Surgical registration method, apparatus, and surgical robotic system

Abstract

The application relates to a surgical registration method, device and surgical robot system, comprising the following steps: acquiring a three-dimensional image of an object to be registered and a registration point set planned in an image space of the three-dimensional image; acquiring physical space coordinates of a plurality of marker point sets of the object to be registered; wherein the marker point set is a point set in a preset region of each registration point; determining the physical space coordinates corresponding to each registration point according to the physical space coordinates of the marker point set corresponding to each registration point; and generating a registration matrix according to the transformation relationship between the image space coordinates of the registration point set on the three-dimensional image and the physical space coordinates of the registration point set. According to the three-dimensional image of the object to be registered, the registration point is obtained, the marker point set is planned in the preset range of the registration point, and the physical space coordinates of the registration point are determined according to the physical space coordinates of the marker point set, so that the corresponding coarse registration point on the actual bone is not needed to be found by using a probe, and the registration efficiency of the surgical robot system is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of surgical robots, in particular to a surgical registration and registration method, device and surgical robot system. BACKGROUND

[0002] Surgical robot systems are increasingly widely used in orthopedic surgery. The registration and registration process is one of the key steps for the surgical robot system to perform surgery by establishing the relationship between the image space and the actual entity object. Registration and registration is usually divided into two steps: coarse registration and fine registration. Coarse registration is to provide an initial value for fine registration to avoid falling into local minimum solution. The accuracy and efficiency of registration and registration are two important aspects in practical application. The level of accuracy directly affects the surgical effect. The improvement of efficiency can reduce the exposure time during the operation, reduce the risk of infection, and improve the experience of doctors.

[0003] In the prior art, a coarse registration matrix is generated by finding at least three sets of corresponding points on the image data and the actual entity object. Specifically, according to the prompt of the navigation interface, the corresponding coarse registration points are found on the actual bone by using the probe. These coarse registration points are usually selected as some feature points with obvious marks, but for hip replacement surgery, the acetabular fossa is relatively deep, and it takes a lot of time to find the corresponding coarse registration points, which seriously affects the registration efficiency.

[0004] In view of the low registration efficiency of the surgical robot system in the prior art, there is currently no effective solution to this problem. SUMMARY

[0005] Therefore, it is necessary to provide a surgical registration and registration method, device and surgical robot system to solve the problem of low registration efficiency of the surgical robot system in the related art.

[0006] In a first aspect, the present application provides a surgical registration and registration method, which comprises the following steps:

[0007] Obtaining a three-dimensional image of an object to be registered and a set of registration points planned in the image space of the three-dimensional image;

[0008] Obtaining the physical space coordinates of a plurality of marker point sets of the object to be registered; wherein the marker point set is a point set within a predetermined region of each registration point;

[0009] Determining the physical space coordinates corresponding to each registration point according to the physical space coordinates of the marker point set corresponding to each registration point;

[0010] Generating a registration matrix according to the transformation relationship between the image space coordinates of the registration point set on the three-dimensional image and the physical space coordinates of the registration point set.

[0011] In one of the embodiments, each of the registration points in the planned registration point set is determined according to a feature point of the object to be registered.

[0012] In one of the embodiments, the set of marker points in each of the registration points is a set of points in a preset region of the registration point, including:

[0013] The preset region is determined according to a structure feature of the object to be registered corresponding to a preset range of the registration point.

[0014] In one of the embodiments, the registration point is located at a center position or a centroid position of the preset region; and a plurality of marker points corresponding to the registration point are non-randomly distributed in the preset region.

[0015] In one of the embodiments, the plurality of marker points are non-randomly distributed in the preset region, including:

[0016] The plurality of marker points form a set of marker points corresponding to the registration point; and the plurality of marker points are distributed in the preset region; the set of marker points can be fitted into a geometric figure or the plurality of marker points in the set of marker points are distributed in an array.

[0017] In one of the embodiments, when the preset region is circular or approximately circular, the geometric figure is at least one of a ring shape and a cross shape.

[0018] When the preset region is arc-shaped or strip-shaped, the geometric figure is at least one of an arc shape and a straight line shape.

[0019] In one of the embodiments, after a registration matrix is generated according to a transformation relationship between image space coordinates of the set of registration points on the three-dimensional image and physical space coordinates of the set of registration points, the method further includes:

[0020] The registration matrix is verified to obtain a verification result.

[0021] In one of the embodiments, the verification of the registration matrix to obtain the verification result includes the following steps:

[0022] An image space coordinate of a verification point planned on the three-dimensional image of the object to be registered is obtained;

[0023] A theoretical physical space coordinate corresponding to the image space coordinate of the verification point is calculated according to the registration matrix;

[0024] An actual physical space coordinate of the verification point planned on the three-dimensional image of the object to be registered is obtained;

[0025] determine a deviation between the theoretical physical space coordinate of the verification point and the actual physical space coordinate of the verification point, and compare the deviation with a preset threshold value;

[0026] If the deviation is less than the preset threshold value, the verification passes; if the deviation is not less than the preset threshold value, the verification fails.

