Model generation method, system, device, storage medium and program product

Abstract

The present disclosure provides a model generation method, system, device, storage medium and program product. The generation method includes: obtaining a plurality of ultrasound images of a target object and corresponding searchlight position information; extracting a contour feature point set of the target object in each ultrasound image, wherein the contour feature point set includes a plurality of contour feature points; obtaining the spatial position information of each contour feature point based on the contour feature point set and the searchlight position information corresponding to each ultrasound image; obtaining the target projection point of each contour feature point on the standard three-dimensional model corresponding to the target object according to the spatial position information of each contour feature point; calibrating the standard three-dimensional model based on the spatial position information and the target projection point of each contour feature point to obtain the target three-dimensional model of the target object. The present disclosure automatically completes the rapid construction of a three-dimensional heart model without manual intervention, significantly shortening the time for constructing a three-dimensional heart model before surgery.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a model generation method, system, device, storage medium and program product. Background Art

[0002] In intracardiac surgery (such as minimally invasive surgery for atrial fibrillation), surgeons usually need to use intracardiac echocardiography (ICE) catheters to draw three-dimensional models of some of the heart's chambers before performing treatment operations. These three-dimensional models of the heart chambers can help doctors establish three-dimensional spatial information between the heart chamber tissues and establish the relative positions of surgical instruments in the heart chambers. Doctors can also mark points on the three-dimensional model to record part of the surgical operation process. By constructing a three-dimensional model of the heart chamber, doctors can more accurately plan surgical operations, navigate surgical instruments, locate lesions, and minimize surgical risks and improve surgical success rates.

[0003] However, the current operation of drawing three-dimensional models using ICE catheters still relies on manual work. First, the operator needs to accurately operate the ICE handle to position the ICE probe to the desired position, then manually select the diastolic image at that position, and gradually build the cardiac cavity model by outlining and tracing. This construction method is not only time-consuming, but the generated model also usually lacks accuracy and loses many details. At the same time, the operator needs to have a high level of industry knowledge background to be able to judge and select ultrasound images in the appropriate cardiac cycle that meet specific requirements. Summary of the invention

[0004] The technical problem to be solved by the present disclosure is to overcome the defects of the prior art such as long time consumption and rough and inaccurate model of cardiac cavity drawn by using ICE catheter, and to provide a model generation method, system, device, storage medium and program product.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] According to a first aspect of the present disclosure, a method for generating a model is provided, the method comprising:

[0007] Acquire several ultrasonic images of the target object and corresponding searchlight position information;

[0008] Extracting a contour feature point set of the target object in each of the ultrasound images, wherein the contour feature point set includes a plurality of contour feature points;

[0009] Based on the contour feature point set corresponding to each of the ultrasound images and the searchlight position information, obtaining the spatial position information of each of the contour feature points;

[0010] Obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on a standard three-dimensional model corresponding to the target object;

[0011] Based on the spatial position information of each of the contour feature points and the target projection point, the standard three-dimensional model is calibrated to obtain a target three-dimensional model of the target object.

[0012] Preferably, the step of obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on the standard three-dimensional model corresponding to the target object comprises:

[0013] Obtaining a set of intersection points between the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model;

[0014] Based on the spatial position information, each of the contour feature point sets is aligned with the corresponding intersection point set using a preset alignment method;

[0015] Each of the contour feature points in each of the aligned contour feature point sets is mapped to the standard three-dimensional model to obtain the target projection point corresponding to each of the contour feature points.

[0016] Preferably, the step of obtaining the set of intersection points between the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model comprises:

[0017] Creating a virtual sector of the contour feature point set based on the spatial position information and the corresponding searchlight position information;

[0018] Acquire the intersection point set of the virtual sector and the standard three-dimensional model;

[0019] The step of aligning each of the contour feature point sets with the corresponding intersection point set using a preset alignment method based on the spatial position information comprises:

[0020] Acquire first centroid positions corresponding to a plurality of the contour feature points in the contour feature point set, and second centroid positions corresponding to a plurality of intersection points in the intersection point set;

[0021] Based on the first center of gravity position and the second center of gravity position, move each of the contour feature points in the contour feature point set by the same displacement along the same direction, so that the contour feature point set is aligned with the corresponding intersection point set;

[0022] and / or,

[0023] The step of mapping each of the aligned contour feature points in each contour feature point set to the standard three-dimensional model to obtain the target projection point corresponding to each contour feature point comprises:

[0024] Mapping each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each of the contour feature points;

[0025] Obtaining the distance between each of the contour feature points and the corresponding initial projection point to obtain the total distance corresponding to the contour feature point set;

[0026] If the total distance does not meet the preset condition, each of the contour feature points is moved by the same preset distance to expand or shrink each of the contour feature points in spatial position;

[0027] Repeat the step of mapping each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each contour feature point until the total distance meets the preset condition;

[0028] The initial projection point corresponding to each of the contour feature points is used as the target projection point.

[0029] Preferably, the step of calibrating the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain the target three-dimensional model of the target object comprises:

[0030] Obtain the nearest neighbor point of each target projection point on the standard three-dimensional model;

[0031] Based on the spatial position information, each of the nearest neighbor points is moved to the position of the contour feature point corresponding to the target projection point;

[0032] Acquire a set of points to be updated, the set of points to be updated including points to be updated whose distances to the nearest neighbor points are less than a preset threshold;

[0033] Each of the to-be-updated points in the to-be-updated point set is calibrated using a preset algorithm to obtain the target three-dimensional model.

[0034] Preferably, the step of calibrating each of the to-be-updated points in the to-be-updated point set by a preset algorithm to obtain the target three-dimensional model comprises:

[0035] Obtaining the original curvature of the point of the standard three-dimensional model;

[0036] Acquire the curvature of each of the to-be-updated points in the to-be-updated point set to obtain the point calibration curvature of the to-be-updated point set;

[0037] A genetic algorithm is used to minimize the difference between the calibration curvature of the point and the original curvature of the point as an optimization goal, and a target position of each point to be updated is calculated;

[0038] Each of the points to be updated is moved to the corresponding target position to obtain the target three-dimensional model.

