Registration method, device, computer equipment and readable storage medium

Abstract

The application relates to a registration method, device, computer equipment and readable storage medium, which comprises the following steps: acquiring a first image model of a to-be-registered object used in last registration and a first conversion matrix obtained through last registration; adjusting the first image model based on the first conversion matrix to obtain a second image model for current registration; projecting a first registration point set on the surface of the to-be-registered object to the surface of the second image model to obtain a projection point set; and registering the first registration point set with the projection point set to obtain a second conversion matrix. The registration method provided by the application can improve the accuracy of registration.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a registration method, apparatus, computer device, and readable storage medium. Background Technology

[0002] With increasing life expectancy and a rapidly aging population, the incidence of orthopedic diseases is also rising, leading to a year-on-year increase in the demand for orthopedic surgery. During surgery, it is crucial to ensure that the three-dimensional model of the bone corresponds precisely to the actual bone of the patient to be registered.

[0003] Traditional techniques typically use a generic 3D model to register the actual bone of the object to be registered. However, traditional registration methods often result in inaccurate registration results. Summary of the Invention

[0004] Therefore, it is necessary to provide a registration method, apparatus, computer equipment, and readable storage medium to address the aforementioned technical problems.

[0005] In a first aspect, one embodiment of this application provides a registration method, the method comprising:

[0006] Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration;

[0007] For the current registration, the first image model is adjusted based on the first transformation matrix to obtain the second image model;

[0008] The first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain the projection point set;

[0009] The first set of registration points is registered with the set of projection points to obtain the second transformation matrix.

[0010] In one embodiment, each projection point in the projection point set is the projection point closest to each corresponding registration point in the first registration point set.

[0011] In one embodiment, the first registration point set is registered with the projection point set to obtain a second transformation matrix, including:

[0012] The pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the first objective function to solve for the second transformation matrix.

[0013] The optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set. The first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0014] In one embodiment, the first registration point set is registered with the projection point set to obtain a second transformation matrix, including:

[0015] Obtain the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weight is obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point of the registration point;

[0016] The registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set are taken as known quantities. The second transformation matrix is ​​taken as an unknown quantity and substituted into the second objective function to solve for the second transformation matrix.

[0017] In one embodiment, each registration point in the first registration point set is a physiological and anatomical feature point on the surface of the object to be registered. After registering the first registration point set with the projection point set to obtain the second transformation matrix, the registration method further includes:

[0018] Determine whether the number of registrations in the current registration has reached the threshold of the first iteration.

[0019] If the number of registrations in the current registration has not reached the threshold of the first iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0020] In one embodiment, the registration method further includes:

[0021] If the number of registrations in the current registration reaches the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the second set of registration points on the surface of the object to be registered is used as the first set of registration points. The process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model, until the number of registrations in the current registration reaches the second iteration threshold. Here, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0022] In one embodiment, each registration point in the first registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered. After registering the first registration point set with the projection point set to obtain the second transformation matrix, the registration method further includes:

[0023] Determine whether the number of registrations in the current registration has reached the threshold for the third iteration.

[0024] If the number of registrations in the current registration does not reach the threshold of the third iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0025] In one embodiment, obtaining the first transformation matrix obtained from the previous registration includes:

[0026] The first image model surface registration point set is registered with the first registration point set to obtain the first transformation matrix.

[0027] In one embodiment, the method for obtaining the registration point set of the surface of the first image model includes:

[0028] Obtain the template image model, whose surface has a template point set;

[0029] The template image model is matched with the first image model to map the template point set onto the surface of the first image model, thus obtaining the registration point set of the first image model surface.

[0030] Secondly, one embodiment of this application provides a registration apparatus, comprising:

[0031] The acquisition module is used to acquire the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration.

[0032] The adjustment module is used to adjust the first image model based on the first transformation matrix for the current registration to obtain the second image model;

[0033] The projection module is used to project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain the projection point set.

[0034] The registration module is used to register the first registration point set with the projection point set to obtain the second transformation matrix.

[0035] Thirdly, one embodiment of this application provides a computer device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method provided in the first aspect above.

[0036] Fourthly, one embodiment of this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0037] Fifthly, one embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0038] This application provides a registration method, apparatus, computer device, and readable storage medium. The method involves obtaining a first image model of the object to be registered, used in the previous registration, and a transformation matrix obtained in the previous registration. For the current registration, the first image model is adjusted based on the first transformation matrix to obtain a second image model. A first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain a projection point set. The first set of registration points and the projection point set are then registered to obtain a second transformation matrix. This embodiment uses the projection point set projected from the first set of registration points onto the surface of the second image model for registration with the first set of registration points. Compared to the prior art, which directly registers the registration point set on the second image model with the first set of registration points, this avoids inaccurate registration points on the second image model, which could lead to an inaccurate final second transformation matrix. In other words, it reduces the dependence on registration points on the second image model, thereby improving the accuracy of registration. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 An application environment diagram of the registration method provided in one embodiment;

