Head image registration method and device, equipment and storage medium

Abstract

The invention discloses a head image registration method and device, equipment and a storage medium. A target point cloud set and a laser point cloud set in an image registration result are obtained, the target point cloud set and the laser point cloud set both correspond to the face T area of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a main axis registration algorithm; in the laser point cloud set, determining data closest to each data in the target point cloud set to obtain a closest point cloud set; correcting the laser point cloud set according to a set position relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set; and if the target point cloud set and the target laser point cloud set meet a set registration condition, determining that registration succeeds. According to the embodiment of the invention, the corresponding relation between the medical image space and the operation space where the target object is located can be accurately determined without marks.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a head image registration method, device, equipment and storage medium. Background Art

[0002] When a surgical robot assists a doctor in performing surgery, it is usually necessary to complete intraoperative image registration so that the robot can obtain the accurate correspondence between the medical image space and the surgical space where the patient is located, and determine the spatial position of the surgical area based on the correspondence.

[0003] At present, intraoperative registration is usually completed through markers as an intermediary. Common markers are markers pasted on the skin surface. However, when markers are pasted on the skin surface, there is a problem that the markers fall off or the skin deforms, causing the markers to move and affect the registration accuracy.

[0004] Therefore, the technology needs to rely on the position of markers to determine the correspondence between the medical image space and the surgical space where the patient is located. Summary of the invention

[0005] The present invention provides a head image registration method, device, equipment and storage medium to solve the problem that the prior art relies on the position of a marker to determine the correspondence between the medical image space and the surgical space where the patient is located.

[0006] According to one aspect of the present invention, a head image registration method is provided, comprising:

[0007] Acquire a target point cloud set and a laser point cloud set in the image registration result, wherein both the target point cloud set and the laser point cloud set correspond to the facial T zone of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm;

[0008] In the laser point cloud set, determining the data closest to each data in the target point cloud set to obtain the closest point cloud set;

[0009] Correcting the laser point cloud set according to a set positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set;

[0010] If the target point cloud set and the target laser point cloud set meet the set registration conditions, it is determined that the registration is successful.

[0011] According to another aspect of the present invention, there is provided a head image registration device, comprising:

[0012] A data acquisition module, used to acquire a target point cloud set and a laser point cloud set in an image registration result, wherein both the target point cloud set and the laser point cloud set correspond to a facial T zone of a target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm;

[0013] A data extraction module, used for determining, in the laser point cloud set, data closest to each data in the target point cloud set, so as to obtain a closest point cloud set;

[0014] A correction module, used for correcting the laser point cloud set according to the positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set;

[0015] The determination module is used to determine that the registration is successful if the target point cloud set and the target laser point cloud set meet the set registration conditions.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the head image registration method described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the head image registration method described in any embodiment of the present invention when executed.

[0021] The technical solution for head image registration provided by the embodiment of the present invention optimizes the distribution of each data in the laser point cloud set again from a global level by correcting the laser point cloud set based on the set position relationship between the nearest point cloud set and the target point cloud set, thereby effectively avoiding the registration result from falling into the local optimal solution and achieving the technical effect of optimizing the registration result.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a head image registration method provided according to an embodiment of the present invention;

[0025] Figure 2 is another flow chart of a head image registration method provided according to an embodiment of the present invention;

[0026] Figure 3 is a schematic diagram of the correspondence between initial point cloud data and face provided according to an embodiment of the present invention;

[0027] Figure 4 is a schematic diagram of initial laser point cloud data provided according to an embodiment of the present invention;

[0028] Figure 5 is another flow chart of a head image registration method provided according to an embodiment of the present invention;

[0029] Figure 6 is a distribution diagram of target point cloud data and target laser point cloud data provided according to an embodiment of the present invention;

[0030] Figure 7 is another flow chart of a head image registration method provided according to an embodiment of the present invention;

[0031] Figure 8 is a schematic diagram of the structure of a head image registration device provided according to an embodiment of the present invention;

[0032] Fig. 9 is another structural schematic diagram of a head image registration device provided according to an embodiment of the present invention;

