Method, apparatus, computer device and medium for determining pulmonary artery blood flow fraction

Abstract

The present invention relates to the technical field of image processing, and discloses a method, device, computer device and medium for determining the pulmonary artery blood flow fraction. The method includes: obtaining a pulmonary artery tomographic scan image to be processed, pulmonary artery blood flow parameters, and pulmonary artery orifice pressure parameters; performing multi-planar reconstruction processing on the pulmonary artery tomographic scan image to obtain three views corresponding to the pulmonary artery tomographic scan image; segmenting a pulmonary artery image sequence from the three views, performing three-dimensional reconstruction on the pulmonary artery image sequence to generate a three-dimensional pulmonary artery image; extracting a pulmonary artery stenosis region from the three-dimensional pulmonary artery image; and determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters. In the embodiments of the present invention, the lesions of the pulmonary artery image can be objectively and accurately determined through the pulmonary artery blood flow fraction.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method, device, computer device and storage medium for determining the pulmonary artery blood flow fraction. Background Art

[0002] In current pulmonary arteriography surgeries, the characteristics of the patient's lesion sites are small in individual volume, uncertain in location, and unfixed in quantity, making it impossible to accurately determine the pulmonary artery lesions from the pulmonary arteries with a large number of vessels and complex structures.

[0003] Currently, doctors often determine the stenosis location of the pulmonary artery from angiographic images based on their own experience, and then determine the pulmonary artery lesions through the stenosis location of the pulmonary artery. However, the method of determining pulmonary artery lesions based on personal experience has a large degree of subjectivity and cannot objectively determine pulmonary artery lesions through changes in some parameters. Since the method of doctors subjectively determining pulmonary artery lesions may have deviations, it is impossible to accurately determine pulmonary artery lesions. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, computer device and medium for determining the pulmonary artery blood flow fraction to solve the problem that doctors cannot accurately determine pulmonary artery lesions because the method of determining pulmonary artery lesions based on their own experience has a large degree of subjectivity.

[0005] In a first aspect, the present invention provides a method for determining the pulmonary artery blood flow fraction. The method includes: obtaining a pulmonary artery tomographic scan image to be processed, pulmonary artery blood flow parameters, and pulmonary artery orifice pressure parameters; performing multi-planar reconstruction processing on the pulmonary artery tomographic scan image to obtain three views corresponding to the pulmonary artery tomographic scan image; segmenting a pulmonary artery image sequence from the three views, performing three-dimensional reconstruction on the pulmonary artery image sequence to generate a pulmonary artery three-dimensional image; extracting a pulmonary artery stenosis region from the pulmonary artery three-dimensional image; and determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters.

[0006] The method for determining the pulmonary artery blood flow fraction provided in this embodiment determines the pulmonary artery blood flow fraction of the pulmonary artery stenosis region in the pulmonary artery image sequence through the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters. The pulmonary artery blood flow fraction can characterize the blood flow situation in the pulmonary artery stenosis region, and the lesion situation in the pulmonary artery can be reflected through this blood flow situation, that is, the lower the pulmonary artery blood flow fraction, the more serious the lesion situation. Compared with subjectively determining the lesion situation relying on human experience, this method objectively reflects the lesion situation of the pulmonary artery by determining the pulmonary artery blood flow fraction.

[0007] In an alternative embodiment, extracting the pulmonary artery stenosis region from the three-dimensional pulmonary artery image includes: for any target blood vessel in the three-dimensional pulmonary artery image, segmenting the target blood vessel to obtain a plurality of blood vessel segments corresponding to the target blood vessel; determining the point cloud data corresponding to each blood vessel segment; performing fitting processing on the point cloud data to generate a spherical surface corresponding to each blood vessel segment; and determining the pulmonary artery stenosis region of the target blood vessel based on the center point and the spherical radius corresponding to each spherical surface.

[0008] In the method for determining the pulmonary artery blood flow fraction provided in this embodiment, the spherical radii corresponding to each center point may be different, that is, there are spherical radii with normal values and spherical radii with abnormal values, and the spherical radii with abnormal values constitute the pulmonary artery stenosis region. Thus, by determining the center point and the spherical radius of each blood vessel in the three-dimensional pulmonary artery image, the pulmonary artery stenosis region of the target blood vessel can be accurately located.

[0009] In an alternative embodiment, determining the pulmonary artery stenosis region of the target blood vessel based on the center point and the spherical radius corresponding to each spherical surface includes: determining the center point and the spherical radius of each spherical surface; generating a center line corresponding to the blood vessel based on each center point; determining the pulmonary artery stenosis position based on the change state of the spherical radius corresponding to each center point on the center line; and determining the pulmonary artery stenosis region based on the pulmonary artery stenosis position and a first preset distance.

[0010] In the method for determining the pulmonary artery blood flow fraction provided in this embodiment, the change state of the spherical radius is determined through the center line, so that the pulmonary artery stenosis position can be accurately determined, and the pulmonary artery stenosis region is determined through the pulmonary artery stenosis position and the first preset distance, so that the lesion area can be increased, the omission of the lesion position can be avoided, and the lesion of the pulmonary artery can be determined more accurately.

[0011] In an alternative embodiment, the method for determining the spherical radius includes: obtaining the target position on the inner wall of the blood vessel segment; determining the intersection point of the target position and the spherical surface; and determining the spherical radius based on the intersection point and the center point.