[0041] Figure 2 A flowchart illustrating the steps of a registration method provided in one embodiment;

[0042] Figure 3 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0043] Figure 4 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0044] Figure 5 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0045] Figure 6 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0046] Figure 7 A schematic diagram illustrating the distribution of coarse registration points for one embodiment;

[0047] Figure 8 A schematic diagram of the distribution of precision matching points provided for one embodiment;

[0048] Figure 9 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0049] Figure 10 A flowchart illustrating the steps of a registration method provided in another embodiment;

[0050] Figure 11 A schematic diagram of the registration apparatus provided in one embodiment;

[0051] Figure 12 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0052] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the specific embodiments of this application are described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0053] The serial numbers assigned to components in this article, such as "first" and "second", are used only to distinguish the objects being described and have no sequential or technical meaning.

[0054] The registration method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown includes a terminal 100 and a medical scanning device 200. The terminal 100 can communicate with the medical scanning device 200 via a network. The terminal 100 can be, but is not limited to, various personal computers, laptops, and tablets. The medical scanning device 200 can be, but is not limited to, a CT (Computed Tomography) device and a PET (Positron Emission Computed Tomography)-CT device.

[0055] The technical solution of this application and how it solves the technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0056] In one embodiment, such as Figure 2 As shown, a registration method is provided, which can be applied to... Figure 1Taking the terminal in the example, the explanation includes the following steps:

[0057] Step 200: Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration.

[0058] The first image model of the object to be registered used in the previous registration refers to the image model that was registered with the object to be registered in the previous registration process. The first transformation matrix is ​​used to characterize the transformation relationship between the image space and physical space of the object to be registered as determined in the previous registration. Before the terminal performs the current registration, the first image model of the object to be registered used in the previous registration, as well as the first transformation matrix obtained in the previous registration, are first acquired. This embodiment does not limit the specific method used in the previous registration, as long as it can achieve its function.

[0059] Step 210: For the current registration, adjust the first image model based on the first transformation matrix to obtain the second image model.

[0060] When performing the current registration, the terminal adjusts the first image model according to the first transformation matrix obtained from the previous registration to obtain the second image model. The first transformation matrix includes the displacement magnitude and the rotation angle required. In other words, the terminal moves and rotates the first image model according to the displacement magnitude and rotation angle in the first transformation matrix to obtain the second image model.

[0061] Step 220: Project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain the projection point set.

[0062] The registration points in the first registration point set on the surface of the object to be registered can be registration points that have been pre-set by the staff on the surface of the object to be registered. This embodiment does not limit the specific number of registration points in the first registration point set, nor the specific location of each registration point, as long as its function can be achieved.

[0063] After obtaining the second image model, the terminal projects the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain a set of projection points. In other words, for each registration point in the first set of registration points on the surface of the object to be registered, by projecting that registration point onto the surface of the second image model, the corresponding projection point on the second image model surface can be obtained, thus obtaining the corresponding projection points on the second image model surface for each registration point in the first set of registration points, i.e., the set of projection points.

[0064] Step 230: Register the first registration point set with the projection point set to obtain the second transformation matrix.

[0065] After obtaining the projection point set, the terminal registers the first registration point set of the object to be registered with the projection point set to obtain a second transformation matrix. The second transformation matrix characterizes the transformation relationship between the image space and physical space of the object to be registered, as determined in the current registration. The second transformation matrix includes the magnitude of the required displacement and the required rotation angle. This embodiment does not limit the specific process of registering the first registration point set with the projection point set, as long as the function can be achieved.

[0066] In an optional embodiment, after obtaining the second transformation matrix, the terminal moves and rotates the second image model according to the displacement magnitude and rotation angle in the second transformation matrix, thereby obtaining an image model that matches the object to be registered.

[0067] The registration method provided in this application obtains a first image model of the object to be registered used in the previous registration and a transformation matrix obtained in the previous registration. For the current registration, the first image model is adjusted based on the first transformation matrix to obtain a second image model. The first registration point set on the surface of the object to be registered is projected onto the surface of the second image model to obtain a projection point set. The first registration point set and the projection point set are registered to obtain a second transformation matrix. This embodiment uses the projection point set projected from the first registration point set onto the surface of the second image model to register with the first registration point set. Compared with the prior art, which directly registers the registration point set on the second image model with the first registration point set, this method avoids inaccurate registration points on the second image model, which would lead to inaccurate final second transformation matrix. In other words, it reduces the dependence on registration points on the second image model, thereby improving the accuracy of registration.

[0068] Furthermore, the registration method provided in this application can achieve high-precision registration results with a small number of registration points.

[0069] In one embodiment, each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set. That is, each registration point in the first registration point set has multiple initial projection points projected onto the surface of the second image model, and the projection point in the projection point set corresponding to that registration point is the projection point among the multiple initial projection points that is closest to the registration point.

