Optimization method and device in blood vessel contour adjustment process
By monitoring and updating the vascular contour points in real time to ensure that they are perpendicular to the vascular center line, the problem of inaccurate vascular contour acquisition in the prior art is solved, and more efficient and precise vascular morphology optimization is achieved.
Patent Information
- Application Number
- CN202411632095.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-03-04
AI Technical Summary
The existing fully automatic vascular contour methods cannot accurately fit the contour of the vascular lumen, especially in positions where contrast agents are blurred, resulting in inaccurate assessment of vascular stenosis.
By responding to the user's contour adjustment operation, obtain the initial contour points to be adjusted and monitor the adjustment process in real time to ensure that the cross-requirement requirements are met. Then, based on the initial morphological parameters of the blood vessel and the position information of the candidate contour points, the candidate contour points are updated to ensure that the contour point connection line is perpendicular to the blood vessel center line, and finally optimize the vascular morphology.
It realizes more accurate acquisition of blood vessel contour information, reduces the contour crossing or overlapping problems caused by user operation errors, improves the accuracy of operation and process control flexibility, and improves the accuracy and efficiency of contour adjustment.
Smart Images
Figure CN119559202A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of medical data processing, and in particular to an optimization method and device in a blood vessel contour adjustment process. Background Art
[0002] At present, the incidence of coronary heart disease in my country is still high, and minimally invasive interventional therapy has become one of the standard treatments for the disease. During diagnosis and treatment, coronary angiography is usually used to evaluate the patient's coronary artery status. However, the degree of vascular stenosis shown by coronary angiography cannot fully and accurately reflect the actual situation of myocardial ischemia.
[0003] QFR (Quantitative Flow Fraction) is an advanced technology based on coronary angiography images that can quickly calculate FFR (Fractional Flow Reserve) without the use of a guidewire, thereby assisting PCI (percutaneous coronary intervention) surgery. Through three-dimensional reconstruction of blood vessels and fluid dynamics analysis, this technology can quickly calculate functional parameters such as pressure drop and QFR value at the lesion site, as well as structural indicators such as lesion length, proximal and distal diameters of blood vessels, and stenosis rate. Therefore, doctors can more quickly and accurately identify clinically significant vascular stenosis and select appropriate stents to develop more accurate interventional treatment plans.
[0004] Among them, accurate vascular contours will affect the diameter of the vascular lumen and are the key to calculating the above important parameters. However, the existing fully automatic vascular contouring methods cannot obtain contours that accurately fit the vascular lumen, especially the positions where the contrast agent is blurred. Therefore, it is very necessary to introduce interactive functions that can accurately and efficiently adjust the contours in the actual clinical QFR system. Summary of the invention
[0005] In view of this, the purpose of the present application is to provide an optimization method and device in the process of adjusting the blood vessel contour, to optimize the process of adjusting the blood vessel contour and obtain more accurate blood vessel contour information.
[0006] The present application embodiment provides an optimization method in a blood vessel contour adjustment process, the optimization method comprising:
[0007] In response to a contour adjustment operation by a user, an initial contour point to be adjusted selected by the user is obtained, and the contour adjustment process is monitored in real time to determine whether the adjustment process meets the crossover requirement;
[0008] If satisfied, obtain the candidate contour points selected by the user at the end of adjustment;
[0009] According to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the candidate contour points are updated according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points to determine the target contour points;
[0010] According to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the initial blood vessel morphological parameters of the blood vessel to be adjusted are updated according to the target contour points to determine the optimized target blood vessel.
[0011] Optionally, determine whether the adjustment process meets the crossover requirements by performing the following steps:
[0012] Real-time acquisition of moving contour points during adjustment;
[0013] Calculating the minimum distance between the moving contour point and the near side contour; wherein the near side contour is the contour where the non-initial contour point to be adjusted is located;
[0014] If the minimum distance is not less than the distance threshold, it is determined that the intersection requirement is met; otherwise, it is determined that the intersection requirement is not met.
[0015] Optionally, the calculating the minimum distance between the moving contour point and the near side contour includes:
[0016] Performing interpolation processing on a first initial contour point set of the near side contour to determine a first dense contour point set of the near side contour;
[0017] Calculate the moving distance between the moving contour point and each dense contour point in the first dense contour point set;
[0018] According to all the moving distances, the minimum distance between the moving contour point and the near side contour is determined.
[0019] Optionally, the updating of the candidate contour points according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel and according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the coordinate information of the candidate contour points to determine the target contour points includes:
[0020] According to the initial contour point to be adjusted, the corresponding initial center line point is determined, and a first vector from the initial center line point to the initial contour point to be adjusted and a second vector from the initial center line point to the candidate contour point are determined;
[0021] Determine a third vector from the initial center line point to the target contour point using a vector projection calculation method based on the first vector and the second vector;
[0022] The target contour point is determined according to the third vector and the initial centerline point.
[0023] Optionally, the third vector is calculated by the following formula:
[0024]
[0025] Among them, a is the second vector, b is the first vector, and c is the third vector.
