Clustering-based path planning method, surgical robot and related products

Abstract

The invention discloses a path planning method based on clustering, a surgical robot and related products. The method comprises the following steps: acquiring a first three-dimensional CT image, wherein the first three-dimensional CT image comprises a skin area of a target object and a first tissue of the target object; an end point of the target path is determined from the first tissue. At least two first candidate points of the target path are determined from the skin region. And determining at least two first candidate paths based on the at least two first candidate points and the end point of the target path. And clustering the at least two first candidate paths to obtain at least one first path set. And determining a second path set from the at least one first path set, wherein the number of the first candidate paths in the second path set is greater than or equal to a second threshold. And determining a target path based on the second path set. Through the method, the error-tolerant rate of the target path can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, in particular to a path planning method based on clustering, a surgical robot and related products. BACKGROUND

[0002] By performing computed tomography (CT) on a target object, a three-dimensional CT image of the target object can be obtained, and then a target point position in the target object can be located based on the three-dimensional CT image, and a path from a skin region of the target object to the target point of the target object can be planned.

[0003] At present, a common way is for a doctor to plan a path from a skin region of a target object to a target point of the target object based on experience.

[0004] Considering that there are infeasible regions including infeasible tissues in the target object, wherein the infeasible tissues are larger in damage to the target object when collided, such as blood vessels. Therefore, the path from the skin region of the target object to the target point of the target object should avoid the infeasible regions. For the convenience of description, the following includes. However, the safety deviation of the path planned by this way is small, and then the fault tolerance is low. Among them, in the process of moving from the skin region of the target object to the target point according to the path determined based on this way, if the deviation between the actual path and the planned path is greater than or equal to the safety deviation, the actual path passes through the infeasible region, and if the deviation between the actual path and the planned path is less than the safety deviation, the actual path does not pass through the infeasible region. SUMMARY

[0005] The present application provides a path planning method based on clustering, a surgical robot and related products, wherein the related products include a path planning device based on clustering, an electronic device, and a computer readable storage medium, to improve the fault tolerance of the target path.

[0006] In a first aspect, a path planning method based on clustering is provided, and the path planning method based on clustering comprises: obtaining a first three-dimensional CT image, wherein the first three-dimensional CT image comprises a skin region of a target object and a first tissue of the target object; determining a terminal point of a target path from the first tissue; determining at least two first candidate points of the target path from the skin region; determining at least two first candidate paths based on the at least two first candidate points and the terminal point of the target path; clustering the at least two first candidate paths to obtain at least one first path set, any two first candidate paths in a same first path set having a distance less than or equal to a first threshold, any two first candidate paths belonging to different first path sets having a distance greater than or equal to the first threshold; determining a second path set from the at least one first path set, the second path set having a number of first candidate paths greater than or equal to a second threshold; determining the target path based on the second path set.

[0007] In combination with any embodiment of the present application, the at least two first candidate points determined from the skin region include: determining at least two second candidate paths based on at least two skin points in the skin region and an end point of the target path, an origin of a second candidate path in the at least two second candidate paths being the skin point in the at least two skin points, and an end point of the second candidate path being the end point of the target path; determining at least two first normal vectors of the at least two skin points based on the first three-dimensional CT image; determining at least two first angles between the second candidate path in the at least two second candidate paths and the corresponding first normal vector in the at least two first normal vectors; in a case where a number of the first angles less than or equal to a third threshold in the at least two first angles is greater than or equal to 2, determining the at least two first candidate points based on the skin points in the at least two skin points corresponding to the first angles less than or equal to the third threshold; in a case where the number of the first angles less than or equal to the third threshold in the at least two first angles is less than 2, determining the at least two first candidate points based on the skin points in the at least two skin points corresponding to the n smallest first angles in the at least two first angles, the n being an integer greater than or equal to 2.

[0008] In combination with any embodiment of the present application, before the at least two second candidate paths are determined based on the at least two skin points in the skin region and the end point of the target path, the clustering-based path planning method further includes: determining a reference sphere based on the end point of the target path and a preset radius, the reference sphere having a sphere center at the end point of the target path and a radius at the preset radius; determining at least two second candidate points based on the skin points in the skin region within the reference sphere. determine the at least two skin points based on the at least two second candidate points.

[0009] In combination with any of the embodiments of the present application, the determining the at least two first candidate points based on the skin point corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points comprises: determining at least two third candidate paths based on the skin point corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points and the end point of the target path, the start point of the third candidate path in the at least two third candidate paths being the skin point corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points, and the end point of the third candidate path in the at least two third candidate paths being the end point of the target path; clustering the at least two third paths to obtain at least one third path set, the distance between any two third candidate paths in the same third path set being less than or equal to a fourth threshold value, and the distance between any two third candidate paths respectively belonging to different third path sets being greater than or equal to the fourth threshold value; determining a fourth path set from the at least one third path set, the number of third candidate paths in the fourth path set being greater than or equal to a fifth threshold value; determining the at least two first candidate points based on the start points of the third candidate paths in the fourth path set.

[0010] In combination with any of the embodiments of the present application, before the determining the at least two first candidate paths based on the at least two first candidate points and the end point of the target path, the clustering-based path planning method further comprises: determining a second tissue from the first three-dimensional CT image, the second tissue being different from the first tissue; the determining the at least two first candidate paths based on the at least two first candidate points and the end point of the target path comprises: determining at least two fourth candidate paths based on the at least two first candidate points and the end point of the target path, the start point of the fourth candidate path in the at least two fourth candidate paths being the candidate point in the at least two first candidate points, and the end point of the fourth candidate path in the at least two fourth candidate paths being the end point of the target path; determining the minimum distances between the fourth candidate paths in the at least two fourth candidate paths and the second tissue to obtain at least two first distances; in a case that the first distance greater than or equal to a sixth threshold value in the at least two first distances is greater than or equal to 2, obtaining the at least two first candidate paths based on the fourth candidate paths corresponding to the first distance greater than or equal to the sixth threshold value in the at least two fourth candidate paths; in a case that the first distance greater than or equal to a sixth threshold value in the at least two first distances is less than 2, obtaining the at least two first candidate paths based on s fourth candidate paths with the largest first distance in the at least two fourth candidate paths, the s being an integer greater than or equal to 2.