[0039] Preferably, the target object includes the entire target organ or the entire target tissue;

[0040] and / or,

[0041] The target object includes the entire target organ or several target sites contained in the entire target tissue;

[0042] The contour feature point set of the target object includes a sub-contour feature point set corresponding to each target part;

[0043] The step of obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on the standard three-dimensional model corresponding to the target object comprises:

[0044] Acquire all sub-contour feature point sets corresponding to the same target part, and the spatial position information corresponding to each sub-contour feature point set;

[0045] Based on each sub-contour feature point set and the spatial position information, obtaining a sub-projection point of each sub-contour feature point on the sub-standard three-dimensional model corresponding to the target part;

[0046] The step of calibrating the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain the target three-dimensional model of the target object comprises:

[0047] Based on the spatial position information of each sub-contour feature point corresponding to the target part and the sub-projection point, calibrate the sub-standard three-dimensional model corresponding to the target part to obtain a sub-three-dimensional model of each target part;

[0048] Based on the sub-three-dimensional model of each of the target parts, the target three-dimensional model of the target object is obtained.

[0049] Preferably, the entire target organ or the entire target tissue includes a heart;

[0050] The target sites include the left atrium, the left ventricle, the right atrium, the right ventricle, the aorta, the pulmonary artery, and the superior vena cava.

[0051] According to a second aspect of the present disclosure, there is provided a model generation system, the generation system comprising an acquisition module, an extraction module, a mapping module, a projection module and a calibration module;

[0052] The acquisition module is used to acquire a plurality of ultrasonic images of the target object and corresponding searchlight position information;

[0053] The extraction module is used to extract a contour feature point set of the target object in each of the ultrasound images, wherein the contour feature point set includes a plurality of contour feature points;

[0054] The mapping module is used to obtain the spatial position information of each of the contour feature points based on the contour feature point set and the searchlight position information corresponding to each of the ultrasound images;

[0055] The projection module is used to obtain a target projection point of each contour feature point on a standard three-dimensional model corresponding to the target object according to the spatial position information of each contour feature point;

[0056] The calibration module is used to calibrate the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain a target three-dimensional model of the target object.

[0057] Preferably, the projection module includes an acquisition unit, an alignment unit and a mapping unit:

[0058] The acquisition unit is used to acquire a set of intersection points between the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model;

[0059] The alignment unit is used to align each of the contour feature point sets with the corresponding intersection point set in a preset alignment manner based on the spatial position information;

[0060] The mapping unit is used to map each of the contour feature points in each of the aligned contour feature point sets to the standard three-dimensional model to obtain the target projection point corresponding to each of the contour feature points.

[0061] Preferably, the acquisition unit includes a creation subunit and an acquisition subunit, and the alignment unit includes a center of gravity subunit and an alignment subunit;

[0062] The creation subunit is used to create a virtual sector of the contour feature point set based on the spatial position information and the corresponding searchlight position information;

[0063] The acquisition subunit is used to acquire the intersection point set between the virtual sector and the standard three-dimensional model;

[0064] The center of gravity determination subunit is used to obtain the first center of gravity positions corresponding to the plurality of contour feature points in the contour feature point set and the second center of gravity positions corresponding to the plurality of intersection points in the intersection point set;

[0065] The alignment subunit is used for moving each of the contour feature points in the contour feature point set by the same displacement along the same direction based on the first center of gravity position and the second center of gravity position, so as to align the contour feature point set with the corresponding intersection point set;

[0066] and / or,

[0067] The mapping unit includes a mapping subunit, a distance subunit, an adjustment subunit and a determination subunit;

[0068] The mapping subunit is used to map each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each of the contour feature points;

[0069] The distance subunit is used to obtain the distance between each of the contour feature points and the corresponding initial projection point, and obtain the total distance corresponding to the contour feature point set;

[0070] The adjusting subunit is used for moving each of the contour feature points by the same preset distance to expand or shrink each of the contour feature points in spatial position if the total distance does not meet the preset condition;

[0071] Calling the mapping subunit to repeatedly execute the step of mapping each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each of the contour feature points until the total distance meets the preset condition;

[0072] The determination subunit is used to use the initial projection point corresponding to each of the contour feature points as the target projection point.

[0073] Preferably, the calibration module comprises an extraction unit, a movement unit and a calibration unit;

[0074] The extraction unit is used to obtain the nearest neighbor point of each target projection point on the standard three-dimensional model;

[0075] The moving unit is used to move each of the nearest neighbor points to the position of the contour feature point corresponding to the target projection point based on the spatial position information;

[0076] The extraction unit is further used to obtain a set of points to be updated, wherein the set of points to be updated includes points to be updated whose distances to the nearest neighboring points are less than a preset threshold;

[0077] The calibration unit is used to calibrate each of the to-be-updated points in the to-be-updated point set by using a preset algorithm to obtain the target three-dimensional model.

[0078] Preferably, the calibration unit includes an original curvature calculation subunit, a calibration curvature calculation subunit, an optimization subunit and a movement subunit;

[0079] The original curvature calculation subunit is used to obtain the original curvature of the points of the standard three-dimensional model;

[0080] The calibration curvature calculation subunit is used to obtain the curvature of each of the to-be-updated points in the to-be-updated point set, and obtain the point calibration curvature of the to-be-updated point set;

[0081] The optimization subunit is used to adopt a genetic algorithm to minimize the difference between the point calibration curvature and the point original curvature as the optimization target, and calculate the target position of each point to be updated;

[0082] The moving subunit is used to move each of the to-be-updated points to the corresponding target position to obtain the target three-dimensional model.

