CN116721137B

CN116721137B - Registration method and device, storage medium and electronic equipment

Info

Publication number: CN116721137B
Application number: CN202310994089.7A
Authority: CN
Inventors: 冯彦彰; 申一君; 郑贺亮; 刘兴业; 顾席铭; 陈亚刚; 陈庸非
Original assignee: Beijing AK Medical Co Ltd
Current assignee: Beijing AK Medical Co Ltd
Priority date: 2023-08-08
Filing date: 2023-08-08
Publication date: 2023-10-27
Anticipated expiration: 2043-08-08
Also published as: CN116721137A

Abstract

The embodiment of the application provides a registration method and device, a storage medium and electronic equipment, wherein the method comprises the following steps: affine transformation is carried out on a far-end point on a bone object, a plurality of fine registration points on the bone object and a collection point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results; determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result; a registration matrix corresponding to the bone object is determined based on the first matrix and the second matrix to register a target operation performed on the bone object using the registration matrix. The application solves the problems that the high-precision registration can not be realized in the registration in the related technology, the preliminary requirement in the registration process is high, and the global optimality of the registration result is poor.

Description

Registration method and device, storage medium and electronic equipment

Technical Field

The embodiment of the application relates to the field of registration and registration of medical images, in particular to a registration method and device, a storage medium and electronic equipment.

Background

In recent years, with the rapid development of artificial intelligence technology, various navigation robots for medical assistance are layered out, but good registration is indispensable to perform surface hip replacement surgery with the help of modern navigation robots. Deviations in the intraoperative tracking and measurement data may negatively impact the outcome of the surgery if there is no effective registration. Currently, in the registration process of surface hip replacement surgery, there are mainly two difficulties: (1) fewer exposed areas are used in the operation. During actual surgery, the area exposed to the physician's vision is limited. (2) the femoral head portion has high symmetry. This symmetry makes it very easy to get into local optima when using conventional Iterative Closest Point (ICP) algorithms, and it is difficult to achieve an ideal registration effect.

Therefore, for the surface hip replacement surgery, the registration in the prior art cannot realize high-precision registration, and the initial requirement in the registration process is high, and the global optimality of the registration result is poor.

No effective solution has been proposed for the problems in the related art.

Disclosure of Invention

The embodiment of the application provides a registration method and device, a storage medium and electronic equipment, which at least solve the problems that high-precision registration cannot be realized in the registration in the related technology, the preliminary requirement in the registration process is high, and the global optimality of a registration result is poor.

According to an embodiment of the present application, there is provided a registration method including: affine transformation is carried out on a far-end point on a bone object, a plurality of fine registration points on the bone object and a collection point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results; determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result; a registration matrix corresponding to the bone object is determined based on the first matrix and the second matrix to register a target operation performed on the bone object using the registration matrix.

According to yet another embodiment of the present application, there is provided a registration apparatus including: the transformation unit is used for carrying out affine transformation on the far end points on the bone object, the plurality of fine registration points on the bone object and the acquisition point set corresponding to the rough registration indication points on the indication model on the bone object by using the first matrix to obtain a transformation result; the optimizing unit is used for optimizing the multiple sub-chains through a target algorithm under the condition that the multiple sub-chains corresponding to the transformation result are determined, so that multiple optimized results are obtained; the acquisition unit is used for determining a target result meeting a preset iteration exit condition from a plurality of optimization results and acquiring a second matrix corresponding to the target result; a first determining unit, configured to determine a registration matrix corresponding to the bone object based on the first matrix and the second matrix, so as to register the target operation performed on the bone object using the registration matrix.

According to a further embodiment of the application, there is also provided a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

According to a further embodiment of the application there is also provided an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

According to the embodiment of the application, affine transformation is carried out on a far end point on a bone object, a plurality of fine registration points on the bone object and an acquisition point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results; determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result; a registration matrix corresponding to the bone object is determined based on the first matrix and the second matrix to register a target operation performed on the bone object using the registration matrix. Therefore, in the registration matrix corresponding to the bone object formed by the first matrix and the second matrix, the problems that high-precision registration cannot be realized in the registration in the related art, the preliminary requirement in the registration process is high, and the global optimality of the registration result is poor can be solved, and the technical effect of high-precision registration and registration of the bone object is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a block diagram of a hardware architecture of a mobile terminal of a model deployment method according to an embodiment of the present application;

FIG. 2 is a flow chart diagram of a registration method of an embodiment of the present application;

FIG. 3 is a schematic structural diagram of an alternative electronic device according to an embodiment of the present application;

FIG. 4 is a schematic illustration of the exposed area of the femoral side in a surface hip replacement surgery in accordance with an embodiment of the present application;

fig. 5 is a photograph of three different viewing angles of a femoral head in an embodiment of the present application;

FIG. 6 is a flow chart of a coarse registration process according to an embodiment of the present application;

FIG. 7 is a schematic illustration of selection of a coarse registration indicator in accordance with an embodiment of the present application;

FIG. 8 is a schematic diagram showing the effect of ordering the indication point set and the collection point set according to the embodiment of the present application;

FIG. 9 is a flow chart of a fine registration process according to an embodiment of the present application;

FIG. 10 is a schematic illustration of an attachment point marking in accordance with an embodiment of the present application;

fig. 11 is a block diagram of a registration device according to an embodiment of the present application;

FIG. 12 is a block diagram of an alternative electronic device computer system in accordance with an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The method according to the first embodiment of the present application may be implemented in a mobile terminal, a computer terminal or a similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of a mobile terminal of a model deployment method according to an embodiment of the present application. As shown in fig. 1, the mobile terminal may include one or more (only one is shown in the figure) processors 102 (the processors 102 may include, but are not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 and an input-output device 108 for communication functions. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 1 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the model deployment method in the embodiment of the present application, and the processor 102 executes the software programs and modules stored in the memory 104, thereby performing various functional applications and data processing, that is, implementing the method described above. Memory 104 may include high-speed random access memory, but may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal 10 via a network. Examples of such networks may include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 106 is used to receive or transmit data via a network. The specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal 10. In one example, the transmission device 106 may include a network adapter (Network Interface Controller, NIC) that may be connected to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module for communicating with the internet wirelessly.