[0011] With any of the embodiments of the present application, the determining a second tissue from the first three-dimensional CT image comprises: determining at least one first enclosing region based on the at least two first candidate points, the first enclosing region in the at least one first enclosing region comprising the at least two first candidate points; taking the first enclosing region with the smallest area in the at least one first enclosing region as a second enclosing region; determining a normal vector of the first candidate point in the second enclosing region based on the first three-dimensional CT image, to obtain at least one second normal vector; determining a third tissue of the target object from the first three-dimensional CT image, the third tissue being a tissue different from the first tissue; determining the second tissue based on a point in the third tissue with a distance to the at least two second normal vectors less than or equal to a seventh threshold value.

[0012] In a second aspect, a clustering-based path planning apparatus is provided, and the clustering-based path planning apparatus comprises: an acquisition unit configured to acquire a first three-dimensional CT image, the first three-dimensional CT image comprising a skin region of a target object and a first tissue of the target object; a determination unit configured to determine a terminal point of a target path from the first tissue; the determination unit is further configured to determine at least two first candidate points of the target path from the skin region; the determination unit is further configured to determine at least two first candidate paths based on the at least two first candidate points and the terminal point of the target path; a clustering unit configured to cluster the at least two first paths to obtain at least one first path set, a distance between any two first candidate paths in a same first path set being less than or equal to a first threshold value, and a distance between any two first candidate paths respectively belonging to different first path sets being greater than or equal to the first threshold value. The determining unit is further configured to determine a second path set from the at least one first path set, a number of the first candidate paths in the second path set being greater than or equal to a second threshold value. The determining unit is further configured to determine the target path based on the second path set.

[0013] With reference to any one of the embodiments of the present application, the determining unit is further configured to: determine at least two second candidate paths based on at least two skin points in the skin region and the end point of the target path, the start point of the second candidate path in the at least two second candidate paths being the skin point in the at least two skin points, and the end point of the second candidate path in the at least two second candidate paths being the end point of the target path; determine at least two first normal vectors of the at least two skin points based on the first three-dimensional CT image; determine at least two first angles between the second candidate path in the at least two second candidate paths and the corresponding first normal vector in the at least two first normal vectors; in a case where a number of the first angles less than or equal to the third threshold value in the at least two first angles is greater than or equal to 2, determine the at least two first candidate points based on the skin points in the at least two skin points corresponding to the first angles less than or equal to the third threshold value; in a case where the number of the first angles less than or equal to the third threshold value in the at least two first angles is less than 2, determine the at least two first candidate points based on the skin points in the at least two skin points corresponding to the n smallest first angles in the at least two first angles, the n being an integer greater than or equal to 2.

[0014] With reference to any one of the embodiments of the present application, the determining unit is further configured to: determine a reference sphere based on the end point of the target path and a preset radius, the center of the reference sphere being the end point of the target path, and the radius of the reference sphere being the preset radius; determine at least two second candidate points based on the skin points in the skin region within the reference sphere; determine the at least two skin points based on the at least two second candidate points.

[0015] With reference to any one of the embodiments of the present application, the determining unit is further configured to: determine at least two third candidate paths based on the skin point corresponding to the first included angle less than or equal to the third threshold and the end point of the target path, wherein the start point of the third candidate path in the at least two third candidate paths is the skin point corresponding to the first included angle less than or equal to the third threshold, and the end point of the third candidate path in the at least two third candidate paths is the end point of the target path; cluster the at least two third paths to obtain at least one third path set, wherein the distance between any two third candidate paths in a same third path set is less than or equal to a fourth threshold, and the distance between any two third candidate paths respectively belonging to different third path sets is greater than or equal to the fourth threshold; determine a fourth path set from the at least one third path set, wherein the number of third candidate paths in the fourth path set is greater than or equal to a fifth threshold; determine the at least two first candidate points based on the start points of the third candidate paths in the fourth path set.

[0016] With reference to any one of the embodiments of the present application, the determining unit is further configured to: determine a second tissue from the first three-dimensional CT image, wherein the second tissue is different from the first tissue; determine at least two fourth candidate paths based on the at least two first candidate points and the end point of the target path, wherein the start point of the fourth candidate path in the at least two fourth candidate paths is the candidate point in the at least two first candidate points, and the end point of the fourth candidate path in the at least two fourth candidate paths is the end point of the target path; determine the minimum distances between the fourth candidate paths in the at least two fourth candidate paths and the second tissue to obtain at least two first distances; in a case where the first distance greater than or equal to the sixth threshold in the at least two first distances is greater than or equal to 2, obtain the at least two first candidate paths based on the fourth candidate paths in the at least two fourth candidate paths corresponding to the first distance greater than or equal to the sixth threshold; in a case where the first distance greater than or equal to the sixth threshold in the at least two first distances is less than 2, obtain the at least two first candidate paths based on s fourth candidate paths with the maximum first distance in the at least two fourth candidate paths, wherein s is an integer greater than or equal to 2.

[0017] With reference to any one of the embodiments of the present application, the determining unit is further configured to: determine at least one first enclosing region based on the at least two first candidate points, wherein each of the first enclosing regions in the at least one first enclosing region comprises the at least two first candidate points; determine a second enclosing region from the first enclosing region with the smallest area in the at least one first enclosing region; determine a normal vector of the first candidate point in the second enclosing region based on the first three-dimensional CT image, to obtain at least one second normal vector; determine a third tissue of the target object from the first three-dimensional CT image, wherein the third tissue is different from the first tissue; determine the second tissue based on a point in the third tissue, wherein a distance from the point to the at least two second normal vectors is less than or equal to a seventh threshold value.

[0018] In a third aspect, a surgical robot is provided, comprising the clustering-based path planning device according to the second aspect. In the third aspect, the surgical robot can perform the clustering-based path planning method by the clustering-based path planning device, so as to improve the fault tolerance of the target path.

[0019] In a fourth aspect, an electronic device is provided, comprising a processor and a memory, wherein the memory is configured to store computer program code, and the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device performs the method according to the first aspect and any possible implementation manner thereof.

[0020] In a fifth aspect, another electronic device is provided, comprising a processor, a sending device, an input device, an output device and a memory, wherein the memory is configured to store computer program code, and the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device performs the method according to the first aspect and any possible implementation manner thereof.

[0021] In a sixth aspect, a computer readable storage medium is provided, wherein the computer readable storage medium stores a computer program, and the computer program comprises program instructions, and when the program instructions are executed by a processor, the processor performs the method according to the first aspect and any possible implementation manner thereof.

