Blood vessel image fusion method and system, electronic equipment and storage medium
Through the fusion of IVUS images and contrast images, the angle and shape of blood vessels are adjusted, and the problem of vascular information loss when two-dimensional contrast images are mapped with three-dimensional images is solved, and the accuracy of hemodynamic analysis is improved.
Patent Information
- Application Number
- CN202311155715.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-07
- Publication Date
- 2025-03-07
AI Technical Summary
In the prior art, when performing hemodynamic analysis, two-dimensional contrast image mapping three-dimensional images may lead to loss of vascular information, resulting in inaccurate hemodynamic analysis.
By fusing the IVUS image with the contrast image, adjust the vascular angle and vascular shape in the IVUS image sequence, supplement the real information of the lost blood vessels in the contrast image, and then perform image fusion to obtain the vascular fusion image.
Improve the accuracy of hemodynamic analysis, ensuring the integrity of vascular information by supplementing the missing details in the contrast image.
Smart Images
Figure CN119579423A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical image processing technology, and in particular to a vascular image fusion method, system, electronic device and storage medium. Background Art
[0002] In order to perform hemodynamic analysis, such as analyzing the degree of vascular stenosis, the length of the stenotic area, etc., an imaging image based on the blood vessel is required as the analysis basis.
[0003] In the related art, IVUS (Intravascular Ultrasound) image is a high-resolution ultrasound imaging technology used to evaluate the internal structure and abnormalities of blood vessels. It generates real-time cross-sectional images by placing an ultrasound probe inside the blood vessel. IVUS images can provide detailed information on the structure of the blood vessel wall. However, it is a two-dimensional image and cannot meet the needs of hemodynamic analysis.
[0004] Coronary angiography technology can accurately obtain angiography images of coronary vessels and can map two-dimensional angiography images into three-dimensional images through computer software.
[0005] However, when two-dimensional angiography images are mapped to three-dimensional images, vascular information may be lost, which may lead to inaccurate hemodynamic analysis. Summary of the invention
[0006] In order to solve or partially solve the problems existing in the related art, the present application provides a vascular image fusion method, device, electronic device and storage medium, which can use IVUS images and angiography images to fuse and supplement the real vascular information lost in the angiography image, so that the subsequent hemodynamic analysis of the three-dimensional image is more accurate.
[0007] The first aspect of the present application provides a blood vessel image fusion method, comprising:
[0008] Obtaining an IVUS image sequence; the IVUS image sequence includes N vascular images of the target blood vessel;
[0009] Generating M center lines of each of the blood vessel images based on the center point of the lumen area in each of the blood vessel images;
[0010] Adjusting the vascular angle and vascular shape of the target blood vessel in the N vascular images based on the M center lines of each of the blood vessels to obtain a reconstructed IVUS image sequence; wherein M and N are both positive integers;
[0011] The reconstructed IVUS image sequence is fused with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
[0012] A second aspect of the present application provides a vascular image fusion device, comprising:
[0013] An acquisition module, used for acquiring an IVUS image sequence; the IVUS image sequence includes N vascular images of the target blood vessel;
[0014] A segmentation module, used for generating M center lines of each of the blood vessel images based on the center point of the lumen area in each of the blood vessel images;
[0015] An adjustment module, configured to adjust the vessel angle and vessel shape of the target vessel in the N vessel images based on the M center lines of each of the vessels to obtain a reconstructed IVUS image sequence; wherein M and N are both positive integers;
[0016] A fusion module is used to fuse the reconstructed IVUS image sequence with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
[0017] A third aspect of the present application provides an electronic device, including:
[0018] Processor; and
[0019] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.
[0020] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.
[0021] The present application provides a vascular image fusion method, device, electronic device and storage medium. The method first obtains an IVUS image sequence; the IVUS image sequence includes N vascular images of a target blood vessel; then, M center straight lines of each vascular image are generated based on the center point of the lumen area in each vascular image; then, the vascular angle and vascular shape of the target blood vessel in the N vascular images are adjusted based on the M center straight lines of each blood vessel to obtain a reconstructed IVUS image sequence; finally, the reconstructed IVUS image sequence is image-fused with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel. The present application can adjust the vascular angle and vascular shape of the target blood vessel in the vascular image in the IVUS image sequence, and then fuse it with the angiography image, which can supplement the details lost in the angiography image, thereby improving the accuracy of hemodynamic analysis.