[0033] Fig.10 is another structural schematic diagram of a head image registration device provided according to an embodiment of the present invention;

[0034] Fig.11 It is a structural schematic diagram of an electronic device for implementing the head image registration method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Figure 1 The flowchart of the head image registration method provided in the embodiment of the present invention is applicable to the case where the registration accuracy of the target laser point cloud set and the target point cloud set is improved by correcting the laser point cloud set by the positional relationship between the nearest point cloud set and the target point cloud set, wherein the nearest point cloud set is the set of data in the laser point cloud set that is closest to each data in the target point cloud set. The method can be executed by a head image registration device, which can be implemented in the form of hardware and / or software, and the head image registration device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0038] S110. Obtain a target point cloud set and a laser point cloud set in the image registration result, wherein both the target point cloud set and the laser point cloud set correspond to the facial T zone of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm.

[0039] Among them, the principal axis registration algorithm is an algorithm for image registration through the positional relationship between the first coordinate axis and the second coordinate axis, wherein the first coordinate axis corresponds to the principal axis directions of the first image data, and the second coordinate axis corresponds to the principal axis directions of the second image data.

[0040] The target point cloud set is CT (Computed Tomography) point cloud data or MRI (Magnetic Resonance Imaging) point cloud data.

[0041] The facial T zone refers to the forehead and nose. Since the combination of the two looks like a capital T, it is called the facial T zone.

[0042] In one embodiment, the target object is a surgical subject or a surgical patient.

[0043] S120, determining in the laser point cloud set the data closest to each data in the target point cloud set to obtain a closest point cloud set.

[0044] In one embodiment, for each data in the target point cloud set, the data closest to the current data is determined in the laser point cloud set, and the data is used as the closest point of the current data; the combination of the closest points of all the data in the target point cloud set is used as the closest point cloud set.

[0045] S130, correcting the laser point cloud set according to the set positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set.

[0046] This step aims to redistribute the laser point cloud from a global level by correcting the laser point cloud set based on the set positional relationship between the nearest point cloud set and the target point cloud set, thereby effectively avoiding the alignment result from falling into a local optimal solution and achieving the technical effect of optimizing the alignment result.

[0047] The set positional relationship is a positional relationship on at least one set spindle plane.

[0048] Step a1, determining the angle between the projections of two corresponding data in the nearest point cloud set and the registered laser point cloud set on each set principal axis plane, wherein each set principal axis plane is each principal axis plane in at least one principal axis plane; the at least one principal axis plane is at least one of the three principal axis planes whose three principal axis directions of the target point cloud data can be determined.

[0049] The target point cloud set corresponds to three main axis directions, namely the normal main axis direction, the vertical main axis direction and the transverse main axis direction. Among the three main axis directions, two main axis directions can determine a corresponding main axis plane. The at least one main axis plane is one or more main axis planes among the three main axis planes.

[0050] For each data in the registered laser point cloud set, the current data and the data closest to the current data in the nearest point cloud set are defined as two data with a corresponding relationship. Take the principal axis plane determined by the vertical coordinate axis and the horizontal coordinate axis as an example. Determine the first projection of the current data on the principal axis plane, determine the second projection of the data corresponding to the current data in the nearest point cloud set on the principal axis plane, and determine the angle between the first projection and the second projection.

[0051] Step a2: determine the average of all the angles corresponding to each of the set main axis planes to obtain an angle average.

[0052] For each of the at least two set main axis planes, the average of all angles corresponding to the current set main axis plane is determined to obtain the angle average corresponding to the current set main axis plane.

[0053] Step a3: Taking the centroid of the target point cloud set as the rotation point, the registered laser point cloud set is rotated according to the angle mean corresponding to each of the set principal axis planes to obtain a target laser point cloud set.

[0054] In one embodiment, for each of the at least two set spindle planes, the centroid of the target point cloud data is used as the rotation point, and the aligned laser point cloud set is rotated accordingly on the current set spindle plane according to the angle mean corresponding to the current set spindle plane to obtain the target laser point cloud set.