[0022] In a seventh aspect, a computer program product is provided, wherein the computer program product comprises a computer program or instructions, and when the computer program or instructions are executed on a computer, the computer performs the method according to the first aspect and any possible implementation manner thereof.

[0023] In the embodiments of the present application, the first three-dimensional CT image includes a skin region of the target object and a first tissue of the target object. After obtaining the first three-dimensional CT image, the planning device determines a terminal point of the target path from the first tissue and at least two first candidate points of the target path from the skin region. Then, based on the at least two first candidate points and the terminal point of the target path, at least two first candidate paths are determined. The at least two first candidate paths are clustered to obtain at least one first path set, wherein the distance between any two first candidate paths in the same first path set is less than or equal to a first threshold, and the distance between any two first candidate paths belonging to different first path sets is greater than or equal to the first threshold. A second path set is determined from the at least one first path set, wherein the number of first candidate paths in the second path set is greater than or equal to a second threshold. Based on the second path set, the target path is determined, which can improve the safety deviation of the target path and further improve the fault tolerance of the target path. It should be understood that the deviation of the actual path from the target path can be the distance between the actual path and the target path. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the drawings needed to be used in the embodiments of the present application or the background art will be described below.

[0025] The drawings herein are incorporated into the specification and form part of the specification, which show embodiments consistent with the present application, and together with the specification serve to explain the technical solutions of the present application.

[0026] Figure 1 A flowchart of a path planning method based on clustering provided by an embodiment of the present application; Figure 2 A flowchart of another path planning method based on clustering provided by an embodiment of the present application; Figure 3 A flowchart of still another path planning method based on clustering provided by an embodiment of the present application; Figure 4 A structural diagram of a path planning device based on clustering provided by an embodiment of the present application; Figure 5 A hardware structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0028] The terms "first", "second", etc. in the specification and claims of the present application and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0029] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. It should be understood that in the present application, "at least one" means one or more, "multiple" means two or more, and "at least two" means two or more.

[0030] The execution subject of the clustering-based path planning method in the embodiments of the present application is a clustering-based path planning device (hereinafter referred to as a path planning device), wherein the segmentation device can be any electronic device capable of executing the technical solutions disclosed in the embodiments of the present application. Optionally, the segmentation device can be one of the following: a computer, a server.

[0031] It should be understood that the embodiments of the present application can also be implemented by a processor executing computer program code. The embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Please refer to Figure 1 , Figure 1 A flowchart of a clustering-based path planning method provided in the embodiments of the present application is shown.

[0032] 101, a first three-dimensional CT image is obtained, wherein the first three-dimensional CT image includes a skin region of a target object and a first tissue of the target object.

[0033] In the embodiments of the present application, the target object can be a human being. The first three-dimensional CT image is a three-dimensional image obtained by CT scanning of the target object. The first three-dimensional CT image includes a plurality of tissues of the target object body, such as skin, kidney, lung, blood vessel, bone, etc.

[0034] In an implementation of obtaining the first three-dimensional CT image, the path planning apparatus receives the first three-dimensional CT image input by a user through an input component. The input component includes a keyboard, a mouse, a touch screen, a touch pad, and an audio input device.

[0035] In another implementation of obtaining the first three-dimensional CT image, the path planning apparatus receives the first three-dimensional CT image sent by a terminal. Optionally, the terminal can be any one of a mobile phone, a computer, a tablet computer, and a server.

[0036] 102. Determining an end point of the target path from the first tissue.

[0037] In the embodiments of the present application, the target path is a path to be planned, and the end point of the target path is located in the first tissue. Optionally, the end point of the target path is a target point in the first tissue. In some schemes, the path planning apparatus performs semantic segmentation on the first tissue in the first three-dimensional CT image to obtain the semantics of pixels in the first tissue. The end point of the target path is determined based on the semantics of the pixels in the first tissue. In other schemes, the path planning apparatus obtains the position of the end point of the target path in the first tissue, and determines the end point of the target path from the first tissue based on the position.

[0038] 103. Determining at least two first candidate points of the target path from the skin region.

[0039] In the embodiments of the present application, the first candidate point is a candidate point of the start point of the target path. Since the start point of the target path is located in the skin region, the path planning apparatus determines at least two first candidate points of the target path from the skin region. In some schemes, the path planning apparatus receives a first instruction input by a user, wherein the first instruction is used to indicate the positions of the at least two first candidate points in the skin region. The at least two first candidate points are determined from the skin region based on the positions of the at least two first candidate points in the skin region.

[0040] 104. Determining at least two first candidate paths based on the at least two first candidate points and the end point of the target path.

[0041] In the embodiment of the present application, the starting point of the first candidate path is the first candidate point, and the end point of the first candidate path is the end point of the target path. In one possible implementation, the path planning device determines a first candidate path based on one of the at least two first candidate points and the end point of the target path. Therefore, based on the at least two first candidate points and the end point of the target path, at least two first candidate paths can be determined.

[0042] Optionally, the first candidate path is a feasible path between the skin area of ​​the target object and the end point of the target path. For example, if the target object includes a blood vessel and the path cannot pass through the blood vessel, then the feasible path refers to a path that does not pass through the blood vessel.

[0043] Optionally, the first candidate path is a straight line, that is, the first candidate path is a straight line between a starting point of the first candidate path and an end point of the first candidate path.

[0044] 105. Cluster the at least two first candidate paths to obtain at least one first path set, wherein a distance between any two first candidate paths in the same first path set is less than or equal to a first threshold, and a distance between any two first candidate paths in different first path sets is greater than or equal to the first threshold.

[0045] In an embodiment of the present application, the path planning device clusters at least two first candidate paths based on the distance between the first candidate paths to obtain at least one first path set. Among them, the distance between any two first candidate paths in the same first path set is small, and the distance between any two first candidate paths in different first path sets is large. In an embodiment of the present application, the path planning device determines whether the distance between two first candidate paths is large or small based on the first threshold. Specifically, if the distance between the two first candidate paths is less than or equal to the first threshold, it means that the distance between the two first candidate paths is small. Conversely, if the distance between the two first candidate paths is greater than the first threshold, it means that the distance between the two first candidate paths is large. Optionally, the distance between the two first candidate paths is the minimum distance between the two first candidate paths.

