Double-body-position blood vessel automatic matching method and system, electronic equipment and storage medium
By automatically matching vascular features with end-diastolic angiography images of the heart and calculating the matching error, automatic vascular matching in two positions without human intervention was achieved, improving the accuracy of coronary artery three-dimensional reconstruction and QFR.
Patent Information
- Application Number
- CN202310566891.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-18
- Publication Date
- 2024-11-22
AI Technical Summary
In existing technologies, automatic vascular matching in two positions requires manual intervention, which is time-consuming and has large matching errors, affecting the accuracy of coronary artery three-dimensional reconstruction and QFR.
By using an automatic matching method, based on the angiographic images of the heart at end-diastole, the matching error of vascular features is calculated, and the automatic matching of the vascular segment of interest between the first angiographic angle and the second angiographic angle is achieved, reducing human intervention.
It improves the accuracy of 3D vascular reconstruction and QFR, reduces human operation time, lowers matching errors, and improves the accuracy of automated matching.
Smart Images

Figure CN119006859A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of medical image processing, and in particular to a method, system, electronic device and storage medium for automatic matching of blood vessels in two body positions. Background Art
[0002] Quantitative Flow Ratio (QFR) is a non-invasive cardiac imaging technique that does not require the use of contrast agents and can be used to assess the degree of coronary artery stenosis and the severity of coronary heart disease. This technique uses computer simulation technology to measure hemodynamic parameters in the coronary arteries to assess the degree of stenosis.
[0003] Compared with traditional coronary angiography techniques such as Fractional Flow Reserve (FFR), QFR does not require cannulation into the coronary artery, reducing the pain and discomfort of the patient, while also avoiding the use of contrast agents and reducing the impact on renal function. The core of QFR is to digitize coronary angiography from two different angles and reconstruct a three-dimensional model.
[0004] In the related art, experienced industry personnel are required to manually intervene to select target blood vessel segments of angiography images at two angles, which takes a long time. Summary of the invention
[0005] In order to solve or partially solve the problems existing in the related art, the present application provides a dual-position blood vessel automatic matching method, system, electronic device and storage medium, which can automatically and accurately match the blood vessel segments in two angiography images without human intervention.
[0006] The first aspect of the present application provides a dual-position blood vessel automatic matching method, comprising:
[0007] Obtain a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole;
[0008] determining a first blood vessel segment of interest of a first blood vessel in the first angiography image;
[0009] determining a blood vessel characteristic of a second blood vessel in the second angiography image;
[0010] calculating a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel;
[0011] A second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest is determined based on the matching error.
[0012] A second aspect of the present application provides a dual-position blood vessel automatic matching system, comprising:
[0013] An acquisition module, used for acquiring a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole;
[0014] a first recommendation module, configured to determine a first blood vessel segment of interest of a first blood vessel in the first angiography image;
[0015] a determination module, configured to determine a blood vessel feature of a second blood vessel in the second angiography image;
[0016] a calculation module, configured to calculate a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel;
[0017] The second recommendation module is configured to determine a second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest based on the matching error.
[0018] A third aspect of the present application provides an electronic device, including:
[0019] Processor; and
[0020] 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.
[0021] 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.
[0022] The present application provides a dual-position blood vessel automatic matching method, system, electronic device and storage medium, the method first obtains a first angiography image at a first angiography angle and a second angiography image at a second angiography angle; wherein the first angiography image and the second angiography image are images of the end diastole of the heart; then determines a first vascular segment of interest of the first blood vessel in the first angiography image; determines the vascular features of the second blood vessel in the second angiography image; then calculates the matching error between the first vascular segment of interest and the vascular features of the second blood vessel; finally, based on the matching error, determines the second vascular segment of interest in the second angiography image corresponding to the first vascular segment of interest. It can be seen that the present application can automatically match the second vascular segment of interest at the second angiography angle through the matching error after automatically obtaining the first vascular segment of interest at the first angiography angle, without human intervention, and with high accuracy, thereby improving the accuracy of vascular three-dimensional reconstruction and QFR.
[0023] 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
[0024] 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.
[0025] Figure 1 It is a flowchart of a dual-position blood vessel automatic matching method shown in an embodiment of the present application.
[0026] Figure 2 It is a flow chart of determining a first vascular segment of interest of a first vascular in a first angiography image in a dual-position vascular automatic matching method shown in an embodiment of the present application.
[0027] Figure 3 It is a structural schematic diagram of a dual-position blood vessel automatic matching system shown in an embodiment of the present application.
[0028] Figure 4 A schematic diagram of a scenario shown in an embodiment of the present application.
[0029] Figure 5 It is a structural schematic diagram of a dual-position blood vessel automatic matching system shown in an embodiment of the present application.
[0030] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION
[0031] 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.
[0032] 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.
[0033] 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.