[0055] In one embodiment, the centroid of the target point cloud set is used as the rotation point, and the spatial angle mean is determined according to the angle mean corresponding to each set principal axis plane. The corresponding spatial rotation operation is performed on the registered laser point cloud set according to the spatial angle mean to obtain the target laser point cloud set.

[0056] S140: If the target point cloud set and the target laser point cloud set meet the set registration conditions, it is determined that the registration is successful.

[0057] If the target point cloud set and the target laser point cloud set meet the set registration conditions, it means that the position deviation between the two is within an acceptable range, so the registration is determined to be successful. It can be understood that once the registration is successful, the corresponding relationship between the medical image space corresponding to the target point cloud set and the surgical space corresponding to the target laser point cloud set is accurately established.

[0058] When it is determined that the registration is successful, an indicator is output to indicate that the registration is successful, or the spatial position of the next surgical area is determined based on the registration result, and then the robot arm is controlled to drive the surgical instrument to move to the spatial position to perform subsequent surgical operations.

[0059] The technical solution for head image registration provided by the embodiment of the present invention optimizes the distribution of each data in the laser point cloud set again from a global level by correcting the laser point cloud set based on the set position relationship between the nearest point cloud set and the target point cloud set, thereby effectively avoiding the registration result from falling into a local optimal solution, achieving the technical effect of optimizing the registration result and improving the accuracy of the correspondence between the medical image space and the surgical space of the target object.

[0060] Figure 2 Flow chart of the method for determining the image registration result provided by an embodiment of the present invention, which is used to determine the image registration result in S110 of the above embodiment. Figure 2 As shown, the method includes:

[0061] S2001. Obtain an initial point cloud set and an initial laser point cloud set corresponding to the T zone on the face of the target object.

[0062] Obtain a medical image sequence of the target object, determine a three-dimensional head model of the target object based on the medical image sequence; determine the facial contour of the target object according to the three-dimensional head model; extract an initial point cloud set corresponding to the T zone of the target object's face from the facial contour (see Figure 3 Compared with the use of a three-dimensional head model for image registration, the use of an initial point cloud set for image registration here can effectively reduce the number of point clouds and improve the speed of image registration while ensuring the acquisition of facial features.

[0063] In one embodiment, an infrared laser pen or structured light device is used to scan the head of the target object to obtain laser scanning data, which includes facial information of the target object. Laser point cloud data corresponding to the T zone of the face of the target object is extracted from the laser scanning data to obtain an initial laser point cloud set (see Figure 4 ). Compared with using laser scanning data for image registration, using the initial laser point cloud set for subsequent image registration can reduce the amount of data calculation, improve the image registration speed, and reduce the image registration time.

[0064] In one embodiment, an infrared laser scanning device is used to scan the T zone of the face of the target object to obtain initial laser point cloud data.

[0065] After the initial point cloud set and the initial laser point cloud set are obtained, filtering operations are performed on the initial point cloud set and the initial laser point cloud set to update the initial point cloud set and the initial laser point cloud set. The filtering operation includes but is not limited to at least one of downsampling, deduplication, and removal of discrete interference points. The purpose is to reduce the number of point clouds and improve the speed of image registration.

[0066] The updated initial point cloud set and the updated initial laser point cloud set are used as the current initial point cloud set and the initial laser point cloud set respectively.

[0067] Determine the centroid of the current initial point cloud set and the initial laser point cloud set and the initial axis of each main axis. In one embodiment, PCA (principal component analysis) is used to determine the initial axis of each main axis of the initial point cloud set and the initial laser point cloud set.

[0068] S2002, performing principal axis direction correction on the initial point cloud set and the initial laser point cloud set to obtain a target point cloud set and a first laser point cloud set.

[0069] In one embodiment, the main axis direction correction of the initial point cloud set is completed by the following steps:

[0070] Step b1, determining the centroid of the initial point cloud set and the data in the initial point cloud set closest to the centroid, and using the data as the closest point data.

[0071] Step b2: determine a first vector pointing from the centroid to the nearest point data, and update the normal principal axis direction of the initial point cloud set according to the angle between the first vector and the initial normal axis to obtain a first point cloud set.