[0027] In one of the embodiments, the verification of the registration matrix to obtain a verification result comprises the following steps:

[0028] obtain a physical space coordinate of a verification point planned on the three-dimensional image of the object to be registered;

[0029] calculate an actual image space coordinate corresponding to the physical space coordinate of the verification point according to the registration matrix;

[0030] obtain an image space coordinate of a verification point planned on the three-dimensional image of the object to be registered;

[0031] determine a deviation between the actual image space coordinate of the verification point and the image space coordinate of the verification point, and compare the deviation with a preset threshold value;

[0032] If the deviation is less than the preset threshold value, the verification passes; if the deviation is not less than the preset threshold value, the verification fails.

[0033] In one of the embodiments, the method further comprises:

[0034] If the verification result is a failure, the verification point is taken as a supplementary marker point, and the marker point set is updated;

[0035] update the physical space coordinate corresponding to each registration point according to the updated marker point set;

[0036] generate a coarse registration matrix according to the transformation relationship between the image space coordinate of the registration point set on the three-dimensional image and the physical space coordinate of the registration point set.

[0037] re-generate a fine registration matrix according to the initial value provided by the coarse registration matrix, the physical space coordinate of the verification point, and the physical space coordinate of the marker point.

[0038] In a second aspect, the application further provides a registration device of a surgical robot system, the device comprising: a first obtaining module, a second obtaining module, a determining module, and a generating module;

[0039] The first obtaining module is configured to obtain a three-dimensional image of an object to be registered and a registration point set planned in the image space of the three-dimensional image.

[0040] The second acquisition module is configured to acquire physical space coordinates of a plurality of marker point sets of the object to be registered, wherein the marker point set is a point set in a preset region of each registration point;

[0041] The determination module is configured to determine the physical space coordinates of each registration point according to the physical space coordinates of the marker point set corresponding to each registration point.

[0042] The generation module is configured to generate a registration matrix according to the transformation relationship between the image space coordinates of the registration point set on the three-dimensional image and the physical space coordinates of the registration point set.

[0043] In a third aspect, the present application further provides a surgical robot system, which comprises an image display system and a control system.

[0044] The image display system is configured to display and update the three-dimensional image of the physical object in real time.

[0045] The control system is configured to implement the steps of the method of the first aspect.

[0046] The registration method, device and surgical robot system of the surgical robot system, according to the three-dimensional image of the object to be registered, obtain registration points, plan a marker point set in a preset range of the registration points, and determine the physical space coordinates of the registration points according to the physical space coordinates of the marker point set, without the need to find corresponding coarse registration points on the actual bone by using a probe, thereby effectively improving the registration efficiency of the surgical robot system. BRIEF DESCRIPTION OF DRAWINGS

[0047] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of the present application, and the illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute improper limitations on the present application. In the drawings:

[0048] Figure 1 A hardware structure block diagram of a terminal of a surgical registration method of an embodiment;

[0049] Figure 2 A flowchart of a surgical registration method of an embodiment;

[0050] Figure 3 A flowchart of an orthopedic surgical registration method of an embodiment;

[0051] Figure 4 A schematic diagram of a registration probe collecting marker points in a ring shape scattered on the inner wall of a socket of an embodiment;

[0052] Figure 5Fig. 2 is a schematic diagram of a marker point distribution in a cross shape for a probe registration in an embodiment;

[0053] Figure 6 Fig. 3 is a schematic diagram of a marker point distribution in an arc shape for a probe registration in an embodiment;

[0054] Figure 7 Fig. 4 is a schematic diagram of a verification point in an embodiment;

[0055] Figure 8 Fig. 5 is a structural block diagram of a registration device of a surgical robot system in an embodiment;

[0056] Figure 9 Fig. 6 is a structural block diagram of a surgical robot system in an embodiment;

[0057] Figure 10 Fig. 7 is an internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0058] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and explained below in conjunction with the accompanying drawings and embodiments.

[0059] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the general meaning understood by a person with ordinary skill in the art to which the present application belongs. In the present application, the terms "one", "a", "an", "the", "these", and similar words do not represent a quantitative limitation, but can be singular or plural. In the present application, the terms "include", "contain", "have" and any variants thereof are intended to cover non-exclusive inclusion; for example, a process, method and system, product or device containing a series of steps or modules (units) are not limited to the listed steps or modules (units), but can include steps or modules (units) not listed, or can include other steps or modules (units) inherent to the process, method, product or device. In the present application, the terms "connected", "connected", "coupled" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. In the present application, "multiple" means two or more. The association between the associated objects is described by the term "and / or", which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. In general, the character " / " represents an "or" relationship between the associated objects. In the present application, the terms "first", "second", "third" and the like are only used to distinguish similar objects, and do not represent a specific order of the objects.

