥1.1.

Low attenuation plaque refers to an area within the plaque with a CT value of <30HU in an area of >1 square millimeter (mm ² ). Low attenuation plaque is closely associated with severe macrophage infiltration and a large lipid necrotic core (>40% of the total plaque volume).

Spotty calcification refers to a high-density lesion with a long diameter of <3 mm and an average density of >130HU in any plane within a non-calcified plaque, and the long diameter of the calcification is less than 1.5 times the diameter of the blood vessel, and the short diameter of the calcification is less than 2/3 of the diameter of the blood vessel.

"Napkin-ring" sign: refers to the ring-shaped slightly higher density sign at the edge of the low-density plaque.

The selection of designated area types is determined according to the high-risk plaque assessment rules. The above four high-risk plaques (i.e., positive remodeling, "napkin ring" sign, punctate calcification, and low-density plaques) are all non-calcified areas, so the designated area types include: non-calcified plaque areas with necrotic cores, non-calcified plaque areas with fibrofat, and non-calcified plaque areas with fibers.

The corresponding image parameters are determined according to the assessment indexes required for identifying each high-risk plaque in the high-risk plaque assessment rules.

For example, quantitative analysis indicators for evaluating plaque characteristics also include luminal stenosis caused by plaques, plaque size, plaque length, total plaque volume, calcified plaque volume, non-calcified plaque volume, minimum luminal area, reconstruction index, and plaque load. Among them, the plaque size is determined based on parameters such as total plaque load and/or non-calcified plaque load (volume ratio) and/or calcified plaque load (volume ratio) and/or plaque length. When determining luminal stenosis caused by plaques, parameters such as plaque cross-sectional area and/or luminal cross-sectional area need to be obtained.

The step S103 of identifying each target plaque sub-region in the target branch vessel may be, for example, identifying each plaque region in the target branch vessel where a target plaque sub-region exists.

When a high-risk plaque is identified in any plaque region, it is determined that the target branch vessel has a high-risk plaque.

In one embodiment provided in the present application, for each target branch vessel in a target plaque sub-region with any specified region type, according to a high-risk plaque assessment rule and corresponding imaging parameters, Identifying a plaque region in the target branch vessel where a target plaque sub-region exists, and determining whether the target branch vessel has a high-risk plaque, includes:

S1031. For each plaque region having a target plaque sub-region in each target branch blood vessel, determine an identification order of high-risk plaques according to the region type of the target plaque sub-region in the plaque region.

S1032. According to the determined recognition order of the high-risk plaques, image parameters required for identifying each high-risk plaque are acquired in sequence.

S1033, identifying the high-risk plaque according to the high-risk plaque assessment rules and the image parameters corresponding to the high-risk plaque, until all high-risk plaques in the identification sequence are identified, and obtaining the high-risk plaque identification result corresponding to the plaque area.

S1034: When the high-risk plaque identification result corresponding to any plaque region in the target branch blood vessel indicates the existence of a high-risk plaque, determine that the target branch blood vessel has a high-risk plaque.

For step S1031, for example, assuming that the region type of the target plaque sub-region in a plaque region is a non-calcified plaque region with a necrotic core, the corresponding high-risk plaque identification order may be: low-density plaque → "napkin ring" sign → positive reconstruction. If the region type of the target plaque sub-region in a plaque region is a non-calcified plaque region with fibrofat, the corresponding high-risk plaque identification order may be: point calcification → positive reconstruction.

By determining the recognition order of high-risk plaques, the recognition of unnecessary types of high-risk plaques can be reduced, thereby increasing the recognition speed. Moreover, by performing recognition in sequence according to the determined recognition order, the accuracy of high-risk plaque recognition can also be improved.

With respect to step S1033, the high-risk plaque is identified according to the high-risk plaque assessment rule and the image parameters corresponding to the high-risk plaque. Four high-risk plaque identification methods are provided below.