[0012] In the method for determining the pulmonary artery blood flow fraction provided in this embodiment, by determining the intersection point of the target position on the inner wall of the blood vessel segment and the spherical surface, the intersection point can be on the target position and the spherical surface, so as to ensure that the connection line between the intersection point and the center point is perpendicular to the center line, and thus the width of the inner wall of the blood vessel segment can be determined more accurately.

[0013] In an alternative embodiment, determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters includes: determining the pressure drop at each vascular point in the pulmonary artery stenosis region based on the pulmonary artery orifice pressure parameters and the pulmonary artery blood flow parameters; for any target vascular point among each vascular point, determining any other vascular point that is at a second preset distance from the target vascular point; and determining the pulmonary artery blood flow fraction corresponding to the target vascular point in the pulmonary artery stenosis region based on the pressure drop at the target vascular point and the pressure drop at any other vascular point.

[0014] The method for determining the pulmonary artery blood flow fraction provided in this embodiment can accurately determine the pressure drop at each vascular point through the pulmonary artery blood flow parameters. Since the pressure drops at different positions in the pulmonary artery stenosis region are different, the ratio of the pressure drop at the target vascular point to the pressure drop at other vascular points can be used to determine the change in the pressure drop corresponding to each target vascular point, thereby accurately determining the pulmonary artery blood flow fraction corresponding to each target vascular point.

[0015] In an alternative embodiment, the method further includes: detecting the value of the pulmonary artery blood flow fraction at the target vascular point; and determining the lesion location of the pulmonary artery based on the target vascular point with the minimum value.

[0016] The method for determining the pulmonary artery blood flow fraction provided in this embodiment indicates that the target vascular point with the minimum value represents the most severe lesion condition at the position corresponding to the target vascular point. By determining the target vascular point with the minimum value from the values of the pulmonary artery blood flow fractions of each target vascular point, the lesion location of the pulmonary artery can be accurately determined.

[0017] In an alternative embodiment, the three-view images have grayscale data; wherein, before extracting the pulmonary artery stenosis region from the three-dimensional pulmonary artery image, the method further includes: performing a conversion process on the grayscale data to generate binary data corresponding to the grayscale data; and mapping the binary data to the three-view images and performing a color assignment process on the three-view images so that the pulmonary artery is displayed on the three-view images.

[0018] The method for determining the pulmonary artery blood flow fraction provided in this embodiment can display the pulmonary artery on the three-view images by performing a conversion process and a color assignment process on the grayscale data in the three-view images, thereby facilitating the viewing of the pulmonary artery.

[0019] Second aspect, the present invention provides a device for determining pulmonary artery blood flow fraction. The device includes an acquisition module for acquiring pulmonary artery tomography images to be processed, pulmonary artery blood flow parameters, and pulmonary artery pressure parameters; a multi-planar reconstruction module for performing multi-planar reconstruction processing on the pulmonary artery tomography images to obtain three views corresponding to the pulmonary artery tomography images; a segmentation and reconstruction module for segmenting a pulmonary artery image sequence from the three views, performing three-dimensional reconstruction on the pulmonary artery image sequence to generate a three-dimensional pulmonary artery image; an extraction module for extracting a pulmonary artery stenosis region from the three-dimensional pulmonary artery image; and a pulmonary artery blood flow fraction determination module for determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery pressure parameters.

[0020] Third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method for determining pulmonary artery blood flow fraction according to the first aspect or any corresponding embodiment thereof.

[0021] Fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the method for determining pulmonary artery blood flow fraction according to the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 is a flowchart of the method for determining pulmonary artery blood flow fraction according to an embodiment of the present invention;

[0024] Figure 2 is a flowchart of another method for determining pulmonary artery blood flow fraction according to an embodiment of the present invention;

[0025] Figure 3 is a flowchart of yet another method for determining pulmonary artery blood flow fraction according to an embodiment of the present invention;

[0026] Figure 4 is a structural block diagram of the device for determining pulmonary artery blood flow fraction according to an embodiment of the present invention;

[0027] Figure 5It is a schematic diagram of the hardware structure of the computer device according to an embodiment of the present invention. Detailed implementation manners

[0028] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] In the related art, doctors often determine the stenosis position of the pulmonary artery from the angiographic images based on their own experience, and then determine the pulmonary artery lesions through the stenosis position of the pulmonary artery. However, the method of determining pulmonary artery lesions based on personal experience has a large degree of subjectivity and cannot objectively determine pulmonary artery lesions through changes in some parameters. Since the method of subjectively determining pulmonary artery lesions by doctors may have deviations, the pulmonary artery lesions cannot be accurately determined.

[0030] Based on this, the technical solution of the present invention combines pulmonary artery blood flow parameters and pulmonary artery orifice pressure parameters to determine the pulmonary artery blood flow fraction in the pulmonary artery stenosis area, and objectively determines the lesions of the pulmonary artery through the pulmonary artery blood flow fraction.

[0031] According to an embodiment of the present invention, an embodiment of a method for determining the pulmonary artery blood flow fraction is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0032] In this embodiment, a method for determining the pulmonary artery blood flow fraction is provided, which can be used in computer devices such as computers and CT scanning devices. Figure 1 It is a flowchart of the method for determining the pulmonary artery blood flow fraction according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0033] Step S101, obtain the pulmonary artery tomographic scan image, pulmonary artery blood flow parameters, and pulmonary artery orifice pressure parameters to be processed.