[0070] In this embodiment, each projection point in the projection point set is set as the projection point closest to the corresponding registration point in the first registration point set. Using this projection point set to register with the first registration point set can improve the accuracy of registration, thereby obtaining a more accurate second transformation matrix.

[0071] In one embodiment, a possible implementation of registering a first set of registration points with a set of projection points to obtain a second transformation matrix includes:

[0072] The pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the first objective function to solve for the second transformation matrix. The optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set. The first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0073] Suppose that the pose coordinates of the i-th registration point in the first registration point set are represented as q. i The pose coordinates of the projection point corresponding to the i-th registration point in the projection point set are represented as p. i The second transformation matrix includes displacement t2 and rotation angle R2. The first transformation point set can be represented as: (R2*p i If '+t2), then the first objective function can be expressed as: Where N1 is the number of registration points in the first registration point set. The terminal substitutes the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set into the first objective function to obtain the displacement and rotation angles in the second transformation matrix, thus obtaining the second transformation matrix.

[0074] In this embodiment, the first transformation matrix can be obtained by solving the first objective function using the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set. This method for calculating the second transformation matrix is ​​logically simple, easy to implement, and computationally efficient.

[0075] In one embodiment, such as Figure 3 As shown, one possible implementation of registering the first set of registration points with the projection point set to obtain the second transformation matrix includes:

[0076] Step 300: Obtain the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weight is obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point.

[0077] During the registration process, the registration weights of each registration point differ depending on the number of registration attempts. The registration weight of each registration point in the first registration point set is related to the number of registration attempts in the current attempt, the preset number of registration attempts set by the operator, and the pose difference between the registration point and its corresponding projection point. This embodiment does not limit the specific method for determining the registration weights, as long as the function can be achieved. The terminal obtains the registration weights corresponding to each registration point in the first registration point set.

[0078] In an optional embodiment, the registration weights can be calculated using the following formula:

[0079] Where l represents the number of registrations in the current registration, M is the preset number of registrations, and w i Let ||p be the registration weight corresponding to the i-th registration point. i '-q i || is the projection point p corresponding to the i-th registration point. i 'With the i-th registration point q i The difference in posture between them.

[0080] Step 310: Substitute the registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set as known quantities, and the second transformation matrix as an unknown quantity into the second objective function to solve for the second transformation matrix. The optimization objective of the second objective function is to minimize the pose difference between the first transformation point set and the first registration point set. The first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0081] The second objective function can be expressed as: The terminal substitutes the known registration weights of each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set into the second objective function, and can solve for the displacement and rotation angles in the second transformation matrix, thus obtaining the second transformation matrix.

[0082] In this embodiment, to reduce the impact of noisy registration points on the registration result during the registration process, registration weights are increased. As the number of registration iterations increases, the weight of registration points with higher noise levels decreases. This reduces the impact of noise on the registration result and improves the registration accuracy. Furthermore, the calculation method for the second transformation matrix in this embodiment is logically simple, easy to implement, and computationally efficient.

[0083] In one embodiment, each registration point in the first registration point set is a physiological and anatomical feature point on the surface of the object to be registered, i.e., a coarse registration point. The coarse registration points can be set using a probe, and the probe's positioning can be either visual tracking or magnetic navigation positioning, etc. This embodiment does not limit this. Based on this, as... Figure 4 As shown, after registering the first registration point set and the projection point set to obtain the second transformation matrix, the registration method further includes the following steps:

[0084] Step 400: Determine whether the number of registrations in the current registration has reached the threshold of the first iteration.

[0085] The first iteration threshold can be preset by the staff and stored in the terminal. After obtaining the second transformation matrix, the terminal obtains the registration number of the current registration of the second transformation matrix and the first iteration threshold, and compares the registration number of the current registration with the first iteration threshold to determine whether the registration number of the current registration reaches the first iteration threshold, that is, whether the registration number of the current registration is equal to the first iteration threshold.

[0086] Step 410: If the number of registrations in the current registration has not reached the threshold of the first iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0087] If the terminal determines that the number of registrations for the current registration has not reached the first iteration threshold, that is, the number of registrations for the current registration is less than the first iteration threshold, then the model used for the current registration (the second image model) is used as the first image model, and the second transformation matrix obtained from the current registration is used as the first transformation matrix, and the process returns to execute steps 210, 220, 230, 400 and 410.

[0088] In this embodiment, when the number of registrations in the current registration has not reached the first iteration threshold, the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the execution returns to steps 210, 220, 230, 400 and 410. Multiple registrations are performed based on coarse registration points, which can improve the accuracy of registration.

[0089] In an optional embodiment, the condition for stopping the current registration also includes whether the second transformation matrix obtained by the current registration reaches a preset transformation matrix threshold. That is, if the second transformation matrix obtained by the current registration does not reach the preset transformation matrix threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and steps 210, 220, 230, 400, and 410 are returned to be executed until the second transformation matrix obtained by the current registration reaches the preset transformation threshold.