Method for identifying low-density plaques: if the area type of the target plaque sub-area within the plaque area is a non-calcified plaque area with a necrotic core, calculate the CT mean of the target plaque sub-area; if the CT mean is less than 30HU, continue to measure the volume of the target plaque sub-area; if the CT mean is not less than 30HU, end the low-density plaque identification; wherein, the volume of the target plaque sub-area = the number of pixels of the necrotic core × the physical resolution of the pixel (x_spacing (horizontal pixel spacing) × y_spacing (vertical pixel spacing) × interval (interval)); if the volume of the target plaque sub-area is > 1 cubic millimeter (mm ³ ), it is identified as a low-density plaque, otherwise the identification result of not being a high-risk plaque is output.

Method for identifying point-like calcification: if the area type of the target plaque sub-area within the plaque area is a non-calcified plaque area with fibers, calculate the CT mean of the fiber and fibrous fat area; if the CT mean is greater than 130HU, continue to measure the volume of the fiber and fibrous fat; if the CT mean is not greater than 130HU, end the identification of point-like calcification; where the volume of fiber and fibrous fat = the number of pixels of fiber and fibrous fat × the physical resolution of the pixel (x_spacing × y_spacing × interval (interval)); calculate the volume of fiber and fibrous fat. The inner diameter of the fat location is calculated; the farthest two pixels in the volume are calculated to see whether the long diameter of the point-like calcification is less than 1.5 times the inner diameter, and the short diameter of the point-like calcification is less than 2/3 of the inner diameter. If both are true, it is identified as point-like calcification.

The identification method of the "napkin ring" sign is as follows: if the area type of the target plaque sub-area within the plaque area is a non-calcified plaque area with a necrotic core, the necrotic core is morphologically expanded; if the ratio of fiber and fibrous fat within the expanded range exceeds the threshold, it is identified as a "napkin ring" sign, otherwise the output is an identification result that is not a high-risk plaque.

Positive reconstruction was identified by arranging the contours of the target branch vessels in sequence; calculating the ratio of the current outer membrane contour diameter to the average of the proximal and distal outer diameter contour diameters; if the ratio was <1.1, identification was terminated; if the ratio was >1.1, and the diameter difference between the outer diameter and the inner diameter of the target branch vessel was >1mm, and the target plaque sub-area was a non-calcified area, it was identified as positive reconstruction.

For example, please refer to Figure 5, which is a schematic diagram of the data results of the positively remodeled high-risk plaque identification process provided by the present application. As shown in Figure 5, whether there is a positively remodeled high-risk plaque and its location can be determined based on the contour data of the blood vessel.

S104. In response to determining that a high-risk plaque exists in the target branch vessel, output a high-risk plaque identification result of the target branch vessel; the plaque identification result includes the high-risk plaque type, the plaque location, and the vessel name of the target branch vessel.

After the high-risk plaque identification result of each target branch vessel is determined, the high-risk plaque identification result of the target vessel can be determined based on the high-risk plaque identification result of each target branch vessel.

In one embodiment provided in the present application, the plaque location includes the plaque location of each high-risk plaque, and the plaque location of each high-risk plaque is determined by the following steps: when a high-risk plaque is identified to exist in the target branch blood vessel, the plaque area to which the high-risk plaque belongs is determined; based on the determined plaque area and the original total medical image, the plaque location of the high-risk plaque is determined by the shortest distance mapping processing method.

An embodiment of the present application provides a method for identifying plaques in a blood vessel, the identification method comprising: when a plaque exists in a target blood vessel to be identified, determining original plaque medical image data corresponding to each plaque according to an original total medical image of the target blood vessel; the target blood vessel includes at least one branch blood vessel; for each branch blood vessel, dividing the plaque area corresponding to each plaque in the branch blood vessel according to the pixel value and area type division rule in the original plaque medical image data, and determining at least one plaque sub-area and the area type of each plaque sub-area; for each target branch blood vessel with a target plaque sub-area of any specified area type, identifying the plaque area in the target branch blood vessel with the target plaque sub-area according to the high-risk plaque assessment rule and the corresponding image parameters, and determining whether the target branch blood vessel has a high-risk plaque; in response to determining that the target branch blood vessel has a high-risk plaque, outputting a high-risk plaque identification result of the target branch blood vessel; the plaque identification result includes the high-risk plaque type, the plaque location, and the blood vessel name of the target branch blood vessel.