[0022] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.
[0024] Figure 1 It is a flowchart of a blood vessel image fusion method shown in an embodiment of the present application.
[0025] Figure 2 It is a schematic diagram of the effect of dividing the center straight line shown in an embodiment of the present application.
[0026] Figure 3 This is another flowchart of a blood vessel image fusion method shown in an embodiment of the present application.
[0027] Figure 4 It is a structural schematic diagram of a blood vessel image fusion device shown in an embodiment of the present application.
[0028] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION
[0029] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0030] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0031] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.
[0032] FFR is an indicator in coronary interventional treatment, and its full name is Fractional Flow Reserve (FFR). It is a method of evaluating the degree of stenosis by measuring the pressure difference before and after the stenosis of the coronary artery. FFR can be obtained by reconstructing a three-dimensional model of the blood vessel of interest through multi-position angiography and combining other boundary conditions for hemodynamic simulation. However, some details of the blood vessel will be lost when reconstructing the blood vessel, resulting in inaccurate subsequent hemodynamic analysis. While IVUS images cannot be directly mapped to three-dimensional images, they can provide detailed information such as the vascular wall structure that cannot be provided in angiography images. In view of this, the present application can propose a vascular image fusion method, which uses IVUS images to modulate angiography images to improve the accuracy of subsequent hemodynamic analysis.
[0033] See also Figure 1 , Figure 1 It is a flowchart of a blood vessel image fusion method provided in an embodiment of the present application.
[0034] The present application provides a blood vessel image fusion method, which includes the following steps.
[0035] S101, obtaining an IVUS image sequence; the IVUS image sequence includes N vascular images of a target blood vessel.
[0036] In an embodiment of the present application, an IVUS image sequence may be obtained first, wherein the IVUS image sequence includes N vascular images of the target vessel. The target vessel may be a coronary artery or other vessel that requires hemodynamic analysis. The IVUS image sequence is collected by inserting an ultrasonic probe into the interior of the blood vessel. Each vascular image may include relevant image data of the target vessel, such as lumen contour, vascular structure, blood flow dynamics, lesion morphology, and other vascular information related to the target vessel.
[0037] In the process of sampling vascular images, the blood vessels will contract and relax during the cardiac cycle, causing the morphology of the blood vessels to change periodically, and the shape of the blood vessels will change. In addition, the position and operation of the ultrasonic probe will also cause the vascular image to rotate. Therefore, the vascular images in the IVUS image sequence are not actually imaged under ideal conditions. The vascular angle and vascular shape of the target blood vessels in the vascular images in the IVUS image sequence need to be adjusted first, so that the vascular images that can be used for image fusion can be obtained.
[0038] S102 , generating M center lines of each blood vessel image based on the center point of the lumen region in each blood vessel image.
[0039] In the embodiment of the present application, if it is necessary to adjust the blood vessel image to an ideal state, it can be achieved based on the central straight line of the lumen area in the blood vessel image.
[0040] For each vascular image, the vascular information is divided into regions, which may include lumen regions and other regions, and other regions may include vascular-related tissue regions such as external elastic membrane regions and lesion regions. Since the changes in the lumen region are easier to identify than those in other regions and can better reflect the changes in the overall blood vessel, it can be used for hemodynamic analysis. Therefore, in the embodiment of the present application, the vascular angle and vascular shape of the target blood vessel in the vascular image can be adjusted based on the lumen region.
[0041] In the embodiment of the present application, for each lumen region in the blood vessel image, a center line can be generated based on the midline point of the lumen region. The center line can refer to a line segment passing through the center point, with both ends of the line segment located on the boundary of the lumen region, where M is a positive integer. That is, at least one center line passing through the center point can be generated.
[0042] In the application, the lumen area in the vascular image can be identified in a variety of ways. For example, the lumen area can be determined by the edge of the vascular wall, the gap in the lumen, and other vascular area features in the vascular image through automatic detection based on an image processing algorithm. Alternatively, the lumen area can be accurately identified by applying morphological processing to the vascular image, such as expansion, corrosion, and filling. Of course, other methods can also be used, as long as the lumen area can be identified, and no specific limitation is made here.