[0034] Pulmonary artery tomographic images can be obtained through CT pulmonary angiography. Among them, CT pulmonary angiography is to rapidly inject an iodine contrast agent into the peripheral superficial vein. The contrast agent enters the pulmonary artery through the superior vena cava, right atrium, and right ventricle, making the pulmonary artery visible, and imaging is performed through CT scanning. Among them, the CT scanning imaging method can use a spiral CT machine or an electron beam CT machine to scan the pulmonary artery to obtain pulmonary artery tomographic images.

[0035] The pulmonary artery blood flow parameter can be the blood flow velocity of the pulmonary artery. Among them, the blood flow velocity of the pulmonary artery can be detected by detection instruments such as vascular detectors and blood flow velocity observation instruments, or the blood flow velocity of the pulmonary artery can be determined by ultrasonic velocity measurement methods and DSA angiography image frame counting methods, which are not specifically limited here.

[0036] The pulmonary artery orifice pressure parameter can be the average pressure parameter of the blood vessels in the pulmonary artery. Among them, the pulmonary artery orifice pressure parameter can be measured by measuring instruments such as pulmonary artery pressure gauges and PICCO monitors, which are not specifically limited here.

[0037] Step S102: Perform multi-planar reconstruction processing on the pulmonary artery tomographic image to obtain the three-view drawings corresponding to the pulmonary artery tomographic image.

[0038] After the computer device obtains the pulmonary artery tomographic image, perform multi-planar reconstruction processing on the pulmonary artery tomographic image to obtain the three-view drawings of the pulmonary artery tomographic image. Among them, the three-view drawings can include the sagittal plane, cross-section, and coronal plane. Among them, the pulmonary artery is cut into left and right parts, and the left section and the right section are the sagittal plane; the pulmonary artery is cut into front and back parts, and the front section and the back section are the coronal plane; the pulmonary artery is cut into upper and lower parts, and the upper section and the lower section are the cross-section.

[0039] Multi-planar reconstruction processing (MPR, multi_planner reformat1n) is specifically characterized by superimposing all the axial images within the scanning range, and then performing image recombination at any angle such as sagittal, transverse, and coronal on the tissue specified by the recombination line marked by certain marking lines.

[0040] Step S103: Segment the pulmonary artery image sequence from the three-view drawings, and perform three-dimensional reconstruction on the pulmonary artery image sequence to generate a three-dimensional pulmonary artery image.

[0041] As can be seen from the above content, the three views are obtained based on pulmonary artery tomography images. The three views not only include the pulmonary artery image sequence, but may also include some other influencing factors. It is necessary to segment the cross-sectional, coronal, and sagittal planes of the pulmonary artery image sequence from the three views, and through three-dimensional reconstruction of the cross-sectional, coronal, and sagittal planes, generate a three-dimensional image of the pulmonary artery, thereby excluding other influencing factors. Specifically, the method of segmenting the pulmonary artery image sequence from the three views can adopt region growing algorithms, semantic segmentation algorithms, etc., which are not specifically limited herein.

[0042] Specifically, for the region generation algorithm, the computer device can obtain the gray values of each pixel corresponding to multiple regions in the three views. For each region, a target pixel point of the pulmonary artery is specified, and starting from this target pixel point, other pixel points around the target pixel point are compared. According to the comparison results, pixel points with the same gray value are merged until all pixel points with the same gray value as the target pixel point in all regions are merged, and then the process stops, thereby obtaining the cross-sectional, coronal, and sagittal planes of the pulmonary artery image sequence.

[0043] It should be noted that the purpose of three-dimensional reconstruction of the pulmonary artery image sequence is to grid the pixel points in the three views. Specifically, a pile of discrete point clouds is structured, the topological relationship between points is found, and then two pixel points are connected according to certain rules to form a grid.

[0044] Step S104, determine the pulmonary artery stenosis region from the three-dimensional image of the pulmonary artery.

[0045] The pulmonary artery stenosis region can be the region where lesions occur in the pulmonary artery. If a pulmonary artery stenosis region appears in the three-dimensional image of the pulmonary artery, it indicates that blood cannot normally pass through the pulmonary artery into the pulmonary circulation. Among them, the computer device can determine the pulmonary artery stenosis region from the three-dimensional image of the pulmonary artery. Specifically, the specific steps for determining the pulmonary artery stenosis region are described in detail below.

[0046] Step S105, based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters, determine the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region.

[0047] Since the stenosis widths of the pulmonary artery vessels at different positions in the pulmonary artery stenosis region are different, the pulmonary artery blood flow parameters at different positions in the pulmonary artery stenosis region are different, and the corresponding pressures at their positions are also different. Therefore, the pressure corresponding to each position can be determined through the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters at each position, thereby determining the pulmonary artery blood flow fraction. Among them, the pulmonary artery blood flow fraction is used to characterize the lesion situation in the pulmonary artery stenosis region. For example, the smaller the pulmonary artery blood flow fraction, the greater the impact of the lesion.

[0048] The method for determining the pulmonary artery blood flow fraction provided in this embodiment determines the pulmonary artery blood flow fraction in the pulmonary artery stenosis region of the pulmonary artery image sequence through pulmonary artery blood flow parameters and pulmonary artery orifice pressure parameters. This pulmonary artery blood flow fraction can characterize the blood flow condition in the pulmonary artery stenosis region, and the lesion condition in the pulmonary artery can be reflected through this blood flow condition, that is, the lower the pulmonary artery blood flow fraction, the more serious the lesion condition. Compared with subjectively determining the lesion condition relying on human experience, this method objectively reflects the lesion condition of the pulmonary artery by determining the pulmonary artery blood flow fraction.