[0026] Optionally, the updating of the initial vascular morphological parameters of the blood vessel to be adjusted according to the target contour point to determine the optimized target blood vessel includes:
[0027] Using the target contour points to replace the initial contour points to be adjusted in the initial contour point set to obtain an updated contour point set of the blood vessel to be adjusted, and updating the initial centerline point set according to the updated contour point set to determine the target centerline point set;
[0028] For each target centerline point within a specified range of the target centerline point set, determining a normal vector of the target centerline point; the specified range is determined according to the target contour points;
[0029] Extend the normal vector of the target centerline point on both sides to determine the intersection points with the two contours;
[0030] For two contour points to be updated in the update contour point set corresponding to each target center line point, the two intersection points determined at the target center line point are used to update the two contour points to be updated;
[0031] After all the contour points to be updated in the updated contour point set are updated, the optimized target blood vessel is obtained.
[0032] Optionally, for each target centerline point, two contour points to be updated in the update contour point set corresponding to the target centerline point are updated using two intersection points determined at the target centerline point, including:
[0033] Acquire, from the updated contour point set, a second initial contour point set for each of two contours within a preset range with the target contour point as the center;
[0034] Performing dense sampling processing on the second initial contour point sets respectively to determine the second dense contour point sets of the two contours;
[0035] For each intersection point, determine the target dense contour point that is closest to the intersection point and the corresponding second dense contour point set;
[0036] The target dense contour point is used to update the contour point to be updated corresponding to the intersection point.
[0037] The embodiment of the present application also provides an optimization device in the process of adjusting the blood vessel contour, the optimization device comprising:
[0038] A response module, for responding to a contour adjustment operation of a user, obtaining an initial contour point to be adjusted selected by the user, and monitoring the contour adjustment process in real time to determine whether the adjustment process meets the crossover requirement;
[0039] An acquisition module, used for acquiring the candidate contour points selected by the user when the adjustment is completed if the conditions are met;
[0040] A first updating module is used to update the candidate contour points according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, based on the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points, to determine the target contour points;
[0041] The second updating module is used to update the initial vascular morphological parameters of the blood vessel to be adjusted according to the target contour points in accordance with the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, and determine the optimized target blood vessel.
[0042] Optionally, the response module is further configured to determine whether the adjustment process meets the crossover requirement by the following steps:
[0043] Real-time acquisition of moving contour points during adjustment;
[0044] Calculating the minimum distance between the moving contour point and the near side contour; wherein the near side contour is the contour where the non-initial contour point to be adjusted is located;
[0045] If the minimum distance is not less than the distance threshold, it is determined that the intersection requirement is met; otherwise, it is determined that the intersection requirement is not met.
[0046] Optionally, when the response module is used to calculate the minimum distance between the moving contour point and the near side contour, the response module is used to:
[0047] Performing interpolation processing on a first initial contour point set of the near side contour to determine a first dense contour point set of the near side contour;
[0048] Calculate the moving distance between the moving contour point and each dense contour point in the first dense contour point set;
[0049] According to all the moving distances, the minimum distance between the moving contour point and the near side contour is determined.
[0050] Optionally, when the first updating module is used to update the candidate contour points according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the coordinate information of the candidate contour points, and to determine the target contour points, the first updating module is used to:
[0051] According to the initial contour point to be adjusted, the corresponding initial center line point is determined, and a first vector from the initial center line point to the initial contour point to be adjusted and a second vector from the initial center line point to the candidate contour point are determined;
[0052] Determine a third vector from the initial center line point to the target contour point using a vector projection calculation method based on the first vector and the second vector;
[0053] The target contour point is determined according to the third vector and the initial centerline point.
[0054] Optionally, the third vector is calculated by the following formula:
[0055]
[0056] Among them, a is the second vector, b is the first vector, and c is the third vector.
[0057] Optionally, when the second updating module is used to update the initial vascular morphological parameters of the to-be-adjusted blood vessel according to the target contour point to determine the optimized target blood vessel, the second updating module is used to:
[0058] Using the target contour points to replace the initial contour points to be adjusted in the initial contour point set to obtain an updated contour point set of the blood vessel to be adjusted, and updating the initial centerline point set according to the updated contour point set to determine the target centerline point set;
[0059] For each target centerline point within a specified range of the target centerline point set, determining a normal vector of the target centerline point; the specified range is determined according to the target contour points;
[0060] Extend the normal vector of the target centerline point on both sides to determine the intersection points with the two contours;
[0061] For two contour points to be updated in the update contour point set corresponding to each target center line point, the two intersection points determined at the target center line point are used to update the two contour points to be updated;
[0062] After all the contour points to be updated in the updated contour point set are updated, the optimized target blood vessel is obtained.
[0063] Optionally, when the second updating module is used to update two contour points to be updated in the update contour point set corresponding to each target center line point using two intersection points determined at the target center line point, the second updating module is used to:
[0064] Acquire, from the updated contour point set, a second initial contour point set for each of two contours within a preset range with the target contour point as the center;
[0065] Performing dense sampling processing on the second initial contour point sets respectively to determine the second dense contour point sets of the two contours;
[0066] For each intersection point, determine the target dense contour point that is closest to the intersection point and the corresponding second dense contour point set;
[0067] The target dense contour point is used to update the contour point to be updated corresponding to the intersection point.
[0068] An embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the optimization method described above are performed.
[0069] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the optimization method described above are executed.