[0083] Preferably, the target object includes the entire target organ or the entire target tissue;

[0084] and / or,

[0085] The target object includes the entire target organ or several target sites contained in the entire target tissue;

[0086] The contour feature point set of the target object includes a sub-contour feature point set corresponding to each target part;

[0087] The projection module is also used to obtain all sub-contour feature point sets corresponding to the same target part, and the spatial position information corresponding to each sub-contour feature point set; based on each sub-contour feature point set and the spatial position information, obtain a sub-projection point of each sub-contour feature point on the sub-standard three-dimensional model corresponding to the target part;

[0088] The calibration module is also used to calibrate the sub-standard three-dimensional model corresponding to the target part based on the spatial position information and the sub-projection point of each sub-contour feature point corresponding to the target part to obtain a sub-three-dimensional model of each target part; based on the sub-three-dimensional model of each target part, the target three-dimensional model of the target object is obtained.

[0089] Preferably, the entire target organ or the entire target tissue includes a heart;

[0090] The target sites include the left atrium, the left ventricle, the right atrium, the right ventricle, the aorta, the pulmonary artery, and the superior vena cava.

[0091] According to a third aspect of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein the processor implements the generation method described in the first aspect of the present disclosure when executing the computer program.

[0092] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the generating method described in the first aspect of the present disclosure is implemented.

[0093] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the generating method described in the first aspect of the present disclosure is implemented.

[0094] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0095] The positive progressive effect of the present disclosure is that by combining the overall information of the standard heart model with the local information of the intracardiac ultrasound image, a genetic algorithm is used to quickly fit the patient's three-dimensional heart model, thereby achieving rapid construction of the three-dimensional heart model during the operation, so that the ICE catheter operator can automatically complete operations such as ultrasound image selection and three-dimensional model construction without additional manual intervention, significantly shortening the time required to construct the three-dimensional heart model before the operation, greatly simplifying the workflow of the ICE catheter operator, and reducing the risk of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] Figure 1 This is a flowchart of a method for generating a model according to Embodiment 1 of the present disclosure;

[0097] Figure 2 This is a flowchart of step S4 of the method for generating a model in Embodiment 1 of the present disclosure;

[0098] Figure 3 This is a schematic diagram of image distribution of the intersection set of Embodiment 1 of the present disclosure;

[0099] Figure 4 This is a first schematic diagram of the alignment process of the contour feature point set and the intersection point set in Embodiment 1 of the present disclosure;

[0100] Figure 5 This is a second schematic diagram of the alignment process of the contour feature point set and the intersection point set in Embodiment 1 of the present disclosure;

[0101] Figure 6This is a flowchart of step S43 of the method for generating a model in Embodiment 1 of the present disclosure;

[0102] Figure 7 This is a flowchart of step S5 of the method for generating a model in Embodiment 1 of the present disclosure;

[0103] Figure 8 This is a flowchart of step S54 of the method for generating a model in Embodiment 1 of the present disclosure;

[0104] Fig. 9 is an algorithm flow chart of Embodiment 1 of the present disclosure;

[0105] Fig.10 This is a module schematic diagram of a system for generating a model according to Embodiment 2 of the present disclosure;

[0106] Fig.11 This is a schematic diagram of the structure of an electronic device according to Embodiment 3 of the present disclosure. DETAILED DESCRIPTION

[0107] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0108] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0109] In the embodiments of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0110] Example 1

[0111] In a specific embodiment of the present disclosure, a method for generating a model is provided, such as Figure 1 As shown, the generation method includes:

[0112] S1. Acquire several ultrasonic images of the target object and corresponding searchlight position information;

[0113] S2, extracting a contour feature point set of the target object in each ultrasound image, where the contour feature point set includes a plurality of contour feature points;

[0114] S3, based on the contour feature point set and searchlight position information corresponding to each ultrasound image, obtaining the spatial position information of each contour feature point;

[0115] S4, obtaining a target projection point of each contour feature point on a standard three-dimensional model corresponding to the target object according to the spatial position information of each contour feature point;

[0116] S5. Based on the spatial position information of each contour feature point and the target projection point, the standard three-dimensional model is calibrated to obtain a target three-dimensional model of the target object.

[0117] Specifically, in order to realize the rapid construction of the target three-dimensional model, it is necessary to pre-construct a standard three-dimensional model of the target object. The target object includes the entire target organ or the entire target tissue. For example, taking the entire heart organ as an example, the heart scanning data of several patients' in vitro ultrasound, CT (computer tomography) and MRI (magnetic resonance imaging) can be collected, and a three-dimensional model of the heart can be constructed by a three-dimensional reconstruction algorithm. The average shape model of each three-dimensional heart model is obtained by using a statistical shape model construction method as the standard three-dimensional model of the heart. The three-dimensional reconstruction algorithm can use a pixel-based volume reconstruction method and / or a contour point-based surface reconstruction method. When constructing the statistical shape model, Fourier decomposition can be used, or point distribution model construction can be used.

[0118] Step S1: By using an intracorporeal ultrasound device (eg, an ICE catheter), a plurality of ultrasound images D = {D1, D2, ..., D n}, and simultaneously record the searchlight position information matrix L = {L1,L2,...,L n For example, the target object may be a heart, and an ultrasound image of the heart during isovolumetric relaxation and corresponding searchlight position information may be obtained by using an ICE catheter, wherein the searchlight position information may be provided by a hardware probe, or may be inferred and predicted based on an intracardiac probe position model, and this embodiment does not specifically limit this.

[0119] After acquiring several ultrasound images, ultrasound image contour extraction and contour structure edge processing are performed on each ultrasound image in step S2 to obtain the contour of the target object in each ultrasound image. Each contour is composed of multiple contour feature points, and each contour feature point together constitutes a contour feature point set corresponding to the contour.