[0072] Subtract the centroid data from the nearest point data to get the first vector pointing from the centroid to the nearest point. Since the initial point cloud set is convex, the centroid is inside the initial point cloud set, and the direction of the first vector points to the outside of the initial point cloud set. Determine the angle between the initial normal principal axis direction of the initial point cloud set and the first vector. If the angle is an acute angle, the initial normal principal axis direction is used as the normal principal axis direction; if the angle is an obtuse angle, the opposite direction of the initial normal principal axis direction is used as the normal principal axis direction. The initial point cloud set with the normal principal axis direction updated is used as the first point cloud set.

[0073] Step b3: Determine two endpoint data corresponding to the two ends of the forehead of the target object in the initial point cloud set.

[0074] Among them, the two endpoint data can be understood as Figure 2 The left and right boundary points of the lateral area in the middle T-shaped zone.

[0075] Step b4, determine the midpoint corresponding to the two endpoint data and a second vector from the midpoint to the nearest point, and update the vertical principal axis direction of the first point cloud set according to the second vector and the initial vertical principal axis direction to obtain a second cloud set.

[0076] Determine the midpoint between the left boundary point and the right boundary point, subtract the midpoint data from the nearest point data to obtain the second vector; determine the angle between the initial vertical main axis direction and the second vector; if the angle is an acute angle, use the initial vertical main axis direction as the vertical main axis direction; if the angle is an obtuse angle, use the opposite direction of the initial vertical main axis direction as the vertical main axis direction. Use the first point cloud set after the vertical main axis direction is updated as the second point cloud set.

[0077] Step b5: Update the transverse principal axis direction of the second point cloud set according to the updated normal principal axis direction and the updated vertical principal axis direction to obtain a target point cloud set.

[0078] It can be understood that after the normal principal axis direction and the vertical principal axis direction are determined, the transverse principal axis direction corresponding to the normal principal axis direction and the vertical principal axis direction can be determined based on the set direction rules, and the second point cloud set is updated according to the transverse principal axis direction, and the updated second point cloud set is used as the target point cloud set.

[0079] The processing object of the above steps b1 to b5 is replaced by the initial point cloud data with the initial laser point cloud data to complete the correction of the main axis direction of the initial laser point cloud data.

[0080] S2003. Perform an initial registration on the target point cloud set and the first laser point cloud set to obtain an initial image registration result, wherein the initial image registration result includes a second laser point cloud set, and the centroid and main axis directions of the second laser point cloud set coincide with the centroid and main axis directions of the target point cloud set respectively.

[0081] Determine the angles between the main axis directions of the first laser point cloud set and the corresponding main axis directions of the target point cloud set; take the centroid of the target point cloud set as the rotation point, and rotate the first laser point cloud set accordingly according to the angles to obtain the second laser point cloud set. This step aims to make the centroid and main axis directions of the target point cloud set coincide with the centroid and main axis of the second laser point cloud set based on the registration operation of the centroid and main axis directions.

[0082] S2004: Accurately align the target point cloud set with the second laser point cloud set to obtain the image registration result.

[0083] Determine the normal vector corresponding to each data of the target point cloud set, and use the point-to-surface ICP (Iterative Closest Point, iterative closest point algorithm) precise registration method to determine the registration matrix corresponding to the second laser point cloud set; determine the laser point cloud set based on the second laser point cloud set and the registration matrix, specifically, Q = M2*Q2, where Q is the laser point cloud set, Q2 is the second laser point cloud set, and M2 is the registration matrix. The point-to-surface ICP precise registration method can ensure the accuracy of the registration result and the efficiency of the registration.

[0084] The embodiment of the present invention ensures the accuracy of the main axis directions of the target point cloud set and the first laser point cloud set by correcting the main axis direction. On this basis, the speed and accuracy of image registration are ensured by combining initial registration with precise registration.

[0085] Figure 5 This is a flow chart of a method for determining image registration results provided by an embodiment of the present invention. This embodiment is used to refine the "if the target point cloud set and the target laser point cloud set meet the set registration conditions, then determine that the registration is successful" in the above embodiment. Figure 5 As shown, the method includes:

[0086] S310. Obtain a target point cloud set and a laser point cloud set in the image registration result, wherein both the target point cloud set and the laser point cloud set correspond to the facial T zone of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm.