In this embodiment, a registration method is provided, and fig. 2 is a schematic flow chart of the registration method according to an embodiment of the present application, as shown in fig. 2, where the flow may include, but is not limited to, the following steps:

step S202, affine transformation is carried out on a far-end point on a bone object, a plurality of fine registration points on the bone object and an acquisition point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result;

optionally, the first matrix is a coarse registration affine matrix determined by coarse registration indicating points and acquisition point sets, and is mainly used for positioning the approximate position of the bone object.

It should be noted that the above-mentioned coarse registration indication points may be a plurality of reference points selected by the operation object on the indication model according to actual requirements, the number of the coarse registration indication points may be flexibly determined, and optionally, the above-mentioned coarse registration indication points may be 3 points.

Step S204, under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results;

optionally, the plurality of sub-chains is determined by adding a perturbation matrix to a plurality of initial chains present in the transformed result. The disturbance matrix can randomly sample the translation amount and the rotation amount on the X, Y and Z axes corresponding to the bone object by using standard normal distribution, and m groups of random rotation matrices and translation matrices are generated so as to be formed based on the m groups of random rotation matrices and translation matrices, wherein m is a positive integer greater than or equal to 1.

Step S206, determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result;

it can be appreciated that, in order to avoid the waste of computing resources caused by continuous optimization of each optimization result, a maximum iteration step for optimizing the sub-chain can be set, and further, the optimization of the sub-chain is stopped when the maximum iteration step is reached.

Step S208, determining a registration matrix corresponding to the bone object based on the first matrix and the second matrix, so as to register the target operation performed on the bone object by using the registration matrix.

Through the steps, affine transformation is carried out on the far end points on the bone object, the plurality of fine registration points on the bone object and the acquisition point set corresponding to the rough registration indication points on the indication model on the bone object by using the first matrix, so that a transformation result is obtained; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results; determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result; a registration matrix corresponding to the bone object is determined based on the first matrix and the second matrix to register a target operation performed on the bone object using the registration matrix. Therefore, in the registration matrix corresponding to the bone object formed by the first matrix and the second matrix, the problems that high-precision registration cannot be realized in the registration in the related art, the preliminary requirement in the registration process is high, and the global optimality of the registration result is poor can be solved, and the technical effect of high-precision registration and registration of the bone object is achieved.

In an alternative embodiment, before affine transformation of the distal point on the bone object, the plurality of precision points on the bone object, the collection point set on the bone object corresponding to the coarse registration indication points on the indication model using the first matrix, the method further comprises: acquiring a coarse registration indication point set corresponding to the coarse registration indication points selected from the indication model and used for initially positioning the bone object; indicating the bone probe to acquire position information on the bone object through the rough registration indicating point set; determining an acquisition point set corresponding to the rough registration indication points on the indication model on the bone object according to the acquisition result; and determining a first matrix corresponding to the bone object based on the acquisition point set and the rough registration indication point set.

In an alternative embodiment, before determining the first matrix corresponding to the bone object based on the collection point set and the coarse registration indication point set, the method further includes: determining distance features among different coarse registration indicating points in the coarse registration indicating point set, and generating definition information of the coarse registration indicating point set according to the distance features; calculating Euclidean distances among different acquisition points in the acquisition point set to obtain a plurality of Euclidean distances; and setting target distance characteristics for two acquisition points corresponding to each Euclidean distance in the multiple Euclidean distances by using the definition information so as to sort the different acquisition points by using the target distance characteristics.

It can be understood that, since the order of the acquisition points corresponding to the coarse registration indication points is not fixed in the actual operation, after the coarse registration indication points are acquired, the indication point sets and the acquisition point sets need to be ordered according to the relationship between the coarse registration indication points, so that the corresponding points have the same definition in the two point sets.

In an alternative embodiment, determining a first matrix corresponding to the bone object based on the collection point set and the coarse registration indication point set includes: determining first unit vectors among different coarse registration indicating points in the coarse registration indicating point set to obtain a first vector group, and determining second unit vectors among different acquisition points in the acquisition point set to obtain a second vector group; calculating the first vector group and the second vector group by using a preset covariance matrix to generate a target covariance matrix; singular value decomposition is carried out on the target covariance matrix, a rotation matrix corresponding to the target covariance matrix is determined, and a translation matrix corresponding to the coarse registration indication point set is determined based on the rotation matrix; and determining a combined matrix of the rotation matrix and the translation matrix as a first matrix corresponding to the bone object.

In an alternative embodiment, determining a translation matrix corresponding to the coarse registration indication point set based on the rotation matrix includes: calculating first midpoints corresponding to different coarse registration indicating points in the coarse registration indicating point set and second midpoints corresponding to different acquisition points in the acquisition point set; rotating the second midpoint by using the rotation matrix to obtain a target point; and determining the translation amount between the target point and the first midpoint to obtain a translation matrix corresponding to the acquisition point set.

Optionally, three points may be selected as coarse registration indication points in the indication model, for example, the points a, B and C, for better positioning the direction of the indication model through the coarse registration indication points, the distance between the two points A, C may be determined as the maximum during selection, the distance between the two points A, B is greater than the distance between the two points BC, and the three points are ensured to be located in a green or yellow area, then the actual acquisition points corresponding to the coarse registration indication points are identified and acquired according to the indication model on the bone of the patient according to any sequence, the indication point set and the acquisition point set are ordered, after the ordering, an optimal rotation matrix between the indication point set and the acquisition point set is determined, and a translation matrix between the determined target points after the points in the coarse registration indication point set and the midpoints in the acquisition point set rotate through the optimal rotation matrix is determined, so as to combine the optimal rotation matrix and the translation matrix, and write the optimal rotation matrix and the translation matrix into a homogeneous form, thereby obtaining an affine matrix for coarse registration, that is the first matrix.