[0049] In this embodiment, a method for determining the pulmonary artery blood flow fraction is provided, which can be used in computer devices, such as computers, CT scanning devices, etc. Figure 2 It is a flowchart of the method for determining the pulmonary artery blood flow fraction according to an embodiment of the present invention, as Figure 2 shown, and this process includes the following steps:

[0050] Step S201, obtain the pulmonary artery tomographic scan image to be processed, pulmonary artery blood flow parameters, and pulmonary artery orifice pressure parameters. For details, please refer to Figure 1 step S101 of the embodiment shown, which will not be elaborated here.

[0051] Step S202, perform multi-planar reconstruction processing on the pulmonary artery tomographic scan image to obtain three views corresponding to the pulmonary artery tomographic scan image. For details, please refer to Figure 1 step S102 of the embodiment shown, which will not be elaborated here.

[0052] Step S203, segment the pulmonary artery image sequence from the three views, and perform three-dimensional reconstruction on the pulmonary artery image sequence to generate a pulmonary artery three-dimensional image. For details, please refer to Figure 1 step S103 of the embodiment shown, which will not be elaborated here.

[0053] Step S204, determine the pulmonary artery stenosis region from the pulmonary artery three-dimensional image.

[0054] Specifically, the above step S204 includes:

[0055] Step S2041, for any target blood vessel in the pulmonary artery three-dimensional image, segment the target blood vessel to obtain multiple blood vessel segments corresponding to the target blood vessel.

[0056] The pulmonary artery three-dimensional image includes multiple target blood vessels. The target blood vessel can be segmented from the starting end of the target blood vessel until the end of the blood vessel, so as to obtain multiple blood vessel segments. For example, the length of each blood vessel segment can be 1-8 millimeters, and no specific limitation is made here.

[0057] Step S2042, determine the point cloud data corresponding to each blood vessel segment.

[0058] As can be seen from the above content, the pixel points in the three-dimensional pulmonary artery image are all meshed to form point cloud data. Then, the pixel points corresponding to each target blood vessel are meshed to form point cloud data corresponding to each target blood vessel. The target blood vessels include multiple blood vessel segments. Then, the pixel points corresponding to each blood vessel segment are meshed to form point cloud data corresponding to each blood vessel segment. Among them, after the computer device divides the target blood vessels into multiple blood vessel segments, it can collect or extract the point cloud data corresponding to each blood vessel segment.

[0059] Step S2043: Perform fitting processing on the point cloud data to generate spheres corresponding to each blood vessel segment.

[0060] The point cloud data within the blood vessel segment is scattered point cloud data. It is necessary to fit the scattered point cloud data into a sphere, and then fit the point cloud data within each blood vessel segment into a sphere corresponding to each blood vessel segment.

[0061] Specifically, performing fitting processing on the point cloud data means approximating or fitting the point cloud data through a mathematical model to extract the geometric shapes or features therein, and generating corresponding spheres in combination with the extracted geometric shapes or features. For example, here, the Nurbs curve fitting algorithm can be used to connect multiple data points into a broken line, and the least squares fitting method is used to gradually convert the broken line into a curve to fit and generate a sphere. It can also be the Random Sample Consensus (RANSAC) algorithm, which randomly samples a set of data from the point cloud data to fit the sphere model, and judges whether the point cloud data conforms to the sphere model according to a predetermined threshold to obtain the best sphere fitting result. Of course, other fitting methods can also be used, which are not specifically limited here.

[0062] Step S2044: Determine the pulmonary artery stenosis region of the target blood vessel based on the center points and sphere radii corresponding to each sphere.

[0063] Each sphere includes a center point and a sphere radius. Among them, after the computer device determines the sphere radii corresponding to the center points in the target blood vessel, it can determine the sphere radii that do not meet the conditions from the sphere radii, determine the position of the center point corresponding to the sphere radius that does not meet the conditions through the sphere radius that does not meet the conditions, and determine the pulmonary artery stenosis region through the position of the center point. Among them, by taking the derivative of each sphere radius, the point where the derivative is equal to zero can be used as the stenosis position.

[0064] Specifically, the above step S2044 includes:

[0065] Step a1: Determine the center points and sphere radii of each sphere.

[0066] When the computer device performs spherical fitting, it can determine the center point of the sphere, and the sphere radius can be determined through the intersection points of the sphere and the blood vessel wall. Specifically, the method for determining the sphere radius is described in detail below.

[0067] Specifically, the method for determining the sphere radius in step a1 includes:

[0068] Step a11, obtain the target position of the inner wall of the blood vessel segment.

[0069] Step a12, determine the intersection points of the target position and the sphere.

[0070] Step a13, determine the sphere radius based on the intersection points and the center point.

[0071] As can be seen from the above content, the pulmonary artery stenosis region is determined by the sphere radius corresponding to the center point. Among them, the sphere radius can be the distance from the inner wall of the blood vessel segment to the center point. The computer device can determine the sphere radius through the connection line between the center point and the intersection point of the sphere. Among them, the detection instrument can be used to determine the target position of the inner wall of the blood vessel segment. Specifically, the detection instrument can be a blood vessel imaging instrument, an intravascular ultrasound diagnostic instrument, etc., which is not specifically limited here.