[0087] S320: Determine, in the laser point cloud set, data that is closest to each data in the target point cloud set to obtain a closest point cloud set.

[0088] S330, correcting the laser point cloud set according to the set positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set.

[0089] S3401. For each data in the target point cloud set, determine the target data corresponding to the current data and the Euclidean distance between the current data and the target data, wherein the target data is the data in the target laser point cloud set that is closest to the current data.

[0090] This step aims to determine the Euclidean distance between two data with corresponding relationship in the target point cloud set and the target laser point cloud set. For each data in the target point cloud data, the current data and the data with the closest distance to the current data in the target laser point cloud data are regarded as two data with corresponding relationship.

[0091] S3402. Determine the mean of all the Euclidean distances to obtain a distance mean.

[0092] After determining the Euclidean distances corresponding to each data in the target point cloud set, the mean of all Euclidean distances is calculated and the mean is taken as the distance mean.

[0093] S3403: If the distance mean meets the set distance condition, it is determined that the registration is successful.

[0094] In one embodiment, if the distance mean is less than the set distance threshold, it means that the registration error is within an acceptable range, so the registration result corresponding to the target point cloud set and the target laser point cloud set is determined to be the target registration result, see Figure 6 shown. Figure 6 In the figure, the gray part is the target point cloud, and the white flocculent pattern is the target laser point cloud.

[0095] In one embodiment, if the registration is successful, the spatial position of the surgical area is determined according to the correspondence between the target point cloud set and the target laser point cloud set, so that the robot arm can be controlled to drive the surgical instrument to perform the corresponding surgical operation according to the spatial position and the set surgical content. This embodiment achieves the technical effect of improving the success rate of robotic surgery through accurate image registration results.

[0096] In one embodiment, Figure 7 As shown, the method also includes:

[0097] S3404: If the distance mean does not meet the set distance condition, return to the step of obtaining an initial laser point cloud set corresponding to the T zone on the face of the target object until the distance mean meets the set distance condition.

[0098] In one embodiment, if the distance mean is greater than or equal to a set distance threshold, it indicates that the registration error exceeds an acceptable error range, and therefore the registration is determined to have failed, and the process returns to the step of obtaining an initial laser point cloud set corresponding to the target object's face until the distance mean meets the set distance condition.

[0099] The embodiment of the present invention determines the degree of position deviation between two data with a corresponding relationship by determining the Euclidean distance between two data with a corresponding relationship in a target point cloud set and a target laser point cloud set; the degree of position deviation between the target point cloud set and the target laser point cloud set is reflected by the distance mean corresponding to all Euclidean distances, and whether the registration is successful is determined by the relationship between the distance mean and the set distance condition, thereby ensuring the accuracy of the image registration results used for surgical navigation.

[0100] Figure 8 Schematic diagram of the structure of the head image registration device provided by the embodiment of the present invention. Figure 8As shown, the device includes: a data acquisition module 41, used to acquire a target point cloud set and a laser point cloud set in an image registration result, wherein the target point cloud set and the laser point cloud set both correspond to the facial T zone of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm; a data extraction module 42, used to determine, in the laser point cloud set, the data closest to each data in the target point cloud set to obtain a nearest point cloud set; a correction module 43, used to correct the laser point cloud set according to the positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set; a determination module 44, used to determine that the registration is successful if the target point cloud set and the target laser point cloud set meet the set registration conditions.

[0101] In one embodiment, Fig. 9 As shown, the device further includes an image registration module 40, and the image registration module 40 includes:

[0102] A data acquisition unit, used to acquire an initial point cloud set and an initial laser point cloud set corresponding to the T zone on the face of the target object;

[0103] A main axis direction correction unit, used for performing main axis direction correction on the initial point cloud set and the initial laser point cloud set to obtain a target point cloud set and a first laser point cloud set;

[0104] an initial registration unit, configured to perform initial registration on the target point cloud set and the first laser point cloud set to obtain an initial image registration result, wherein the initial image registration result includes a second laser point cloud set, wherein the centroid and each main axis direction of the second laser point cloud set coincide with the centroid and each main axis direction of the target point cloud set respectively;

[0105] The precise registration unit is used to precisely register the target point cloud set with the second laser point cloud set to obtain the image registration result.