[0060] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of a terminal for a surgical registration and registration method according to an embodiment of this application. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0061] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the surgical registration and alignment method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the aforementioned method. The memory 104 may include high-speed random access memory and 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 instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0062] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0063] In one embodiment, such as Figure 2 As shown, a surgical registration method is provided, which can be applied to... Figure 1The method is described by taking a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is realized through interaction of the terminal and the server.

[0064] The method includes the following steps in this embodiment:

[0065] In step S201, a three-dimensional image of an object to be registered and a set of registration points planned in an image space of the three-dimensional image are obtained.

[0066] The three-dimensional image is obtained by scanning the object to be registered by a three-dimensional scanning device. The registration points are obtained according to the physiological structure of the object to be registered in the image space. The set of registration points is a collection of all registration points in the image space of the three-dimensional image. For example, the three-dimensional image of the object to be registered is obtained by scanning the object to be registered by a three-dimensional scanning device. At least one registration point is planned according to the structural features of the three-dimensional image, and a set of registration points is obtained.

[0067] In step S202, physical space coordinates of a plurality of sets of marker points of the object to be registered are obtained. Each set of marker points is a set of points in a preset region of each registration point.

[0068] The physical space coordinates are the coordinates of the set of marker points in a physical space coordinate system. The preset region is a region containing the registration point, and the preset region and the registration point are one-to-one corresponding. The marker point is located in the preset region and does not coincide with the registration point. Each set of marker points and the registration point is one-to-one corresponding, and there is a known positional relationship between each marker point in the set of marker points and the corresponding registration point.

[0069] For example, according to the position of a registration point in a set of registration points, a preset region containing the registration point is planned in the image space of the three-dimensional image. In the preset region, a plurality of marker points are planned around the registration point to obtain a set of marker points corresponding to the registration point and the physical space coordinates of the set of marker points. Subsequently, according to the position of another registration point in the set of registration points, a set of marker points of the other registration point and the physical space coordinates of the set of marker points are obtained. The above steps are repeated until the set of marker points of each registration point in the set of registration points is obtained.

[0070] In step S203, the physical space coordinates of each registration point are determined according to the physical space coordinates of the set of marker points corresponding to each registration point.

[0071] Because there is a known positional relationship between the marker points and the registration points, the physical space coordinates of the registration points can be determined according to the physical space coordinates of the plurality of marker points in the marker point set. Exemplarily, the registration point planned in step S201 is a first registration point; and the corresponding planned registration point set is a first registration point set. In step S203, the registration point determined according to the marker point set is a second registration point, and the corresponding registration point set composed of a plurality of registration points is a second registration point set.

[0072] In step S204, a registration matrix is generated according to the transformation relationship between the image space coordinates of the registration point set on the three-dimensional image and the physical space coordinates of the registration point set.

[0073] The image space coordinates are a coordinate system in a three-dimensional image space. According to the projection relationship between the object space and the three-dimensional image space, the transformation relationship can be obtained. Optionally, according to the transformation relationship, the physical space coordinates of the registration point set on the three-dimensional image are converted into the image space coordinate system to obtain the image space coordinates of the registration point set on the three-dimensional image. The registration matrix is obtained according to the image space coordinates of the registration point set on the three-dimensional image.

[0074] In the surgical registration method of the embodiment, the registration point is obtained according to the three-dimensional image of the object to be registered, the marker point set is planned in the preset range of the registration point, and the physical space coordinates of the registration point are determined according to the physical space coordinates of the marker point set. It is not necessary to find the corresponding coarse registration point on the actual bone by using a probe, and the registration efficiency of the surgical robot system is effectively improved.

[0075] In one of the embodiments, each registration point in the planned registration point set is determined according to a feature point of the object to be registered. The feature point refers to a feature point of a physiological structure of the object to be registered. Taking the acetabulum of the human body as an example, the feature points of the object to be registered can be the inner wall of the acetabular fossa and the horse's hoof. Exemplarily, the feature points of the physiological structure of the object to be registered are determined according to the three-dimensional image of the object to be registered. The registration points corresponding to the feature points are planned in the image space of the three-dimensional image according to the plurality of feature points of the object to be registered, and the registration point set is composed of the plurality of planned registration points. Optionally, a registration point marker pattern can be generated in the image space of the three-dimensional image to indicate the position of the registration point to the user.