[0043] The center point of the lumen area can also be determined in a variety of ways, for example, identifying the minimum circumscribed circle of the lumen area, and using the center coordinates of the minimum circumscribed circle as the coordinates of the center point of the lumen area. Alternatively, the center of gravity of the lumen area can be calculated, and the lumen area can be divided into multiple triangles, and the weighted average of the center coordinates of the multiple triangles can be used as the coordinates of the center point of the lumen area. Alternatively, the graphics corresponding to the lumen area can be input into a pre-set neural network model, and the coordinates of the center point of the lumen area can be output through the neural network model. The neural network model can predict the center point of the graphics through machine learning training. Of course, other methods can also be used, and it is only necessary to determine the center point of the lumen area, which is not specifically limited here.
[0044] After the center point of the lumen area is obtained, a center straight line passing through the center point is generated. Figure 2 , Figure 2 : is a schematic diagram of the effect of dividing the center straight line shown in the embodiment of the present application. Among them, the center point of the lumen area Q can be C i The intersection points of the center line at the two ends of the lumen region may be, for example, l1 and l2, and the center line is (l1, l2). The number N of the center lines is at least greater than or equal to 1, that is, there is at least one center line.
[0045] The angle between the center lines can be a preset angle, and the preset angle can be set according to actual needs. For example, N is 180, that is, the angle between every two center lines can be 1 degree, and there can be 180 center lines. In the application, 0 degrees is a fixed position or called a reference position, such as Figure 2 The position of l1 in the figure is used as the reference position, and a central straight line is generated for each vascular image based on the reference position.
[0046] Based on this, assuming that the length of the IVUS image sequence is P, that is, there are P vascular images, then an image sequence with a central straight line of P*180*(l1, l2) can be obtained. P is a positive integer.
[0047] S103 , adjusting the vessel angle and vessel shape of the target vessel in the N vessel images based on the M center lines of each vessel to obtain a reconstructed IVUS image sequence.
[0048] In the embodiment of the present application, the vessel angle and the vessel shape of the target vessel may be adjusted based on the image sequence with the central straight line obtained above.
[0049] In the application, the image sequence containing the center straight line can be aligned based on the center point of the identified lumen area, and the vascular image of each sampling point is aligned to the same position, so that the waveform corresponding to the connecting line of each center straight line matches the standard waveform to eliminate the influence of the cardiac cycle on the cross section, i.e., the shape of the blood vessel. The vascular angle of the target blood vessel can be adjusted based on the cardiac cycle using the calculated motion vector. Alternatively, based on the corresponding relationship between the center straight lines in two adjacent blood vessel images, the vascular shape and vascular angle of the target blood vessel in the vascular image are adjusted so that the trends represented by the target blood vessels in the two adjacent blood vessel images are consistent. The represented trends include, for example, the position of the feature point, the trend of change, whether a specific line segment matches, the direction of the thickness of the blood vessel, etc. As long as the vascular shape and vascular angle of the target blood vessel can be adjusted based on the center straight line of the midline point in the embodiment of the present application, it will be sufficient.
[0050] It is understandable that, in order to achieve better subsequent processing effects, denoising and smoothing processing may be performed before executing step 103. For example, denoising operations may be performed on noise points in the longitudinal section formed by the central straight line and each cross section including the central straight line.
[0051] S104 , fusing the reconstructed IVUS image sequence with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
[0052] In order to achieve subsequent hemodynamic analysis, after obtaining the reconstructed IVUS image sequence, in the embodiment of the present application, it is necessary to fuse it with the angiography image of the target blood vessel to obtain a fused vascular fusion image. The reconstructed IVUS image sequence is used to correct the information lost in the angiography image when mapping from a two-dimensional image to a three-dimensional image. For example, the vascular image lost in the angiography image in the three-dimensional model is replaced with the vascular image in the reconstructed IVUS image sequence.
[0053] After obtaining the vascular fusion image of the target blood vessel, the corrected three-dimensional model can be subjected to hemodynamic analysis, and relevant information such as the blood flow velocity and pressure drop in the target blood vessel can be analyzed.
[0054] In an embodiment of the present application, the vascular angle and vascular shape of the target blood vessel in the vascular image in the IVUS image sequence can be adjusted and then fused with the angiography image, which can supplement the details lost in the angiography image in the three-dimensional model, thereby improving the accuracy of the three-dimensional model for hemodynamic analysis.
[0055] In order to eliminate the influence of the cardiac cycle and the probe on the morphology of the target blood vessel, it was previously introduced that the vascular angle and shape of the target blood vessel can be adjusted based on the center straight line. This process is described in detail below.