In an alternative embodiment, after optimizing the multiple sub-chains by the target algorithm to obtain multiple optimization results, the method further includes: selecting a first indication point from the coarse registration indication points on the indication model; determining a third vector corresponding to a connecting line of the first indication point and the second midpoint, and obtaining a fourth vector of a first acquisition point corresponding to the first indication point and the first midpoint, wherein the first midpoint is used for indicating a midpoint between at least two actual points acquired in a skin area corresponding to the bone object, the second midpoint is used for indicating a midpoint between at least two attachment points marked in advance in the indication model, and the at least two actual points and the at least two attachment points have a corresponding relation; obtaining a plurality of optimization matrixes corresponding to the plurality of optimization results, and carrying out affine transformation on the fourth vector by using the plurality of optimization matrixes to obtain a state vector group of the fourth vector; and calculating an included angle between the third vector and each state vector in the state vector group.

In an alternative embodiment, after calculating the angle between the third vector and each of the state vectors in the state vector group, the method further comprises: deleting a first sub-chain corresponding to the current included angle from the plurality of sub-chains under the condition that the included angle is larger than a preset included angle; and under the condition that all the included angles are larger than a preset included angle, sequencing all the included angles, and deleting the second sub-chain corresponding to half of larger included angles in all the included angles.

In an optional embodiment, in a case of determining a plurality of sub-chains corresponding to the transformation result, optimizing the plurality of sub-chains by a target algorithm to obtain a plurality of optimized results, before the method further includes: carrying out affine transformation on the plurality of fine registration points by using a plurality of optimization matrixes corresponding to the plurality of optimization results to obtain a moving point set corresponding to the plurality of fine registration points; and calculating errors among all the moving points in the moving point set, and merging third sub-chains associated with the target fine registration points corresponding to at least two moving points with the errors smaller than the preset errors.

In an alternative embodiment, determining a target result that meets a preset iteration exit condition from the plurality of optimization results includes: determining residual fine registration positions corresponding to the plurality of sub-chains after completion, and calculating root mean square errors of the residual fine registration positions and the surface of the indication model to obtain an error set; determining a minimum error from the error set, and acquiring a target sub-chain corresponding to the minimum error and determining iteration times corresponding to a target optimization result of the target sub-chain; and under the condition that the iteration times and the minimum error meet the preset iteration exit condition, determining the target sub-chain as the target result.

As an alternative embodiment, determining a distal point of the bone object and obtaining a plurality of precisely-registered points on the bone object, wherein the distal point comprises a first midpoint between at least two actual points acquired at a skin region corresponding to the bone object according to position information indicative of at least two attachment points marked in advance in the model and a second midpoint between at least two attachment points determined based on the position information; affine transformation is carried out on a far-end point, a plurality of fine registration points and an acquisition point set by using a first matrix to obtain a transformation result, wherein the acquisition point set is used for indicating the set of acquisition points correspondingly acquired by a bone probe on a bone object according to the coarse registration indication points selected on the indication model, and the first matrix is used for indicating a coarse registration affine matrix determined according to the coarse registration indication points and the acquisition point set; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results, wherein the plurality of sub-chains are determined by adding disturbance matrixes into a plurality of initial chains existing in the transformation result; and determining a target result meeting a preset iteration exit condition from the plurality of optimization results, and acquiring a second matrix corresponding to the target result so as to determine a registration matrix corresponding to the bone object based on the first matrix and the second matrix.

Alternatively, in the present embodiment, the above-described registration method may be performed by an electronic device as shown in fig. 3. As shown in fig. 3, the electronic device 200 may include: at least one processor 201, at least one network interface 202, a bus system 203, and memory 204. The various components in the electronic device 200 are coupled together by a bus system 203. It is understood that the bus system 203 is used to enable connected communications between these components. The bus system 203 includes a power bus, a control bus, and a status signal bus in addition to the data bus. But for clarity of illustration the various buses are labeled as bus system 203 in fig. 3.

The processor 201 may be an integrated circuit chip with signal processing capabilities such as a general purpose processor, which may be a microprocessor or any conventional processor, or the like, a digital signal processor (DSP, digital Signal Processor), or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

The memory 204 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard drives, optical drives, and the like. Memory 204 optionally includes one or more storage devices physically remote from processor 201.

Memory 204 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a random access Memory (RAM, random Access Memory). The memory 204 described in embodiments of the present application is intended to comprise any suitable type of memory.

In some embodiments, memory 204 is capable of storing data to support various operations, examples of which include programs, modules and data structures, or subsets or supersets thereof, as exemplified below.

An operating system 2041 including system programs for handling various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and handling hardware-based tasks;

network communication module 2402 for reaching other computing devices via one or more (wired or wireless) network interfaces 202, exemplary network interfaces 202 include: bluetooth, wireless compatibility authentication (WiFi), and universal serial bus (USB, universal Serial Bus), etc.;

in some embodiments, the apparatus provided by the embodiments of the present application may be implemented in software, and fig. 3 shows a registration apparatus 2043 stored in a memory 204, which may be software in the form of a program, a plug-in, or the like, including the following software elements: the transformation unit, the optimization unit, the acquisition unit, the first determination unit, which are logical, so that any combination or further splitting may be performed depending on the implemented functions. The functions of the respective units will be described hereinafter.

As an alternative embodiment, fig. 4 is a schematic view of the exposed area of the femoral side in a surface hip replacement surgery in accordance with an embodiment of the present application. The green area in the figure is the area where data can be directly acquired by the bone probe; the yellow area is covered by soft tissues, and data on a bone surface can be acquired through tools such as a bone probe, but the acquired data have larger deviation because the bone surface area cannot be directly seen; the red region is a region deeply wrapped by soft tissues, and the region cannot be acquired by a method such as a bone probe to obtain bone surface data.