[0076] In one of the embodiments, the marker point set is a point set in the preset area of each registration point, including: determining the preset area according to the structure features of the corresponding registration point on the object to be registered. The structure features include the characteristics of the physiological structure to which the registration point belongs, such as protruding, concave and other features. The preset area is generated around the registration point according to the structure features. Optionally, according to the preset area, an identifier for indicating the position of the preset area is generated in the image space of the three-dimensional image.

[0077] In one of the embodiments, the registration point is located at the center or centroid of the preset area; and the plurality of mark points corresponding to the registration point are non-randomly scattered in the preset area. There is a correlation between the scattering position of the mark points and the position of the registration point. By non-randomly scattering the mark points in the preset area, the positional relationship between the mark points and the registration point can be determined, so that it is possible to calibrate the registration point according to the collection position of the mark points.

[0078] In one of the embodiments, the plurality of mark points are non-randomly scattered in the preset area, including: the plurality of mark points form a mark point set corresponding to the registration point; and the plurality of mark points are scattered in the preset area; the mark point set can be fitted into a geometric figure, or the plurality of mark points of the mark point set are scattered in an array. The geometric figure includes a ring, an arc, a circle, and a superposition of a plurality of geometric figures, etc. If the plurality of mark points are scattered in the preset area in the form of a geometric figure, the positional relationship between the mark points and the registration point can be obtained according to the shape characteristics of the geometric figure. If the plurality of mark points are scattered in the preset area in the form of an array, the positional relationship between the mark points and the registration point can be obtained according to the array characteristics. The plurality of mark points are scattered in the preset area and arranged in a specific arrangement to form a specific geometric figure. For example, for a preset area in the shape of a circle, the plurality of mark points can be scattered in the form of a ring (the plurality of mark points are uniformly arranged along the circumference) or form a regular polygon (each mark point is a vertex of the regular polygon).

[0079] In one of the embodiments, when the preset area is a circle or substantially a circle, the geometric figure is at least one of a ring and a cross; and when the preset area is an arc or a strip, the geometric figure is at least one of an arc and a straight line.

[0080] According to the shape feature of the preset region, a shape formed by the plurality of marker points in the preset region is planned. Optionally, in the case where the preset region is circular or approximately circular: when the shape formed by the marker points corresponding to the registration points is circular, the centroid coordinates of the circle are calculated based on the physical space coordinates of the marker points corresponding to the registration points, and the centroid coordinates are taken as the physical space coordinates of the corresponding registration points; when the shape formed by the marker points corresponding to the registration points is cross-shaped, the intersection point is taken as the physical space coordinates of the registration points; and the shape of the marker points corresponding to the registration points can also be set as a combination of the circular shape and the cross-shaped shape. It can be understood that, since the shape of the preset region is not always regular circular, the approximately circular shape includes elliptical shape, heart-shaped, etc., and the specific selection of the shape is set according to the shape feature of the physiological structure of the preset region. The cross-shaped shape includes cross-shaped (X-shaped), Y-shaped, star-shaped (*-shaped), and rice-shaped, etc. In the cross-shaped shape, at least one marker point is at the central intersection, and a plurality of marker points are respectively at the end of each branch. For example, in the cross-shaped shape, at least five marker points are included, at least one of which is at the intersection, and the remaining at least four marker points are respectively at the end of the four branches; in addition, at least one marker point can also be planned on the path of each branch.

[0081] In the case where the preset region is arc-shaped or long-strip-shaped: when the shape of the marker points corresponding to the registration points is arc-shaped, the center coordinates of the arc line fitted based on the physical space coordinates of the marker points corresponding to the registration points are taken as the physical space coordinates of the corresponding registration points; when the shape formed by the marker points corresponding to the registration points is straight line-shaped, the center coordinates of the line segment are taken as the physical space coordinates of the corresponding registration points; and the combination of the arc-shaped shape and the straight line-shaped shape can also be set.

[0082] In one of the embodiments, after the registration matrix is generated according to the transformation relationship between the image space coordinates of the registration point set on the three-dimensional image and the physical space coordinates of the registration point set, the method further includes: verifying the registration matrix to obtain a verification result.

[0083] The verification of the registration matrix includes: judging whether the relationship between the three-dimensional image space position and the physical space position of at least one verification point in the object to be registered conforms to the position relationship indicated by the registration matrix. The verification point coordinates can be planned on the three-dimensional image, and the verification points can be collected in the actual physical space to judge whether the planned coordinates and the collected coordinates correspond. Alternatively, the verification point coordinates can be planned in the actual physical space, and the verification points can be collected in the actual image space to judge whether the planned coordinates and the collected coordinates correspond.