[0046] In some embodiments, the path planning device clusters the at least two first candidate paths based on one of the following clustering algorithms: density-based spatial clustering of applications with noise (DBSCAN) and K-means clustering.

[0047] 106. Determine a second path set from the at least one first path set, wherein the number of first candidate paths in the second path set is greater than or equal to a second threshold.

[0048] Because the first candidate paths are feasible paths between the skin region of the target object and the end point of the target path, the distance between any two first candidate paths in the first path set is small, and thus the connected region corresponding to the first path set is likely to be a feasible region. For example, the target object includes a blood vessel, and the path cannot pass through the blood vessel, and thus the feasible region is a region excluding the blood vessel.

[0049] Optionally, the connected region corresponding to the first candidate path in the first path set can be determined by the following steps: determining at least one path region based on the first candidate path in the first path set, wherein the at least one path region includes a region through which the first candidate path in the first path set passes; and taking the region with the smallest area in the at least one path region as the connected region of the first path set.

[0050] The larger the area of the connected region corresponding to the first path set is, the higher the probability that the feasible region has a large area is when moving from the skin region of the target object to the end point of the target path according to the first candidate path in the first path set. Therefore, when moving from the skin region of the target object to the end point of the target path according to the first candidate path in the first path set, even if the actual path deviates from the first candidate path during the movement, the probability that the deviated position is still in the feasible region is high, that is, the probability that the actual path from the skin region of the target object to the end point of the target path is in the feasible region is high. In other words, the safety deviation of the target path is large, that is, the fault tolerance of the target path is high. During the movement from the skin region of the target object to the target point according to the path determined based on this mode, if the deviation between the actual path and the planned path is greater than or equal to the safety deviation, the actual path passes through an infeasible region, and if the deviation between the actual path and the planned path is less than the safety deviation, the actual path does not pass through the infeasible region. For example, the feasible region is a region excluding the blood vessel, and thus the infeasible region is a region including the blood vessel. If the area of the connected region corresponding to the first path set is large, when moving from the skin region of the target object to the end point of the target path according to the first candidate path in the first path set, even if the deviation between the actual path and the target path is large, the probability that the actual path passes through the blood vessel is low, and thus the probability that the blood vessel is collided is reduced. That is, the deviation between the actual path and the target path can be allowed to be large.

[0051] Because the probability that the actual path collides with the blood vessel due to the deviation between the actual path and the target path is low.

[0052] Because the number of the first candidate paths in the first path set is related to the area of the connected region corresponding to the first path set, when the number of the first candidate paths in the first path set is large, the area of the connected region corresponding to the first path set is high. In the embodiment of the present application, the path planning device determines whether the number of the first candidate paths in the first path set is large or small based on the second threshold value. Specifically, when the number of the first candidate paths in the first path set is greater than or equal to the second threshold value, it indicates that the number of the first candidate paths in the first path set is large, and vice versa. Therefore, the path planning device determines the second path set from the at least one first path set, wherein the number of the first candidate paths in the second path set is greater than or equal to the second threshold value.

[0053] 107. Determine the target path based on the second path set.

[0054] In one possible implementation, the path planning device selects an optional first candidate path in the second path set as the target path. In another possible implementation, the path planning device determines the center of the start point of the first candidate path in the second path set, and determines the start point closest to the center from the start point of the first candidate path in the second path set as the target start point. The first candidate path between the target start point and the end point of the target path is determined as the target path.

[0055] In Figure 1 In the clustering-based path planning method shown in the figure, the first three-dimensional CT image includes a skin region of the target object and a first tissue of the target object. After obtaining the first three-dimensional CT image, the planning device determines the end point of the target path from the first tissue and at least two first candidate points of the target path from the skin region. Then, based on the at least two first candidate points and the end point of the target path, at least two first candidate paths are determined. The at least two first candidate paths are clustered to obtain at least one first path set, wherein the distance between any two first candidate paths in the same first path set is less than or equal to the first threshold value, and the distance between any two first candidate paths belonging to different first path sets is greater than or equal to the first threshold value. The second path set is determined from the at least one first path set, wherein the number of the first candidate paths in the second path set is greater than or equal to the second threshold value. The target path is determined based on the second path set, which can improve the safety deviation of the target path and further improve the fault tolerance of the target path. It should be understood that the deviation of the actual path from the target path can be the distance between the actual path and the target path. It should be understood that the deviation of the actual path from the target path can be the distance between the actual path and the target path. Optionally, the deviation of the actual path from the target path is the minimum distance between the actual path and the target path.

[0056] As an optional implementation, the path planning device performs the following steps in performing step 103: 201. Determine at least two second candidate paths based on at least two skin points in the skin region and the end point of the target path, wherein the start point of a second candidate path in the at least two second candidate paths is a skin point in the at least two skin points, and the end point of the second candidate path in the at least two second candidate paths is the end point of the target path.

[0057] In the embodiments of the present application, the points in the skin region are skin points, and the at least two skin points in the skin region can be all the skin points in the skin region or part of the skin points in the skin region. The second candidate paths correspond to the skin points in the at least two skin points one by one. For example, the at least two skin points include skin point p1 and skin point p2, and the at least two second candidate paths include second candidate path t1 and second candidate path t2, wherein the start point of the second candidate path t1 is the skin point p1, and the start point of the second candidate path t2 is the skin point p2.

[0058] In a possible implementation, before performing step 201, the path planning device determines the at least two skin points in the skin region by performing the following steps: determine a reference sphere based on the end point of the target path and a preset radius, wherein the center of the reference sphere is the end point of the target path, and the radius of the reference sphere is the preset radius. Determine at least two second candidate points based on the skin points in the skin region that are in the reference sphere. Determine the at least two skin points based on the at least two second candidate points.

[0059] In this implementation, since the center of the reference sphere is the end point of the target path and the radius of the reference sphere is the preset radius, the distance from the skin points in the skin region that are in the reference sphere to the end point of the target path is less than or equal to the preset radius. Therefore, after determining the at least two second candidate points based on the skin points in the skin region that are in the reference sphere, and then determining the at least two skin points based on the at least two second candidate points, the length of the at least two second candidate paths determined based on the at least two skin points is less than or equal to the preset radius.

[0060] Optionally, in the case that the number of the skin points in the skin region that are in the reference sphere is greater than or equal to 2, the skin points in the skin region that are in the reference sphere are taken as the at least two second candidate points. In the case that the number of the skin points in the skin region that are in the reference sphere is less than 2, the at least two second candidate points are determined based on the skin points in the skin region that are in the reference sphere and the skin point in the skin region closest to the reference sphere.