[0070] The embodiment of the present application provides an optimization method and device in a blood vessel contour adjustment process, the optimization method comprising: in response to a contour adjustment operation of a user, obtaining an initial contour point to be adjusted selected by the user, and monitoring the contour adjustment process in real time to determine whether the adjustment process meets the cross requirement; if so, obtaining the candidate contour point selected by the user at the end of the adjustment; updating the candidate contour point according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour point according to the principle that the corresponding contour point line is perpendicular to the blood vessel centerline, and determining the target contour point; updating the initial blood vessel morphological parameters of the blood vessel to be adjusted according to the target contour point according to the principle that the corresponding contour point line is perpendicular to the blood vessel centerline, and determining the target blood vessel after optimization.
[0071] In this way, the method can monitor the adjustment process in real time when the user performs the contour adjustment operation, ensure that the established intersection requirements are met during the operation, reduce the contour intersection or overlap problems caused by user operation errors, and improve the accuracy of the operation and the flexibility of process control. And by obtaining the candidate contour points selected by the user at the end of the adjustment, and combining the initial morphological parameters of the blood vessel, automatically updating to ensure the target contour points of the adjustment, and automatically updating the initial morphological parameters of the blood vessel after determining the target contour points, the overall effect of the blood vessel shape is further optimized, and the accuracy and efficiency of the contour adjustment are improved. In addition, the method introduces the principle of "the contour point connection line is perpendicular to the blood vessel centerline" to ensure that the updated contour point position and the blood vessel geometry maintain reasonable consistency. This optimization based on geometric constraints ensures that the adjustment of the contour points is more physically consistent with the actual morphology of the blood vessel, thereby optimizing the recovery and description accuracy of the blood vessel morphology.
[0072] In summary, this method optimizes the efficiency and accuracy of the adjustment process, reduces the manual operation burden of users, and ensures the accuracy of vascular geometry, which has significant practical value.
[0073] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0075] Figure 1 A flow chart of an optimization method in a blood vessel contour adjustment process provided in an embodiment of the present application;
[0076] Figure 2 A simplified diagram of a blood vessel outline provided in an embodiment of the present application;
[0077] Figure 3 A schematic diagram of the principle of judging the crossover situation in the process of vascular regulation provided by the present application;
[0078] Figure 4 A schematic diagram of a profile information update process provided by this application;
[0079] Figure 5 A schematic diagram of the structure of an optimization device in a blood vessel contour adjustment process provided in an embodiment of the present application;
[0080] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0081] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.
[0082] At present, the incidence of coronary heart disease in my country is still high, and minimally invasive interventional therapy has become one of the standard treatments for the disease. During diagnosis and treatment, coronary angiography is usually used to evaluate the patient's coronary artery status. However, the degree of vascular stenosis shown by coronary angiography cannot fully and accurately reflect the actual situation of myocardial ischemia.
[0083] QFR (Quantitative Flow Fraction) is an advanced technology based on coronary angiography images that can quickly calculate FFR (Fractional Flow Reserve) without the use of a guidewire, thereby assisting PCI (percutaneous coronary intervention) surgery. Through three-dimensional reconstruction of blood vessels and fluid dynamics analysis, this technology can quickly calculate functional parameters such as pressure drop and QFR value at the lesion site, as well as structural indicators such as lesion length, proximal and distal diameters of blood vessels, and stenosis rate. Therefore, doctors can more quickly and accurately identify clinically significant vascular stenosis and select appropriate stents to develop more accurate interventional treatment plans.
[0084] Among them, accurate vascular contours will affect the diameter of the vascular lumen and are the key to calculating the above important parameters. However, the existing fully automatic vascular contouring methods cannot obtain contours that accurately fit the vascular lumen, especially the positions where the contrast agent is blurred. Therefore, it is very necessary to introduce interactive functions that can accurately and efficiently adjust the contours in the actual clinical QFR system.
[0085] Among them, the current contour adjustment method does not take into account that the diameter of the blood vessel contour cannot be less than 0 (i.e., contour intersection occurs). If the setting of limiting contour intersection is not made, the subsequent result analysis will bring many abnormal results. In addition, the current contour adjustment method does not take into account that the line segment formed by the blood vessel contour points at both ends needs to be perpendicular to the blood vessel centerline. If it is not perpendicular to the centerline, the obtained blood vessel diameter will be larger than the actual lumen diameter, making the subsequent results inaccurate.
[0086] Based on this, the embodiments of the present application provide a method and device for optimizing the blood vessel contour adjustment process, which optimizes the blood vessel contour adjustment process to obtain more accurate blood vessel contour information.
[0087] See also Figure 1 , Figure 1 This is a flow chart of an optimization method in the process of adjusting the blood vessel contour provided by an embodiment of the present application. Figure 1 As shown in, the optimization method provided in the embodiment of the present application includes:
[0088] S101 . In response to a contour adjustment operation of a user, an initial contour point to be adjusted selected by the user is obtained, and the contour adjustment process is monitored in real time to determine whether the adjustment process meets a crossover requirement.
[0089] S102: If satisfied, obtain the candidate contour points selected by the user when the adjustment is completed.
[0090] S103 , according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the candidate contour points are updated according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points to determine the target contour points.