[0084] In one of the embodiments, the method for checking the registration matrix to obtain a checking result comprises the following steps: obtaining image space coordinates of a verification point planned on a three-dimensional image of an object to be registered; calculating theoretical physical space coordinates corresponding to the image space coordinates of the verification point according to the registration matrix; obtaining actual physical space coordinates of the verification point planned on the three-dimensional image of the object to be registered; determining a deviation between the theoretical physical space coordinates of the verification point and the actual physical space coordinates of the verification point and comparing the deviation with a preset threshold; if the deviation is less than the preset threshold, the checking passes; and if the deviation is not less than the preset threshold, the checking fails.

[0085] In the formula, the image space coordinates are coordinates planned on the three-dimensional image. The theoretical physical space coordinates are coordinates obtained by converting the image space coordinates to the physical space according to the registration matrix. The actual physical space coordinates are coordinates obtained by collecting the verification point according to the image space coordinates.

[0086] Optionally, the obtaining of the actual physical space coordinates comprises: determining whether a position where the probe is poked on the entity object of the object to be registered corresponds to a position of the mark point on the three-dimensional image based on the displayed three-dimensional image. If yes, the actual physical space coordinates are located according to the position where the probe is poked.

[0087] For example, at least one verification point is planned on the three-dimensional image to obtain the planned image space coordinates. The image space coordinates are converted to the physical space according to the registration matrix to obtain the theoretical physical space coordinates. The probe is controlled to collect the mark point according to the image space coordinates, and the actual physical space coordinates are located when the position where the probe is poked on the entity object of the object to be registered corresponds to the position of the mark point on the three-dimensional image. The deviation value is calculated according to the actual physical space coordinates and the theoretical physical space coordinates.

[0088] In one of the embodiments, the method for checking the registration matrix to obtain a checking result comprises the following steps: obtaining image space coordinates of a verification point planned on a three-dimensional image of an object to be registered; calculating theoretical physical space coordinates corresponding to the image space coordinates of the verification point according to the registration matrix; obtaining actual physical space coordinates of the verification point planned on the three-dimensional image of the object to be registered; determining a deviation between the theoretical physical space coordinates of the verification point and the actual physical space coordinates of the verification point and comparing the deviation with a preset threshold; if the deviation is less than the preset threshold, the checking passes; and if the deviation is not less than the preset threshold, the checking fails.

[0089] In the formula, the physical space coordinates are coordinates of the verification point planned in the physical space. The actual image space coordinates are coordinates obtained by converting the physical space coordinates to the image space according to the registration matrix. The image space coordinates of the verification point are image space coordinates located and obtained when the verification point is collected according to the physical space coordinates.

[0090] Exemplarily, at least one verification point is planned in the physical space, and a planned physical space coordinate is obtained. The physical space coordinate is converted into the image space according to the registration matrix, and an actual image space coordinate is obtained. The probe is controlled to collect the marker point, and when the position of the probe needle tip corresponds to the physical space coordinate, a collected image space coordinate is located. A deviation value is calculated according to the actual image space coordinate and the image space coordinate, and the deviation value is compared with a preset threshold value.

[0091] In one of the embodiments, the method further comprises: if the verification result is not passed, taking the verification point as a supplementary marker point and updating the marker point set; updating the physical space coordinate corresponding to each registration point according to the updated marker point set; generating a coarse registration matrix according to the transformation relationship between the image space coordinate of the registration point set on the three-dimensional image and the physical space coordinate of the registration point set; and regenerating a fine registration matrix according to the initial value provided by the coarse registration matrix, the physical space coordinate of the verification point and the physical space coordinate of the marker point. The verification point is used to verify whether the marker point is accurate and is obtained by collection. A new marker point set and a corresponding new registration matrix are obtained according to the verification point. If the verification result of the new registration matrix is passed, the new registration matrix is taken as the coarse registration matrix. On the basis of the coarse registration matrix, the fine registration matrix is iteratively obtained according to the physical space coordinate of the verification point and the physical space coordinate of the marker point according to the registration algorithm. Optionally, the registration algorithm can be an ICP registration algorithm or other algorithms, which are not limited herein. If the verification result of the new registration matrix is not passed, the registration matrix is updated according to the new verification point until the updated registration matrix passes the verification.

[0092] In one of the embodiments, as shown in Figure 3 , a flowchart of an orthopedic surgery registration and registration method is provided. As shown in Figure 3 , the method comprises the following steps:

[0093] Step S301, place the patient in a planned position, implant a registration array and a check screw. The patient can be taken as a registration object, or a part of the patient to be registered can be taken as a registration object. The planned position is the position of the patient during the surgery, which is planned according to the part of the patient to be operated on, so that the part of the patient to be operated on can be exposed well. Taking hip surgery as an example, the hip joint includes a left hip joint and a right hip joint, and the left hip joint and the right hip joint correspond to different patient positions respectively. The registration array is rigidly linked with the patient, and is used to position the patient. The check screw is used to determine whether the registration array moves relatively. If the registration array moves relatively, the positioning accuracy is affected, and then the registration accuracy is affected. Alternatively, the position of the check screw on the patient is obtained by using a probe before the surgery, and the relative position of the check screw and the registration array is determined. In the surgery, the position of the check screw on the patient is found again by using the probe, and whether the registration array moves relatively during the surgery is determined by judging whether the relative position of the check screw and the registration array changes.