[0034] Coronary heart disease is a heart disease, which is a pathophysiological process of myocardial ischemia, hypoxia and necrosis caused by insufficient blood supply to the coronary arteries. The coronary arteries are the main blood vessels supplying the heart. When the coronary arteries are narrowed or blocked, the myocardium will be damaged due to ischemia, causing symptoms such as angina pectoris and myocardial infarction. Methods for treating coronary heart disease include drug therapy, interventional therapy and surgical treatment. Drug therapy mainly improves the symptoms of myocardial ischemia by lowering blood pressure, lowering blood lipids, and dilating coronary arteries. Interventional treatments include coronary artery balloon angioplasty and stent implantation, which can improve blood flow by dilating or supporting narrowed coronary arteries. Surgical treatments include coronary artery bypass grafting and heart bypass surgery, which can improve myocardial ischemia by building new blood vessels.
[0035] 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. The smaller the FFR value, the more severe the coronary artery stenosis is, and interventional treatment is required, such as stent implantation or coronary artery bypass grafting. FFR technology can help doctors more accurately assess the degree of coronary artery stenosis, avoid unnecessary interventional treatment, and improve treatment effect and safety. However, the measurement process of FFR is complicated. It is necessary to insert a pressure intervention guidewire or microcatheter into the coronary artery for measurement. It requires multiple measurements and calculations. The operation process is relatively complicated and requires experienced doctors to operate. Dependent on catheter insertion, FFR measurement requires a catheter to be inserted into the coronary artery for measurement. This process may cause certain discomfort and risks to the patient, such as bleeding, infection, etc. Professional equipment is required. FFR measurement requires professional equipment and technical support, which is costly, and vasodilator drugs are usually required to assist in the maximum congestion of the blood vessels during measurement, which increases the load on the human heart.
[0036] QFR is a new type of coronary intervention treatment indicator, and its full name is Quantitative Flow Reserve (Quantitative Flow Ratio). Similar to FFR, QFR also evaluates the degree of stenosis by measuring the pressure difference before and after the stenosis of the coronary artery. However, QFR is a non-invasive examination method that does not require the insertion of a catheter. Instead, it is achieved through computer simulation and digital technology. QFR technology can help doctors more accurately assess the degree and location of coronary artery stenosis, avoid unnecessary interventional treatment, and improve treatment efficacy and safety. Compared with FFR, QFR has the advantages of simple operation, non-invasiveness, and low cost, and can be more widely used in clinical practice. One of the core technologies of QFR technology is to digitize coronary angiography at two different angles and reconstruct a three-dimensional model, which can more intuitively observe the structure and lesions of the coronary arteries.
[0037] However, the coronary artery structure is complex, and it is very difficult to accurately match the vascular segments in the two angiography images. The relevant technology uses a manual matching method, which requires experienced industry personnel to manually intervene to select the target vascular segments of the angiography images at two angles, which takes a long time.
[0038] Another way is to use the epipolar line matching method, manually select the starting and ending points of the target vascular segment on the angiogram at one angle, project the marked points onto the epipolar line of the angiogram at another angle through the principle of perspective projection imaging, and find the matching vascular segment based on the epipolar line constraints. However, due to the influence of heart beat, patient movement, and parameter errors of the equipment, there is a large error in epipolar line matching.
[0039] In order to solve the technical problems in the related art, the present application provides a dual-position blood vessel automatic matching method, system, electronic device and storage medium, which can automatically obtain a first blood vessel segment of interest at a first angiography angle and a second blood vessel segment of interest at a second angiography angle without human intervention and without using a perspective projection method.
[0040] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.
[0041] Figure 1 It is a flowchart of a dual-position blood vessel automatic matching method shown in an embodiment of the present application.
[0042] See also Figure 1 The embodiment of the present application provides a dual-position blood vessel automatic matching method, comprising:
[0043] S100, obtaining a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole.
[0044] In the embodiment of the present application, angiography images at multiple angiography angles can be obtained, and in particular, a first angiography image at a first angiography angle and a second angiography image at a second angiography angle can be obtained. The angiography angle can be an angiography angle carried in the coronary angiography data used to characterize different body positions and / or different projection angles.
[0045] Among them, coronary angiography data includes information in multiple dimensions. For example, basic information: patient name, ID number, gender, age, etc., angiography acquisition information: acquisition date, equipment manufacturer, equipment model, etc., angiography sequence information: grayscale, window width, window position, etc., equipment information: angiography angle, distance from source to detector, distance from source to patient, etc., electrocardiogram information: such as heart rate, rhythm, ST segment changes, etc. Of course, it can also include any parameters or information that can help improve the automatic vascular matching method.
[0046] In the embodiment of the present application, in order to better meet the accuracy required for three-dimensional reconstruction, the first angiography image and the second angiography image are both images of the end diastole of the heart.
[0047] In the embodiment of the present application, a first contrast image at a first contrast angle and a second contrast image at a second contrast angle may be obtained through the following process.
[0048] Coronary angiography data of multiple body positions / projection angles may be obtained first, and then two angiography sequences that meet the screening conditions may be selected, such as a first angiography angle sequence and a second angiography angle sequence. The angiography vessel sequence is used to characterize the coronary angiography data of different angiography angles. Meeting the screening condition may be meeting the angiography angle difference. The best is the one with the largest angiography angle difference between the two angiography vessel sequences.