[0106] In one embodiment, the main axis direction correction unit is specifically used for:

[0107] Determine the centroid of the initial point cloud set and the data in the initial point cloud set closest to the centroid, and use the data as the closest point data;

[0108] Determine a first vector pointing from the centroid to the nearest point data, and update the normal principal axis direction of the initial point cloud set according to the angle between the first vector and the initial normal principal axis direction to obtain a first point cloud set;

[0109] Determine two endpoint data corresponding to two ends of the forehead of the target object in the initial point cloud set;

[0110] Determine a midpoint corresponding to the two endpoint data and a second vector from the midpoint to the nearest point, and update the vertical principal axis direction of the first point cloud set according to the second vector and the initial vertical principal axis direction to obtain a second point cloud set;

[0111] The transverse principal axis direction of the second point cloud set is updated according to the updated normal principal axis direction and the updated vertical principal axis direction to obtain a target point cloud set.

[0112] In one embodiment, the correction module 43 is specifically used to:

[0113] Determine the angle between the projections of two corresponding data in the nearest point cloud set and the registered laser point cloud set on each set principal axis plane, wherein each set principal axis plane is each principal axis plane in at least one principal axis plane; the at least one principal axis plane is at least one of the three principal axis planes whose three principal axis directions of the target point cloud data can be determined;

[0114] Determine the average of all the angles corresponding to each of the set principal axis planes to obtain an angle average;

[0115] The centroid of the target point cloud set is used as a rotation point, and the registered laser point cloud set is rotated according to the angle mean corresponding to each of the set principal axis planes to obtain a target laser point cloud set.

[0116] In one embodiment, the determination module 44 is specifically configured to:

[0117] For each data in the target point cloud set, determine the target data corresponding to the current data and the Euclidean distance between the current data and the target data, wherein the target data is the data in the target laser point cloud set that is closest to the current data;

[0118] determining the mean of all said Euclidean distances to obtain a distance mean;

[0119] If the distance mean meets the set distance condition, it is determined that the registration is successful.

[0120] In one embodiment, the determination module 44 is further configured to:

[0121] If the distance mean does not meet the set distance condition, return to the step of obtaining an initial laser point cloud set corresponding to the T zone on the face of the target object until the distance mean meets the set distance condition.

[0122] In one embodiment, Fig.10 As shown, the device further includes a surgery control module 45, which is used to:

[0123] Determine the spatial position of the surgical area according to the correspondence between the target point cloud set and the target laser point cloud set;

[0124] According to the spatial position and the set surgical content, the robot arm is controlled to drive the surgical instrument to perform the corresponding surgical operation.

[0125] The technical solution for head image registration provided by the embodiment of the present invention optimizes the distribution of each data in the laser point cloud set again from a global level by correcting the laser point cloud set based on the set position relationship between the nearest point cloud set and the target point cloud set, thereby effectively avoiding the registration result from falling into a local optimal solution, achieving the technical effect of optimizing the registration result and improving the accuracy of the correspondence between the medical image space and the surgical space of the target object.

[0126] The head image registration device provided in the embodiment of the present invention can execute the head image registration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0127] Fig.11 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0128] like Fig.11 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0129] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0130] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a head image registration method.

[0131] In some embodiments, the head image registration method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the head image registration method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the head image registration method in any other appropriate manner (e.g., by means of firmware).

[0132] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0134] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0136] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0137] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0138] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0139] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A head image registration method, characterized in that: include: Acquire a target point cloud set and a laser point cloud set in the image registration result, wherein both the target point cloud set and the laser point cloud set correspond to the facial T zone of the target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm; In the laser point cloud set, determining the data closest to each data in the target point cloud set to obtain the closest point cloud set; Correcting the laser point cloud set according to a set positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set; If the target point cloud set and the target laser point cloud set meet the set registration conditions, it is determined that the registration is successful.