[0061] 202. Determine at least two first normal vectors of the at least two skin points based on the first three-dimensional CT image.

[0062] In the embodiments of the present application, the first normal vector is a normal vector of a skin point in the at least two skin points. Optionally, based on the three-dimensional information of the pixel in the first three-dimensional CT image in the image coordinate system of the first three-dimensional CT image, the normal vector of the skin point in the at least two skin points in the image coordinate system can be determined, and the first normal vector is a vector in the image coordinate system of the first three-dimensional CT image.

[0063] 203. Determine the included angle between the second candidate path in the at least two second candidate paths and the corresponding first normal vector in the at least two first normal vectors to obtain at least two first included angles.

[0064] In the embodiments of the present application, the second candidate path corresponds to the first normal vector of the starting point of the second candidate path. For example, the at least two candidate paths include a second candidate path t1 and a second candidate path t2, and the at least two first normal vectors include a first normal vector v1 and a first normal vector v2, wherein the first normal vector t1 is the normal vector of the starting point of the second candidate path t1, and the first normal vector t2 is the normal vector of the starting point of the second candidate path t2. Then the second candidate path t1 corresponds to the first normal vector v1, and the second candidate path t2 corresponds to the first normal vector v2.

[0065] The first included angle is the included angle between the second candidate path and the corresponding first normal vector. Because the number of the second candidate paths is at least two, the number of the first included angles is also at least two.

[0066] 204. In the case that the number of the first included angles less than or equal to the third threshold value in the at least two first included angles is greater than or equal to 2, determine at least two first candidate points based on the skin points in the at least two skin points corresponding to the first included angles less than or equal to the third threshold value.

[0067] For example, the at least two second candidate paths include a second candidate path t1, a second candidate path t2 and a second candidate path t3, wherein the starting point of the second candidate path t1 is a skin point p1, the starting point of the second candidate path t2 is a skin point p2, and the starting point of the second candidate path t3 is a skin point p3. The first included angle between the second candidate path t1 and the normal vector of the skin point p1 is a first included angle j1, the first included angle between the second candidate path t2 and the normal vector of the skin point p2 is a first included angle j2, and the first included angle between the second candidate path t3 and the normal vector of the skin point p3 is a first included angle j3, wherein the skin point corresponding to the first included angle j1 is the skin point p1, the skin point corresponding to the first included angle j2 is the skin point p2, and the skin point corresponding to the first included angle j3 is the skin point p3. If the first included angle j1 and the first included angle j2 are both less than or equal to the third threshold value, then the path planning device determines at least two first candidate points based on the skin point p1 and the skin point p2.

[0068] 205、in the case that the number of the first included angles less than or equal to the third threshold value is less than 2, determining the at least two first candidate points based on the skin points corresponding to the n smallest first included angles among the at least two first included angles, wherein n is an integer greater than or equal to 2.

[0069] When moving along the target path from the skin region of the target object into the target object and towards the end point of the target object, the smaller the included angle between the target path and the normal vector of the start point of the target path in the skin region, the more conducive to reducing the deviation between the actual path moving towards the end point of the target object and the target path. Therefore, when the first included angle is small, the first candidate points are determined based on the skin points corresponding to the first included angle, which is conducive to reducing the deviation between the actual path moving towards the end point of the target object and the target path when the first candidate path is determined based on the first candidate points and the target path is determined based on the first candidate path.

[0070] In the embodiments of the present application, the path planning device determines whether the first included angle is large or small based on the third threshold value. Specifically, when the first included angle is less than or equal to the third threshold value, it indicates that the first included angle is small, and vice versa. Therefore, the path planning device determines the at least two first candidate points by executing step 204 or step 205.

[0071] In some schemes, the path planning device implements the step of "determining the at least two first candidate points based on the skin points corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points" in step 204 by executing the following steps: determining at least two third candidate paths based on the skin points corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points and the end point of the target path, wherein the start point of the third candidate path in the at least two third candidate paths is the skin point corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points, and the end point of the third candidate path in the at least two third candidate paths is the end point of the target path. Clustering the at least two third paths to obtain at least one third path set, wherein the distance between any two third candidate paths in the same third path set is less than or equal to a fourth threshold value, and the distance between any two third candidate paths belonging to different third path sets is greater than or equal to the fourth threshold value. Determining a fourth path set from the at least one third path set, wherein the number of third candidate paths in the fourth path set is greater than or equal to a fifth threshold value. Determining the at least two first candidate points based on the start points of the third candidate paths in the fourth path set.

[0072] In the scheme, because the distance between any two third candidate paths in the third path set is small, the connected region corresponding to the third path set is more likely to be a feasible region. Moreover, the area of the connected region corresponding to the third path set is large, which means that when the third candidate paths in the third path set are followed to move from the skin region of the target object to the end point of the target path, the area of the feasible region is more likely to be large. Therefore, when the start point of the third candidate path in the third path set is taken as the start point of the target path, even if the actual start point deviates from the start point of the target path during the actual movement along the target path, the actual path moving towards the end point of the target path is more likely to be in the feasible region. In other words, selecting the start point of the target path from the start points of the third candidate paths in the third path set can reduce the probability that the actual path enters the infeasible region due to deviation of the start point, thereby improving the safety deviation of the target path and further improving the fault tolerance of the target path.

[0073] Moreover, because the number of third candidate paths in the third path set is related to the area of the connected region corresponding to the third path set, when the number of third candidate paths in the third path set is large, the area of the connected region corresponding to the third path set is more likely to be large. In the embodiment of the present application, the path planning device determines whether the number of third candidate paths in the third path set is large or small based on the fifth threshold value. Specifically, when the number of third candidate paths in the third path set is greater than or equal to the fifth threshold value, it means that the number of third candidate paths in the third path set is large, and vice versa. Therefore, the path planning device determines a fourth path set from the at least one third path set, wherein the number of third candidate paths in the fourth path set is greater than or equal to the fifth threshold value. Then, based on the start points of the third candidate paths in the fourth path set, at least two first candidate points are determined, which can improve the fault tolerance of the target path determined based on the at least two first candidate points subsequently.