[0049] Preferably, the first contrast imaging angle and the second contrast imaging angle meet the angle range of left and right angle LAO90°~RAO90° and front and rear angle CAUD45°~CRAN45°, and the difference between the first contrast imaging angle and the second contrast imaging angle should be greater than a preset degree, such as 20°, 25°. It is understandable that the angle difference between the first contrast imaging angle of the first contrast imaging image and the second contrast imaging angle of the second contrast imaging image is greater than a preset degree; the preset degree is used to indicate that the three-dimensional reconstruction of the blood vessel can be performed based on the preset degree.
[0050] Afterwards, based on the grayscale information of the image, a first contrast image at the first contrast angle and a second contrast image at the second contrast angle at the end of cardiac diastole may be selected from the first contrast angle sequence and the second contrast angle sequence.
[0051] Among them, in the embodiment of the present application, judging whether the heart is in the end diastole may include three means. (1) According to the electrocardiogram information, that is, ECG information, the coronary angiography image at the same moment is selected according to the R peak of the ECG. In this case, the end diastolic image is selected; (2) According to the reference blood pressure, during the coronary angiography process, the doctor usually monitors the patient's blood pressure. Usually, during the systolic period, the blood pressure is higher; and during the diastolic period, the blood pressure is lower; (3) According to the flow of the contrast agent and the grayscale information of the image, during the diastolic period, the coronary artery is in a relaxed state, the flow is larger, and the grayscale information of the image is larger, while during the systolic period, the coronary artery is squeezed, the flow is smaller, and the grayscale information of the image is smaller.
[0052] The first contrast image and the second contrast image can be obtained through the above process.
[0053] S200 , determining a first blood vessel segment of interest of a first blood vessel in a first angiography image.
[0054] S300: Determine a blood vessel feature of a second blood vessel in a second angiography image.
[0055] In the embodiment of the present application, the first blood vessel may be a blood vessel in a first angiography image obtained through image processing, and the second blood vessel may be a blood vessel in a second image obtained through image processing; wherein the blood vessels may include main blood vessels and branch blood vessels.
[0056] The image processing may be coronary vessel image segmentation of the end-diastolic image at the first angiography angle and the end-diastolic image at the second angiography angle, and the vessel region in the coronary vessel image is separated from the background. The image processing method may include threshold-based segmentation, edge-based segmentation, region-based segmentation, and deep learning-based segmentation. The deep learning-based segmentation algorithm includes steps such as image preprocessing, feature extraction, classification, and post-processing.
[0057] The coronary vessel area can be accurately segmented through image processing, and the coronary vessel tree binary images corresponding to the first angiography angle and the second angiography angle can be extracted. Analysis of the coronary vessel tree binary image can obtain a first main vessel binary image corresponding to the first vessel and a second main vessel binary image corresponding to the second vessel.
[0058] Alternatively, a first main vessel binary image and a second main vessel binary image may be extracted from the first angiography image and the second angiography image respectively based on a deep learning method, such as using an R-CNN target detection algorithm. It is understandable that the target retrieval algorithm may be to construct a training set to find the main vessel, which is a complete section of the vessel, from the coronary artery ostium to the end of the vessel.
[0059] Based on the first main vessel binary image, a first vessel segment of interest of the first vessel can be obtained. The vessel segment of interest is the narrowed part of the lesion. Doctors are generally concerned about the lesion near the narrowed part of the vessel, so the vessel segment near the narrowed part of the vessel is called the target vessel segment of interest.
[0060] Based on the second main blood vessel binary image, the blood vessel characteristics of the second blood vessel, such as topological characteristics, can be determined.
[0061] S400: Calculate a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel.
[0062] S500 : Determine a second blood vessel segment of interest in a second angiography image corresponding to the first blood vessel segment of interest based on a matching error.
[0063] In the embodiment of the present application, the second interesting blood vessel segment in the second angiography image is automatically matched with the first interesting blood vessel segment by using the matching error method, and no complex algorithms such as projection are used.
[0064] The matching error may include multiple dimensions, and the matching error between the first blood vessel segment of interest and the blood vessel feature of the second blood vessel is calculated, including:
[0065] Based on the vessel segment diameter matching error, the branch vessel position matching error, the branch vessel diameter matching error and / or the branch vessel angle matching error, the matching degree error between the vessel features of the first vessel segment of interest and the second vessel is calculated.
[0066] In the embodiment of the present application, the second vascular segment of interest that matches the first vascular segment of interest can be accurately matched from the second angiography image by using the diameter of the vascular segment in combination with the branch vessel information of the vascular segment.
[0067] It is understandable that, in order to improve the comprehensiveness of three-dimensional reconstruction, angiography images with more angiography angles may be selected, and the recommendation process of the vascular segments in other angiography images may refer to the recommendation process of the vascular segments in the second angiography image.
[0068] The embodiment of the present application can automatically obtain a first blood vessel segment of interest at a first angiography angle from angiography images at different angiography angles, namely, a first angiography image and a second angiography image, and after automatically obtaining the first blood vessel segment of interest at the first angiography angle, automatically match the second blood vessel segment of interest at a second angiography angle by means of a matching error, without the need for human intervention or a complex projection algorithm, and with high accuracy, thereby improving the accuracy of vascular three-dimensional reconstruction and QFR.