Alternatively, fig. 5 is a photograph of three different viewing angles of the femoral head in the embodiment of the present application, and the femoral head and the femoral neck portion can be intuitively seen through fig. 5, so that the symmetry is significant. This symmetry makes it very easy to get into local optima when using conventional Iterative Closest Point (ICP) algorithms, and it is difficult to achieve an ideal registration effect. Therefore, for superficial hip replacement surgery, a more accurate registration method is needed to cope with the problems of small exposed surface on the femoral side, strong symmetry between the femoral head and the femoral neck, etc.

In this regard, the first matrix for the coarse registration portion may be corrected by an adaptive angle, and the second matrix for the fine registration portion may be determined by introducing a multi-chain parallel optimization strategy under constraint conditions of the distal femoral midpoint, and then the registration matrix generated by using the coarse registration result and the fine registration result may provide more accurate registration accuracy for the surface hip replacement surgery, so as to avoid the problems of less exposed area in the surface hip replacement surgery, high symmetry of the femoral head portion, and the like.

Furthermore, the coarse registration stage for determining the first matrix allows a large error between the sampling points and the indication points, and the sequence of the sampling points is not required to be considered; the solution space is fully explored in the fine registration stage of the second matrix, the high symmetry problem is solved and high-precision registration is realized through iterative optimization on the basis of the coarse registration result, specifically, a femur distal end constraint method is adopted, iterative optimization and chain screening are carried out by utilizing a multi-chain parallel optimization strategy, so that the high-precision registration matrix is generated through rapid convergence, the operation difficulty of an operator is greatly reduced, and the operation effect and the patient satisfaction are improved.

In order to better understand the technical solutions of the embodiments and the alternative embodiments of the present application, the following description is given with reference to the flowchart of the above-mentioned registration method by way of example, but is not intended to limit the technical solutions of the embodiments of the present application.

Aiming at the problems existing in the related art, an alternative embodiment of the application provides a femur side registration method based on a multi-chain optimization strategy, which mainly comprises a coarse registration part and a fine registration part. The coarse registration portion employs an adaptive angular correction method that is primarily used to calculate the approximate position of the patient's bone. The fine registration part realizes high-precision registration by introducing a multi-chain parallel optimization strategy under the constraint condition of the middle point of the distal femur.

Optionally, fig. 6 is a flowchart of a coarse registration process according to an embodiment of the present application, where, for a coarse registration portion, the requirement of the coarse registration stage is relatively low due to the characteristics of strong symmetry and small exposure area of the femoral head portion. The goal of this stage is to determine the general orientation of the patient's bone so that it substantially coincides with the orientation of the pointing model. In particular, the angle between the two is allowed to be not higher than 30 °. Furthermore, a certain degree of translation error is allowed when calculating the translation matrix.

Specifically, the coarse registration process includes the steps of:

step S602, selecting three points in the indication model as rough registration indication points. When the rough registration indication points are selected, the maximum distance between the two points of AC is required to be ensured, the distance between the two points of AB is larger than the distance between the two points of BC, the three points are positioned in a green or yellow area and cannot be positioned in a red area (refer to fig. 4), and the points which are easy to identify are selected as much as possible.

Alternatively, fig. 7 is a schematic diagram illustrating selection of a coarse registration indication point according to an embodiment of the present application.

Step S604, identifying and acquiring rough registration points on the patient' S bone (corresponding to the bone object in the above embodiment) according to the indication model in any order. During collection, an operator only needs to collect in a rough area. The specific acquisition mode is not limited, and the method such as infrared tracking can be selected according to an actual system, and the acquired characteristic point coordinates are only required to be processed and positioned at the correct positions.

Step S606, ordering the indication point set and the collection point set.

It should be noted that, since the acquisition order is not fixed, after the coarse registration points are acquired, the indication point set and the acquisition point set need to be ordered, so that ABC three points have the same definition in the two point sets. The specific method comprises the following steps:

step one, calculating Euclidean distance among three points, taking two points with the largest distance as A, C alternative points, and taking the rest points as B points.

And step two, A, C, wherein the point far from the point B is A, and the point close to the point B is C, so that the sorting process is completed.

Optionally, fig. 8 is a schematic diagram of an effect of ordering the indication point set and the collection point set according to an embodiment of the present application.

Step S608, jointly evaluating the optimal rotation matrix using a kabsch algorithm.

Alternatively, the present application uses conditions different from the kabsch algorithm, and thus the calculation process will be described herein. The specific calculation process is as follows:

and A, constructing a unit vector. Let the vector from the point A to the point C in the indicating point set be V _AC By the following constitutionThe vector from the point A to the point B is V _AB The method comprises the steps of carrying out a first treatment on the surface of the Let the corresponding vector in the collection point set be V' _AC And V' _AB The method comprises the steps of carrying out a first treatment on the surface of the The four vectors are unitized as shown in fig. 1: v (V) _norm =V/║V║（1）；

And B, constructing a covariance matrix H. Unitized V _AC And V _AB Form vector group a= [ V _AC ,V _AB ]The corresponding construction of the vectors in the collection points as vector group b= [ V ]' _AC , V' _AB ]. The covariance matrix H can be expressed as: h=a·b ^T (2)；

And C, singular value decomposition is carried out on the covariance matrix, and a rotation matrix R is constructed. After obtaining the covariance matrix, U, L, V are obtained using Singular Value Decomposition (SVD) _t ：U,L,V _t =svd (H) (3); wherein U is a left singular matrix, V is a right singular matrix, and L is a singular value; further, a rotation matrix R can be obtained: r=v _t ^T ·U ^T (4)；

And D, verifying determinant of the rotation matrix R and correcting the result of R. After R is obtained, it is necessary to determine that the determinant is positive, and the value DetR of the determinant is calculated by the laplace expansion method shown in fig. 5: detr=a ₁₁ c ₁₁ +…+ a _1n c _1n (5)；

If DetR < 0, V _t The last row is multiplied by-1 and the rotation matrix is recalculated according to equation 4 to ensure that the resulting rotation matrix R is an orthogonal matrix.