[0074] As an optional implementation, the path planning device further determines a second tissue from the first three-dimensional CT image before performing step 104, wherein the second tissue is different from the first tissue. Optionally, the second tissue is a tissue that cannot be passed through by the target path, for example, the second tissue is a blood vessel in the infeasible region mentioned in the foregoing example.

[0075] After the second tissue is determined, the path planning device performs the following steps in performing step 104: determining, based on the at least two first candidate points and the end point of the target path, at least two fourth candidate paths, wherein a start point of a fourth candidate path in the at least two fourth candidate paths is a candidate point in the at least two first candidate points, and an end point of the fourth candidate path in the at least two fourth candidate paths is the end point of the target path. Determining a minimum distance between the fourth candidate path in the at least two fourth candidate paths and the second tissue, to obtain at least two first distances. In a case where a first distance greater than or equal to a sixth threshold value in the at least two first distances is greater than or equal to 2, obtaining the at least two first candidate paths based on a fourth candidate path in the at least two fourth candidate paths corresponding to the first distance greater than or equal to the sixth threshold value. In a case where the first distance greater than or equal to the sixth threshold value in the at least two first distances is greater than 2, obtaining the at least two first candidate paths based on s fourth candidate paths in the at least two fourth candidate paths with the largest first distances, wherein s is an integer greater than or equal to 2. In this way, the probability that the at least two first candidate paths pass through the second tissue can be reduced, and in turn, the probability of collision with the second tissue when the target path is determined based on the at least two first candidate paths and the target object moves from the skin region of the target object to the end point of the target path according to the target path can be reduced.

[0076] In some schemes, the path planning device determines the second tissue from the first three-dimensional CT image by performing the following steps: determining, based on the at least two first candidate points, at least one first enclosing region, wherein a first enclosing region in the at least one first enclosing region includes the at least two first candidate points. Taking a first enclosing region with the smallest area in the at least one first enclosing region as a second enclosing region. Determining, based on the first three-dimensional CT image, a normal vector of the first candidate point in the second enclosing region, to obtain at least one second normal vector. Determining a third tissue of the target object from the first three-dimensional CT image, wherein the third tissue is a tissue different from the first tissue. Optionally, the third tissue is an unpassable tissue. It should be understood that in the embodiments of the present application, the unpassable tissue refers to a tissue that the target path cannot pass through, for example, the blood vessels mentioned above, or can also be an organ other than the first tissue, for example, the first tissue is the lung, and the unpassable tissue is the kidney. Determining the second tissue based on a part of the third tissue for which the distance to the at least two second normal vectors is less than or equal to a seventh threshold value.

[0077] In this scheme, the first enclosing region is a region including the at least two first candidate points, that is, the first enclosing region includes the at least two first candidate points. Optionally, the bounding box mentioned in the embodiments of the present application refers to an axis-aligned bounding box (AABB). The second enclosing region is a region with the smallest area in the at least one first enclosing region, that is, the second enclosing region is the smallest enclosing region of the at least two first candidate points.

[0078] Since the angle between the direction of entering the target object and the normal vector of the start point of the path is small when entering the target object from the skin area of the target object, the angle between the actual path and the normal vector of the start point is small when moving to the end point of the target path in the target object. Therefore, the probability of collision between the point in the impassable tissue far from the normal vector of the start point of the path and the actual path is small. Based on this, when it is necessary to determine the distance between the fourth candidate path in the at least two fourth candidate paths and the impassable tissue, the distance between the point far from the normal vector of the start point of the path in the impassable tissue and the fourth candidate path in the at least two fourth candidate paths can be determined after the point far from the normal vector of the start point of the path in the impassable tissue is determined, so that the data processing amount can be reduced and the processing efficiency can be improved.

[0079] In the embodiment of the present application, the path planning device determines the normal vector of the first candidate point in the second surrounding area based on the first three-dimensional CT image to obtain at least one second normal vector after determining the second surrounding area. Then, the third tissue of the target object is determined from the first three-dimensional CT image, and the second tissue is determined based on the points in the third tissue that are determined to be less than or equal to a seventh threshold value from the at least two second normal vectors, so that when the distance between the fourth candidate path in the at least two fourth candidate paths and the second tissue is determined subsequently, the data processing amount can be reduced and the processing efficiency can be improved. The seventh threshold value is a basis for determining whether the distance from the point in the third tissue to the second normal vector is small or large. The third tissue is a region in the first three-dimensional CT image, and the point in the third tissue can be understood as a pixel in the third tissue. The distance from the point in the third tissue to the at least two second normal vectors can be determined by the following steps: determining the minimum distance from the point in the third tissue to each of the at least two second normal vectors respectively to obtain at least two third distances. The minimum value of the at least two third distances is taken as the distance from the point in the third tissue to the at least two second normal vectors.