[0094] Step S302, adjust the optical tracking device to a suitable position, and use the probe to check the check screw. The position of the screw is collected twice, the first time is used to record the position of the check screw relative to the registration array, and the second time is used to complete the check of the position of the check screw.

[0095] Step S303, according to the prompt of the software interface, collect the landmark points in the dashed boundary until the specified number of points is collected. The registration point position and the landmark point position can be marked with different marks on the software interface, such as points of different colors. The dashed boundary is used to indicate the position of the preset area.

[0096] Among them, one registration point corresponds to a plurality of landmark points, the plurality of landmark points are scattered in the preset area in a non-random manner, and the plurality of landmark points surround the corresponding registration point. The distribution of the landmark points can be annular, or can be cross-shaped, or can be other shapes that meet the two conditions of being in the preset area and surrounding the registration point, or can be a superposition of the above shapes. The number of landmark points can be planned according to user demand. It should be known that the more the number of landmark points, the higher the registration accuracy, and correspondingly, as the number of landmark points increases, the collection time will increase.

[0097] Among them, the preset area is associated with the feature of the part of the patient to be registered. Taking the acetabulum as an example, the preset area can be the fovea of the acetabular inner wall, or the edge of the acetabulum and the edge of the fovea.

[0098] Figure 4 FIG. 1 is a schematic diagram of the registration probe of the embodiment collecting the landmark points scattered in the annular shape on the inner wall of the acetabulum;

[0099] Figure 5 is a schematic diagram of the registration probe collecting the marker points scattered in the cross shape in the fovea of the horse's hoof in this embodiment;

[0100] Figure 6 is a schematic diagram of the registration probe collecting the marker points scattered in the arc shape in the edge of the acetabulum in this embodiment, wherein 1 is a registration point, 2 is a marker point, 3 is an acetabulum, and 4 is a registration probe.

[0101] In step S304, the physical space coordinates of the corresponding registration points are generated according to the collected marker points in step S303, a coarse registration matrix is obtained according to the registration points, and a fine registration matrix is obtained by iteration according to the coarse registration matrix. If the preset area corresponding to the registration point is circular, the centroid of the points in the area can be taken as the coarse registration point; if the preset area corresponding to the registration point is arc-shaped, the center of the arc line can be taken as the coarse registration point. Alternatively, the coarse registration matrix can be generated according to the physical space coordinates of the collected marker points, and the generation method can adopt the SVD decomposition method. The fine registration matrix is obtained by iteration according to the initial value provided by the coarse registration matrix, and the iteration algorithm can adopt the ICP registration and registration algorithm.

[0102] In step S305, the verification points are collected, and it is judged whether the verification points pass the verification. If all the verification points pass the verification, the registration and registration are completed; if there are verification points that do not pass the verification, step S306 is executed. Figure 7 is a schematic diagram of the verification points in this embodiment, wherein the number 5 indicates the verification points. The verification points are used to prompt the roughly collected area. The number of verification points is set according to user demand, and the number can be 3, 4 or more.

[0103] The judgment on whether the verification point meets the checking requirement includes: generating the verification point and the image space coordinates of the verification point in the three-dimensional image; converting the image space coordinates of the verification point according to the registration matrix to obtain the theoretical physical space coordinates of the verification point; collecting the verification point by registering the probe based on the three-dimensional image, so that the position of the probe on the patient entity corresponds to the position of the marker point on the three-dimensional image; when the probe reaches the position of the theoretical physical space coordinates of the verification point, the distance between the needle tip of the probe and the bone surface is obtained; the distance between the needle tip of the probe and the bone surface is taken as the deviation between the theoretical physical space coordinates of the verification point and the actual physical space coordinates of the verification point; and the distance between the probe and the bone surface of the object to be registered is judged to meet the checking standard. If the distance between the needle tip of the probe and the bone surface is 0 when the probe is clicked on the bone surface, it is judged that the registration matrix has no error. If the distance between the needle tip of the probe and the bone surface is not 0, it is judged whether the distance is lower than a preset threshold value, and if the distance is lower than the threshold value, it is considered that the registration matrix meets the checking standard. The preset threshold value can generally be set to 1 mm, or can be set to other values. The lower the threshold value, the higher the accuracy of detection, and the higher the threshold value, the greater the possibility of false judgment.