[0091] S104 , according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the initial blood vessel morphological parameters of the blood vessel to be adjusted are updated according to the target contour points to determine the optimized target blood vessel.
[0092] Before executing step S101, initial vascular morphological parameters of the blood vessel to be adjusted may be obtained first. The initial vascular morphological parameters may include initial vascular contour parameters (initial contour point set) and initial vascular centerline parameters (initial centerline point set).
[0093] The acquired initial blood vessel morphology parameters may specifically be two-dimensional blood vessel morphology parameters, so the initial contour point set may include a left contour point set and a right contour point set.
[0094] For examples, see Figure 2 , Figure 2 A simplified diagram of a blood vessel outline is provided in an embodiment of the present application, such as Figure 2 As shown, the schematic diagram includes a left contour line, a right contour line, and a center line of the blood vessel. The initial blood vessel morphological parameters obtained at this time may include the blood vessel center line C = [c1, c2, ..., c n ], left contour L = [l1,l2,…,l n ] and the right contour R = [r1, r2, ..., r n The point coordinates of the three curves are in one-to-one correspondence. For example, c1, l1r1 correspond to each other, and the line segment formed by their connection is the blood vessel diameter at that location, and is the normal vector of the center line at c1 (i.e., perpendicular to the center line).
[0095] Regarding step S101, in this step, when the user performs a contour adjustment operation, the system will obtain the initial contour point to be adjusted selected by the user (i.e., the point that the user wishes to adjust). Then, the system will monitor the contour changes in real time during the adjustment process to ensure that the adjustment process meets specific intersection requirements (the intersection requirements may be: contour lines cannot intersect or cannot violate geometric constraints).
[0096] For example, assuming that the user is adjusting the left contour point in a two-dimensional blood vessel image, the system will automatically capture this point and continue to detect the user's adjustment operation to monitor whether the movement of the adjusted contour point will intersect with the right contour or cause abnormal blood vessel morphology.
[0097] With respect to step S101, in one implementation mode provided in the present application, whether the adjustment process meets the crossover requirement is determined by the following steps:
[0098] S1011. Acquire moving contour points during the adjustment process in real time.
[0099] S1012: Calculate the minimum distance between the moving contour point and the near side contour.
[0100] S1013: If the minimum distance is not less than the distance threshold, it is determined that the intersection requirement is met; otherwise, it is determined that the intersection requirement is not met.
[0101] With respect to step S1011, when the user performs a contour adjustment operation, the position information of the contour point being adjusted by the user is tracked and acquired in real time. This point is called a "moving contour point".
[0102] For example, assuming that the user is adjusting a left contour point of a blood vessel image (selected but not moved, called the initial contour point to be adjusted), the system will record the current position of this point (moved, called the moving contour point) in real time and monitor its movement at any time.
[0103] Regarding step S1012, in this step, the minimum distance between the moving contour point and another adjacent contour line (ie, the "near side contour") is calculated.
[0104] The near side contour is the contour where the non-initial contour point to be adjusted is located, that is, the near side contour refers to the other side contour that has not been adjusted by the user. For example, when the user adjusts the left contour point, the right side contour will be regarded as the near side contour.
[0105] For example, if the user is moving the left contour point, the system will calculate the minimum distance between this left contour point and the right contour line. Assuming that the left contour point moves to the right, the system calculates the distance between this point and the right contour in real time.
[0106] In an embodiment provided in the present application, the calculating the minimum distance between the moving contour point and the proximal contour includes:
[0107] S10121. Perform interpolation processing on a first initial contour point set of the near-side contour to determine a first dense contour point set of the near-side contour.
[0108] S10122. Calculate the moving distance between the moving contour point and each dense contour point in the first dense contour point set.
[0109] S10123. Determine the minimum distance between the moving contour point and the near side contour according to all moving distances.
[0110] Regarding step S10121, in this step, in order to improve calculation accuracy, firstly, interpolation processing is performed on all proximal contours (ie, contours that have not been adjusted), or interpolation processing is performed on part of the proximal contours.
[0111] When interpolation processing is performed on a portion of the near side contour, a portion of the near side contour may be selected for interpolation with the contour point corresponding to the contour point to be adjusted in the near side contour as the center.
[0112] It should be noted that the original contour point set is a discrete point, and more intermediate points are generated by interpolation to form a denser contour point set, so that a more detailed contour structure can be taken into account when calculating the distance between the moving contour point and the near side contour.
[0113] For example, assuming that the near side contour is the right side contour, there are only 10 points in the right side contour point set. After interpolation, these points are refined into 50 more dense points to form the first dense contour point set. This makes it possible to more accurately calculate the minimum distance between the left side moving contour point and the right side contour.
[0114] With respect to step S10122, in this step, the distance (movement spacing) between the moving contour point and each dense contour point in the dense contour point set of the near side contour is calculated.
[0115] For example, suppose the moving contour point on the left is at (x1, y1), calculate the Euclidean distance between this point and each point in the dense point set on the right (for example, (x2, y2), (x3, y3), etc.). By traversing all dense points, the moving distance between each dense contour point can be obtained.
[0116] Regarding step S10123, in this step, after calculating the distances between the moving contour point and all the dense contour points, the minimum value is selected as the final minimum distance. This minimum distance is used to determine whether the contour point meets the intersection requirement during the adjustment process.