[0080] The clustering-based path planning method is explained below with the first tissue being the lung and the end point of the target path being the target point in the lung as an example. Please refer to Figure 2 , Figure 2 Another flowchart of the clustering-based path planning method provided in the embodiment of the present application is shown in FIG. 6. As shown in FIG. 6, the path planning device determines the second surrounding area based on the first three-dimensional CT image, and determines the normal vector of the first candidate point in the second surrounding area based on the first three-dimensional CT image to obtain at least one second normal vector. Then, the third tissue of the target object is determined from the first three-dimensional CT image, and the second tissue is determined based on the points in the third tissue that are determined to be less than or equal to a seventh threshold value from the at least two second normal vectors, so that when the distance between the fourth candidate path in the at least two fourth candidate paths and the second tissue is determined subsequently, the data processing amount can be reduced and the processing efficiency can be improved. The seventh threshold value is a basis for determining whether the distance from the point in the third tissue to the second normal vector is small or large. The third tissue is a region in the first three-dimensional CT image, and the point in the third tissue can be understood as a pixel in the third tissue. The distance from the point in the third tissue to the at least two second normal vectors can be determined by the following steps: determining the minimum distance from the point in the third tissue to each of the at least two second normal vectors respectively to obtain at least two third distances. The minimum value of the at least two third distances is taken as the distance from the point in the third tissue to the at least two second normal vectors. Figure 2As shown, the flow of the path planning method includes a first stage and a second stage, wherein the first stage is a simplified grid, and the second stage is path planning. Specifically, in the first stage, first, a first three-dimensional CT image is input to the path planning device, wherein the first three-dimensional CT image includes a lung of a target object, and a region corresponding to the lung in the first three-dimensional CT image has been labeled. Optionally, by segmenting the first three-dimensional CT image, the region corresponding to the lung can be determined, and then the region corresponding to the lung can be labeled. Then, the length of the path is screened, that is, the length of the path is taken as the basis to screen the tissue in the first three-dimensional CT image. Specifically, a reference sphere is determined based on a target point in the lung and a predetermined radius, wherein the center of the reference sphere is the target point in the lung, and the radius of the reference sphere is the predetermined radius. At least two skin points are determined from the first three-dimensional CT image. Then, the angle between the path and the first normal vector is screened, that is, the first angle between the path and the at least two first normal vectors is taken as the basis to determine the skin point corresponding to the first angle less than or equal to a third threshold value from the at least two skin points. Then, the clustering screening is performed, that is, based on the skin point corresponding to the first angle less than or equal to the third threshold value, at least two first candidate points are determined. Specifically, based on the skin point corresponding to the first angle less than or equal to the third threshold value in the at least two skin points and the end point of the target path, at least two third candidate paths are determined. The at least two third paths are clustered to obtain at least one third path set. The fourth path set is determined from the at least one third path set. Based on the start point of the third candidate path in the fourth path set, at least two first candidate points are determined. Then, the bounding box screening is performed, specifically, the first bounding region with the smallest area in the at least one first bounding region is taken as the second bounding region. Based on the first three-dimensional CT image, the normal vector of the first candidate point in the second bounding region is determined to obtain at least one second normal vector. The third tissue of the target object is determined from the first three-dimensional CT image. Based on the points in the third tissue that are determined to be less than or equal to a seventh threshold value from the at least two second normal vectors, the second tissue is determined. Then, based on the at least two first candidate points and the end point of the target path, at least two fourth candidate paths are determined. At this point, the flow of the first stage has been completely executed.

[0081] In stage two, first, at least two fourth candidate paths determined in stage one are obtained. Then collision detection is performed, specifically, the minimum distance between a fourth candidate path in the at least two fourth candidate paths and the second tissue is determined, to obtain at least two first distances. In the case where a first distance greater than or equal to a sixth threshold value in the at least two first distances is greater than or equal to 2, at least two fifth candidate paths are obtained based on a fourth candidate path corresponding to the first distance greater than or equal to the sixth threshold value in the at least two fourth candidate paths. In the case where a first distance greater than or equal to a sixth threshold value in the at least two first distances is less than 2, at least two fifth candidate paths are obtained based on s fourth candidate paths with the largest first distance in the at least two fourth candidate paths. Then, based on the angle between the path and the third normal vector, screening is performed to obtain at least two first candidate paths, wherein the third normal vector is the normal vector of the starting point of the at least two fifth candidate paths. That is, based on the second angle between the path and the at least two third normal vectors, the path corresponding to the second angle less than or equal to a third threshold value is determined from the starting point of the at least two fifth candidate paths as the at least two first candidate paths, wherein the second angle is the angle between the third normal vector and the fifth candidate path. Finally, based on clustering screening, a second path set is obtained, specifically, the at least two first candidate paths are clustered to obtain at least one first path set. At least one second path set is determined from the at least one first path set. Finally, the target path is determined through collision detection, specifically, for each second path set in the at least one second path set, the center of the path in the set is determined respectively to obtain at least one center path of the at least one second path set. Then the minimum distance between the at least one center path and the second tissue is determined to obtain at least two second distances. From the at least two second distances, a target distance less than or equal to the sixth threshold value is determined, and the center path corresponding to the target distance is determined as the target path.

[0082] Please refer to Figure 3 , Figure 3 Another flowchart of a path planning method based on clustering provided by an embodiment of the present application is shown in FIG. 6. In the method, first, a first path set is obtained based on the first tissue and the second tissue. Then, the target path is determined through collision detection, specifically, for each path set in the first path set, the center of the path in the set is determined respectively to obtain at least one center path of the first path set. Then the minimum distance between the at least one center path and the second tissue is determined to obtain at least two second distances. From the at least two second distances, a target distance less than or equal to the sixth threshold value is determined, and the center path corresponding to the target distance is determined as the target path. Figure 3In some embodiments, the image input to the path planning device is a first three-dimensional CT image, wherein the first three-dimensional CT image includes an end point of the target path. Optionally, the coordinates of the end point of the target path in the first three-dimensional CT image are (499, 250, 332). After the first three-dimensional CT image is input to the path planning device, the path planning device can output a result image, wherein the result image includes a start point of the target path. Optionally, the number of the start points of the target path is four, i.e., the target path can be determined based on any one of the four start points and the end point of the target path, wherein the coordinates of the four start points of the target path in the result image are (462.18, 415.86, 332.08), (492.18, 416.67, 332.88), (501.18, 183.31, 361.05), and (454.18, 175.26, 348.17), respectively.

[0083] Those skilled in the art can understand that, in the above method of the specific implementation, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0084] If the technical solution of the present application involves personal information, the product applying the technical solution of the present application has been explicitly informed of the personal information processing rules before processing the personal information and has obtained the personal independent consent. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the personal independent consent before processing the sensitive personal information and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as a camera, an explicit and prominent sign is set to inform that the personal information collection range has been entered and the personal information will be collected. If the individual voluntarily enters the collection range, it is deemed to consent to the collection of personal information. Or, on the device for processing personal information, the personal information processing rules are informed by using obvious signs / information, and the personal authorization is obtained by means of pop-up information or asking the individual to upload his / her personal information. The personal information processing can include the personal information processor, the processing purpose, the processing method, and the type of personal information processed.

[0085] The above describes the method of the embodiments of the present application in detail. The device of the embodiments of the present application is provided below.

[0086] Please refer to Figure 4 , Figure 4 A structure schematic diagram of a path planning device based on clustering provided by the embodiments of the present application is provided. The path planning device based on clustering 1 comprises an acquisition unit 11, a determination unit 12, and a clustering unit 13. The acquisition unit 11 is configured to acquire a first three-dimensional CT image, the first three-dimensional CT image comprising a skin region of a target object, and a first tissue of the target object; The determination unit 12 is configured to determine an end point of a target path from the first tissue; The determination unit 12 is further configured to determine at least two first candidate points of the target path from the skin region; The determination unit 12 is further configured to determine at least two first candidate paths based on the at least two first candidate points and the end point of the target path; The clustering unit 13 is configured to cluster the at least two first paths to obtain at least one first path set, a distance between any two first candidate paths in a same first path set being less than or equal to a first threshold, and a distance between any two first candidate paths respectively belonging to different first path sets being greater than or equal to the first threshold; The determination unit 12 is further configured to determine a second path set from the at least one first path set, a number of the first candidate paths in the second path set being greater than or equal to a second threshold; The determination unit 12 is further configured to determine the target path based on the second path set.