[0069] The above embodiment introduces the process of determining the first blood vessel segment of interest, and the following describes this process in detail. Figure 2, a schematic diagram of a flow chart of determining a first vascular segment of interest of a first vascular in a first angiography image in a dual-position vascular automatic matching method shown in an embodiment of the present application.
[0070] In the embodiment of the present application, determining a first blood vessel segment of interest of a first blood vessel in a first angiography image includes:
[0071] S201, determining a first main blood vessel and a first blood vessel tree skeleton of a first blood vessel in a first angiography image;
[0072] S202, calculating a first blood vessel stenosis position based on the first main blood vessel and the first blood vessel tree skeleton;
[0073] S203: Determine a first blood vessel segment of interest according to the first blood vessel stenosis position.
[0074] Calculating the stenosis position of the first blood vessel based on the first main blood vessel and the first blood vessel tree skeleton, including:
[0075] Calculating a blood vessel diameter of the first blood vessel based on the first blood vessel tree skeleton;
[0076] calculating the vascular stenosis rate of the first main blood vessel by using the proportional relationship between the blood vessel diameter of the first main blood vessel and the blood vessel diameter of a normal blood vessel corresponding to the first blood vessel;
[0077] The stenosis position of the first blood vessel is determined based on the stenosis rate of the first blood vessel.
[0078] In the embodiment of the present application, the skeleton lines of the first main blood vessel and the first blood vessel tree binary image at the first angiography angle can be calculated using the first main blood vessel binary image obtained in the above embodiment.
[0079] The main blood vessel and skeleton line can be calculated by calculating the distance from each pixel point in the binary image to the nearest pixel point in the non-vascular area to obtain a distance transformation image, extracting the maximum value point from the distance transformation image as the starting point of the skeleton line, and then iterating along the gradient direction in the distance transformation image to finally obtain the skeleton line of the binary image. In this way, the first main blood vessel and the first blood vessel tree skeleton line of the first angiography image can be calculated.
[0080] Based on the first vascular skeleton line, the diameter of the first main blood vessel at the first angiography angle can be calculated, and according to the vascular diameter characteristic information of the diameter of the first main blood vessel, the vascular stenosis rate of the first main blood vessel, or the coronary vascular stenosis rate, can be calculated. The coronary vascular stenosis rate refers to the ratio of the diameter of the vascular segment with vascular lesions to the diameter of the normal vascular segment, indicating the degree of atherosclerotic plaque lesions. The coronary vascular stenosis rate is evaluated by the percentage of coronary vascular diameter stenosis, and the calculation formula is as follows:
[0081]
[0082] Among them, R represents the coronary artery stenosis rate, d r represents the diameter of the stenotic vessel, d m Represents normal blood vessel diameter.
[0083] The normal blood vessel diameter is the normal blood vessel diameter at the distal end of the stenotic blood vessel. The degree of stenosis is generally divided into four levels: the first level stenosis rate is 1% to 25%, the second level stenosis rate is 26% to 50%, the third level stenosis rate is 51% to 75%, and the fourth level stenosis rate is 76% to 100%.
[0084] In actual use, the stenosis position can be first determined through the above implementation method, and then the diameter on the main blood vessel is calculated to obtain a diameter curve, and then the trend line of the diameter curve is fitted to the diameter curve and the trend line, and the stenotic blood vessel segment is found according to the trend of diameter change. When there is vascular stenosis, the stenotic blood vessel segment is found by calculating the peak value of the curve.
[0085] It is understandable that there may be multiple first vessel segments of interest for the first vessel, each of which may be automatically determined with reference to the method in the above embodiment. Of course, the first vessel segment of interest may also be obtained by, for example, using a vessel specified by a user as the first main vessel through the above embodiment.
[0086] In the embodiment of the present application, determining the first blood vessel segment of interest according to the stenosis position of the first blood vessel includes:
[0087] Obtaining the selection range of the target blood vessel segment of interest;
[0088] The first blood vessel within the selected range is used as a first blood vessel segment of interest, with the stenosis position of the first blood vessel being used as a reference.
[0089] Since most stenosis lengths are about 5 mm, or about 20 to 30 pixels, the selection range in the embodiment of the present application may be at least greater than or equal to 30 pixels before and after the stenosis position. Of course, it can also be adjusted according to actual conditions to obtain the first vascular segment of interest that best meets the needs of the user.
[0090] In the embodiment of the present application, after the first blood vessel segment of interest is obtained, the blood vessel characteristics of the first blood vessel segment of interest, such as blood vessel topological characteristics, may also be calculated.
[0091] The vascular topology refers to the connection mode and distribution between the various blood vessels in the vascular system, such as the connection mode between the vascular segment of interest and the branch vessels, including the location of the branch vessels, the diameter of the branch vessels, and the angle between the branch vessels and the vascular segment of interest. The angle calculation formula is as follows:
[0092]
[0093] in represents the unit direction vector of the vessel segment of interest, represents the unit direction vector of the branch vessel, and α represents the angle between the branch vessel and the vessel segment of interest.