[0090] In an optional embodiment, the condition for stopping the current registration may include whether the number of registrations in the current registration has reached a first iteration threshold or whether the second transformation matrix obtained by the current registration has reached a preset transformation matrix. That is, the current registration stops as long as either of these two conditions for stopping the current registration is met.

[0091] In one embodiment, please see [link to embodiment]. Figure 4 In one embodiment, the registration method further includes the following steps:

[0092] Step 420: If the number of registrations in the current registration reaches the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the second registration point set on the surface of the object to be registered is used as the first registration point set. The process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model, until the number of registrations in the current registration reaches the second iteration threshold; wherein, each registration point in the second registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0093] The second set of registration points on the surface of the object to be registered consists of points other than the physiological and anatomical feature points on the surface of the object. That is, each registration point in the second set of registration points is different from each registration point in the first set of registration points. Each registration point in the second set of registration points can also be called a fine registration point. Fine registration points can be in the form of probes, and the positioning of these probes can be achieved through visual tracking or magnetic navigation positioning, among other methods. This embodiment does not impose any limitations on this.

[0094] When the terminal determines that the number of registrations for the current registration has reached the first iteration threshold (i.e., the number of registrations for the current registration is equal to the first iteration threshold), it uses the model (second image model) used for the current registration as the first image model, the second transformation matrix obtained from the current registration as the first transformation matrix, and the second set of registration points on the surface of the object to be registered as the first set of registration points. Then it returns to execute steps 210, 220, 230, 400, and 410 until it determines that the number of registrations for the current registration has reached the second iteration threshold.

[0095] In this embodiment, after the number of registrations in the current registration reaches the first iteration number, that is, after multiple registrations using the first registration point set (i.e., coarse registration using coarse registration points), multiple registrations are then performed using the second registration point set (i.e., fine registration using fine registration points), which can improve the accuracy of registration.

[0096] In one embodiment, each registration point in the first registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered; that is, a fine registration point. A detailed description of the fine registration points can be found in the above embodiments and will not be repeated here. Based on this, as... Figure 5 As shown, after registering the first set of registration points with the projection point set to obtain the second transformation matrix, the registration method further includes the following steps:

[0097] Step 500: Determine whether the number of registrations in the current registration has reached the threshold of the third iteration.

[0098] The threshold for the third iteration count can be preset by the operator and stored in the terminal's memory. The third iteration count threshold can be the same as or different from the first iteration count threshold. After obtaining the second transformation matrix, the terminal acquires the registration count of the current registration and the third iteration count threshold, and compares the current registration count with the third iteration count threshold to determine whether the current registration count reaches the third iteration count threshold, i.e., whether the current registration count is equal to the third iteration count threshold.

[0099] Step 510: If the number of registrations in the current registration has not reached the threshold of the third iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0100] If the terminal determines that the number of registrations for the current registration has not reached the threshold of the third iteration, then the model used for the current registration (the second image model) is used as the first image model, and the second transformation matrix obtained from the current registration is used as the first transformation matrix. Then, the terminal returns to execute steps 210, 220, 230, 500, and 510.

[0101] In this embodiment, when the number of registrations in the current registration has not reached the threshold of the third iteration, the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the execution returns to steps 210, 220, 230, 500 and 510. Multiple registrations are performed based on the fine registration points, which can improve the accuracy of registration.

[0102] In one embodiment, the previous registration is considered the initial registration, meaning the first image model used in the first registration is image data obtained by scanning the object to be registered using a CT scanner. This image data is then sent to the terminal, where a 3D surface reconstruction algorithm is used to perform 3D reconstruction of the image data to obtain the image model of the object to be registered. Based on this, a possible implementation for obtaining the first transformation matrix obtained from the previous registration includes:

[0103] The first image model surface registration point set is registered with the first registration point set to obtain the first transformation matrix.

[0104] After acquiring the first image model, the terminal selects corresponding points on the surface of the object to be registered using the registration point set on the surface of the first image model to form a first registration point set. The first registration point set is then registered with the registration point set on the surface of the first image model to obtain a first transformation matrix. This embodiment does not limit the specific method used to register the registration point set on the surface of the first image model with the first registration point set, as long as the first transformation matrix can be obtained.

[0105] In an optional embodiment, the terminal may use a point-to-point registration algorithm to register the registration point set on the surface of the first image model with the first registration point set to obtain a first transformation matrix.

[0106] In an optional embodiment, the terminal can use the pose coordinates of each registration point in the registration point set on the surface of the first image model and the pose coordinates of each registration point in the first registration point set as known quantities, and the first transformation matrix as an unknown quantity, and substitute them into the third objective function to solve for the first transformation matrix.

[0107] Assume that the pose coordinates of the i-th registration point in the registration point set on the surface of the first image model are p. i The pose coordinates of the i-th registration point in the first registration point set are q. i The first transformation matrix includes displacement t1 and rotation angle R1. The third objective function can be expressed as: The terminal substitutes the pose coordinates of each registration point in the registration point set on the surface of the first image model with the pose coordinates of each registration point in the first registration point set into the third objective function, and can obtain the displacement and rotation angle in the first transformation matrix, thus obtaining the first transformation matrix.