The present application divides the plaque area according to pixel values, determines the type of sub-areas included in each plaque area, and then determines whether to identify high-risk plaques and the identification order according to the type of sub-areas, and obtains corresponding image parameters and identifies the high-risk plaques in sequence according to the identification order, thereby improving the identification speed and accuracy of high-risk plaques in blood vessels.

Please refer to Figures 6 and 7. Figure 6 is a schematic diagram of the structure of a device for identifying plaque in a blood vessel provided in an embodiment of the present application, and Figure 7 is a schematic diagram of the structure of a device for identifying plaque in a blood vessel provided in an embodiment of the present application. As shown in Figure 6, the identification device 600 includes:

The first determination module 610 is configured to determine original plaque medical image data corresponding to each plaque according to an original total medical image of the target blood vessel in response to the presence of plaque in the target blood vessel to be identified; the target blood vessel includes at least one branch blood vessel;

The division module 620 is configured to divide the plaque area corresponding to each plaque in the branch blood vessel according to the pixel value and area type division rule in the original plaque medical image data, and determine at least one plaque sub-area and the area type of each plaque sub-area;

The identification module 630 is configured to identify, for each target branch vessel having a target plaque sub-region of any specified region type, a plaque region in the target branch vessel having a target plaque sub-region according to a high-risk plaque assessment rule and corresponding image parameters, to determine whether the target branch vessel has a high-risk plaque;

The output module 640 is configured to output a high-risk plaque identification result of the target branch vessel in response to determining that the target branch vessel has a high-risk plaque; the plaque identification result includes the high-risk plaque type, plaque location and vessel name of the target branch vessel.

Optionally, as shown in FIG. 7 , the identification device 600 further includes a second determination module 650, and the second determination module 650 is configured to:

Acquiring a three-dimensional reconstructed blood vessel model of the target blood vessel;

identifying, according to a morphological processing method, whether there is a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel;

In response to identifying the presence of a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel, it is determined that a plaque exists in the target blood vessel.

Optionally, the identification device 600 further includes a construction module 660, and the construction module 660 is configured to:

Performing centerline extraction processing on the original total medical image of the target blood vessel to determine the centerline of the target blood vessel;

Performing contour recognition according to the centerline of the target blood vessel and the original total medical image to determine the intima contour and the adventitia contour of the target blood vessel;

Performing lofting processing on the intima contour and the adventitia contour of the target blood vessel respectively to obtain an intima curved surface model and an adventitia curved surface model of the target blood vessel;

According to the intima curved surface model and the adventitia curved surface model of the target blood vessel, volume filling processing is performed to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel; the three-dimensional reconstructed blood vessel model of the target blood vessel includes an intima three-dimensional model and an adventitia three-dimensional model.

Optionally, when the first determining module 610 is configured to determine the original plaque medical image data corresponding to each plaque in the following manner, the first determining module 610 is configured to:

Determine a three-dimensional reconstruction result of all plaques in the target blood vessel using a result obtained by subtracting a three-dimensional model of the inner membrane from a three-dimensional model of the outer membrane of the target blood vessel;

According to the three-dimensional reconstruction results of all plaques, the medical image at the corresponding position is extracted from the original total medical image of the target blood vessel to determine the original plaque medical image data corresponding to each plaque.

Optionally, the region type division rule is a rule for setting different pixel threshold ranges for different region types to perform plaque quantitative analysis.