[0094] Through the above calculation process, the vascular characteristics of the first vascular segment of interest can be obtained, which can be used as basic data for matching error calculation.
[0095] In the embodiment of the present application, the vascular characteristics of the second blood vessel may also be determined. Figure 3 , a schematic diagram of a flow chart of determining the vascular features of a second blood vessel in a second angiography image in a dual-position blood vessel automatic matching method shown in an embodiment of the present application.
[0096] Determining a blood vessel characteristic of a second blood vessel in the second angiography image includes:
[0097] S301, determining a second main blood vessel and a second blood vessel tree skeleton of a second blood vessel in a second angiography image;
[0098] S302, determining a vascular feature of the second blood vessel based on the second main blood vessel and the blood vessel centerline corresponding to the second blood vessel tree skeleton; the vascular feature is used to characterize at least the position and diameter of the second blood vessel in the second angiography image and the relationship between the branch blood vessel and the second blood vessel.
[0099] The implementation method of determining the second main blood vessel and the second blood vessel tree skeleton line can refer to the implementation method of obtaining the first main blood vessel and the first blood vessel skeleton line in the above embodiment. It can be understood that the blood vessel feature calculation method of the second main blood vessel can be obtained by the above blood vessel topology calculation method. It will not be repeated here.
[0100] Alternatively, the vascular features of the second blood vessel may be determined through the second main blood vessel and the centerline of the second blood vessel tree. In the process of calculating the vascular skeleton line through the main blood vessel and the branch blood vessels of the main blood vessel, the centerline of each blood vessel branch can be advanced until the end is reached, and the centerline of the blood vessel tree can be determined. Based on the centerline of the blood vessel tree, a variety of vascular features can be extracted, including parameters such as the position of the branch blood vessel, the diameter of the branch blood vessel, and the angle between the branch blood vessel and the target blood vessel segment.
[0101] It is understandable that the order of step 200 and step 300 is not limited, and they can be executed simultaneously or one after another.
[0102] The following is an introduction to the process of determining the second blood vessel segment of interest based on the matching error.
[0103] In the embodiment of the present application, determining a second blood vessel segment of interest in a second angiography image corresponding to the first blood vessel segment of interest based on the matching error includes:
[0104] obtaining a vascular characteristic of a first vascular segment of interest and a vascular characteristic of a second vascular segment;
[0105] Determine the vascular features of the first vascular segment of interest as a feature template and the vascular feature set of the vascular features of the second blood vessel as an object to be matched;
[0106] Calculate the matching error between the feature template and the object to be matched to obtain an error set;
[0107] The area corresponding to the minimum value in the error set is used as the second blood vessel segment of interest in the second angiography image.
[0108] In the implementation of this application, the matching process is as follows: assuming that the diameter of the first target blood vessel segment of interest at the first angiography angle is D o (d o1 ,d o2 ,...,d om ), the position P of the branch vessel in the vascular topological feature of the first target vessel segment of interest o (p o1 ,p o2 ,...,p on ), the diameter of the branch vessel is R o1 (r o1 ,r o2 ,...,r on ), the angle of the branch vessels is α o (α o1 ,α o2 ,...,α on ), assuming that the diameter of the second blood vessel at the second angiographic angle is D t (d t1 ,d t2 ,...,d ts ), the position P of the branch vessel in the vessel feature of the second vessel t (p t1 ,p t2 ,...,p th ), the diameter of the branch vessel is R t (r t1 ,r t2 ,...,r th ), the angle of the branch vessels is α t (α t1 ,α t2 ,...,α th ).
[0109] In the example of the present application, the vascular features of the first vascular segment of interest can be used as a template, and the feature set of the vascular features of the second blood vessel at the second angiography angle is used as the object to be matched. Starting from the first feature of the object to be matched, the template feature set is compared one by one with the corresponding features of the object to be matched, that is, the feature set, and the errors between the features are calculated in sequence to obtain an error set including multiple matching error values. The minimum value is found in the error set, and the area corresponding to the minimum value is the area with the highest matching degree. The vascular segment represented by the area is used as the second vascular segment of interest in the second angiography image. It can be understood that the number of feature points can be set according to actual needs, and the range of the area represented by the points can be set according to actual needs.
[0110] The matching error may be composed of four parts: a diameter matching error of a blood vessel segment, a position matching error of a branch blood vessel, a diameter matching error of a branch blood vessel, and an angle matching error of a branch blood vessel.
[0111] The diameter matching error calculation formula of the blood vessel segment is as follows:
[0112]
[0113] Where D error is the diameter matching error, M is the number of template diameter feature points, d oi is the diameter of the i-th feature point of the template, d ti is the diameter of the i-th feature point of the object region to be matched. In the embodiment of the present application, the blood vessel segment may be the blood vessel segment corresponding to the first main blood vessel and the second main blood vessel.
[0114] The calculation formula of the position matching error of branch blood vessels is as follows:
[0115]
[0116] Among them, P error The position matching error of the branch blood vessels, N is the number of feature points of the template branch position, p oi is the position of the feature point of the i-th branch of the template, p t i is the position of the i-th branch feature point in the object area to be matched.