[0120] For example, the heart contour of each ultrasound image is extracted, and then the whole heart contour feature point set C = {C1, C2, ..., C m}, where each contour has and only corresponds to one probe position. Each contour consists of a cluster of contour feature points, so there is C i =P i ={p1,p2,...,p u}, where P i C is the contour feature point set i A set of two-dimensional points, p u For contour C i The value of the u-th point on the u =(x u ,y u ,0.0,0.0).

[0121] Since each ultrasound image is a two-dimensional image, it needs to be converted into a three-dimensional space to obtain the three-dimensional spatial information of the target object. Therefore, in step S3, each contour feature point can be converted into an expression in the three-dimensional space according to the contour feature point set and the searchlight position information corresponding to each ultrasound image. u Take point as an example, p u By using C i The corresponding searchlight position information 4×4 matrix L i Multiplying them, we get p u The expression in three-dimensional space, that is, p u '=p u ×L i Similarly, by multiplying all points in the contour feature point set corresponding to the target object with the searchlight position information matrix corresponding to the contour where it is located, the expression of the entire target object contour in three-dimensional space can be obtained.

[0122] After obtaining the spatial information of each contour feature point in the target object, each contour feature point can be mapped to the standard three-dimensional model corresponding to the target object in step S4 to obtain the target projection point of each contour feature point on the standard three-dimensional model. Then, in step S5, the standard three-dimensional model is calibrated according to the spatial position information and the target projection point of each contour feature point to quickly fit the target three-dimensional model of the target object.

[0123] This specific implementation method establishes a standard three-dimensional model of the heart, and uses the contour edge data of a portion of the heart collected by ultrasound images to fit and approximate the standard three-dimensional model to the patient's actual heart shape, thereby quickly fitting the patient's three-dimensional model of the heart, thereby achieving rapid construction of a three-dimensional model of the heart during surgery. The ICE catheter operator can automatically complete operations such as ultrasound image selection and three-dimensional model construction without additional manual intervention, thereby significantly shortening the time required to construct a three-dimensional heart model before surgery.

[0124] In a specific embodiment, Figure 2As shown, step S4 includes:

[0125] S41, obtaining a set of intersection points between a contour feature point set corresponding to each ultrasound image and a standard three-dimensional model;

[0126] S42, based on the spatial position information, aligning each contour feature point set with the corresponding intersection point set using a preset alignment method;

[0127] S43, mapping each contour feature point in each contour feature point set after alignment to the standard three-dimensional model to obtain a target projection point corresponding to each contour feature point.

[0128] Wherein, step S41 includes:

[0129] S411, creating a virtual sector of the contour feature point set based on the spatial position information and the corresponding searchlight position information;

[0130] S412: Obtain a set of intersection points between the virtual sector and the standard three-dimensional model.

[0131] Step S42 includes:

[0132] S421, obtaining first centroid positions corresponding to a plurality of contour feature points in the contour feature point set and second centroid positions corresponding to a plurality of intersection points in the intersection point set;

[0133] S422: Based on the first centroid position and the second centroid position, move each contour feature point in the contour feature point set in the same direction by the same displacement, so that the contour feature point set is aligned with the corresponding intersection point set.

[0134] Specifically, the contour feature points obtained in step S3 may be aligned with the standard three-dimensional model using global alignment and local alignment methods respectively.

[0135] For example, the whole point set C of the contour feature point set C is obtained by step S3 = {C1, C2, ..., C m} and its corresponding searchlight position information matrix L={L1,L2,...,L n}. So, for the contour feature point set C j , there is only one searchlight position information matrix L j Corresponding to it. Use the searchlight position information matrix L j , we can create a contour feature point set C j The corresponding virtual fan F intersects with the standard 3D model LA to obtain the contour feature point set C j The intersection point set I with the standard three-dimensional model LA. At this time, the image distribution of the intersection point set can be closed or open, such as Figure 3 shown.

[0136] When the image distribution of the intersection set is closed, that is, when the distance between two points in the intersection set is less than the threshold θ, the global alignment method can be used, that is, by placing the contour feature point set C j The centroid of the contour feature point set C j All points in will move the same displacement as the center of gravity, such as Figure 4 shown.

[0137] When the image distribution of the intersection set is not closed, that is, when the distance between two points in the intersection set is greater than or equal to the threshold θ, the local alignment method can be used, that is, by placing the contour feature point set C j The center points of the two endpoints of are moved to the center points of the two endpoints of the intersection set I. Similarly, the contour feature point set C j All points in will move the same displacement as the endpoint center, such as Figure 5 As shown. The endpoint can be determined based on the number of adjacent points. For example, when the endpoint is within the range If there is only one neighboring point in the contour, this point is one of the endpoints of the contour feature point set.

[0138] Similarly, by performing the above alignment processing steps on all contour feature point sets C of the target object, all contour point sets C' aligned with the standard three-dimensional model can be obtained.

[0139] By mapping each contour feature point in each contour feature point set after alignment to the standard three-dimensional model in step S43, a target projection point of each contour feature point on the standard three-dimensional model can be obtained.

[0140] In a specific embodiment, Figure 6 As shown, step S43 includes:

[0141] S431, mapping each contour feature point in the contour feature point set to a standard three-dimensional model to obtain an initial projection point corresponding to each contour feature point;

[0142] S432, obtaining the distance between each contour feature point and the corresponding initial projection point, and obtaining the total distance corresponding to the contour feature point set;

[0143] S433, if the total distance does not meet the preset condition, each contour feature point is moved by the same preset distance to expand or shrink each contour feature point in spatial position;

[0144] Repeat step S431 until the total distance meets the preset condition;

[0145] S434, taking the initial projection point corresponding to each contour feature point as the target projection point.