2. The method according to claim 1, characterized in that The image registration results are determined by the following steps: Acquire an initial point cloud set and an initial laser point cloud set corresponding to the T zone on the face of the target object; Performing principal axis direction correction on the initial point cloud set and the initial laser point cloud set to obtain a target point cloud set and a first laser point cloud set; Performing an initial registration on the target point cloud set and the first laser point cloud set to obtain an initial image registration result, wherein the initial image registration result includes a second laser point cloud set, and the centroid and each main axis direction of the second laser point cloud set coincide with the centroid and each main axis direction of the target point cloud set respectively; The target point cloud set and the second laser point cloud set are accurately registered to obtain the image registration result.

3. The method according to claim 2, characterized in that The main axis direction correction of the initial point cloud set is completed by the following steps: Determine the centroid of the initial point cloud set and the data in the initial point cloud set closest to the centroid, and use the data as the closest point data; Determine a first vector pointing from the centroid to the nearest point data, and update the normal principal axis direction of the initial point cloud set according to the angle between the first vector and the initial normal principal axis direction to obtain a first point cloud set; Determine two endpoint data corresponding to two ends of the forehead of the target object in the initial point cloud set; Determine a midpoint corresponding to the two endpoint data and a second vector from the midpoint to the nearest point, and update the vertical principal axis direction of the first point cloud set according to the second vector and the initial vertical principal axis direction to obtain a second point cloud set; The transverse principal axis direction of the second point cloud set is updated according to the updated normal principal axis direction and the updated vertical principal axis direction to obtain a target point cloud set.

4. The method according to claim 1, characterized in that: The setting position relationship is the position relationship of at least two main axis planes, and the correcting of the laser point cloud set according to the position relationship between the nearest point cloud set and the target point cloud set to obtain the target laser point cloud set includes: Determine the angle between the projections of two corresponding data in the nearest point cloud set and the registered laser point cloud set on each set principal axis plane, wherein each set principal axis plane is each principal axis plane in at least one principal axis plane; the at least one principal axis plane is at least one of the three principal axis planes whose three principal axis directions of the target point cloud data can be determined; Determine the average of all the angles corresponding to each of the set principal axis planes to obtain an angle average; The centroid of the target point cloud set is used as a rotation point, and the registered laser point cloud set is rotated according to the angle mean corresponding to each of the set principal axis planes to obtain a target laser point cloud set.

5. The method according to claim 2, characterized in that: If the target point cloud set and the target laser point cloud set meet the set registration condition, determining that the registration is successful includes: For each data in the target point cloud set, determine the target data corresponding to the current data and the Euclidean distance between the current data and the target data, wherein the target data is the data in the target laser point cloud set that is closest to the current data; determining the mean of all said Euclidean distances to obtain a distance mean; If the distance mean meets the set distance condition, it is determined that the registration is successful.

6. The method according to claim 5, characterized in that Also includes: If the distance mean does not meet the set distance condition, return to the step of obtaining an initial laser point cloud set corresponding to the T zone on the face of the target object until the distance mean meets the set distance condition.

7. The method according to claim 1, characterized in that Also includes: Determine the spatial position of the surgical area according to the correspondence between the target point cloud set and the target laser point cloud set; According to the spatial position and the set surgical content, the robot arm is controlled to drive the surgical instrument to perform the corresponding surgical operation.

8. A head image registration device, characterized in that: include: A data acquisition module, used to acquire a target point cloud set and a laser point cloud set in an image registration result, wherein both the target point cloud set and the laser point cloud set correspond to a facial T zone of a target object, the target point cloud set is medical image data, and the image registration result is determined based on a principal axis registration algorithm; A data extraction module, used for determining, in the laser point cloud set, data closest to each data in the target point cloud set, so as to obtain a closest point cloud set; A correction module, used for correcting the laser point cloud set according to the positional relationship between the nearest point cloud set and the target point cloud set to obtain a target laser point cloud set; The determination module is used to determine that the registration is successful if the target point cloud set and the target laser point cloud set meet the set registration conditions.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the head image registration method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the head image registration method according to any one of claims 1 to 7 when executed.

Images