[0056] Figure 3This is another flowchart of a blood vessel image fusion method shown in an embodiment of the present application.
[0057] In this embodiment, the execution process of step 101, step 102 and step 104 can refer to the above embodiment. In step 103, the vascular angle and vascular shape of the target blood vessel in N vascular images are adjusted based on the M center straight lines of each blood vessel, and the reconstructed IVUS image sequence can include the following steps.
[0058] S201, obtaining M longitudinal sections of a target blood vessel based on a central straight line; wherein the dividing angles of the central straight line in any longitudinal section in respective blood vessel images are the same.
[0059] S202: Adjust the shape of the target blood vessel based on the M longitudinal sections.
[0060] S203, obtaining N cross sections of the target blood vessel based on the center straight lines; wherein any cross section includes M center straight lines.
[0061] S204 : Adjust the blood vessel angle of the target blood vessel based on the N cross sections.
[0062] S205, obtaining a reconstructed IVUS image sequence.
[0063] In this embodiment, in the image sequence composed of the blood vessel images with a center line, M longitudinal sections of the target blood vessel can be constructed based on the center line, and each plane generated with the center line is a longitudinal section, which can have N cross sections.
[0064] In application, if there are 180 angles of the center straight line, N*(l1, l2) can be called a longitudinal section, and there are 180 longitudinal sections of different angles. M*(l1, l2) can be called a cross section, and there are M cross sections.
[0065] In this embodiment, the vascular shape of the target blood vessel can be adjusted based on M longitudinal sections. For example, the planes in the longitudinal section that do not meet the preset conditions are adjusted to meet the preset conditions. The preset condition can be a parameter value, a function, or a change trend, etc., which can be set according to actual needs. The vascular shape of the target blood vessel can be adjusted based on multiple longitudinal sections to eliminate the influence of the heartbeat cycle on the vascular shape.
[0066] In some embodiments, adjusting the vascular angle of the target blood vessel based on M longitudinal sections includes: determining the cardiac cycles corresponding to the M longitudinal sections; and adjusting the vascular shape of the target blood vessel in the blood vessel image based on the cardiac waveform corresponding to the cardiac cycle.
[0067] In this embodiment, the vascular shape of the target blood vessel can be adjusted based on the cardiac cycle. The cardiac cycle can be obtained based on other auxiliary equipment (such as an electrocardiogram device ECG), or it can be calculated based on the cardiac waveform corresponding to the longitudinal section. The curve corresponding to the longitudinal section can be used as the cardiac waveform, and the cardiac cycle is regular. Therefore, the cardiac cycle can be calculated based on the cardiac waveform. For example, the maximum value of the curve is identified as the R wave peak value, and the cardiac cycle is calculated by calculating the time interval during RR.
[0068] After obtaining the cardiac cycle, the effect of the heartbeat on the shape of the target blood vessel can be clearly understood. For example, when at the peak of the R wave, the shape of the target blood vessel is larger than that in the normal state. At this time, the area of the target blood vessel shape should be proportionally reduced. Of course, the way to change the blood vessel shape can be based on the original shape of the target blood vessel, using overall scaling or giving other adjustment coefficients for adjustment, which will not be elaborated here.
[0069] In this embodiment, the blood vessel angle of the target blood vessel may also be adjusted based on the N cross sections.
[0070] In some embodiments, adjusting the vessel shape of the target vessel based on the N cross sections includes:
[0071] According to the position information of the N cross sections in the IVUS image sequence, the N cross sections are stitched in sequence;
[0072] In the process of sequentially splicing N cross sections, the vessel shape of the target vessel corresponding to the spliced cross sections is used to correct the vessel shape of the target vessel corresponding to the cross section to be spliced that is located after the target cross section.
[0073] In this embodiment, the cross sections are spliced according to the sampling time, and during the splicing process, it is calculated whether there is any misalignment between adjacent cross sections. If there is any misalignment, the blood vessel angle of the target blood vessel is corrected to eliminate the influence of the probe on the rotation angle of the target blood vessel.
[0074] In the application, the fitting formula can be used to use the latter cross section to correct the former cross section. Since there are M center lines, the angle of the cross section can be adjusted based on the M center lines.
[0075] Alternatively, the vessel angle of the target vessel may be adjusted based on the longitudinal section according to the cardiac cycle.