[0117] For step S1013, in this step, the distance between two contour points is determined according to a preset spacing threshold. If the minimum spacing between the moving contour point and the near side contour is greater than or equal to the threshold, it means that the adjustment process is safe and meets the intersection requirement. Otherwise, if the distance is less than the threshold, it is considered that the adjustment is unreasonable and does not meet the intersection requirement.
[0118] The distance threshold can be set according to the blood vessel conditions.
[0119] For example: Assume that the preset spacing threshold is 0.1 mm. If the minimum distance between the left contour point and the right contour line remains above 0.1 mm when the left contour point moves to the right, it is judged that the adjustment at this time meets the intersection requirement. On the contrary, if the distance is less than 2 mm, the system will judge that the intersection requirement is not met, and rebound can be triggered at this time, that is, the position of the moving point is updated to the position where the user starts to drag the point (back to the initial contour point to be adjusted).
[0120] For examples, see Figure 3 , Figure 3 A schematic diagram of the principle of judging the crossover situation in the process of vascular regulation provided by this application is shown as follows: Figure 3 As shown, the large dots are the original contour points (relatively sparse), and the small dots are the interpolated points (relatively dense).
[0121] Assume that the user moves the i-th point r of the right contour i , only the left contour is spline interpolated, assuming that the number of points is increased by 3 times, that is, the dense left contour Calculate r in real time during the user's movement i The distance from each dense point on the left contour. Select the minimum value of all distances calculated above as the judgment distance to determine whether the distance is less than or equal to the threshold (such as 0.1mm). If it is equal to the threshold, rebound is triggered, that is, the position of the moving point is updated to the position where the user starts dragging.
[0122] Regarding step S102, in this step, if the intersection requirements are met during the adjustment process (ie, the adjustment process is legal and complies with the preset geometric and intersection rules), the system will obtain the final candidate contour points selected by the user at the end of the adjustment and prepare for further optimization.
[0123] Example: After the user completes the adjustment, the system will obtain the new contour point position. Suppose the user moves the left contour point from position A to position B, then position B is the candidate contour point.
[0124] Regarding step S103, in this step, the candidate contour points are optimized and updated according to the geometric principle of "the line connecting the corresponding contour points is perpendicular to the centerline of the blood vessel" and combined with the initial morphological parameters of the blood vessel to be adjusted (such as the width and shape of the blood vessel). That is, under the condition that the contour points and the centerline of the blood vessel remain perpendicular, the final position of the contour points is adjusted to ensure that the optimized contour and the blood vessel morphology are reasonably matched.
[0125] For example, suppose that during the adjustment process the user moves the left contour point excessively to an unreasonable oblique position. The system adjusts the position of the contour point according to the centerline of the blood vessel and its geometric characteristics so that the contour point is perpendicular to the centerline while ensuring the integrity of the blood vessel morphology.
[0126] In an embodiment provided in the present application, the candidate contour points are updated according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, according to the initial vascular morphological parameters of the blood vessel to be adjusted and the coordinate information of the candidate contour points, to determine the target contour points, including:
[0127] S1031 . Determine the corresponding initial centerline point according to the initial contour point to be adjusted, and determine a first vector from the initial centerline point to the initial contour point to be adjusted, and a second vector from the initial centerline point to the candidate contour point.
[0128] S1032. Determine a third vector from the initial center line point to the target contour point by using a vector projection calculation method according to the first vector and the second vector.
[0129] S1033. Determine the target contour point according to the third vector and the initial center line point.
[0130] Regarding step S1031, in this step, starting from the initial contour point to be adjusted (ie, the initial blood vessel contour position), a point on the blood vessel centerline corresponding to the contour point is determined, which is called the initial centerline point.
[0131] After the initial centerline point is determined, two vectors are calculated: a vector pointing from the initial centerline point to the initial contour point to be adjusted (first vector) and a vector pointing from the initial centerline point to the candidate contour point (second vector).
[0132] Regarding step S1032, in this step, a new vector pointing from the initial centerline point to the target contour point is calculated based on the first vector and the second vector using a vector projection method, which is called a third vector. The third vector can be regarded as an adjusted result to ensure that the new contour point meets the constraints of the vascular morphology.
[0133] In one implementation provided in the present application, the third vector is calculated by the following formula:
[0134]
[0135] Among them, a is the second vector, b is the first vector, and c is the third vector.
[0136] With respect to step S1033, after the third vector and the initial center line point are determined, reverse calculation is performed to determine the target contour point (specifically, the coordinate information of the target contour point is determined).
[0137] For examples, please see Figure 2 ,like Figure 2 As shown in the figure, there are 4 points in total. Assume that the user adjusts the point of the left contour (the initial contour point to be adjusted li ) and drag to n i point (candidate contour point), then through the contour projection adjustment algorithm, the last dragged point will automatically change to t i The location of the point (target contour point).
[0138] Assume that the adjusted point is the i-th point l on the left contour i , the initial centerline point on the corresponding centerline is c i .
[0139] The specific algorithm process includes:
[0140] First calculate c i l i Vector (second vector), use l i -c i Then calculate c i n i Vector (first vector), use n i -c i You can get it.