[0108] In this embodiment, a registration method is provided to obtain a first transformation matrix by registering the registration point set on the surface of a first image model with a first registration point set. This method is simple, easy to understand, and easy to implement. Furthermore, by performing a registration first using the registration method provided in this embodiment, and then performing the current registration, the efficiency and accuracy of the current registration can be improved.

[0109] In one embodiment, see Figure 6 This relates to a possible implementation of obtaining the registration point set of the surface of a first image model, the implementation of which includes:

[0110] Step 600: Obtain the template image model. The surface of the template image model has a template point set.

[0111] A template image model refers to a general model used for registration. For example, a general 3D digital model of the pelvis. The template image model can be pre-stored in the terminal's memory by the operator. The terminal retrieves the template image model directly from the memory. The template image model surface has a template point set, which can include physiological and anatomical feature points (coarse registration points) and points other than physiological and anatomical feature points (fine registration points). The setting of physiological and anatomical feature points facilitates the operator in finding the corresponding points on the object to be registered. Typically, the template point set contains at least three non-collinear physiological and anatomical feature points.

[0112] Specifically, for pelvic images, coarse alignment points are the physiological and anatomical features of the pelvis, while fine alignment points are set on the bone surface of the area to be processed. The number of fine alignment points should be at least 3, and ideally more than 10.

[0113] Step 610: Match the template image model with the first image model to map the template point set onto the surface of the first image model, thereby obtaining the registration point set of the first image model surface.

[0114] After acquiring the template image model, the terminal matches the template image model with the first image model, and can map the template point set on the template image model to the surface of the first image model to obtain the registration point set on the surface of the first image model.

[0115] In this embodiment, by matching the model image model with the first image model, the template point set is mapped onto the surface of the first image model to obtain the registration point set of the first image model. This allows for the individualized registration points of the object to be detected, thus providing a more intuitive way for staff to determine the registration point set corresponding to the registration point set of the object surface and the first image model surface.

[0116] In one specific embodiment, the distribution of coarse registration points on the surface of the first image model is as follows: Figure 7 As shown, the distribution of fine-calibration points on the surface of the first image model is as follows: Figure 8 As shown.

[0117] Please see Figure 9 In one embodiment, this application provides a registration method, the steps of which include:

[0118] Step 900: Obtain the template image model; the template image model surface has a template point set; wherein, the template point set includes a first template point set and a second template point set, each template point in the first template point set is a physiological and anatomical feature point of the general template object image model surface, and each template point in the second template point set is a point other than the physiological and anatomical feature points of the general template object image model surface.

[0119] Step 910: Match the template image model with the first image model of the object to be registered, so as to map the template point set onto the surface of the first image model to obtain the registration point set of the first image model surface; wherein, the registration point set of the first image model surface includes a first sub-registration point set corresponding to the first template point set, and a second sub-registration point set corresponding to the second template point set, wherein each sub-registration point in the first sub-registration point set is a physiological and anatomical feature point of the image model surface of the object to be registered, and each sub-registration point in the second sub-registration point set is a point other than the physiological and anatomical feature point of the image model surface of the object to be registered;

[0120] Step 920: Select corresponding points on the surface of the object to be registered using the first sub-registration point set on the surface of the first image model to form a first registration point set; select corresponding points on the surface of the object to be registered using the second sub-registration point set on the surface of the first image model to form a second registration point set. The first registration point set consists of physiological and anatomical feature points selected on the surface of the object to be registered, and the second registration point set consists of points other than the physiological and anatomical feature points selected on the surface of the object to be registered.

[0121] Step 930: Register the first sub-registration point set on the surface of the first image model with the first registration point set on the surface of the object to be registered to obtain the first transformation matrix;

[0122] Step 940: Adjust the first image model based on the first transformation matrix to obtain the second image model;

[0123] Step 950: Project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain the projection point set;

[0124] Step 960: Register the first registration point set and the projection point set to obtain the second transformation matrix;

[0125] The pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the first objective function to solve for the second transformation matrix.

[0126] Step 970: Determine whether the number of registrations in the current registration has reached the threshold of the first iteration.

[0127] Step 980: If the number of registrations in the current registration has not reached the threshold of the first iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to steps 940-980.

[0128] Step 990: If the number of registrations in the current registration reaches the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the second registration point set on the surface of the object to be registered is used as the first registration point set. Then, return to steps 940-990 until the number of registrations in the current registration reaches the second iteration threshold. Wherein, each registration point in the second registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0129] Please see Figure 10 In one embodiment, this application provides a registration method, the steps of which include:

[0130] Step 101: Obtain the template image model; the surface of the template image model has a template point set; wherein, the template point set includes a first template point set and a second template point set, each template point in the first template point set is a physiological and anatomical feature point of the surface of the image model of the general template object, and each template point in the second template point set is a point other than the physiological and anatomical feature point of the surface of the image model of the general template object.