Step S610, calculating a translation matrix. Let the coarse registration indicate that the point set point is P and the point set point is P'. Rotation of P 'using R to obtain a new position P' _R And calculate P and P' _R The distance between them is taken as the translation M: M=P-P '' _R P-r·p' (6); in the above formula: p'. _R = R·P'；

And S612, constructing a rough registration affine matrix. Combining the rotation matrix and the translation matrix obtained in the step (4) and the step (5), and writing the rotation matrix and the translation matrix into a homogeneous form to obtain a rough registered affine matrix T _Rough ；

T _Rough = (7)；

Specifically, fig. 9 is a flowchart of a fine registration process according to an embodiment of the present application, where the fine registration process includes the following steps:

step S702, collecting a femur distal point. Ligament attachment points A of medial and lateral femoral condyles are marked in advance in model _IN And A _OUT The marking positions are shown in fig. 10. FIG. 10 is a schematic illustration of an attachment point marking of an embodiment of the present application, wherein an operator roughly collects the attachment point on the surface of the patient's skin during surgery to obtain A' _IN And A' _OUT And then calculating the connecting midpoint E of the attachment points and the connecting midpoint E' of the medial and lateral condyle acquisition points in the model respectively.

And S704, collecting the accurate point. Uniformly acquiring n fine registration points in an exposed area of a patient, wherein n is a positive integer, (optionally, n is more than or equal to 20) to form a fine registration point set U _P ={P ₁ …P _n }, wherein P _n Coordinate points are acquired in homogeneous form. Alternatively, the collection points should be evenly distributed, for example, some points should be distributed in the yellow region in fig. 4, and the spatial distance should be at least 3mm. For speed considerations, the number of precision registration points during use is not more than 60, which is only an example and is not limiting of the solution of the application.

Step S706, moving the sampling point. Affine transformation is carried out on the medial and lateral condyle acquisition points, the rough registration acquisition points and the fine registration acquisition points by using a rough registration affine transformation matrix, so that all points are close to the indication model.

Step S708, setting an iteration exit condition. Let the maximum iteration number be beta _max The exit iteration threshold is δ.

Step S710, generating an initial state of multi-chain parallel optimization: and randomly sampling the translation quantity and the rotation quantity on X, Y and Z axes by using standard normal distribution to generate m groups of random rotation matrixes and translation matrixes to form corresponding disturbance affine matrixes.

Let the disturbance matrix be T _Di Then the initial state of each optimization chain is T _i =T _Di U, correspondingly obtain a subchain set U _SC ={ S ₁ …S _m }。

It should be noted that, the number of initial chains and the sampling method are not specified in the alternative embodiment of the present application, and other users can increase or decrease the number of initial chains and the disturbance matrix generation method according to the needs, only the number of initial chains is required to be ensured to be not less than 10. Furthermore, while more initial chains can give more possibilities to the iterative approach, alternative embodiments of the present application do not suggest that the number of initial chains exceeds 50, due to computational rate considerations.

Step S712 optimizes each sub-chain using an ICP algorithm (equivalent to the target algorithm in the above embodiment). Optionally, the moved fine registration points are taken as source data, the indication model is taken as target data, and the current state T in each chain is caused to be _i Setting the maximum iteration step length as N for an initial affine matrix of an ICP algorithm, respectively optimizing each sub-chain, and obtaining an optimized affine matrix group G _T ={ T ₁ …T _m }。

Step S714, constraint is performed using the distal femur point. Specifically, the midpoint E of the connection line between the rough registration indication point A and the attachment point in the indication model is taken as a vector V _A→E And taking A 'and E' obtained by actual acquisition and determining as a vector V _A'→E' And according to G respectively _T Affine transformation is carried out on the translated A 'and E' and a vector group V under each state is obtained _T = [V ¹ _A'→E' …V ^m _A'→E' ]. V is calculated using the method shown in formula 8 _A→E And V is equal to _T The included angle of each vector in the model is obtained to obtain an included angle group Anlgue _T =[θ ₁ …θ _m ] 。

θ _i =arccos() (8)；

Further, one by one comparison of Anlge _T θ in (a) _i From sub-chain set U _SC Middle deleted daughter strand S _i If all sub-chains correspond to theta _i All are larger than 10 degrees, then in U _SC Half of theta is deleted _i Larger sub-chains。

Step S716, merging the sub-chains with similar results. Using G _T The affine matrix in the model is aligned with the fine registration point set U one by one _p Affine transformation is carried out to obtain a moved affine point set U _TP ={U _T1 …U _Tn }. Subsequently, to U _TP U in (B) _Ti One by one comparison is performed, if two affine point subsets U _Ti And U _Tk If the error of all the moved accurate registration points is less than 1mm, the two point sets are considered to be similar point sets, and the sub-chain S can be deleted at the moment _k Leave S _i And U is _TP Fine registration point sets with the same number are eliminated.

Step S718, calculating the minimum error. U is indexed by using KdTrae and other fast indexing methods _TP The remaining fine registration positions in (b) calculate the Root Mean Square Error (RMSE) from the indicated model surface.

RMSE = (9)；

Wherein, in the above formula, d is the distance between each point and the bone surface, and n is the number of points to be calculated. Through the above, the RMSE set U of the residual sub-chain is calculated _RMSE ={R ₁ …R _n Let the sub-chain S with minimum error _min As the optimal sub-chain S of this iteration _i Minimum error delta of this iteration _imin =min（U _RMSE ）。

Step S720, judging whether the condition of ending the iteration is reached. If delta _imin If delta is less than delta, the iteration termination condition is satisfied, so that the optimal registration matrix T of the fine registration is achieved _fine Is the optimal sub-chain S _i Is an optimized affine matrix G _Ti . If the iteration termination condition is not satisfied, continuously judging whether the maximum iteration number upper limit beta is reached _max If the maximum iteration number upper limit beta is reached _max Then still use the current optimal sub-chain S _i Is an optimized affine matrix G _Ti As an optimal registration matrix T _fine 。

If the maximum iteration number upper limit is not reached, a random disturbance is added to the remaining sub-chains according to the method in step S708 to generate new sub-chains, so that the number of sub-chains is increased to m again, and steps S710 to S718 are repeated until the end iteration condition is reached.