[0141] Denoted as vector a=n i -c i , vector b = l i -c i , using the mathematical formula of vector projection, we get c i t i Vector (third vector):
[0142]
[0143] New point t i The position coordinates of (target contour point) are:
[0144]
[0145] Through this algorithm, the position coordinates of the final dragged point will become This method can restrict the user from dragging the outline arbitrarily and can respond to the user's interaction in real time.
[0146] Regarding step S104, in this step, after determining the target contour points, the system will update the morphological parameters of the blood vessel according to these new contour points, and finally obtain the optimized target blood vessel morphology. This step ensures that the overall blood vessel morphology is consistent with the adjustment of the new contour points.
[0147] In one embodiment provided in the present application, the updating of the initial vascular morphological parameters of the blood vessel to be adjusted according to the target contour points to determine the optimized target blood vessel includes:
[0148] S1041. Use the target contour points to replace the initial contour points to be adjusted in the initial contour point set to obtain an updated contour point set of the blood vessel to be adjusted, and update the initial centerline point set according to the updated contour point set to determine a target centerline point set.
[0149] S1042. For each target centerline point within a specified range of the target centerline point set, determine a normal vector of the target centerline point; the specified range is determined according to the target contour point.
[0150] S1043, extending the normal vector of the target center line point on both sides to determine the intersection points with the two contours.
[0151] S1044 . For two contour points to be updated in the update contour point set corresponding to each target center line point, update the two contour points to be updated using two intersection points determined at the target center line point.
[0152] S1045 , after all the contour points to be updated in the updated contour point set are updated, the optimized target blood vessel is obtained.
[0153] With respect to step S1041, in this step, the target contour points determined in the previous step replace the contour points to be adjusted in the initial contour point set, thereby obtaining an updated contour point set. Based on this new contour point set, the initial centerline point set of the blood vessel is adjusted to obtain an updated target centerline point set.
[0154] With respect to step S1042, in this step, each target centerline point within a specified range of the target centerline point set refers to all or part of the target centerline points in the target centerline point set.
[0155] For each target centerline point, determine its corresponding normal vector, where the normal vector is a vector perpendicular to the centerline and is used to define the geometric "orthogonal direction".
[0156] Regarding step S1043, in this step, the normal vector of each target centerline point is extended on both sides to find the intersection points of the normal vector and the left and right contours of the blood vessel. These two intersection points will be used to update the left and right contour points.
[0157] With respect to step S1044, in an implementation manner provided in the present application, for each target centerline point, two contour points to be updated in the update contour point set corresponding to the target centerline point are updated using two intersection points determined at the target centerline point, including:
[0158] S10441. Acquire, from the updated contour point set, second initial contour point sets of two contours within a preset range centered on the target contour point.
[0159] S10442. Perform dense sampling processing on the second initial contour point sets respectively to determine the second dense contour point sets of the two contours.
[0160] S10443. For each intersection point, determine a target dense contour point that is closest to the intersection point and the corresponding second dense contour point set.
[0161] S10444: Use the target dense contour point to update the contour point to be updated corresponding to the intersection point.
[0162] With respect to step S10441, in the latter step, from the updated contour point set, the initial contour point sets on the left and right sides of the range near the target contour point are obtained. These contour points belong to a local area and are screened with the target contour point as the center.
[0163] The second initial contour point set is the initial point set of the left and right contours within this range.
[0164] With respect to step S10442, the second initial contour point sets on the left and right sides are sampled more densely to generate a more refined contour point set, which is called a second dense contour point set.
[0165] The sampling process aims to increase the number of contour points to ensure more accurate contour updates and adapt to the complex morphology of blood vessels.
[0166] With respect to step S1043 , for each left and right intersection point extending from the normal vector of the target centerline point, the distance between the left and right intersection point and each point in the second dense contour point set is calculated respectively.
[0167] Determine a dense contour point that is closest to the intersection point. This point is called the target dense contour point.
[0168] With respect to step S10444, in this step, the position of the previously found target dense contour point is used to update the corresponding contour point to be updated. That is, there is one contour point to be updated on each side, and it is replaced by the nearest target dense contour point at the intersection to ensure that the updated contour point is more consistent with the vascular morphology.
[0169] With respect to step S1045, when all contour points at the target centerline points are updated, the entire contour point set is optimized, and the optimized target blood vessel morphology is finally determined.
[0170] For examples, see Figure 4 , Figure 4 A schematic diagram of a profile information update process provided by this application. Figure 4 As shown in the figure, after the user adjusts the contour, the left and right contours of the middle blood vessel in the left figure are obviously tilted, and the right figure is the corresponding line segment of the contour regenerated after executing step S104. The specific generation process is as follows:
[0171] According to the position of the user's operation point, the range of the corresponding points of the regenerated contour is determined. A threshold value (such as the range of 10 points before and after the operation point) can be set here.
[0172] The left and right contours of the range are densely sampled using spline interpolation to obtain a dense left contour and a dense right contour (eg, 2000 points).
[0173] The new center line is calculated based on the contour adjusted by the user. The calculation formula is: (As shown in the yellow center line in the right picture).