[0131] Step 102: Match the template image model with the first image model of the object to be registered, so as to map the template point set onto the surface of the first image model to obtain the registration point set of the first image model surface; wherein, the registration point set of the first image model surface includes a first sub-registration point set corresponding to the first template point set, and a second sub-registration point set corresponding to the second template point set, wherein each sub-registration point in the first sub-registration point set is a physiological and anatomical feature point of the image model surface of the object to be registered, and each sub-registration point in the second sub-registration point set is a point other than the physiological and anatomical feature point of the image model surface of the object to be registered;

[0132] Step 103: Select corresponding points on the surface of the object to be registered using the first sub-registration point set on the surface of the first image model to form the first registration point set; select corresponding points on the surface of the object to be registered using the second sub-registration point set on the surface of the first image model to form the second registration point set. The first registration point set consists of physiological and anatomical feature points selected on the surface of the object to be registered, and the second registration point set consists of points other than the physiological and anatomical feature points selected on the surface of the object to be registered.

[0133] Step 104: Register the first sub-registration point set on the surface of the first image model with the first registration point set on the surface of the object to be registered to obtain the first transformation matrix;

[0134] Step 105: Adjust the first image model based on the first transformation matrix to obtain the second image model;

[0135] Step 106: Project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain the first set of projection points;

[0136] Step 107: Register the first registration point set and the first projection point set to obtain the second transformation matrix;

[0137] The pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the first projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the first objective function to solve for the second transformation matrix.

[0138] Step 108: Determine whether the number of registrations in the current registration has reached the threshold of the first iteration.

[0139] Step 109: If the number of registrations in the current registration has not reached the threshold of the first iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to steps 105-109.

[0140] Step 110: If the number of registrations in the current registration reaches the threshold of the first iteration, then proceed with the next registration:

[0141] Step 111: For the next registration, adjust the first image model based on the second transformation matrix to obtain the third image model; project the second registration point set on the surface of the object to be registered onto the surface of the third image model to obtain the second projection point set;

[0142] Step 112: Obtain the registration weights corresponding to each registration point in the second registration point set; wherein, for each registration point in the second registration point set, the registration weight is obtained based on the difference between the registration number of the next registration and the first iteration number threshold, the preset registration number, and the pose difference between the registration point and the second projection point corresponding to the registration point; wherein, the preset registration number is equal to the difference between the second iteration number threshold and the first iteration number threshold;

[0143] Step 113: Take the registration weights corresponding to each registration point in the second registration point set, the pose coordinates of each registration point in the second registration point set, and the pose coordinates of each projection point in the second projection point set as known quantities, and take the third transformation matrix as an unknown quantity, and substitute them into the second objective function to solve for the third transformation matrix.

[0144] Step 114: Determine whether the number of registrations for the next registration has reached the threshold for the second iteration.

[0145] Step 115: If not, use the third image model as the first image model and the third transformation matrix as the second transformation matrix, and return to execute steps 111-115.

[0146] It should be understood that although the steps in the flowchart are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order constraint on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the diagram may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0147] Based on the same inventive concept, this application also provides a registration apparatus for implementing the registration method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more registration apparatus embodiments provided below can be found in the limitations of the registration method described above, and will not be repeated here.

[0148] Please see Figure 11 One embodiment of this application provides a registration device 10, which includes an acquisition module 11, an adjustment module 12, a projection module 13, and a registration module 14.

[0149] The acquisition module 11 is used to acquire the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration;

[0150] The adjustment module 12 is used to adjust the first image model based on the first transformation matrix for the current registration to obtain the second image model;

[0151] Projection module 13 is used to project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain the projection point set;

[0152] The registration module 14 is used to register the first registration point set with the projection point set to obtain the second transformation matrix.

[0153] In one embodiment, each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set.

[0154] In one embodiment, the registration module 14 is specifically used to take the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set as known quantities, and the second transformation matrix as an unknown quantity, and substitute them into the first objective function to solve for the second transformation matrix; wherein, the optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set, and the first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0155] In one embodiment, the registration module 14 is further configured to obtain the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weight is obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point; the registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity, and substituted into the second objective function to solve for the second transformation matrix.

[0156] In one embodiment, each registration point in the first registration point set is a physiological and anatomical feature point on the surface of the object to be registered, and the registration device 10 further includes a judgment module. The judgment module is used to determine whether the number of registrations in the current registration has reached the first iteration threshold; if the number of registrations in the current registration has not reached the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the step of adjusting the first image model based on the first transformation matrix to obtain the second image model is returned.

[0157] In one embodiment, the judgment module is further configured to, if the number of registrations in the current registration reaches the first iteration threshold, use the second image model as the first image model, the second transformation matrix as the first transformation matrix, and the second set of registration points on the surface of the object to be registered as the first set of registration points, and return to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model, until the number of registrations in the current registration reaches the second iteration threshold; wherein, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0158] In one embodiment, each registration point in the first registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered. The judgment module is also used to determine whether the number of registrations in the current registration reaches the third iteration threshold. If the number of registrations in the current registration does not reach the third iteration threshold, the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the step of adjusting the first image model based on the first transformation matrix to obtain the second image model is returned.