[0104] In step S306, the collected verification point is replaced with the unverified marker point, a new registration matrix is generated, and step S305 is executed.

[0105] In a special scenario, the error of the new registration matrix is still large, and the algorithm can be trapped in a local minimum solution. A random consistency sampling algorithm can be used to randomly select the collected marker point in each region as a registration point, or the position of the registration point can be manually adjusted to obtain a new registration point, and the registration matrix is calculated according to the new registration point.

[0106] Based on the same inventive concept, the embodiments of the present application also provide a registration device for implementing the surgical registration method described above. The implementation scheme of the device for solving the problem is similar to the implementation scheme described in the above method, so the specific limitations in the following registration device embodiments can be referred to the limitations of the surgical registration method in the above text, which will not be repeated here.

[0107] In one of the embodiments, the present application also provides a registration device of a surgical robot system, as shown in Figure 8 The device includes a first acquisition module, a second acquisition module, a determination module and a generation module.

[0108] The first obtaining module is configured to obtain a three-dimensional image of the object to be registered and a set of registration points planned in an image space of the three-dimensional image; the second obtaining module is configured to obtain physical space coordinates of a plurality of sets of marker points of the object to be registered; wherein each set of marker points is a set of points in a preset region of each registration point; the determining module is configured to determine a physical space coordinate corresponding to each registration point according to the physical space coordinates of the set of marker points corresponding to each registration point; and the generating module is configured to generate a registration matrix according to a transformation relationship between the image space coordinates of the set of registration points on the three-dimensional image and the physical space coordinates of the set of registration points.

[0109] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. Each of the above modules can be embedded in or independent of a processor in the computer device in a hardware form, or can be stored in a memory in the computer device in a software form, so as to be called and executed by the processor to perform the operations corresponding to each of the above modules.

[0110] In one of the embodiments, a surgical robot system is also provided, as shown in Figure 10 The system includes an image display system and a control system; the image display system is configured to display and update a three-dimensional image of a physical object in real time; and the control system is configured to implement the steps in each of the above method embodiments.

[0111] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 10 The computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store a registration matrix and information related to the registration matrix. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the surgical registration method in the above method embodiments.

[0112] In an embodiment, a computer device is provided, which can be a terminal. The computer device comprises a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements a surgical registration method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0113] Those skilled in the art can understand that, Figure 10 The structure shown is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In an embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program, when executed by a processor, implements the steps of the above-mentioned method embodiments.

[0115] In an embodiment, a computer program product is provided, which comprises a computer program. The computer program, when executed by a processor, implements the steps of the above-mentioned method embodiments.

[0116] It should be understood that the specific embodiments described herein are merely intended to explain the application, but not to limit it. All other embodiments obtained by those of ordinary skill in the art without creative labor based on the embodiments provided in the present application are within the scope of protection of the present application.

[0117] Obviously, the drawings are only some examples or embodiments of the present application, and can be applied to other similar cases by those of ordinary skill in the art without creative labor. In addition, it can be understood that although the work done in the development process can be complex and long, certain design, manufacture or production changes made by those of ordinary skill in the art based on the technical content disclosed in the present application are only routine technical means and should not be regarded as insufficient disclosure of the present application.

[0118] The word "implementation" in this application refers to the specific features, structures, or characteristics described in connection with an implementation can be included in at least one implementation of the present application. The phrase appears in various places throughout the specification is not necessarily meant to refer to the same implementation, nor is it meant to imply that the features, structures, or characteristics so described can not be implemented in other implementations. It will be apparent to those having ordinary skill in the art that the implementations described herein can be combined with other implementations without losing the intended effect.

[0119] The above embodiments only express several implementation manners of the present application, which are described in detail and specifically, but cannot be understood as the limitation of the patent protection scope. It should be pointed out that for ordinary skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, which all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A surgical registration method, characterized by, The method comprises the following steps: acquiring a three-dimensional image of an object to be registered and a set of registration points planned in the image space of the three-dimensional image; acquiring physical space coordinates of a plurality of marker point sets of the object to be registered; wherein the marker point set is a point set within a preset region of each registration point; determining the physical space coordinates corresponding to each registration point according to the physical space coordinates of the marker point set corresponding to each registration point; generating a registration matrix according to the transformation relationship between the image space coordinates of the set of registration points on the three-dimensional image and the physical space coordinates of the set of registration points; verifying the registration matrix to obtain a verification result; verifying the registration matrix comprises judging whether the relationship between the three-dimensional image space position and the physical space position of at least one verification point in the object to be registered conforms to the position relationship indicated by the registration matrix; if the verification result is not passed, the verification point is taken as a supplementary marker point and the marker point set is updated; the physical space coordinates corresponding to each registration point are updated according to the updated marker point set; a coarse registration matrix is generated according to the transformation relationship between the image space coordinates of the set of registration points on the three-dimensional image and the physical space coordinates of the set of registration points; a fine registration matrix is regenerated according to the initial value provided by the coarse registration matrix, the physical space coordinates of the verification point and the physical space coordinates of the marker point; wherein if the verification result of the regenerated fine registration matrix is not passed, the registration matrix is updated according to a new verification point until the updated registration matrix passes the verification.