[0072] Step a2, generate the center line of the corresponding blood vessel based on each center point.

[0073] Connect the center points of each blood vessel segment in the target blood vessel to generate the center line of the corresponding blood vessel.

[0074] Step a3, determine the pulmonary artery stenosis position based on the change state of the sphere radius corresponding to each center point on the center line.

[0075] Along the center line from the starting end to the ending end of the target blood vessel, determine the sphere radius corresponding to each center point on the center line, so as to be able to determine the change state of the sphere radius corresponding to this center line. Then, according to the change state of the sphere radius, determine the sphere radius that does not meet the conditions, determine the position of the center point corresponding to this sphere radius through the sphere radius that does not meet the conditions, and determine the pulmonary artery stenosis position according to the position of the center point.

[0076] Step a4, determine the pulmonary artery stenosis region based on the pulmonary artery stenosis position and the first preset distance.

[0077] Determining the pulmonary artery stenosis position for the center point cannot fully display the lesions of the pulmonary artery, and there may be omissions. Therefore, when determining the pulmonary artery stenosis position, it is necessary to extend forward and / or backward along the center line by the first preset distance to determine the pulmonary artery stenosis region. Specifically, the first preset distance can be 1 cm, 2 cm, etc., which is not specifically limited here.

[0078] Step S205: Based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters, determine the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region. For details, please refer to Figure 1 Step S105 of the embodiment shown, which will not be elaborated here.

[0079] In the method for determining the pulmonary artery blood flow fraction provided in this embodiment, the spherical radii corresponding to each center point may be different, that is, there are spherical radii with normal values and there are also spherical radii with abnormal values. The spherical radii with abnormal values constitute the pulmonary artery stenosis region. Thus, by determining the center points and spherical radii of each blood vessel in the three-dimensional pulmonary artery image, the pulmonary artery stenosis region of the target blood vessel can be accurately located.

[0080] In this embodiment, a method for determining the pulmonary artery blood flow fraction is provided, which can be used in computer devices such as computers and CT scanning devices. Figure 3 It is a flowchart of the method for determining the pulmonary artery blood flow fraction according to an embodiment of the present invention, as Figure 3 shown, and this process includes the following steps:

[0081] Step S301: Obtain the pulmonary artery tomographic scan image to be processed, the pulmonary artery blood flow parameters, and the pulmonary artery orifice pressure parameters. For details, please refer to Figure 2 Step S201 of the embodiment shown, which will not be elaborated here.

[0082] Step S302: Perform multi-planar reconstruction processing on the pulmonary artery tomographic scan image to obtain the three views corresponding to the pulmonary artery tomographic scan image. For details, please refer to Figure 2 Step S202 of the embodiment shown, which will not be elaborated here.

[0083] Step S303: Segment the pulmonary artery image sequence from the three views, and perform three-dimensional reconstruction on the pulmonary artery image sequence to generate a three-dimensional pulmonary artery image. For details, please refer to Figure 2 Step S203 of the embodiment shown, which will not be elaborated here.

[0084] Step S304: Determine the pulmonary artery stenosis region from the three-dimensional pulmonary artery image. For details, please refer to Figure 2 Step S204 of the embodiment shown, which will not be elaborated here.

[0085] Step S305: Based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters, determine the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region.

[0086] Specifically, the above Step S305 includes:

[0087] Step S3051: Based on the pulmonary artery orifice pressure parameters and the pulmonary artery blood flow parameters, determine the pressure drop of each blood vessel point in the pulmonary artery stenosis region.

[0088] The pressure drop refers to the difference in pressure between the next blood vessel point and the previous blood vessel point for a target blood vessel point on a continuous curve.

[0089] Preferably, after the three-dimensional image of the pulmonary artery is meshed, each blood vessel point in the three-dimensional image can be represented by coordinates, for example: (x, y, z). After determining the pressure drop of each blood vessel point, the pressure drop can be brought into the coordinates so that the target value of each blood vessel point is (x, y, z, pressg); where pressg is the pressure drop. If the spatial description of the blood vessel points is changed to colored coordinate points, and different colors can be displayed according to different pressure drops. For example, the pressure drop being too high can be blue, and the pressure drop being too low can be red.

[0090] Step S3052, for any one target blood vessel point among each blood vessel point, determine any one other blood vessel point that is at a second preset distance from the target blood vessel point.

[0091] The second preset distance can be the distance between the target blood vessel point and the other blood vessel point. Specifically, the second preset distance can be a specific value, such as 0.5 cm, 1 cm, 2 cm, etc., or it can be a range value, such as 0.5 - 2 cm, etc., and no specific limitation is made here. Among them, after the computer device determines a target blood vessel point, it can take the target blood vessel point as the starting point and the second preset distance as the range to determine other blood vessel points that meet the second preset distance.

[0092] Step S3053, based on the pressure drop of the target blood vessel point and the pressure drop of any one other blood vessel point, determine the pulmonary artery blood flow fraction corresponding to the target blood vessel point in the pulmonary artery stenosis region.

[0093] The formula is ctpfr = Px / Py; where ctpfr is the pulmonary artery blood flow fraction, Px is the target blood vessel point, and Py is the other blood vessel point that is at a second preset distance from the target blood vessel point. Among them, the pulmonary artery blood flow fraction can be determined through the ratio of the target blood vessel point and the other blood vessel point.