[0159] In one embodiment, the acquisition module 11 is specifically used to register the registration point set of the first image model surface with the first registration point set to obtain the first transformation matrix.

[0160] In one embodiment, the acquisition module 11 is further used to acquire a template image model, the surface of which has a template point set; and to match the template image model with a first image model to map the template point set onto the surface of the first image model to obtain a registration point set on the surface of the first image model.

[0161] Each module in the aforementioned registration device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0162] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a registration method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0163] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0164] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0165] Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration;

[0166] For the current registration, the first image model is adjusted based on the first transformation matrix to obtain the second image model;

[0167] The first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain the projection point set;

[0168] The first set of registration points is registered with the set of projection points to obtain the second transformation matrix.

[0169] In one embodiment, each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set.

[0170] In one embodiment, when the processor executes the computer program, it further implements the following steps: taking the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the first objective function to solve for the second transformation matrix; wherein, the optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set, and the first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0171] In one embodiment, when the processor executes the computer program, it further implements the following steps: obtaining the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weight is obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point; taking the registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the second objective function to solve for the second transformation matrix.

[0172] In one embodiment, when the processor executes the computer program, it further implements the following steps: determining whether the number of registrations in the current registration reaches the first iteration threshold; if the number of registrations in the current registration does not reach the first iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0173] In one embodiment, when the processor executes the computer program, it further implements the following steps: if the number of registrations in the current registration reaches a first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, the second set of registration points on the surface of the object to be registered is used as the first set of registration points, and the process of adjusting the first image model based on the first transformation matrix to obtain the second image model is repeated until the number of registrations in the current registration reaches a second iteration threshold; wherein, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0174] In one embodiment, when the processor executes the computer program, it further implements the following steps: determining whether the number of registrations in the current registration reaches the third iteration threshold; if the number of registrations in the current registration does not reach the third iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0175] In one embodiment, when the processor executes the computer program, it further performs the following steps: registering the registration point set of the surface of the first image model with the first registration point set to obtain a first transformation matrix.

[0176] In one embodiment, when the processor executes the computer program, it further performs the following steps: obtaining a template image model, the surface of which has a template point set; matching the template image model with a first image model to map the template point set onto the surface of the first image model, thereby obtaining a registration point set on the surface of the first image model.

[0177] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0178] Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration;

[0179] For the current registration, the first image model is adjusted based on the first transformation matrix to obtain the second image model;

[0180] The first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain the projection point set;

[0181] The first set of registration points is registered with the set of projection points to obtain the second transformation matrix.

[0182] In one embodiment, each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set.

[0183] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: taking the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the first objective function to solve for the second transformation matrix; wherein, the optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set, and the first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0184] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weights are obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point; taking the registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the second objective function to solve for the second transformation matrix.

[0185] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: determining whether the number of registrations in the current registration reaches the first iteration threshold; if the number of registrations in the current registration does not reach the first iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0186] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: if the number of registrations in the current registration reaches a first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, the second set of registration points on the surface of the object to be registered is used as the first set of registration points, and the step of adjusting the first image model based on the first transformation matrix to obtain the second image model is returned to be executed until the number of registrations in the current registration reaches a second iteration threshold; wherein, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0187] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: determining whether the number of registrations in the current registration has reached the third iteration threshold; if the number of registrations in the current registration has not reached the third iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0188] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: registering the registration point set of the surface of the first image model with the first registration point set to obtain a first transformation matrix.

[0189] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a template image model, the surface of which has a template point set; matching the template image model with a first image model to map the template point set onto the surface of the first image model, thereby obtaining a registration point set on the surface of the first image model.

[0190] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0191] Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration;

[0192] For the current registration, the first image model is adjusted based on the first transformation matrix to obtain the second image model;

[0193] The first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain the projection point set;

[0194] The first set of registration points is registered with the set of projection points to obtain the second transformation matrix.

[0195] In one embodiment, each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set.

[0196] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: taking the pose coordinates of each registration point in the first registration point set and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the first objective function to solve for the second transformation matrix; wherein, the optimization objective of the first objective function is to minimize the pose difference between the first transformation point set and the first registration point set, and the first transformation point set is obtained by transforming the projection point set based on the second transformation matrix.

[0197] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weights are obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the corresponding projection point; taking the registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set as known quantities, and taking the second transformation matrix as an unknown quantity, and substituting them into the second objective function to solve for the second transformation matrix.