[0117] The diameter matching error of branch vessels is calculated as follows:
[0118]
[0119] Where R error The diameter matching error of the branch blood vessels, N is the number of feature points of the branch diameter of the template, R oi is the i-th branch diameter feature point of the template, R ti is the i-th branch diameter feature point of the object area to be matched.
[0120] The calculation formula of the angle matching error of branch vessels is as follows:
[0121]
[0122] where α error The angle matching error of the branch blood vessels, N is the number of feature points of the template branch angle, α oi is the template’s i-th branch angle feature point, α ti is the i-th branch angle feature point of the object area to be matched.
[0123] The overall matching error calculation formula is as follows:
[0124] error=a*D error +b*P error +c*R error +d*α error
[0125] Among them, a, b, c, d represent weight factors, and the weight factors satisfy a+b+c+d=1.
[0126] In the embodiment of the present application, the matching errors represented by the respective dimensions can be calculated respectively by the formulas of the above four parts. The smaller the matching error, the greater the degree of matching. The area with the largest degree of matching is selected as the best matching area, and finally the second blood vessel segment of interest under the second angiography angle is obtained.
[0127] It can be seen that the embodiment of the present application can obtain automatic recommendations for vascular segments of interest in dual positions / first angiography angles and second angiography angles, reduce human intervention, quickly and accurately match vascular segments of interest, and establish a solid foundation for vascular three-dimensional reconstruction and QFR.
[0128] Furthermore, the first blood vessel segment of interest and the second blood vessel segment of interest may be modified according to actual needs.
[0129] In the embodiment of the present application, it also includes:
[0130] receiving a first modification operation of a user on a first blood vessel segment of interest;
[0131] According to the first modification operation, updating the blood vessel characteristics of the first blood vessel segment of interest;
[0132] updating the vascular characteristics of the second vascular segment of interest based on the updated vascular characteristics of the first vascular segment of interest;
[0133] or,
[0134] receiving a second modification operation for modifying a second blood vessel segment of interest;
[0135] updating the blood vessel feature of the second blood vessel segment of interest according to the second modification operation;
[0136] The vessel feature of the first vessel segment of interest is updated based on the updated vessel feature of the second vessel segment of interest.
[0137] And, also includes:
[0138] receiving a first locking operation for modifying a region where a first blood vessel segment of interest is located;
[0139] According to a first locking operation, locking the blood vessel feature of the first blood vessel segment of interest;
[0140] receiving a third modification operation for modifying the region where the second blood vessel segment of interest is located;
[0141] According to the third modification operation, modify the blood vessel characteristics of the second blood vessel segment of interest;
[0142] or,
[0143] receiving a second locking operation for modifying the region where the second blood vessel segment of interest is located;
[0144] According to a second locking operation, locking the blood vessel feature of the second blood vessel segment of interest;
[0145] receiving a fourth modification operation for modifying the region where the first blood vessel segment of interest is located;
[0146] According to the fourth modification operation, the vessel characteristics of the first vessel segment of interest are modified.
[0147] In the embodiment of the present application, the user can perform modification operations on the first blood vessel of interest and / or the second blood vessel of interest.
[0148] Among them, the vascular characteristics of the first vessel of interest, such as the vascular topological characteristics of the first vessel of interest, the vascular characteristics related to the branch vessels, etc., can be updated based on the first modification operation. The vascular characteristics of the first vessel of interest are updated in a timely manner, and the above implementation is performed based on the updated first vessel of interest characteristics, and the second vessel of interest characteristics are updated accordingly. Similarly, the vascular characteristics of the second vessel of interest can also be modified through the second modification operation, and the vascular characteristics of the first vessel of interest can be updated.
[0149] Of course, the region where the blood vessel segment of interest is located may also be locked, and after one of the blood vessel segments of interest is locked, a modification operation may be performed on another blood vessel segment of interest to modify the blood vessel characteristics of the other blood vessel segment of interest.
[0150] It is understandable that in the embodiment of the present application, the second vascular segment of interest can be directly calculated in the same way as the first vascular segment of interest is calculated, but there may be a problem of poor matching. Therefore, after obtaining the first vascular segment of interest and the second vascular segment of interest, one of the vascular segments can be locked according to the operation specified by the user, and the other vascular segment can be updated by executing the embodiment of the present application.
[0151] Figure 4 A schematic diagram of a scene is shown in an embodiment of the present application, which includes a matching result of a first blood vessel segment of interest in a first angiography image and a second blood vessel segment of interest in a second angiography image.
[0152] Among them, 401 is a first blood vessel segment of interest in the first angiography image, and 402 is a second blood vessel segment of interest in the second angiography image.
[0153] Corresponding to the aforementioned application function realization method embodiment, the present application also provides a dual-position blood vessel automatic matching system, an electronic device and corresponding embodiments.
[0154] Figure 5 It is a structural schematic diagram of a dual-position blood vessel automatic matching system shown in an embodiment of the present application.
[0155] See also Figure 5 The embodiment of the present application discloses a dual-position blood vessel automatic matching system 500, comprising:
[0156] An acquisition module 1 is used to obtain a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole;
[0157] A first recommendation module 2, configured to determine a first blood vessel segment of interest of a first blood vessel in a first angiography image;
[0158] A determination module 3, used to determine a blood vessel feature of a second blood vessel in a second angiography image;
[0159] A calculation module 4 is used to calculate a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel;
[0160] The second recommendation module 5 is configured to determine a second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest based on the matching error.