[0076] In this embodiment, adjusting the blood vessel angle of the target blood vessel based on M longitudinal sections includes:
[0077] Determine the cardiac cycles corresponding to the M longitudinal sections;
[0078] Calculate the motion vector of the vascular region during the cardiac cycle;
[0079] The blood vessel angle of the target blood vessel is adjusted based on the magnitude and direction of the motion vector.
[0080] Among them, the method of obtaining the cardiac cycle can refer to the content in the aforementioned embodiment. In this embodiment, the motion vector of the blood vessel area can be calculated based on the cardiac cycle, and the motion vector of each pixel can be calculated according to the motion field of the blood vessel area. Then, the motion status of the target blood vessel in M longitudinal sections is obtained based on the motion vector and information such as direction, speed, and acceleration, so as to adjust the blood vessel angle of the target blood vessel based on the size and direction of the motion vector.
[0081] It can be seen that in this embodiment, the vascular angle and vascular shape of the target blood vessel in the target image can be adjusted based on the generated center straight line, so that the vascular image in the IVUS image sequence is in a reference state, and the reference state can calibrate the angiography image of the target blood vessel. If the IVUS image sequence is used directly, the vascular image in the IVUS image sequence cannot be matched with the angiography image due to factors such as lesions, causing the subsequent calculation process to fail. Therefore, in this embodiment, the vascular shape and vascular angle of the target blood vessel can be calibrated based on the center straight line of the vascular image in the IVUS image sequence to obtain a reconstructed IVUS image sequence.
[0082] In this embodiment, after the reconstructed IVUS image sequence is obtained, the reconstructed IVUS image sequence and the angiography image of the target blood vessel are subjected to image fusion processing.
[0083] In this embodiment, the image fusion of the reconstructed IVUS image sequence and the angiography image of the target blood vessel includes the following steps:
[0084] determining a contrast centerline of the contrast image of the target blood vessel;
[0085] Taking the IVUS center line and the angiography center line corresponding to the reconstructed IVUS image sequence as references, respectively determining a first matching point in the reconstructed IVUS image sequence and a second matching point in the angiography image;
[0086] The blood vessel image corresponding to the first matching point is used to replace the blood vessel image corresponding to the second matching point to perform image fusion.
[0087] Also includes:
[0088] The first matching point that fails to match the second matching point is used as a matching point to be processed;
[0089] An interpolated image is generated based on the blood vessel images corresponding to the neighboring matching points of the matching point to be processed, and the blood vessel image of the second matching point corresponding to the matching point to be processed is replaced by the interpolated image.
[0090] In this embodiment, if you want to obtain a vascular fusion image, you need to determine the matching points first. After the reconstructed IVUS image sequence is spliced, it can actually be regarded as a three-dimensional model. In this embodiment, the center line corresponding to the reconstructed IVUS image sequence and the center line corresponding to the angiography image can be used as a reference for segmented matching to find the best matching point. Among them, the best matching point can be a certain feature point or several feature points. The best matching point can be determined based on the location of the matching point, the change trend of the blood vessel, the best matching line segment, etc.
[0091] In the application, the thickness trend of the blood vessels and the direction of blood flow can be determined. Usually, the blood vessels at the ends are thinner. Therefore, the best matching point can be determined based on the overall change trend of the blood vessels, the direction of blood flow, etc.
[0092] In the application, assuming that P1 is the first matching point of the reconstructed IVUS image sequence and P2 is the second matching point of the angiography image, the section at P2 is replaced by the section at P1. It can be understood that the angiography image is a three-dimensional image.
[0093] Of course, since there is a gap between each section of the IVUS image when it is retracted, if the first matching point or the second matching point still cannot find a corresponding matching point after the fused vascular image is generated, an interpolation is generated based on the section of the adjacent matching point of the first matching point or the second matching point as its corresponding matching point.
[0094] It can be understood that, during the replacement process, the area of the cross section corresponding to the first matching point may be modified to the area of the cross section corresponding to the second matching point.
[0095] After the fused blood vessel image is obtained, the fused blood vessel image may be a three-dimensional image or a three-dimensional model, and hemodynamic analysis may be performed based on the fused blood vessel image to obtain data such as blood flow velocity and pressure drop of the target blood vessel.