[0174] The tangent vector is obtained based on the new center line, and then rotated 90° to generate the normal vector. The calculation method of the tangent vector is: The normal direction vector calculation formula is: R=[[0,-1],[1,0]]
[0175] Set a fixed length, such as 8 pixels, to get a i A line segment with a length of 16 extending in the direction of the left and right contours ( Figure 4 ), for each point at both ends of a line segment, find the point closest to the dense left contour and the dense right contour as the corresponding point of the new contour.
[0176] In this way, the method can monitor the adjustment process in real time when the user performs the contour adjustment operation, ensure that the established intersection requirements are met during the operation, reduce the contour intersection or overlap problems caused by user operation errors, and improve the accuracy of the operation and the flexibility of process control. And by obtaining the candidate contour points selected by the user at the end of the adjustment, and combining the initial morphological parameters of the blood vessel, automatically updating to ensure the target contour points of the adjustment, and automatically updating the initial morphological parameters of the blood vessel after determining the target contour points, the overall effect of the blood vessel shape is further optimized, and the accuracy and efficiency of the contour adjustment are improved. In addition, the method introduces the principle of "the contour point connection line is perpendicular to the blood vessel centerline" to ensure that the updated contour point position and the blood vessel geometry maintain reasonable consistency. This optimization based on geometric constraints ensures that the adjustment of the contour points is more physically consistent with the actual morphology of the blood vessel, thereby optimizing the recovery and description accuracy of the blood vessel morphology.
[0177] Based on the same inventive concept, an optimization device corresponding to the optimization method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned optimization method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.
[0178] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an optimization device in the process of adjusting the blood vessel contour provided by an embodiment of the present application. Figure 5 As shown in , the optimization device 500 includes:
[0179] A response module 510 is used to respond to the contour adjustment operation of the user, obtain the initial contour point to be adjusted selected by the user, and monitor the contour adjustment process in real time to determine whether the adjustment process meets the crossover requirement;
[0180] An acquisition module 520 is used to acquire the candidate contour point selected by the user when the adjustment is completed if the conditions are met;
[0181] A first updating module 530 is used to update the candidate contour points according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points, and determine the target contour points;
[0182] The second updating module 540 is used to update the initial vascular morphological parameters of the blood vessel to be adjusted according to the target contour points in accordance with the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, and determine the optimized target blood vessel.
[0183] Optionally, the response module 510 is further configured to determine whether the adjustment process meets the cross-requirement through the following steps:
[0184] Real-time acquisition of moving contour points during adjustment;
[0185] Calculating the minimum distance between the moving contour point and the near side contour; wherein the near side contour is the contour where the non-initial contour point to be adjusted is located;
[0186] If the minimum distance is not less than the distance threshold, it is determined that the intersection requirement is met; otherwise, it is determined that the intersection requirement is not met.
[0187] Optionally, when the response module 510 is used to calculate the minimum distance between the moving contour point and the near side contour, the response module 510 is used to:
[0188] Performing interpolation processing on a first initial contour point set of the near side contour to determine a first dense contour point set of the near side contour;
[0189] Calculate the moving distance between the moving contour point and each dense contour point in the first dense contour point set;
[0190] According to all the moving distances, the minimum distance between the moving contour point and the near side contour is determined.
[0191] Optionally, when the first updating module 530 is used to update the candidate contour points according to the initial vascular morphological parameters of the blood vessel to be adjusted and the coordinate information of the candidate contour points in accordance with the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, and to determine the target contour points, the first updating module 530 is used to:
[0192] According to the initial contour point to be adjusted, the corresponding initial center line point is determined, and a first vector from the initial center line point to the initial contour point to be adjusted and a second vector from the initial center line point to the candidate contour point are determined;
[0193] Determine a third vector from the initial center line point to the target contour point using a vector projection calculation method based on the first vector and the second vector;
[0194] The target contour point is determined according to the third vector and the initial centerline point.
[0195] Optionally, the third vector is calculated by the following formula:
[0196]
[0197] Among them, a is the second vector, b is the first vector, and c is the third vector.
[0198] Optionally, when the second updating module 540 is used to update the initial vascular morphological parameters of the to-be-adjusted blood vessel according to the target contour point to determine the optimized target blood vessel, the second updating module 540 is used to:
[0199] Using the target contour points to replace the initial contour points to be adjusted in the initial contour point set to obtain an updated contour point set of the blood vessel to be adjusted, and updating the initial centerline point set according to the updated contour point set to determine the target centerline point set;
[0200] For each target centerline point within a specified range of the target centerline point set, determining a normal vector of the target centerline point; the specified range is determined according to the target contour points;
[0201] Extend the normal vector of the target centerline point on both sides to determine the intersection points with the two contours;
[0202] For two contour points to be updated in the update contour point set corresponding to each target center line point, the two intersection points determined at the target center line point are used to update the two contour points to be updated;
[0203] After all the contour points to be updated in the updated contour point set are updated, the optimized target blood vessel is obtained.
[0204] Optionally, when the second updating module 540 is used to update two contour points to be updated in the update contour point set corresponding to each target center line point using two intersection points determined at the target center line point, the second updating module 540 is used to:
[0205] Acquire, from the updated contour point set, a second initial contour point set for each of two contours within a preset range with the target contour point as the center;
[0206] Performing dense sampling processing on the second initial contour point sets respectively to determine the second dense contour point sets of the two contours;
[0207] For each intersection point, determine the target dense contour point that is closest to the intersection point and the corresponding second dense contour point set;
[0208] The target dense contour point is used to update the contour point to be updated corresponding to the intersection point.