[0161] The first recommended module is specifically used for:
[0162] Determine a first main blood vessel and a first blood vessel tree skeleton of a first blood vessel in the first angiography image;
[0163] Calculating a first blood vessel stenosis position based on the first main blood vessel and the first blood vessel tree skeleton;
[0164] A first blood vessel segment of interest is determined according to the stenosis position of the first blood vessel.
[0165] The step of calculating the first blood vessel stenosis position based on the first main blood vessel and the first blood vessel tree skeleton includes:
[0166] Calculating a blood vessel diameter of the first blood vessel based on the first blood vessel tree skeleton;
[0167] calculating the vascular stenosis rate of the first main blood vessel by using the proportional relationship between the blood vessel diameter of the first main blood vessel and the blood vessel diameter of a normal blood vessel corresponding to the first blood vessel;
[0168] The first blood vessel stenosis position is determined based on the blood vessel stenosis rate of the first blood vessel.
[0169] Wherein, determining the first blood vessel segment of interest according to the stenosis position of the first blood vessel includes:
[0170] Obtaining the selection range of the target blood vessel segment of interest;
[0171] The first blood vessel within the selected range is used as a first blood vessel segment of interest, with the first blood vessel stenosis position as a reference.
[0172] The determination module is specifically used for:
[0173] determining a second main blood vessel and a second blood vessel tree skeleton of a second blood vessel in the second angiography image;
[0174] The vascular characteristics of the second blood vessel are determined based on the second main blood vessel and the vascular centerline corresponding to the second blood vessel tree skeleton; the vascular characteristics are at least used to characterize the position and diameter of the second blood vessel in the second angiography image and the relationship between the branch blood vessels and the second blood vessel.
[0175] The calculating the matching error between the first interested blood vessel segment and the blood vessel feature comprises:
[0176] Based on the vessel segment diameter matching error, the branch vessel position matching error, the branch vessel diameter matching error and / or the branch vessel angle matching error, the matching degree error between the first vessel segment of interest and the vessel feature is calculated.
[0177] The second recommendation module is specifically used for:
[0178] obtaining a blood vessel characteristic of the first blood vessel segment of interest and a blood vessel characteristic of the second blood vessel;
[0179] determining the vascular features of the first vascular segment of interest as a feature template and the vascular feature set of the vascular features of the second vascular segment as an object to be matched;
[0180] Calculating the matching error between the feature template and the object to be matched to obtain an error set;
[0181] The area corresponding to the minimum value in the error set is used as the second blood vessel segment of interest in the second angiography image.
[0182] Also included is a first update module, configured to:
[0183] receiving a first modification operation of the user on the first blood vessel segment of interest;
[0184] updating the blood vessel characteristics of the first blood vessel segment of interest according to the first modification operation;
[0185] updating the vascular feature of the second vascular segment of interest based on the updated vascular feature of the first vascular segment of interest;
[0186] or,
[0187] receiving a second modification operation for modifying the second blood vessel segment of interest;
[0188] updating the blood vessel feature of the second blood vessel segment of interest according to the second modification operation;
[0189] The vessel feature of the first vessel segment of interest is updated based on the updated vessel feature of the second vessel segment of interest.
[0190] Also included is a second update module, for:
[0191] receiving a first locking operation for modifying the region where the first blood vessel segment of interest is located;
[0192] According to the first locking operation, locking the blood vessel feature of the first blood vessel segment of interest;
[0193] receiving a third modification operation for modifying the region where the second blood vessel segment of interest is located;
[0194] modifying the blood vessel feature of the second blood vessel segment of interest according to the third modification operation;
[0195] or,
[0196] receiving a second locking operation for modifying the area where the second blood vessel segment of interest is located;
[0197] According to the second locking operation, locking the blood vessel feature of the second blood vessel segment of interest;
[0198] receiving a fourth modification operation for modifying the region where the first blood vessel segment of interest is located;
[0199] According to the fourth modification operation, the blood vessel characteristics of the first blood vessel segment of interest are modified.
[0200] Optionally, an angle difference between a first angiography angle of the first angiography image and a second angiography angle of the second angiography image is greater than a preset degree; the preset degree is used to indicate that three-dimensional reconstruction of the blood vessel can be performed based on the preset degree.
[0201] The dual-position blood vessel automatic matching system provided in the present application can automatically match the second blood vessel segment of interest at a second angiography angle through the matching error after automatically obtaining the first blood vessel segment of interest at a first angiography angle, without the need for human intervention and with high accuracy, thereby improving the accuracy of blood vessel three-dimensional reconstruction and QFR.
[0202] 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.
[0203] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.
[0204] See also Figure 6 , the electronic device 1000 includes a memory 1010 and a processor 1020 .
[0205] 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.
[0206] 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.
[0207] 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.
[0208] 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.
[0209] 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.