[0198] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: determining whether the number of registrations in the current registration reaches the first iteration threshold; if the number of registrations in the current registration does not reach the first iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0199] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: if the number of registrations in the current registration reaches a first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, the second set of registration points on the surface of the object to be registered is used as the first set of registration points, and the step of adjusting the first image model based on the first transformation matrix to obtain the second image model is returned to be executed until the number of registrations in the current registration reaches a second iteration threshold; wherein, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

[0200] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: determining whether the number of registrations in the current registration has reached the third iteration threshold; if the number of registrations in the current registration has not reached the third iteration threshold, then using the second image model as the first image model, using the second transformation matrix as the first transformation matrix, and returning to execute the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

[0201] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: registering the registration point set of the surface of the first image model with the first registration point set to obtain a first transformation matrix.

[0202] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: obtaining a template image model, the surface of which has a template point set; matching the template image model with a first image model to map the template point set onto the surface of the first image model, thereby obtaining a registration point set on the surface of the first image model.

[0203] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0204] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0205] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A registration method, characterized in that, include: Obtain the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration; For the current registration, the first image model is adjusted based on the first transformation matrix to obtain the second image model; The first set of registration points on the surface of the object to be registered is projected onto the surface of the second image model to obtain the projection point set; The first set of registration points is registered with the set of projection points to obtain the second transformation matrix; The step of registering the first registration point set with the projection point set to obtain the second transformation matrix includes: Obtain the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weights are obtained based on the registration count of the current registration, the preset registration count, and the pose difference between the registration point and the projection point corresponding to the registration point; The registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the second objective function to solve for the second transformation matrix.

2. The registration method according to claim 1, characterized in that, Each projection point in the projection point set is the projection point closest to its corresponding registration point in the first registration point set.

3. The registration method according to claim 1, characterized in that, The method further includes: The second image model is moved and rotated according to the displacement magnitude and rotation angle in the second transformation matrix to obtain an image model that matches the object to be registered.

4. The registration method according to claim 1, characterized in that, Each registration point in the first registration point set is a physiological and anatomical feature point on the surface of the object to be registered. After registering the first registration point set with the projection point set to obtain the second transformation matrix, the registration method further includes: Determine whether the number of registrations in the current registration reaches the first iteration threshold; If the number of registrations in the current registration has not reached the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

5. The registration method according to claim 4, characterized in that, The registration method further includes: If the number of registrations in the current registration reaches the first iteration threshold, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the second set of registration points on the surface of the object to be registered is used as the first set of registration points. The process of adjusting the first image model based on the first transformation matrix to obtain the second image model is repeated until the number of registrations in the current registration reaches the second iteration threshold. In this case, each registration point in the second set of registration points is a point other than the physiological and anatomical feature points on the surface of the object to be registered.

6. The registration method according to claim 1, characterized in that, Each registration point in the first registration point set is a point other than the physiological and anatomical feature points on the surface of the object to be registered. After registering the first registration point set with the projection point set to obtain the second transformation matrix, the registration method further includes: Determine whether the number of registrations in the current registration reaches the threshold of the third iteration. If the number of registrations in the current registration does not reach the threshold of the third iteration, then the second image model is used as the first image model, the second transformation matrix is ​​used as the first transformation matrix, and the process returns to the step of adjusting the first image model based on the first transformation matrix to obtain the second image model.

7. The registration method according to claim 1, characterized in that, Obtaining the first transformation matrix obtained from the previous registration includes: The first image model surface registration point set is registered with the first registration point set to obtain the first transformation matrix.

8. The registration method according to claim 7, characterized in that, The step of registering the registration point set on the surface of the first image model with the first registration point set to obtain the first transformation matrix includes: The pose coordinates of each registration point in the registration point set on the surface of the first image model and the pose coordinates of each registration point in the first registration point set are taken as known quantities, and the first transformation matrix is ​​taken as an unknown quantity. These are substituted into the third objective function to solve for the first transformation matrix.

9. The registration method according to claim 7, characterized in that, The method for obtaining the registration point set of the surface of the first image model includes: Obtain a template image model, the surface of which has a template point set; The template image model is matched with the first image model to map the template point set onto the surface of the first image model, thereby obtaining the registration point set of the surface of the first image model.

10. A registration device, characterized in that, include: The acquisition module is used to acquire the first image model of the object to be registered used in the previous registration and the first transformation matrix obtained in the previous registration. The adjustment module is used to adjust the first image model based on the first transformation matrix for the current registration to obtain the second image model; The projection module is used to project the first set of registration points on the surface of the object to be registered onto the surface of the second image model to obtain a set of projection points. The registration module is used to register the first registration point set with the projection point set to obtain a second transformation matrix; The registration module is further configured to obtain the registration weights corresponding to each registration point in the first registration point set; wherein, for each registration point in the first registration point set, the registration weights are obtained based on the registration number of the current registration, the preset registration number, and the pose difference between the registration point and the projection point corresponding to the registration point; The registration weights corresponding to each registration point in the first registration point set, the pose coordinates of each registration point in the first registration point set, and the pose coordinates of each projection point in the projection point set are taken as known quantities, and the second transformation matrix is ​​taken as an unknown quantity. These are substituted into the second objective function to solve for the second transformation matrix.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images