[0146] Specifically, since the depth of ultrasound can be adjusted, as the depth value increases, the visible tissue in the fixed-size image sector becomes smaller and the imaging content increases; and as the depth value decreases, the visible tissue in the image sector becomes larger and more detailed. After the alignment process is performed in step S42, the overall bounding box size of the contour feature points needs to be converged to the bounding box size range of the standard three-dimensional model.

[0147] Therefore, in a specific implementable method, each contour feature point can be projected onto the surface of a standard three-dimensional model through step S431 to obtain the initial projection point of each contour feature point on the standard three-dimensional model. Since the contour feature point may be outside the standard three-dimensional model (for example, the patient's heart is larger) or inside the standard three-dimensional model (for example, the patient's heart is smaller), when the contour feature point is outside the standard three-dimensional model, the initial projection point can be obtained by intersecting the line from the contour feature point to the center of gravity / center position point with the standard three-dimensional model surface. When the contour feature point is inside the standard three-dimensional model, a ray is made from the center of gravity / center position point to the contour feature point, and the extension line of this ray will intersect with the standard three-dimensional model surface to obtain the initial projection point.

[0148] Then, step S432 is used to obtain the distance between each contour feature point and the corresponding initial projection point, and the distance sum is calculated. Then, step S433 is used to perform overall reduction and enlargement to minimize the distance sum. When the contour feature point is outside the standard three-dimensional model, the distance sum is reduced by overall reduction. When the contour feature point is inside the standard three-dimensional model, the distance sum is reduced by overall enlargement. Multiple adjustments are made to minimize the distance sum, and then step S434 is used to take the initial projection point corresponding to each contour feature point when the distance sum is minimized as the target projection point.

[0149] In a specific practicable manner, the parameter α is obtained so that the distance between the contour feature point set C' and the projection point of the standard three-dimensional model is minimized. Thus, the projection point C"=αC' of the patient's real heart contour in the three-dimensional space of the standard three-dimensional model is obtained. Specifically, through step S42, the contour feature point set C after alignment processing can be obtained. j ', let the point set Q be the contour feature point set C j 'Projection on the standard three-dimensional model can obtain the parameter α, so that argmin f(x) = ∑(αC j '-Q), so there is C j ”=αC j '.

[0150] In a specific embodiment, Figure 7 As shown, step S5 includes:

[0151] S51, obtaining the nearest neighbor point of each target projection point on the standard three-dimensional model;

[0152] S52, based on the spatial position information, moving each nearest neighbor point to the position of the contour feature point corresponding to the target projection point;

[0153] S53, obtaining a set of points to be updated, the set of points to be updated including points to be updated whose distances to the nearest neighboring points are less than a preset threshold;

[0154] S54, calibrating each to-be-updated point in the to-be-updated point set by using a preset algorithm to obtain a target three-dimensional model.

[0155] Specifically, the projection points of the patient's real heart contour on the standard three-dimensional heart model can be obtained through S4. Since the projection point is a virtual point, not a real point, it is necessary to obtain the nearest neighbor points of these projection points on the standard three-dimensional heart model through step S51. While keeping the model topology unchanged, the positions of these nearest neighbor points are moved to the positions of the corresponding projection points through step S52 to obtain the corrected heart model. For example, the nearest neighbor point Q' of the patient's heart projection point P" on the standard three-dimensional heart model is obtained, and then the position coordinates of these points are equal to the projection point, that is, Q'=P", and the displacement vector V=P"-Q' of these points is obtained.

[0156] Then, the updated position of the nearest neighbor point is locked, and the point to be updated whose distance to the nearest neighbor point is less than the preset threshold on the standard three-dimensional model is obtained through step S53. The new position of the point to be updated is determined by using the preset algorithm through step S54, and the point to be updated is moved to the corresponding new position to obtain the target three-dimensional model. For example, after obtaining the displacement vector V between the nearest neighbor point Q' and the projection point P", the near geodesic method is used to obtain the set of points to be updated PB whose neighboring distance of the projection point set P" is less than β.

[0157] In a specific embodiment, Figure 8 As shown, step S54 includes:

[0158] S541, obtaining the original curvature of the points of the standard three-dimensional model;

[0159] S542, obtaining the curvature of each to-be-updated point in the to-be-updated point set, and obtaining the point calibration curvature of the to-be-updated point set;

[0160] S543, using a genetic algorithm to minimize the difference between the point calibration curvature and the point original curvature as an optimization goal, and calculating the target position of each point to be updated;

[0161] S544, moving each point to be updated to the corresponding target position to obtain a target three-dimensional model.

[0162] Specifically, in a three-dimensional model, curvature refers to the degree of curvature or the radius of curvature of a point on a surface. It describes the local geometric characteristics of the surface near the point. The magnitude of the curvature is proportional to the degree of curvature of the surface, and the radius of curvature represents the inverse of the curvature. If the radius of curvature is small, the surface is more significantly curved near the point; if the radius of curvature is large, the surface is relatively flat.

[0163] Therefore, in order to simultaneously obtain the heart shape information of the standard three-dimensional heart model and the real-time information of the patient's heart contour, the heart shape information can be evaluated by the maximum curvature, Gaussian curvature, and mean curvature. Taking the mean curvature as an example, the position of the nearest neighbor point can be fixed, and the total amount of mean curvature change between the new model and the original model can be minimized by adjusting the position of the point to be updated, that is, the target is Where X and Y are the distribution of model points, and f(X) and f(Y) are the total amount of average curvature change under the distribution of X and Y points.

[0164] In order to solve the above single-objective optimization problem, we can use the constrained optimization genetic algorithm. The algorithm flow is as follows: Fig. 9 As shown. It mainly includes parameter encoding, population initialization, fitness evaluation, and updating the total population through selection, crossover, and compilation operators. In the constrained optimization rule, there are two conditions: 1) only the positions of the points to be updated in the projection point set of the patient's true heart contour are updated; 2) the direction vectors of the positions of these points to be updated are equal to the sum of the parameters of the displacement vectors of the projection point set.