[0094] The method for determining the pulmonary artery blood flow fraction provided in this embodiment can accurately determine the pressure drop of each blood vessel point through the pulmonary artery blood flow parameters. Since the pressure drops at various positions in the pulmonary artery stenosis region are different, through the ratio of the pressure drop of the target blood vessel point and the pressure drop of the other blood vessel point, the change in the pressure drop corresponding to each target blood vessel point can be determined, thereby accurately determining the pulmonary artery blood flow fraction of each target blood vessel point.

[0095] In an optional implementation manner, after step S3053, the above method further includes:

[0096] Step b1, detect the value of the pulmonary artery blood flow fraction of the target blood vessel point.

[0097] Step b2: Determine the lesion location of the pulmonary artery based on the target vascular point with the smallest value.

[0098] After the computer device obtains the pulmonary artery blood flow fraction of each target vascular point, it can detect the value of the pulmonary artery blood flow fraction corresponding to each target vascular point in the pulmonary artery stenosis region, and determine the pulmonary artery blood flow fraction with the smallest value from the values of multiple pulmonary artery blood flow fractions. Based on the pulmonary artery blood flow fraction with the smallest value, the lesion location of the pulmonary artery can be determined.

[0099] In the method for determining the pulmonary artery blood flow fraction provided in this embodiment, the target vascular point with the smallest value represents the most severe lesion condition at the position corresponding to the target vascular point. By determining the target vascular point with the smallest value from the values of the pulmonary artery blood flow fraction of each target vascular point, the lesion location of the pulmonary artery can be accurately determined.

[0100] In an alternative embodiment, the above method further includes:

[0101] Step c1: Perform conversion processing on the grayscale data to generate binary data corresponding to the grayscale data.

[0102] The grayscale data can be characterized by the image in the three-view drawing being a grayscale image. Among them, the range of the grayscale data is (0 - 255). The binary data can be used to characterize that the image is a black and white image. Among them, converting the grayscale data into binary data is to convert the pixel values in the image from a continuous grayscale range into a binary image with only two discrete values. Among them, the range of the binary data is (0 - 1). For example, the grayscale data can be converted into binary data by using a fixed threshold algorithm, an adaptive threshold algorithm, etc. Here, the conversion method is not specifically limited.

[0103] It should be noted that the color of the image is determined by the grayscale value. The grayscale value refers to the brightness value of each pixel in the image, usually represented by an integer from 0 to 255. In a grayscale image, the grayscale value of each pixel represents the brightness of the pixel. The larger the grayscale value, the higher the brightness of the pixel, and the smaller the grayscale value, the lower the brightness of the pixel. For example, a grayscale value of 0 represents black, a grayscale value of 255 represents white, and the values between 0 and 255 represent different grayscale levels.

[0104] Step c2: Map the binary data to the three-view drawing and perform color assignment processing on the three-view drawing so that the pulmonary artery is displayed on the three-view drawing.

[0105] The binary data can be gray and white. For example, RGB(255, 225, 255) is white, and RGB(123, 123, 123) is gray. Among them, the RGB color model is a color standard in the industrial field, which is based on red (R), green (G), and blue (B). Map the binary data into the three-view drawings so that the three-view drawings show gray and white, and perform color assignment processing on the three-view drawings. For example, RGB(255, 0, 0) is red, so that the pulmonary artery can be clearly shown and distinguished from other parts on the three-view drawings.

[0106] Preferably, on the basis of color assignment, transparency can be added to the pulmonary artery, such as RGBA(255, 0, 0, 128), where A is the transparency, so as to avoid the color of red being too deep and blocking other contents.

[0107] The method for determining the pulmonary artery blood flow fraction provided in this embodiment can display the pulmonary artery on the three-view drawings by performing conversion processing and color assignment processing on the gray data in the three-view drawings, thereby facilitating the viewing of the pulmonary artery.

[0108] In this embodiment, a device for determining the pulmonary artery blood flow fraction is also provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0109] This embodiment provides a device for determining the pulmonary artery blood flow fraction, as Figure 4 shown, including:

[0110] An acquisition module 401, configured to acquire a pulmonary artery tomographic scan image to be processed, pulmonary artery blood flow parameters, and pulmonary artery pressure parameters;

[0111] A multi-planar reconstruction module 402, configured to perform multi-planar reconstruction processing on the pulmonary artery tomographic scan image to obtain three-view drawings corresponding to the pulmonary artery tomographic scan image;

[0112] A segmentation and reconstruction module 403, configured to segment a pulmonary artery image sequence from the three-view drawings, perform three-dimensional reconstruction on the pulmonary artery image sequence, and generate a pulmonary artery three-dimensional image;

[0113] An extraction module 404, configured to extract a pulmonary artery stenosis region from the pulmonary artery three-dimensional image;

[0114] A pulmonary artery blood flow fraction determination module 405, configured to determine the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery pressure parameters.

[0115] In an alternative embodiment, the extraction module 404 includes: a segmentation processing unit configured to perform segmentation processing on any target blood vessel in the three-dimensional pulmonary artery image to obtain a plurality of blood vessel segments corresponding to the target blood vessel; a first determination unit configured to determine the point cloud data corresponding to each blood vessel segment; a generation unit configured to perform fitting processing on the point cloud data to generate a spherical surface corresponding to each blood vessel segment; and a second determination unit configured to determine the pulmonary artery stenosis region of the target blood vessel based on the center point and the spherical radius corresponding to each spherical surface.