[0096] In the embodiment of the present application, the details lost when the angiographic image is mapped to the three-dimensional model can be supplemented and corrected based on the IVUS image sequence, thereby improving the accuracy of the hemodynamic analysis.
[0097] Corresponding to the aforementioned application function realization method embodiment, the present application also provides a vascular image fusion device, an electronic device and a corresponding embodiment of a medium.
[0098] Figure 4 It is a structural schematic diagram of a blood vessel image fusion device shown in an embodiment of the present application.
[0099] See also Figure 4 In the embodiment of the present application, a blood vessel image fusion device 400 includes:
[0100] An acquisition module 1 is used to acquire an IVUS image sequence; the IVUS image sequence includes N vascular images of the target blood vessel;
[0101] A segmentation module 2, used for generating M center lines of each of the blood vessel images based on the center point of the lumen area in each of the blood vessel images;
[0102] An adjustment module 3 is used to adjust the vascular angle and vascular shape of the target blood vessel in the N vascular images based on the M center lines of each of the blood vessels to obtain a reconstructed IVUS image sequence; wherein M and N are both positive integers;
[0103] The fusion module 4 is used to fuse the reconstructed IVUS image sequence with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
[0104] In some embodiments, adjusting the blood vessel angle and blood vessel shape of the target blood vessel in the N blood vessel images based on the M center lines of each of the blood vessels includes:
[0105] Obtaining M longitudinal sections of the target blood vessel based on the central straight line; wherein the dividing angles of the central straight line in any longitudinal section in the respective blood vessel images are the same;
[0106] adjusting a blood vessel shape of the target blood vessel based on the M longitudinal sections;
[0107] Obtaining N cross sections of the target blood vessel formed based on the center straight lines; wherein any of the cross sections includes M center straight lines;
[0108] The blood vessel angle of the target blood vessel is adjusted based on the N cross sections.
[0109] In some embodiments, adjusting the shape of the target blood vessel based on the M longitudinal sections includes:
[0110] Determine the cardiac cycles corresponding to the M longitudinal sections;
[0111] The blood vessel shape of the target blood vessel in the blood vessel image is adjusted based on the cardiac waveform corresponding to the cardiac cycle.
[0112] In some embodiments, adjusting the blood vessel angle of the target blood vessel based on the N cross sections includes:
[0113] splicing the N cross sections in sequence according to position information of the N cross sections in the IVUS image sequence;
[0114] In the process of sequentially splicing the N cross sections, the vessel shape of the target vessel corresponding to the spliced cross sections is used to correct the vessel angle of the target vessel corresponding to the cross section to be spliced that is located after the target cross section.
[0115] In some embodiments, fusing the reconstructed IVUS image sequence with the angiography image of the target blood vessel comprises:
[0116] determining an angiography centerline of an angiography image of the target blood vessel;
[0117] Taking the IVUS center line corresponding to the reconstructed IVUS image sequence and the angiography center line as references, respectively determining a first matching point in the reconstructed IVUS image sequence and a second matching point in the angiography image;
[0118] The blood vessel image corresponding to the second matching point is replaced with the blood vessel image corresponding to the first matching point to perform image fusion.
[0119] In some embodiments, it also includes:
[0120] taking the first matching point that fails to match the second matching point successfully as a matching point to be processed;
[0121] An interpolated image is generated based on the blood vessel images corresponding to the neighboring matching points of the matching point to be processed, and the blood vessel image of the second matching point corresponding to the matching point to be processed is replaced by the interpolated image.
[0122] In some embodiments, adjusting the blood vessel angle of the target blood vessel based on the M longitudinal sections includes:
[0123] Determine the cardiac cycles corresponding to the M longitudinal sections;
[0124] Calculating a motion vector of the blood vessel region within the cardiac cycle;
[0125] The blood vessel angle of the target blood vessel is adjusted based on the magnitude and direction of the motion vector.
[0126] In some embodiments, it is characterized in that it also includes:
[0127] A hemodynamic analysis is performed on the target blood vessel based on the blood vessel fusion image.
[0128] The present application can adjust the vascular angle and vascular shape of the target blood vessel in the vascular image in the IVUS image sequence, and then merge it with the angiography image, so as to supplement the details lost in the angiography image, thereby improving the accuracy of hemodynamic analysis.
[0129] Regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.
[0130] Figure 5 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.
[0131] See also Figure 5 , the electronic device 1000 includes a memory 1010 and a processor 1020 .