[0165] For example, after obtaining the displacement vector V and the point set PB to be updated, since the number of points in the point set PB to be updated is w, the point pb to be updated is w in the projection point set P". pb points are adjacent, and the displacement vectors of these points are V'. According to the constraint optimization rule, the update direction of the point to be updated pb satisfies the following formula:

[0166]

[0167] Among them, T pb is the update direction of the neighboring point pb, λ is the distance weight vector, and its vector length is w pb , with a value range of [0,γ]. Therefore, the population GW0 can be encoded and randomly initialized according to the length w, with a value range of [0,γ]. Then, according to the update direction of the projection point set PB of each member in the population, the three-dimensional model of the heart after the position update and its total average curvature change are obtained. The total average curvature change of each member in the population is arranged in ascending order, and the first N members are the parent members. Through crossover and mutation operations, the diversity of population members is increased, and then the next generation group GW1 is obtained.

[0168] The above sorting, selection, crossover and mutation operations are looped. Finally, when the current N members are no longer updated, the loop stops and a result that meets the optimization goal is finally obtained.

[0169] In a specific embodiment, the target object includes several target sites contained in the entire target organ or the entire target tissue;

[0170] The contour feature point set of the target object includes a sub-contour feature point set corresponding to each target part;

[0171] Step S4 includes:

[0172] Obtain all sub-contour feature point sets corresponding to the same target part, and the spatial position information corresponding to each sub-contour feature point set;

[0173] Based on each sub-contour feature point set and spatial position information, a sub-projection point of each sub-contour feature point on a sub-standard three-dimensional model corresponding to the target part is obtained;

[0174] Step S5 includes:

[0175] Based on the spatial position information and sub-projection points of each sub-contour feature point corresponding to the target part, the sub-standard three-dimensional model corresponding to the target part is calibrated to obtain a sub-three-dimensional model of each target part;

[0176] Based on the sub-3D model of each target part, a target 3D model of the target object is obtained.

[0177] Specifically, taking the heart as an example, the heart is composed of multiple target parts, wherein the target parts include the left atrium, left ventricle, right atrium, right ventricle, aorta, pulmonary artery, and superior vena cava. When extracting the contour feature point set of the target object in each ultrasound image in step S2, the image segmentation algorithm can be used to perform semantic segmentation of the ultrasound image to achieve accurate segmentation between different heart chambers, and extract the contour edge of the heart chamber through contour structure edge processing, remove the interference component of the ultrasound image fan edge, and finally obtain the real heart chamber edge, thereby obtaining the sub-contour feature point set corresponding to each target part. Among them, the image segmentation algorithm can be a deep learning image segmentation method or a traditional image threshold segmentation method.

[0178] When constructing a three-dimensional model of the heart, corresponding three-dimensional models are constructed for different parts of the heart. It can be understood that the standard three-dimensional model includes sub-standard three-dimensional models corresponding to each part. Taking the left atrium as an example, by obtaining the left atrium contour in each ultrasound image, and obtaining the spatial position information corresponding to each left atrium contour feature point based on the searchlight position information of each ultrasound image, each left atrium contour is mapped to the standard three-dimensional model of the left atrium, and the standard three-dimensional model of the left atrium is calibrated to obtain the sub-three-dimensional model corresponding to the left atrium. The specific calibration process can be found in other embodiments. By analogy, after obtaining the sub-three-dimensional models corresponding to each target part of the heart, the target three-dimensional model of the entire heart can be obtained.

[0179] This specific implementation method can fully reflect the characteristic details of each target part by constructing a corresponding sub-3D model for each target part of the target object, which is more in line with the shape of the patient's actual target object, and is convenient for doctors to make accurate judgments and estimates.

[0180] This embodiment combines the overall information of the standard heart model with the local information of the intracardiac ultrasound image, and uses a genetic algorithm to quickly fit the patient's three-dimensional heart model, thereby realizing the rapid construction of the three-dimensional heart model during the operation. The ICE catheter operator can automatically complete operations such as ultrasound image selection and three-dimensional model construction without additional manual intervention, which significantly shortens the time required to construct the three-dimensional heart model before the operation, greatly simplifies the workflow of the ICE catheter operator, and reduces the risk of the operation.

[0181] Example 2

[0182] Fig.10 A schematic diagram of a module of a model generation system provided by an exemplary embodiment of the present disclosure, the generation system includes an acquisition module 100, an extraction module 200, a mapping module 300, a projection module 400 and a calibration module 500;

[0183] The acquisition module 100 is used to acquire a plurality of ultrasonic images of the target object and corresponding searchlight position information;

[0184] The extraction module 200 is used to extract a contour feature point set of a target object in each ultrasound image, where the contour feature point set includes a plurality of contour feature points;

[0185] The mapping module 300 is used to obtain the spatial position information of each contour feature point based on the contour feature point set and the searchlight position information corresponding to each ultrasound image;

[0186] The projection module 400 is used to obtain a target projection point of each contour feature point on a standard three-dimensional model corresponding to the target object according to the spatial position information of each contour feature point;

[0187] The calibration module 500 is used to calibrate the standard three-dimensional model based on the spatial position information of each contour feature point and the target projection point to obtain a target three-dimensional model of the target object.

[0188] In a specific implementation, the projection module 400 includes an acquisition unit, an alignment unit, and a mapping unit:

[0189] The acquisition unit is used to acquire the intersection point set of the contour feature point set corresponding to each ultrasonic image and the standard three-dimensional model;

[0190] The alignment unit is used to align each contour feature point set with the corresponding intersection point set using a preset alignment method based on the spatial position information;

[0191] The mapping unit is used to map each contour feature point in each contour feature point set after alignment to a standard three-dimensional model to obtain a target projection point corresponding to each contour feature point.