[0116] In an alternative embodiment, the second determination unit includes:

[0117] a first determination subunit configured to determine the center point and the spherical radius of each spherical surface.

[0118] a generation subunit configured to generate a center line of the corresponding blood vessel based on each center point.

[0119] a second determination subunit configured to determine the pulmonary artery stenosis position based on the change state of the spherical radius corresponding to each center point on the center line.

[0120] a third determination subunit configured to determine the pulmonary artery stenosis region based on the pulmonary artery stenosis position and a first preset distance.

[0121] In an alternative embodiment, the first determination subunit includes:

[0122] an acquisition subunit configured to acquire the target position of the inner wall of the blood vessel segment.

[0123] a fourth determination subunit configured to determine the intersection point of the target position and the spherical surface; and a fifth determination subunit configured to determine the spherical radius based on the intersection point and the center point.

[0124] In an alternative embodiment, the pulmonary artery blood flow fraction determination module 405 includes:

[0125] a third determination unit configured to determine the pressure drop of each blood vessel point in the pulmonary artery stenosis region based on the pulmonary artery orifice pressure parameter and the pulmonary artery blood flow parameter.

[0126] a fourth determination unit configured to determine any other blood vessel point spaced apart from the target blood vessel point by a second preset distance for any target blood vessel point among each blood vessel point.

[0127] a fifth determination unit configured to determine the pulmonary artery blood flow fraction corresponding to the target blood vessel point in the pulmonary artery stenosis region based on the pressure drop of the target blood vessel point and the pressure drop of any other blood vessel point.

[0128] In an alternative embodiment, the apparatus for determining the pulmonary artery blood flow fraction further includes:

[0129] A detection module, configured to detect the value of the pulmonary artery blood flow fraction at a target blood vessel point.

[0130] A lesion location determination device, configured to determine the lesion location of the pulmonary artery based on the target blood vessel point with the smallest value.

[0131] In an optional embodiment, the determining device for the pulmonary artery blood flow fraction further includes:

[0132] A conversion processing module, configured to perform conversion processing on the grayscale data to generate binary data corresponding to the grayscale data.

[0133] A color assignment processing module, configured to map the binary data to the three-view drawings and perform color assignment processing on the three-view drawings so that the pulmonary artery is displayed on the three-view drawings.

[0134] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding above-mentioned embodiments, and will not be elaborated here.

[0135] The determining device for the pulmonary artery blood flow fraction in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0136] The determining device for the pulmonary artery blood flow fraction provided in this embodiment determines the pulmonary artery blood flow fraction in the pulmonary artery stenosis region in the pulmonary artery image sequence through the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters. This pulmonary artery blood flow fraction can characterize the blood flow situation in the pulmonary artery stenosis region, and the lesion situation in the pulmonary artery can be reflected through this blood flow situation, that is, the lower the pulmonary artery blood flow fraction, the more serious the lesion situation. Compared with subjectively determining the lesion situation relying on human experience, this method objectively reflects the lesion situation of the pulmonary artery by determining the pulmonary artery blood flow fraction.

[0137] The embodiment of the present invention further provides a computer device having the Figure 5 determining device for the pulmonary artery blood flow fraction as shown above.

[0138] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of a computer device provided by an optional embodiment of the present invention. As shown in Figure 5As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (such as an array of servers, a set of blade servers, or a multi-processor system). Figure 5 In [the figure], a processor 10 is taken as an example.

[0139] The processor 10 can be a central processing unit, a network processor, or a combination thereof. Among them, the processor 10 can further include a hardware chip. The above hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The above programmable logic device can be a complex programmable logic device, a field-programmable gate array, a generic array logic, or any combination thereof.

[0140] Among them, the memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiments.

[0141] The memory 20 can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the computer device, etc. In addition, the memory 20 can include high-speed random access memory and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 can optionally include a memory remotely set relative to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0142] The memory 20 can include volatile memory, such as random access memory; the memory can also include non-volatile memory, such as flash memory, a hard disk, or a solid-state drive; the memory 20 can also include a combination of the above types of memory.