2. The surgical registration method of claim 1, wherein each registration point in the planned set of registration points is determined according to a feature point of the object to be registered.

3. The surgical registration method of claim 1, wherein the marker point set is a point set within a preset region of each registration point, comprising: determining the preset region according to a structure feature of a preset range corresponding to the registration point on the object to be registered.

4. The surgical registration method of claim 1, wherein the registration point is located at a center position or a centroid position of the preset region; and a plurality of marker points corresponding to the registration point are non-randomly distributed within the preset region. The plurality of marker points are non-randomly distributed within the preset region, comprising: the plurality of marker points constitute a marker point set corresponding to the registration point; and the plurality of marker points are distributed within the preset region; the marker point set can be fitted into a geometric figure or the plurality of marker points of the marker point set are distributed in an array.

6. The surgical registration method of claim 5, wherein:

5. The surgical registration method of claim 4, wherein, when the preset region is circular or approximately circular, the geometric figure is at least one of a ring shape and a cross shape; when the preset region is arc-shaped or strip-shaped, the geometric figure is at least one of an arc shape and a straight line shape. The verification of the registration matrix to obtain a verification result comprises the following steps: acquiring the image space coordinates of a verification point planned on the three-dimensional image of the object to be registered; ​ 7. The surgical registration method of claim 1, wherein, ​ ​ According to the registration matrix, a theoretical physical space coordinate corresponding to an image space coordinate of the verification point is calculated; An actual physical space coordinate of the verification point planned on the three-dimensional image of the object to be registered is obtained; A deviation between the theoretical physical space coordinate of the verification point and the actual physical space coordinate of the verification point is determined and compared with a preset threshold value; If the deviation is less than the preset threshold value, the verification passes; if the deviation is not less than the preset threshold value, the verification fails.

8. The surgical registration method of claim 1, wherein, The method for checking the registration matrix comprises the following steps: An actual physical space coordinate of the verification point planned on the three-dimensional image of the object to be registered is obtained; According to the registration matrix, a theoretical physical space coordinate corresponding to an image space coordinate of the verification point is calculated; An actual physical space coordinate of the verification point planned on the three-dimensional image of the object to be registered is obtained; A deviation between the theoretical physical space coordinate of the verification point and the actual physical space coordinate of the verification point is determined and compared with a preset threshold value; If the deviation is less than the preset threshold value, the verification passes; if the deviation is not less than the preset threshold value, the verification fails.

9. A surgical registration registration apparatus, characterized in that, The device comprises a first obtaining module, a second obtaining module, a determining module and a generating module; The first obtaining module is configured to obtain a three-dimensional image of an object to be registered and a set of registration points planned in an image space of the three-dimensional image; The second obtaining module is configured to obtain physical space coordinates of a plurality of marker point sets of the object to be registered; wherein the marker point set is a point set in a preset region of each registration point; The determining module is configured to determine a physical space coordinate corresponding to each registration point according to the physical space coordinates of the marker point set corresponding to each registration point; The generating module is configured to generate a registration matrix according to a transformation relationship between image space coordinates of the set of registration points on the three-dimensional image and physical space coordinates of the set of registration points; after the registration matrix is generated, the registration matrix is checked to obtain a checking result; the checking of the registration matrix comprises judging whether a relationship between a three-dimensional image space position and a physical space position of at least one verification point of the object to be registered conforms to a position relationship indicated by the registration matrix; if the checking result is a failure, the verification point is taken as a supplementary marker point and the marker point set is updated; the physical space coordinate corresponding to each registration point is updated according to the updated marker point set; a coarse registration matrix is generated according to a transformation relationship between image space coordinates of the set of registration points on the three-dimensional image and physical space coordinates of the set of registration points; a fine registration matrix is re-generated according to an initial value provided by the coarse registration matrix, the physical space coordinate of the verification point and the physical space coordinates of the marker points; wherein if the checking result of the re-generated fine registration matrix is a failure, the registration matrix is updated according to a new verification point until the updated registration matrix passes the check.

10. A surgical robotic system, characterized by, The system comprises an image display system and a control system; The image display system is configured to display and update a three-dimensional image of a physical object in real time; The control system is configured to implement the steps of the method according to any one of claims 1 to 8.

Images