[0192] In a specific embodiment, the acquisition unit includes a creation subunit and an acquisition subunit, and the alignment unit includes a center of gravity determination subunit and an alignment subunit;

[0193] The creation subunit is used to create a virtual sector of the contour feature point set based on the spatial position information and the corresponding searchlight position information;

[0194] The acquisition subunit is used to acquire the intersection point set between the virtual sector and the standard three-dimensional model;

[0195] The center of gravity determination subunit is used to obtain the first center of gravity positions corresponding to the multiple contour feature points in the contour feature point set and the second center of gravity positions corresponding to the multiple intersection points in the intersection point set;

[0196] The alignment subunit is used for moving each contour feature point in the contour feature point set in the same direction by the same displacement based on the first centroid position and the second centroid position, so as to align the contour feature point set with the corresponding intersection point set;

[0197] In a specific embodiment, the mapping unit includes a mapping subunit, a distance subunit, an adjustment subunit, and a determination subunit;

[0198] The mapping subunit is used to map each contour feature point in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each contour feature point;

[0199] The distance subunit is used to obtain the distance between each contour feature point and the corresponding initial projection point, and obtain the total distance corresponding to the contour feature point set;

[0200] The adjusting subunit is used for moving each contour feature point by the same preset distance if the total distance does not meet the preset condition, so as to expand or shrink each contour feature point in the spatial position;

[0201] Calling the mapping subunit to repeatedly execute the step of mapping each contour feature point in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each contour feature point until the total distance meets a preset condition;

[0202] The determination subunit is used to take the initial projection point corresponding to each contour feature point as the target projection point.

[0203] In one specific embodiment, the calibration module 500 includes an extraction unit, a movement unit, and a calibration unit;

[0204] The extraction unit is used to obtain the nearest neighbor point of each target projection point on the standard three-dimensional model;

[0205] The moving unit is used to move each nearest neighbor point to the position of the contour feature point corresponding to the target projection point based on the spatial position information;

[0206] The extraction unit is also used to obtain a set of points to be updated, the set of points to be updated includes points to be updated whose distances to the nearest neighboring points are less than a preset threshold;

[0207] The calibration unit is used to calibrate each to-be-updated point in the to-be-updated point set by using a preset algorithm to obtain a target three-dimensional model.

[0208] In a specific embodiment, the calibration unit includes an original curvature calculation subunit, a calibration curvature calculation subunit, an optimization subunit, and a movement subunit;

[0209] The original curvature calculation subunit is used to obtain the original curvature of the points of the standard three-dimensional model;

[0210] The calibration curvature calculation subunit is used to obtain the curvature of each to-be-updated point in the to-be-updated point set, and obtain the point calibration curvature of the to-be-updated point set;

[0211] The optimization subunit is used to use a genetic algorithm to minimize the difference between the point calibration curvature and the point original curvature as the optimization target, and calculate the target position of each point to be updated;

[0212] The moving subunit is used to move each point to be updated to the corresponding target position to obtain a target three-dimensional model.

[0213] In one embodiment, the target object includes the entire target organ or the entire target tissue;

[0214] In a specific embodiment, the target object includes several target sites contained in the entire target organ or the entire target tissue;

[0215] The contour feature point set of the target object includes a sub-contour feature point set corresponding to each target part;

[0216] The projection module 400 is also used to obtain all sub-contour feature point sets corresponding to the same target part, and the spatial position information corresponding to each sub-contour feature point set; based on each sub-contour feature point set and the spatial position information, obtain the sub-projection point of each sub-contour feature point on the sub-standard three-dimensional model corresponding to the target part;

[0217] The calibration module 500 is also used to calibrate the sub-standard three-dimensional model corresponding to the target part based on the spatial position information and sub-projection points of each sub-contour feature point corresponding to the target part, so as to obtain a sub-three-dimensional model of each target part; and obtain a target three-dimensional model of the target object based on the sub-three-dimensional model of each target part.

[0218] In one embodiment, the entire target organ or the entire target tissue comprises a heart;

[0219] Target sites include the left atrium, left ventricle, right atrium, right ventricle, aorta, pulmonary artery, and superior vena cava.

[0220] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0221] This embodiment combines the overall information of the standard heart model with the local information of the intracardiac ultrasound image, and uses a genetic algorithm to quickly fit the patient's three-dimensional heart model, thereby realizing the rapid construction of the three-dimensional heart model during the operation. The ICE catheter operator can automatically complete operations such as ultrasound image selection and three-dimensional model construction without additional manual intervention, which significantly shortens the time required to construct the three-dimensional heart model before the operation, greatly simplifies the workflow of the ICE catheter operator, and reduces the risk of the operation.

[0222] Example 3

[0223] Fig.11 This is a structural schematic diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and the processor implements the model generation method provided in any of the above embodiments when executing the computer program. Fig.11 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0224] like Fig.11 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0225] The bus 33 includes a data bus, an address bus, and a control bus.

[0226] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0227] The memory 32 may also include a program tool 325 (or utility) having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0228] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the model generation method provided in any of the above embodiments.

[0229] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the electronic device 30 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 36. As shown, the network adapter 36 communicates with other modules of the electronic device 30 via a bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0230] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0231] Example 4

[0232] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for generating a model provided by any of the above embodiments is implemented.

[0233] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0234] Example 5

[0235] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the method for generating a model provided in any of the above embodiments.