Optionally, when the identification module 630 is configured to identify the plaque area in the target branch vessel where the target plaque sub-area exists according to the high-risk plaque assessment rule and the corresponding image parameters for each target branch vessel where the target plaque sub-area of any specified area type exists, and to determine whether the target branch vessel has a high-risk plaque, the identification module 630 is configured to:

For each plaque region in each target branch blood vessel where a target plaque sub-region exists, determining an identification order of high-risk plaques according to a region type of the target plaque sub-region in the plaque region;

According to the determined recognition order of high-risk plaques, imaging parameters required for identifying each high-risk plaque are sequentially acquired;

Identify the high-risk plaque according to the high-risk plaque assessment rules and the image parameters corresponding to the high-risk plaque, until all high-risk plaques in the identification sequence are identified, and obtain the high-risk plaque identification result corresponding to the plaque area;

In response to the high-risk plaque identification result corresponding to any plaque area in the target branch blood vessel indicating the existence of a high-risk plaque, it is determined that the target branch blood vessel has a high-risk plaque.

Optionally, the identification module 630 is further configured to:

In response to identifying the presence of a high-risk plaque in the target branch vessel, determining the plaque region to which the high-risk plaque belongs;

According to the determined plaque area and the original total medical image, the plaque position of the high-risk plaque is determined by adopting the shortest distance mapping processing method.

Please refer to FIG8, which is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in FIG. 8 , the electronic device 800 includes a processor 810 , a memory 820 , and a bus 830 .

The memory 820 stores machine-readable instructions executable by the processor 810. When the electronic device 800 is running, the processor 810 communicates with the memory 820 via a bus 830. When the machine-readable instructions are executed by the processor 810, the steps in the method embodiment shown in FIG. 1 above can be executed. For specific implementation methods, please refer to the method embodiment.

An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the method embodiment shown in FIG. 1 can be executed. For specific implementation methods, please refer to the method embodiment.

Those skilled in the art may understand that, for the convenience and brevity of description, the working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments.

In some embodiments provided in the present application, the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are schematic. For example, the division of the units is a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement the solution of this embodiment.

In each embodiment of the present application, multiple functional units may be integrated into one processing unit, or multiple functional units may exist physically separately, or two or more functional units may be integrated into one processing unit.

If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the solution of the present application, or the part that contributes to the relevant technology or the part of the solution, can be embodied in the form of a software product, which is stored in a storage medium and includes at least one instruction to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims (10)