[0210] 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 dual-position blood vessel automatic matching method, characterized in that: include: Obtain a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole; determining a first blood vessel segment of interest of a first blood vessel in the first angiography image; determining a blood vessel characteristic of a second blood vessel in the second angiography image; calculating a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel; A second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest is determined based on the matching error.
2. The method according to claim 1, characterized in that: The determining of a first blood vessel segment of interest of a first blood vessel in the first angiography image comprises: Determine a first main blood vessel and a first blood vessel tree skeleton of a first blood vessel in the first angiography image; Calculating a first blood vessel stenosis position based on the first main blood vessel and the first blood vessel tree skeleton; A first blood vessel segment of interest is determined according to the stenosis position of the first blood vessel.
3. The method according to claim 2, characterized in that The calculating the first blood vessel stenosis position based on the first main blood vessel and the first blood vessel tree skeleton includes: Calculating a blood vessel diameter of the first blood vessel based on the first blood vessel tree skeleton; calculating the vascular stenosis rate of the first main blood vessel by using the proportional relationship between the blood vessel diameter of the first main blood vessel and the blood vessel diameter of a normal blood vessel corresponding to the first blood vessel; The first blood vessel stenosis position is determined based on the blood vessel stenosis rate of the first blood vessel.
4. The method according to claim 2, characterized in that: The step of determining a first blood vessel segment of interest according to the first blood vessel stenosis position includes: Obtaining the selection range of the target blood vessel segment of interest; The first blood vessel within the selected range is used as a first blood vessel segment of interest, with the first blood vessel stenosis position as a reference.
5. The method according to claim 1, characterized in that The determining of the blood vessel feature of the second blood vessel in the second angiography image includes: determining a second main blood vessel and a second blood vessel tree skeleton of a second blood vessel in the second angiography image; The vascular characteristics of the second blood vessel are determined based on the second main blood vessel and the vascular centerline corresponding to the second blood vessel tree skeleton; the vascular characteristics are at least used to characterize the position and diameter of the second blood vessel in the second angiography image and the relationship between the branch blood vessels and the second blood vessel.
6. The method according to claim 1, characterized in that The calculating the matching error between the first interested blood vessel segment and the blood vessel feature comprises: Based on the vessel segment diameter matching error, the branch vessel position matching error, the branch vessel diameter matching error and / or the branch vessel angle matching error, the matching degree error between the first vessel segment of interest and the vessel feature is calculated.
7. The method according to claim 1, characterized in that Determining a second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest based on the matching error includes: obtaining a blood vessel characteristic of the first blood vessel segment of interest and a blood vessel characteristic of the second blood vessel; determining the vascular features of the first vascular segment of interest as a feature template and the vascular feature set of the vascular features of the second vascular segment as an object to be matched; Calculating the matching error between the feature template and the object to be matched to obtain an error set; The area corresponding to the minimum value in the error set is used as the second blood vessel segment of interest in the second angiography image.
8. The method according to claim 1, characterized in that Also includes: receiving a first modification operation of the user on the first blood vessel segment of interest; updating the blood vessel characteristics of the first blood vessel segment of interest according to the first modification operation; updating the vascular feature of the second vascular segment of interest based on the updated vascular feature of the first vascular segment of interest; or, receiving a second modification operation for modifying the second blood vessel segment of interest; updating the blood vessel feature of the second blood vessel segment of interest according to the second modification operation; The vessel feature of the first vessel segment of interest is updated based on the updated vessel feature of the second vessel segment of interest.
9. The method according to claim 1, characterized in that: Also includes: receiving a first locking operation for modifying the region where the first blood vessel segment of interest is located; According to the first locking operation, locking the blood vessel feature of the first blood vessel segment of interest; receiving a third modification operation for modifying the region where the second blood vessel segment of interest is located; modifying the blood vessel feature of the second blood vessel segment of interest according to the third modification operation; or, receiving a second locking operation for modifying the area where the second blood vessel segment of interest is located; According to the second locking operation, locking the blood vessel feature of the second blood vessel segment of interest; receiving a fourth modification operation for modifying the region where the first blood vessel segment of interest is located; According to the fourth modification operation, the blood vessel characteristics of the first blood vessel segment of interest are modified.
10. The method according to claim 1, characterized in that An angle difference between a first contrast angle of the first contrast image and a second contrast angle of the second contrast image is greater than a preset degree; the preset degree is used to indicate that three-dimensional reconstruction of the blood vessel can be performed based on the preset degree.
11. A dual-position blood vessel automatic matching system, characterized in that: include: An acquisition module, used for acquiring a first contrast image at a first contrast angle and a second contrast image at a second contrast angle; wherein the first contrast image and the second contrast image are images at the end of cardiac diastole; a first recommendation module, configured to determine a first blood vessel segment of interest of a first blood vessel in the first angiography image; a determination module, configured to determine a blood vessel feature of a second blood vessel in the second angiography image; a calculation module, configured to calculate a matching error between the first blood vessel segment of interest and the blood vessel features of the second blood vessel; The second recommendation module is configured to determine a second blood vessel segment of interest in the second angiography image corresponding to the first blood vessel segment of interest based on the matching error.
12. 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 10.
13. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 10.