[0143] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0144] Embodiments of the present invention also provide a computer-readable storage medium. The method according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code that is originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0145] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining the pulmonary artery blood flow fraction, characterized in that, the method includes: obtaining a pulmonary artery tomographic image to be processed, pulmonary artery blood flow parameters, and pulmonary artery orifice pressure parameters; wherein, the pulmonary artery tomographic image is obtained by CT pulmonary angiography; performing multi-planar reconstruction processing on the pulmonary artery tomographic image to obtain three views corresponding to the pulmonary artery tomographic image; segmenting a pulmonary artery image sequence from the three views, and performing three-dimensional reconstruction on the pulmonary artery image sequence to generate a three-dimensional pulmonary artery image; determining a pulmonary artery stenosis region from the three-dimensional pulmonary artery image; wherein, the extracting the pulmonary artery stenosis region from the three-dimensional pulmonary artery image specifically includes: for any target blood vessel in the three-dimensional pulmonary artery image, segmenting the target blood vessel to obtain a plurality of blood vessel segments corresponding to the target blood vessel; determining point cloud data corresponding to each blood vessel segment; performing fitting processing on the point cloud data to generate a sphere corresponding to each blood vessel segment; based on the center point and sphere radius corresponding to each sphere, determining the pulmonary artery stenosis region of the target blood vessel; determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters; wherein, the determining the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery orifice pressure parameters includes: determining the pressure drop of each blood vessel point in the pulmonary artery stenosis region based on the pulmonary artery orifice pressure parameters and the pulmonary artery blood flow parameters; for any target blood vessel point among each blood vessel point, determining any other blood vessel point spaced apart from the target blood vessel point by a second preset distance; determining the pulmonary artery blood flow fraction corresponding to the target blood vessel point in the pulmonary artery stenosis region based on the pressure drop of the target blood vessel point and the pressure drop of any one of the other blood vessel points; specifically, determining the pressure drop change corresponding to each target blood vessel point through the ratio of the pressure drop of the target blood vessel point and the pressure drop of the other blood vessel point, thereby determining the pulmonary artery blood flow fraction of each target blood vessel point; wherein, the pressure drop refers to the difference between the pressure of the next blood vessel point and the pressure of the previous blood vessel point for the target blood vessel point on a continuous curve.

2. The method for determining the pulmonary artery blood flow fraction according to claim 1, characterized in that, the determining the pulmonary artery stenosis region of the target blood vessel based on the center point and sphere radius corresponding to each sphere includes: determining the center point of each sphere and the sphere radius; generating a center line corresponding to the blood vessel based on each center point; determining the pulmonary artery stenosis position based on the change state of the sphere radius corresponding to each center point on the center line; determining the pulmonary artery stenosis region based on the pulmonary artery stenosis position and a first preset distance.

3. The method for determining the pulmonary artery blood flow fraction according to claim 2, characterized in that, the manner of determining the sphere radius includes: obtaining a target position on the inner wall of the blood vessel segment; determining the intersection point of the target position and the sphere. Determine the spherical radius based on the intersection point and the center point.

4. The method for determining the pulmonary artery blood flow fraction according to claim 1, wherein, further comprising: detecting the value of the pulmonary artery blood flow fraction at the target blood vessel point; determining the lesion location of the pulmonary artery based on the target blood vessel point with the minimum value.

5. The method for determining the pulmonary artery blood flow fraction according to claim 1, wherein, the three-view images have gray-scale data; and further comprising: performing a conversion process on the gray-scale data to generate binary data corresponding to the gray-scale data; mapping the binary data to the three-view images and performing a color assignment process on the three-view images so that the pulmonary artery is displayed on the three-view images.

6. A device for determining the pulmonary artery blood flow fraction, wherein, the device comprises: an acquisition module, configured to acquire a pulmonary artery tomographic scan image to be processed, pulmonary artery blood flow parameters, and pulmonary artery pressure parameters; wherein, the pulmonary artery tomographic scan image is obtained by CT pulmonary angiography; a multi-planar reconstruction module, configured to perform a multi-planar reconstruction process on the pulmonary artery tomographic scan image to obtain three-view images corresponding to the pulmonary artery tomographic scan image; a segmentation and reconstruction module, configured to segment a pulmonary artery image sequence from the three-view images and perform a three-dimensional reconstruction on the pulmonary artery image sequence to generate a pulmonary artery three-dimensional image; an extraction module, configured to extract a pulmonary artery stenosis region from the pulmonary artery three-dimensional image; the extraction module specifically comprises: a segmentation processing unit, configured to perform a segmentation process on any target blood vessel in the pulmonary artery three-dimensional image to obtain a plurality of blood vessel segments corresponding to the target blood vessel; a first determination unit, configured to determine the point cloud data corresponding to each blood vessel segment; a generation unit, configured to perform a fitting process on the point cloud data to generate a sphere corresponding to each blood vessel segment; a second determination unit, configured to determine the pulmonary artery stenosis region of the target blood vessel based on the center point and the spherical radius corresponding to each sphere; a pulmonary artery blood flow fraction determination module, configured to determine the pulmonary artery blood flow fraction corresponding to the pulmonary artery stenosis region based on the pulmonary artery blood flow parameters and the pulmonary artery pressure parameters; The pulmonary artery blood flow fraction determination module comprises: a third determination unit, configured to determine the pressure drop of each blood vessel point in the pulmonary artery stenosis region based on the pulmonary artery orifice pressure parameter and the pulmonary artery blood flow parameter; a fourth determination unit, configured to, for any one target blood vessel point among each blood vessel point, determine any other blood vessel point spaced apart from the target blood vessel point by a second preset distance; a fifth determination unit, configured to determine the pulmonary artery blood flow fraction corresponding to the target blood vessel point in the pulmonary artery stenosis region based on the pressure drop of the target blood vessel point and the pressure drop of any other blood vessel point; the fifth determination unit is specifically configured to determine the pressure drop change corresponding to each target blood vessel point by the ratio of the pressure drop of the target blood vessel point to the pressure drop of the other blood vessel point, so as to determine the pulmonary artery blood flow fraction of each target blood vessel point; wherein, the pressure drop refers to the difference between the pressure of the next blood vessel point and the pressure of the previous blood vessel point for the target blood vessel point on a continuous curve.

7. A computer device, characterized in that, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method for determining the pulmonary artery blood flow fraction according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method for determining the pulmonary artery blood flow fraction according to any one of claims 1 to 5.

Images