A method for identifying plaque in a blood vessel, comprising: In response to the presence of plaques in the target blood vessel to be identified, original plaque medical image data corresponding to each plaque is determined according to an original total medical image of the target blood vessel; the target blood vessel includes at least one branch blood vessel; For each branch blood vessel, according to the pixel value and region type division rule in the original plaque medical image data, the plaque region corresponding to each plaque in the branch blood vessel is divided to determine at least one plaque sub-region and the region type of each plaque sub-region; For each target branch vessel having a target plaque sub-region of any specified region type, identifying the plaque region of the target branch vessel having the target plaque sub-region according to the high-risk plaque assessment rule and the corresponding imaging parameters, and determining whether the target branch vessel has a high-risk plaque; In response to determining that a high-risk plaque exists in the target branch vessel, a high-risk plaque identification result of the target branch vessel is output; the plaque identification result includes the high-risk plaque type, the plaque location, and the vessel name of the target branch vessel. The identification method according to claim 1, wherein the presence of plaque in the target blood vessel to be identified is determined by: Acquiring a three-dimensional reconstructed blood vessel model of the target blood vessel; identifying, according to a morphological processing method, whether there is a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel; In response to identifying the presence of a mutation region in the three-dimensional reconstructed blood vessel model of the target blood vessel, it is determined that a plaque exists in the target blood vessel. The identification method according to claim 2, wherein the three-dimensional reconstructed blood vessel model of the target blood vessel is constructed by: Performing centerline extraction processing on the original total medical image of the target blood vessel to determine the centerline of the target blood vessel; Performing contour recognition according to the centerline of the target blood vessel and the original total medical image to determine the intima contour and the adventitia contour of the target blood vessel; Performing lofting processing on the intima contour and the adventitia contour of the target blood vessel respectively to obtain an intima curved surface model and an adventitia curved surface model of the target blood vessel; According to the intima curved surface model and the adventitia curved surface model of the target blood vessel, volume filling processing is performed to obtain a three-dimensional reconstructed blood vessel model of the target blood vessel; the three-dimensional reconstructed blood vessel model of the target blood vessel includes an intima three-dimensional model and an adventitia three-dimensional model. The identification method according to claim 3, wherein the determining of the original corresponding to each plaque Initial plaque medical imaging data, including: Determine a three-dimensional reconstruction result of all plaques in the target blood vessel using a result obtained by subtracting a three-dimensional model of the inner membrane from a three-dimensional model of the outer membrane of the target blood vessel; According to the three-dimensional reconstruction results of all plaques, the medical image at the corresponding position is extracted from the original total medical image of the target blood vessel to determine the original plaque medical image data corresponding to each plaque. According to the recognition method according to claim 1, wherein the region type division rule is a rule for setting different pixel threshold ranges for different region types to perform plaque quantitative analysis. The identification method according to claim 1, wherein for each target branch vessel having a target plaque sub-region of any specified region type, identifying the plaque region having the target plaque sub-region in the target branch vessel according to the high-risk plaque assessment rule and the corresponding image parameters, and determining whether the target branch vessel has a high-risk plaque, comprises: For each plaque region in each target branch blood vessel where a target plaque sub-region exists, determining an identification order of high-risk plaques according to a region type of the target plaque sub-region in the plaque region; According to the determined recognition order of high-risk plaques, imaging parameters required for identifying each high-risk plaque are sequentially acquired; Identify the high-risk plaque according to the high-risk plaque assessment rules and the image parameters corresponding to the high-risk plaque, until all high-risk plaques in the identification sequence are identified, and obtain the high-risk plaque identification result corresponding to the plaque area; In response to the high-risk plaque identification result corresponding to any plaque area in the target branch blood vessel indicating the existence of a high-risk plaque, it is determined that the target branch blood vessel has a high-risk plaque. The identification method according to claim 6, wherein the plaque position includes the plaque position of each high-risk plaque, and the plaque position of each high-risk plaque is determined by: In response to identifying the presence of a high-risk plaque in the target branch vessel, determining the plaque region to which the high-risk plaque belongs; According to the determined plaque area and the original total medical image, the plaque position of the high-risk plaque is determined by adopting the shortest distance mapping processing method. A device for identifying plaque in a blood vessel, comprising: A first determination module is configured to determine original plaque medical image data corresponding to each plaque according to an original total medical image of the target blood vessel in response to the presence of plaque in the target blood vessel to be identified; the target blood vessel includes at least one branch blood vessel; The segmentation module is configured to segment the plaque area corresponding to each plaque in the branch vessel according to the pixel value and area type segmentation rule in the original plaque medical imaging data for each branch vessel. Determine at least one plaque sub-region and a region type of each plaque sub-region; an identification module configured to identify, for each target branch vessel having a target plaque sub-region of any specified region type, a plaque region in the target branch vessel having a target plaque sub-region according to a high-risk plaque assessment rule and corresponding imaging parameters, to determine whether the target branch vessel has a high-risk plaque; The output module is configured to output a high-risk plaque identification result of the target branch blood vessel in response to determining that the target branch blood vessel has a high-risk plaque; the plaque identification result includes the high-risk plaque type, the plaque location and the blood vessel name of the target branch blood vessel. An electronic device comprises: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate with each other via the bus, and when the processor runs, the machine-readable instructions execute the method for identifying plaques in blood vessels as described in any one of claims 1 to 7. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, executes the method for identifying plaque in a blood vessel as claimed in any one of claims 1 to 7.