Step S722, calculate the registration affine matrix. Because the position and the posture of the point cloud of the fine registration part and the point cloud of the coarse registration part are different in the registration process, the fine registration matrix and the coarse registration matrix cannot be directly combined. At G _Ti Corresponding U _TPi Optionally three points P _T1 P _T2 P _T3 And accurately registering the point set U _p Extracting to obtain corresponding P _U1 P _U2 P _U3 And calculates a registration matrix T using the coarse registration method proposed in the above embodiment _final 。

In summary, by the above embodiments, the registration matrix comprehensively determined by the coarse registration portion and the fine registration portion provides data processing support for the surface hip replacement surgery, solves the challenging problems of small exposure area in the surgery, high symmetry of the femoral head portion, and the like, and does not require extremely high accuracy in the above embodiments. And larger errors are allowed to exist between the coarse registration result and the real skeleton in the rotation component and the translation component, so that the preliminary requirement of the registration process is greatly reduced, and the applicability of the method is improved. Furthermore, a parallel multi-chain optimization strategy is adopted in the fine registration process, so that the solution space is effectively explored, the registration result has the characteristic of global optimization, high-precision operation positioning is provided, in the use process, through femur distal end constraint, preoperative planning and intraoperative real-time data can be combined, larger rotation errors caused by high symmetry of femoral heads are avoided, and the accuracy and safety of operation are improved.

It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the embodiments of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the embodiments of the present application.

According to still another aspect of the embodiments of the present application, there is further provided a registration apparatus, which is used to implement the registration method provided in the foregoing embodiments, and will not be described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 11 is a block diagram of a registration apparatus according to an embodiment of the present application, as shown in fig. 11, including:

a transformation unit 101, configured to perform affine transformation on a distal point on a bone object, a plurality of accurate registration points on the bone object, and an acquisition point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix, so as to obtain a transformation result;

an optimizing unit 103, configured to optimize, in a case where a plurality of sub-chains corresponding to the transformation result are determined, the plurality of sub-chains through a target algorithm, so as to obtain a plurality of optimized results;

an obtaining unit 105, configured to determine a target result that meets a preset iteration exit condition from the plurality of optimization results, and obtain a second matrix corresponding to the target result;

A first determining unit 107, configured to determine a registration matrix corresponding to the bone object based on the first matrix and the second matrix, so as to register a target operation performed on the bone object using the registration matrix.

According to the embodiment provided by the application, affine transformation is carried out on the far end points on the bone object, the plurality of fine registration points on the bone object and the acquisition point set corresponding to the rough registration indication points on the indication model on the bone object by using the first matrix, so that a transformation result is obtained; under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results; determining a target result meeting a preset iteration exit condition from a plurality of optimization results, and acquiring a second matrix corresponding to the target result; a registration matrix corresponding to the bone object is determined based on the first matrix and the second matrix to register a target operation performed on the bone object using the registration matrix. Therefore, in the registration matrix corresponding to the bone object formed by the first matrix and the second matrix, the problems that high-precision registration cannot be realized in the registration in the related art, the preliminary requirement in the registration process is high, and the global optimality of the registration result is poor can be solved, and the technical effect of high-precision registration and registration of the bone object is achieved.

In an alternative embodiment, the above-mentioned registration device further comprises: a second determining unit, configured to obtain, using a first matrix, a coarse registration indication point set corresponding to a coarse registration indication point selected on an indication model and used for initially positioning a bone object, before affine transformation is performed on a distal point on the bone object, a plurality of precise registration points on the bone object, and an acquisition point set corresponding to a coarse registration indication point on the bone object on the indication model; indicating the bone probe to acquire position information on the bone object through the rough registration indicating point set; determining an acquisition point set corresponding to the rough registration indication points on the indication model on the bone object according to the acquisition result; and determining a first matrix corresponding to the bone object based on the acquisition point set and the rough registration indication point set.

In an alternative embodiment, the above-mentioned registration device further comprises: the sorting unit is used for determining distance features among different coarse registration indicating points in the coarse registration indicating point set before determining a first matrix corresponding to the bone object based on the acquisition point set and the coarse registration indicating point set, and generating definition information of the coarse registration indicating point set according to the distance features; calculating Euclidean distances among different acquisition points in the acquisition point set to obtain a plurality of Euclidean distances; and setting target distance characteristics for two acquisition points corresponding to each Euclidean distance in the multiple Euclidean distances by using the definition information so as to sort the different acquisition points by using the target distance characteristics.

In an optional embodiment, the second determining unit is further configured to determine a first unit vector between different coarse registration indicating points in the coarse registration indicating point set to obtain a first vector group, and determine a second unit vector between different acquisition points in the acquisition point set to obtain a second vector group; calculating the first vector group and the second vector group by using a preset covariance matrix to generate a target covariance matrix; singular value decomposition is carried out on the target covariance matrix, a rotation matrix corresponding to the target covariance matrix is determined, and a translation matrix corresponding to the coarse registration indication point set is determined based on the rotation matrix; and determining a combined matrix of the rotation matrix and the translation matrix as a first matrix corresponding to the bone object.

In an optional embodiment, the second determining unit is further configured to calculate a first midpoint corresponding to between different coarse registration indicating points in the coarse registration indicating point set, and a second midpoint corresponding to between different acquisition points in the acquisition point set; rotating the second midpoint by using the rotation matrix to obtain a target point; and determining the translation amount between the target point and the first midpoint to obtain a translation matrix corresponding to the acquisition point set.