[0236] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0237] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for generating a model, characterized in that: The generation method comprises: Acquire several ultrasonic images of the target object and corresponding searchlight position information; Extracting a contour feature point set of the target object in each of the ultrasound images, wherein the contour feature point set includes a plurality of contour feature points; Based on the contour feature point set corresponding to each of the ultrasound images and the searchlight position information, obtaining the spatial position information of each of the contour feature points; Obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on a standard three-dimensional model corresponding to the target object; Based on the spatial position information of each of the contour feature points and the target projection point, the standard three-dimensional model is calibrated to obtain a target three-dimensional model of the target object; The step of obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on the standard three-dimensional model corresponding to the target object comprises: Obtaining a set of intersection points between the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model; Based on the spatial position information, each of the contour feature point sets is aligned with the corresponding intersection point set using a preset alignment method; Each of the contour feature points in each of the aligned contour feature point sets is mapped to the standard three-dimensional model to obtain the target projection point corresponding to each of the contour feature points.

2. The generation method according to claim 1, characterized in that: The step of obtaining the intersection point set of the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model comprises: Creating a virtual sector of the contour feature point set based on the spatial position information and the corresponding searchlight position information; Acquire the intersection point set of the virtual sector and the standard three-dimensional model; The step of aligning each of the contour feature point sets with the corresponding intersection point set using a preset alignment method based on the spatial position information comprises: Acquire first centroid positions corresponding to a plurality of the contour feature points in the contour feature point set, and second centroid positions corresponding to a plurality of intersection points in the intersection point set; Based on the first center of gravity position and the second center of gravity position, move each of the contour feature points in the contour feature point set by the same displacement along the same direction, so that the contour feature point set is aligned with the corresponding intersection point set; and / or, The step of mapping each of the aligned contour feature points in each contour feature point set to the standard three-dimensional model to obtain the target projection point corresponding to each contour feature point comprises: Mapping each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each of the contour feature points; Obtaining the distance between each of the contour feature points and the corresponding initial projection point to obtain the total distance corresponding to the contour feature point set; If the total distance does not meet the preset condition, each of the contour feature points is moved by the same preset distance to expand or shrink each of the contour feature points in spatial position; Repeat the step of mapping each of the contour feature points in the contour feature point set to the standard three-dimensional model to obtain an initial projection point corresponding to each of the contour feature points until the total distance meets the preset condition; The initial projection point corresponding to each of the contour feature points is used as the target projection point.

3. The generation method according to claim 1, characterized in that: The step of calibrating the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain the target three-dimensional model of the target object comprises: Obtain the nearest neighbor point of each target projection point on the standard three-dimensional model; Based on the spatial position information, each of the nearest neighbor points is moved to the position of the contour feature point corresponding to the target projection point; Acquire a set of points to be updated, the set of points to be updated including points to be updated whose distances to the nearest neighbor points are less than a preset threshold; Each of the to-be-updated points in the to-be-updated point set is calibrated using a preset algorithm to obtain the target three-dimensional model.

4. The generation method according to claim 3, characterized in that: The step of calibrating each of the to-be-updated points in the to-be-updated point set by a preset algorithm to obtain the target three-dimensional model comprises: Obtaining the original curvature of the point of the standard three-dimensional model; Acquire the curvature of each of the to-be-updated points in the to-be-updated point set to obtain the point calibration curvature of the to-be-updated point set; A genetic algorithm is used to minimize the difference between the calibration curvature of the point and the original curvature of the point as an optimization goal, and a target position of each point to be updated is calculated; Each of the points to be updated is moved to the corresponding target position to obtain the target three-dimensional model.

5. The generation method according to any one of claims 1 to 4, characterized in that: The target object includes the entire target organ or the entire target tissue; and / or, The target object includes the entire target organ or several target sites contained in the entire target tissue; The contour feature point set of the target object includes a sub-contour feature point set corresponding to each target part; The step of obtaining, according to the spatial position information of each of the contour feature points, a target projection point of each of the contour feature points on the standard three-dimensional model corresponding to the target object comprises: Acquire all sub-contour feature point sets corresponding to the same target part, and the spatial position information corresponding to each sub-contour feature point set; Based on each sub-contour feature point set and the spatial position information, obtaining a sub-projection point of each sub-contour feature point on the sub-standard three-dimensional model corresponding to the target part; The step of calibrating the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain the target three-dimensional model of the target object comprises: Based on the spatial position information of each sub-contour feature point corresponding to the target part and the sub-projection point, calibrate the sub-standard three-dimensional model corresponding to the target part to obtain a sub-three-dimensional model of each target part; Based on the sub-three-dimensional model of each of the target parts, the target three-dimensional model of the target object is obtained.

6. The generation method according to claim 5, characterized in that: The entire target organ or the entire target tissue includes a heart; The target sites include the left atrium, the left ventricle, the right atrium, the right ventricle, the aorta, the pulmonary artery, and the superior vena cava.

7. A model generation system, characterized in that: The generation system includes an acquisition module, an extraction module, a mapping module, a projection module and a generation module; The acquisition module is used to acquire a plurality of ultrasonic images of the target object and corresponding searchlight position information; The extraction module is used to extract a contour feature point set of the target object in each of the ultrasound images, wherein the contour feature point set includes a plurality of contour feature points; The mapping module is used to obtain the spatial position information of each of the contour feature points based on the contour feature point set and the searchlight position information corresponding to each of the ultrasound images; The projection module is used to obtain a target projection point of each contour feature point on a standard three-dimensional model corresponding to the target object according to the spatial position information of each contour feature point; The generating module is used to calibrate the standard three-dimensional model based on the spatial position information of each of the contour feature points and the target projection point to obtain a target three-dimensional model of the target object; The projection module includes an acquisition unit, an alignment unit and a mapping unit; The acquisition unit is used to acquire a set of intersection points between the contour feature point set corresponding to each of the ultrasound images and the standard three-dimensional model; The alignment unit is used to align each of the contour feature point sets with the corresponding intersection point set in a preset alignment manner based on the spatial position information; The mapping unit is used to map each of the contour feature points in each of the aligned contour feature point sets to the standard three-dimensional model to obtain the target projection point corresponding to each of the contour feature points.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the generation method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the generation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the generating method according to any one of claims 1 to 6 is implemented.

Images