[0209] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown in , the electronic device 600 includes a processor 610 , a memory 620 and a bus 630 .
[0210] The memory 620 stores machine-readable instructions executable by the processor 610. When the electronic device 600 is running, the processor 610 communicates with the memory 620 via the bus 630. When the machine-readable instructions are executed by the processor 610, the above-mentioned figure can be executed. Figure 3 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.
[0211] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 3 The specific implementation of the steps in the method embodiment shown can be found in the method embodiment, and will not be repeated here.
[0212] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0213] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0214] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0215] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0216] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0217] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. An optimization method in a blood vessel contour adjustment process, characterized in that: The optimization method comprises: In response to a contour adjustment operation by a user, an initial contour point to be adjusted selected by the user is obtained, and the contour adjustment process is monitored in real time to determine whether the adjustment process meets the crossover requirement; If satisfied, obtain the candidate contour points selected by the user at the end of adjustment; According to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the candidate contour points are updated according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points to determine the target contour points; According to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the initial blood vessel morphological parameters of the blood vessel to be adjusted are updated according to the target contour points to determine the optimized target blood vessel.
2. The optimization method according to claim 1, characterized in that: Determine whether the reconciliation process meets the crossover requirements by following these steps: Real-time acquisition of moving contour points during adjustment; Calculating the minimum distance between the moving contour point and the near side contour; wherein the near side contour is the contour where the non-initial contour point to be adjusted is located; If the minimum distance is not less than the distance threshold, it is determined that the intersection requirement is met; otherwise, it is determined that the intersection requirement is not met.
3. The optimization method according to claim 2, characterized in that: The calculating the minimum distance between the moving contour point and the near side contour comprises: Performing interpolation processing on a first initial contour point set of the near side contour to determine a first dense contour point set of the near side contour; Calculate the moving distance between the moving contour point and each dense contour point in the first dense contour point set; According to all the moving distances, the minimum distance between the moving contour point and the near side contour is determined.
4. The optimization method according to claim 1, characterized in that: According to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, the candidate contour points are updated according to the initial blood vessel morphological parameters of the blood vessel to be adjusted and the coordinate information of the candidate contour points to determine the target contour points, including: According to the initial contour point to be adjusted, the corresponding initial center line point is determined, and a first vector from the initial center line point to the initial contour point to be adjusted and a second vector from the initial center line point to the candidate contour point are determined; Determine a third vector from the initial center line point to the target contour point using a vector projection calculation method based on the first vector and the second vector; The target contour point is determined according to the third vector and the initial centerline point.
5. The optimization method according to claim 4, characterized in that: The third vector is calculated by the following formula: Among them, a is the second vector, b is the first vector, and c is the third vector.
6. The optimization method according to claim 1, characterized in that: The updating of the initial blood vessel morphological parameters of the blood vessel to be adjusted according to the target contour point to determine the optimized target blood vessel includes: Using the target contour points to replace the initial contour points to be adjusted in the initial contour point set to obtain an updated contour point set of the blood vessel to be adjusted, and updating the initial centerline point set according to the updated contour point set to determine the target centerline point set; For each target centerline point within a specified range of the target centerline point set, determining a normal vector of the target centerline point; the specified range is determined according to the target contour points; Extend the normal vector of the target centerline point on both sides to determine the intersection points with the two contours; For two contour points to be updated in the update contour point set corresponding to each target center line point, the two intersection points determined at the target center line point are used to update the two contour points to be updated; After all the contour points to be updated in the updated contour point set are updated, the optimized target blood vessel is obtained.
7. The optimization method according to claim 6, characterized in that: The method of updating two contour points to be updated in the update contour point set corresponding to each target center line point using two intersection points determined at the target center line point comprises: Acquire, from the updated contour point set, a second initial contour point set for each of two contours within a preset range with the target contour point as the center; Performing dense sampling processing on the second initial contour point sets respectively to determine the second dense contour point sets of the two contours; For each intersection point, determine the target dense contour point that is closest to the intersection point and the corresponding second dense contour point set; The target dense contour point is used to update the contour point to be updated corresponding to the intersection point.
8. An optimization device in the process of adjusting the blood vessel contour, characterized in that: The optimization device comprises: A response module, for responding to a contour adjustment operation of a user, obtaining an initial contour point to be adjusted selected by the user, and monitoring the contour adjustment process in real time to determine whether the adjustment process meets the crossover requirement; An acquisition module, used for acquiring the candidate contour points selected by the user when the adjustment is completed if the conditions are met; A first updating module is used to update the candidate contour points according to the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, based on the initial blood vessel morphological parameters of the blood vessel to be adjusted and the position information of the candidate contour points, to determine the target contour points; The second updating module is used to update the initial vascular morphological parameters of the blood vessel to be adjusted according to the target contour points in accordance with the principle that the line connecting the corresponding contour points is perpendicular to the center line of the blood vessel, and determine the optimized target blood vessel.
9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the optimization method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the optimization method according to any one of claims 1 to 7 are executed.