[0132] The processor 1020 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
[0133] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.
[0134] The memory 1010 stores executable codes, and when the executable codes are processed by the processor 1020 , the processor 1020 can execute part or all of the methods described above.
[0135] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.
[0136] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.
[0137] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A vascular image fusion method, characterized in that: include: Obtaining an IVUS image sequence; the IVUS image sequence includes N vascular images of the target blood vessel; Generating M center lines of each of the blood vessel images based on the center point of the lumen area in each of the blood vessel images; Adjusting the vascular angle and vascular shape of the target blood vessel in the N vascular images based on the M center lines of each of the blood vessels to obtain a reconstructed IVUS image sequence; wherein M and N are both positive integers; The reconstructed IVUS image sequence is fused with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
2. The method according to claim 1, characterized in that The adjusting the blood vessel angle and blood vessel shape of the target blood vessel in the N blood vessel images based on the M center lines of each of the blood vessels includes: Obtaining M longitudinal sections of the target blood vessel based on the central straight line; wherein the dividing angles of the central straight line in any longitudinal section in the respective blood vessel images are the same; adjusting a blood vessel shape of the target blood vessel based on the M longitudinal sections; Obtaining N cross sections of the target blood vessel formed based on the center straight lines; wherein any of the cross sections includes M center straight lines; The blood vessel angle of the target blood vessel is adjusted based on the N cross sections.
3. The method according to claim 2, characterized in that The adjusting the shape of the target blood vessel based on the M longitudinal sections includes: Determine the cardiac cycles corresponding to the M longitudinal sections; The blood vessel shape of the target blood vessel in the blood vessel image is adjusted based on the cardiac waveform corresponding to the cardiac cycle.
4. The method according to claim 2, characterized in that: The adjusting the blood vessel angle of the target blood vessel based on the N cross sections comprises: splicing the N cross sections in sequence according to position information of the N cross sections in the IVUS image sequence; In the process of sequentially splicing the N cross sections, the vessel shape of the target vessel corresponding to the spliced cross sections is used to correct the vessel angle of the target vessel corresponding to the cross section to be spliced that is located after the target cross section.
5. The method according to claim 1, characterized in that The step of fusing the reconstructed IVUS image sequence with the angiography image of the target blood vessel comprises: determining an angiography centerline of an angiography image of the target blood vessel; Taking the IVUS center line corresponding to the reconstructed IVUS image sequence and the angiography center line as references, respectively determining a first matching point in the reconstructed IVUS image sequence and a second matching point in the angiography image; The blood vessel image corresponding to the second matching point is replaced with the blood vessel image corresponding to the first matching point to perform image fusion.
6. The method according to claim 5, characterized in that Also includes: taking the first matching point that fails to match the second matching point successfully as a matching point to be processed; An interpolated image is generated based on the blood vessel images corresponding to the neighboring matching points of the matching point to be processed, and the blood vessel image of the second matching point corresponding to the matching point to be processed is replaced by the interpolated image.
7. The method according to claim 2, characterized in that The adjusting the blood vessel angle of the target blood vessel based on the M longitudinal sections includes: Determine the cardiac cycles corresponding to the M longitudinal sections; Calculating a motion vector of the blood vessel region within the cardiac cycle; The blood vessel angle of the target blood vessel is adjusted based on the magnitude and direction of the motion vector.
8. The method according to claim 1, characterized in that Also includes: A hemodynamic analysis is performed on the target blood vessel based on the blood vessel fusion image.
9. A vascular image fusion device, characterized in that: include: An acquisition module, used for acquiring an IVUS image sequence; the IVUS image sequence includes N vascular images of the target blood vessel; A segmentation module, used for generating M center lines of each of the blood vessel images based on the center point of the lumen area in each of the blood vessel images; An adjustment module, configured to adjust the vessel angle and vessel shape of the target vessel in the N vessel images based on the M center lines of each of the vessels to obtain a reconstructed IVUS image sequence; wherein M and N are both positive integers; A fusion module is used to fuse the reconstructed IVUS image sequence with the angiography image of the target blood vessel to obtain a vascular fusion image of the target blood vessel.
10. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 8.
11. A computer-readable storage medium having executable codes stored thereon, and when the executable codes are executed by a processor of an electronic device, the processor is caused to execute the method according to any one of claims 1 to 8.