In an alternative embodiment, the above-mentioned registration device further comprises: the vector unit is used for optimizing the multiple sub-chains through a target algorithm, and selecting a first indication point from the rough registration indication points on the indication model after obtaining multiple optimization results; determining a third vector corresponding to a connecting line of the first indication point and the second midpoint, and obtaining a fourth vector of a first acquisition point corresponding to the first indication point and the first midpoint, wherein the first midpoint is used for indicating a midpoint between at least two actual points acquired in a skin area corresponding to the bone object, the second midpoint is used for indicating a midpoint between at least two attachment points marked in advance in the indication model, and the at least two actual points and the at least two attachment points have a corresponding relation; obtaining a plurality of optimization matrixes corresponding to the plurality of optimization results, and carrying out affine transformation on the fourth vector by using the plurality of optimization matrixes to obtain a state vector group of the fourth vector; and calculating an included angle between the third vector and each state vector in the state vector group.

In an optional embodiment, the vector unit is further configured to delete, after calculating an included angle between the third vector and each state vector in the state vector group, a first sub-chain corresponding to a current included angle from the multiple sub-chains if the included angle is greater than a preset included angle; and under the condition that all the included angles are larger than a preset included angle, sequencing all the included angles, and deleting the second sub-chain corresponding to half of larger included angles in all the included angles.

In an alternative embodiment, the above-mentioned registration device further comprises: the merging unit is used for carrying out affine transformation on the plurality of fine registration points by using a plurality of optimization matrixes corresponding to the plurality of optimization results before optimizing the plurality of sub-chains through a target algorithm to obtain the plurality of optimization results under the condition that the plurality of sub-chains corresponding to the transformation results are determined, so as to obtain a moving point set corresponding to the plurality of fine registration points; and calculating errors among all the moving points in the moving point set, and merging third sub-chains associated with the target fine registration points corresponding to at least two moving points with the errors smaller than the preset errors.

In an optional embodiment, the obtaining unit is further configured to determine remaining fine registration positions corresponding to the completed multiple sub-chains, calculate a root mean square error between the remaining fine registration positions and the surface of the indication model, and obtain an error set; determining a minimum error from the error set, and acquiring a target sub-chain corresponding to the minimum error and determining iteration times corresponding to a target optimization result of the target sub-chain; and under the condition that the iteration times and the minimum error meet the preset iteration exit condition, determining the target sub-chain as the target result.

It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

According to a further aspect of embodiments of the present application, there is also provided a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.

According to one aspect of the present application, there is provided a computer program product comprising a computer program/instruction containing program code for executing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. When executed by the central processor 801, the computer program performs various functions provided by embodiments of the present application. The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

Fig. 12 schematically shows a block diagram of a computer system of an electronic device for implementing an embodiment of the application. As shown in fig. 12, the computer system 800 includes a central processing unit 801 (Central Processing Unit, CPU) which can execute various appropriate actions and processes according to a program stored in a Read-Only Memory 802 (ROM) or a program loaded from a storage section 808 into a random access Memory 803 (Random Access Memory, RAM). In the random access memory 803, various programs and data required for system operation are also stored. The central processing unit 801, the read only memory 802, and the random access memory 803 are connected to each other through a bus 804. An Input/Output interface 805 (i.e., an I/O interface) is also connected to the bus 804.

The following components are connected to the input/output interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and the like, and a speaker, and the like; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a local area network card, modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the input/output interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

In particular, the processes described in the various method flowcharts may be implemented as computer software programs according to embodiments of the application. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The computer programs, when executed by the central processor 801, perform the various functions defined in the system of the present application.

It should be noted that, the computer system 800 of the electronic device shown in fig. 12 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

According to a further aspect of embodiments of the present application there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

In an exemplary embodiment, the electronic device may further include a transmission device and an input/output device, where the transmission device is connected to the input/output resource pool, and the input/output device is connected to the input/output resource pool.

Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.

It will be appreciated by those skilled in the art that the modules or steps of the embodiments of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described, or they may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps in them may be fabricated into a single integrated circuit module. Thus, embodiments of the application are not limited to any specific combination of hardware and software.

The above is only a preferred embodiment of the present application and is not intended to limit the embodiment of the present application, and various modifications and variations can be made to the embodiment of the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A method of registration, comprising:

affine transformation is carried out on a far-end point on a bone object, a plurality of accurate registration points on the bone object and an acquisition point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result;

under the condition that a plurality of sub-chains corresponding to the transformation result are determined, optimizing the plurality of sub-chains through a target algorithm to obtain a plurality of optimized results, wherein the plurality of sub-chains are determined by adding disturbance matrixes into a plurality of initial chains existing in the transformation result;

determining a target result meeting a preset iteration exit condition from the plurality of optimization results, and acquiring a second matrix corresponding to the target result;

determining a registration matrix corresponding to the bone object based on the first matrix and the second matrix, so as to register target operations performed on the bone object by using the registration matrix;

wherein, the optimizing the multiple sub-chains through the target algorithm, after obtaining multiple optimizing results, the method further comprises:

selecting a first indication point from the coarse registration indication points on the indication model;

Determining a third vector corresponding to a connecting line of the first indication point and the second midpoint, and obtaining a fourth vector of a first acquisition point corresponding to the first indication point and the first midpoint, wherein the first midpoint is used for indicating a midpoint between at least two actual points acquired in a skin area corresponding to the bone object, the second midpoint is used for indicating a midpoint between at least two attachment points marked in advance in the indication model, and the at least two actual points and the at least two attachment points have a corresponding relation;

obtaining a plurality of optimization matrixes corresponding to the plurality of optimization results, and carrying out affine transformation on the fourth vector by using the plurality of optimization matrixes to obtain a state vector group of the fourth vector;

calculating an included angle between the third vector and each state vector in the state vector group;

deleting a first sub-chain corresponding to the current included angle from the plurality of sub-chains under the condition that the included angle is larger than a preset included angle;

and under the condition that all the included angles are larger than a preset included angle, sequencing all the included angles, and deleting the second sub-chain corresponding to one half of the included angles.

2. The method of claim 1, wherein prior to affine transforming the distal point on the bone object, the plurality of precision registration points on the bone object, the collection point set on the bone object corresponding to the coarse registration indication points on the indication model using the first matrix, the method further comprises:

Acquiring a coarse registration indication point set corresponding to the coarse registration indication points selected from the indication model and used for initially positioning the bone object;

indicating the bone probe to acquire position information on the bone object through the rough registration indicating point set;

determining an acquisition point set corresponding to the rough registration indication points on the indication model on the bone object according to the acquisition result;

and determining a first matrix corresponding to the bone object based on the acquisition point set and the rough registration indication point set.

3. The method of claim 2, wherein prior to determining the first matrix corresponding to the bone object based on the collection of points and the coarse registration indication point set, the method further comprises:

determining distance features among different coarse registration indicating points in the coarse registration indicating point set, and generating definition information of the coarse registration indicating point set according to the distance features;

calculating Euclidean distances among different acquisition points in the acquisition point set to obtain a plurality of Euclidean distances;

and setting target distance characteristics for two acquisition points corresponding to each Euclidean distance in the multiple Euclidean distances by using the definition information so as to sort the different acquisition points by using the target distance characteristics.

4. The method of claim 2, wherein determining a first matrix corresponding to the bone object based on the collection set of points and the coarse registration indication set of points comprises:

determining first unit vectors among different coarse registration indicating points in the coarse registration indicating point set to obtain a first vector group, and determining second unit vectors among different acquisition points in the acquisition point set to obtain a second vector group;

calculating the first vector group and the second vector group by using a preset covariance matrix to generate a target covariance matrix;

singular value decomposition is carried out on the target covariance matrix, a rotation matrix corresponding to the target covariance matrix is determined, and a translation matrix corresponding to the coarse registration indication point set is determined based on the rotation matrix;

and determining a combined matrix of the rotation matrix and the translation matrix as a first matrix corresponding to the bone object.

5. The method of claim 4, wherein determining a translation matrix corresponding to the set of coarse registration indication points based on the rotation matrix comprises:

calculating first midpoints corresponding to different coarse registration indicating points in the coarse registration indicating point set and second midpoints corresponding to different acquisition points in the acquisition point set;

Rotating the second midpoint by using the rotation matrix to obtain a target point;

and determining the translation amount between the target point and the first midpoint to obtain a translation matrix corresponding to the acquisition point set.

6. The method according to claim 1, wherein in the case of determining a plurality of sub-chains corresponding to the transformation result, the method further comprises, before optimizing the plurality of sub-chains by a target algorithm to obtain a plurality of optimization results:

carrying out affine transformation on the plurality of fine registration points by using a plurality of optimization matrixes corresponding to the plurality of optimization results to obtain a moving point set corresponding to the plurality of fine registration points;

and calculating errors among all the moving points in the moving point set, and merging third sub-chains associated with the target fine registration points corresponding to at least two moving points with the errors smaller than the preset errors.

7. The method of claim 1, wherein determining a target result from the plurality of optimization results that meets a preset iteration exit condition comprises:

determining residual fine registration positions corresponding to the plurality of sub-chains after completion, and calculating root mean square errors of the residual fine registration positions and the surface of the indication model to obtain an error set;

Determining a minimum error from the error set, and acquiring a target sub-chain corresponding to the minimum error and determining iteration times corresponding to a target optimization result of the target sub-chain;

and under the condition that the iteration times and the minimum error meet the preset iteration exit condition, determining the target sub-chain as the target result.

8. A registration device, comprising:

the transformation unit is used for carrying out affine transformation on a far-end point on a bone object, a plurality of accurate registration points on the bone object and an acquisition point set corresponding to a rough registration indication point on an indication model on the bone object by using a first matrix to obtain a transformation result;

the optimization unit is used for optimizing the multiple sub-chains through a target algorithm under the condition that the multiple sub-chains corresponding to the transformation result are determined, so that multiple optimization results are obtained, wherein the multiple sub-chains are determined by adding disturbance matrixes into multiple initial chains existing in the transformation result;

the acquisition unit is used for determining a target result meeting a preset iteration exit condition from the plurality of optimization results and acquiring a second matrix corresponding to the target result;

A first determining unit, configured to determine a registration matrix corresponding to the bone object based on the first matrix and the second matrix, so as to register a target operation performed on the bone object using the registration matrix;

the apparatus further comprises: the vector unit is used for optimizing the multiple sub-chains through a target algorithm, and selecting a first indication point from the rough registration indication points on the indication model after obtaining multiple optimization results; determining a third vector corresponding to a connecting line of the first indication point and the second midpoint, and obtaining a fourth vector of a first acquisition point corresponding to the first indication point and the first midpoint, wherein the first midpoint is used for indicating a midpoint between at least two actual points acquired in a skin area corresponding to the bone object, the second midpoint is used for indicating a midpoint between at least two attachment points marked in advance in the indication model, and the at least two actual points and the at least two attachment points have a corresponding relation; obtaining a plurality of optimization matrixes corresponding to the plurality of optimization results, and carrying out affine transformation on the fourth vector by using the plurality of optimization matrixes to obtain a state vector group of the fourth vector; calculating an included angle between the third vector and each state vector in the state vector group;

The vector unit is further configured to delete a first sub-chain corresponding to a current included angle from the multiple sub-chains when the included angle is greater than a preset included angle after calculating the included angle between the third vector and each state vector in the state vector group; and under the condition that all the included angles are larger than a preset included angle, sequencing all the included angles, and deleting the second sub-chain corresponding to half of larger included angles in all the included angles.

9. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, wherein the computer program, when being executed by a processor, implements the steps of the method according to any of the claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.