[0087] In combination with any one of the embodiments of the present application, the determination unit 12 is further configured to: determine at least two second candidate paths based on at least two skin points in the skin region and the end point of the target path, a start point of a second candidate path in the at least two second candidate paths being the skin point in the at least two skin points, and an end point of the second candidate path in the at least two second candidate paths being the end point of the target path; determine at least two first normal vectors of the at least two skin points based on the first three-dimensional CT image; determine at least two first angles between the second candidate path in the at least two second candidate paths and the corresponding first normal vector in the at least two first normal vectors; in a case where a number of the first angles less than or equal to a third threshold in the at least two first angles is greater than or equal to 2, determine the at least two first candidate points based on the skin point in the at least two skin points corresponding to the first angle less than or equal to the third threshold; In a case where the number of the first included angles that are less than or equal to the third threshold value among the at least two first included angles is less than 2, determining the at least two first candidate points based on the skin points corresponding to the n smallest first included angles among the at least two first included angles, the n being an integer greater than or equal to 2.

[0088] With reference to any one of the embodiments of the present application, the determining unit 12 is further configured to: determining a reference sphere based on the end point of the target path and a preset radius, the reference sphere having a center at the end point of the target path and a radius of the preset radius; determining at least two second candidate points based on the skin points in the skin region that are within the reference sphere; determining the at least two skin points based on the at least two second candidate points.

[0089] With reference to any one of the embodiments of the present application, the determining unit 12 is further configured to: determining at least two third candidate paths based on the skin points corresponding to the first included angles less than or equal to the third threshold value among the at least two skin points and the end point of the target path, the start point of the third candidate path among the at least two third candidate paths being the skin point corresponding to the first included angle less than or equal to the third threshold value among the at least two skin points, and the end point of the third candidate path among the at least two third candidate paths being the end point of the target path; clustering the at least two third paths to obtain at least one third path set, the distance between any two third candidate paths in a same third path set being less than or equal to a fourth threshold value, and the distance between any two third candidate paths belonging to different third path sets being greater than or equal to the fourth threshold value; determining a fourth path set from the at least one third path set, the number of the third candidate paths in the fourth path set being greater than or equal to a fifth threshold value; determining the at least two first candidate points based on the start points of the third candidate paths in the fourth path set.

[0090] With reference to any one of the embodiments of the present application, the determining unit 12 is further configured to: determining a second tissue from the first three-dimensional CT image, the second tissue being different from the first tissue; determine at least two fourth candidate paths based on the at least two first candidate points and the end point of the target path, wherein a start point of the fourth candidate path in the at least two fourth candidate paths is the candidate point in the at least two first candidate points, and an end point of the fourth candidate path in the at least two fourth candidate paths is the end point of the target path; determine a minimum distance between the fourth candidate path in the at least two fourth candidate paths and the second tissue, to obtain at least two first distances; in a case where the first distance greater than or equal to the sixth threshold value in the at least two first distances is greater than or equal to 2, obtain the at least two first candidate paths based on the fourth candidate path in the at least two fourth candidate paths corresponding to the first distance greater than or equal to the sixth threshold value; in a case where the first distance greater than or equal to the sixth threshold value in the at least two first distances is less than 2, obtain the at least two first candidate paths based on s fourth candidate paths in the at least two fourth candidate paths with the maximum first distance, wherein s is an integer greater than or equal to 2.

[0091] With reference to any one of the embodiments of the present application, the determining unit 12 is further configured to: determine at least one first surrounding area based on the at least two first candidate points, wherein the first surrounding area in the at least one first surrounding area comprises the at least two first candidate points; determine the first surrounding area with the minimum area in the at least one first surrounding area as a second surrounding area; determine a normal vector of the first candidate point in the second surrounding area based on the first three-dimensional CT image, to obtain at least one second normal vector; determine a third tissue of the target object from the first three-dimensional CT image, wherein the third tissue is different from the first tissue; determine the second tissue based on a point in the third tissue with a distance to the at least two second normal vectors less than or equal to a seventh threshold value.

[0092] In the embodiments of the present application, the first three-dimensional CT image includes a skin region of the target object and a first tissue of the target object. After obtaining the first three-dimensional CT image, the clustering-based path planning apparatus determines a terminal point of the target path from the first tissue and at least two first candidate points of the target path from the skin region. Then, based on the at least two first candidate points and the terminal point of the target path, at least two first candidate paths are determined. The at least two first candidate paths are clustered to obtain at least one first path set, wherein the distance between any two first candidate paths in the same first path set is less than or equal to a first threshold, and the distance between any two first candidate paths belonging to different first path sets is greater than or equal to the first threshold. A second path set is determined from the at least one first path set, wherein the number of first candidate paths in the second path set is greater than or equal to a second threshold. Based on the second path set, the target path is determined, which can improve the safety deviation of the target path and further improve the fault tolerance of the target path. It should be understood that the deviation of the actual path from the target path can be the distance between the actual path and the target path. It should be understood that the deviation of the actual path from the target path can be the distance between the actual path and the target path. Optionally, the deviation of the actual path from the target path is the minimum distance between the actual path and the target path.

[0093] In some embodiments, the apparatus provided by the embodiments of the present application has functions or includes modules that can be used to perform the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For brevity, it will not be described here.

[0094] Figure 5 A hardware structure schematic diagram of an electronic device provided by the embodiments of the present application is provided. The electronic device 2 includes a processor 21 and a memory 22. Optionally, the electronic device 2 further includes an input device 23 and an output device 24. The processor 21, the memory 22, the input device 23 and the output device 24 are coupled through a connector, which includes various interfaces, transmission lines or buses, etc. The embodiments of the present application do not make any limitation. It should be understood that in various embodiments of the present application, coupling means mutual contact in a specific way, including direct connection or indirect connection through other devices, for example, connection through various interfaces, transmission lines, buses, etc.

[0095] The processor 21 can be one or more graphics processing units (GPUs). In the case of the processor 21 being a GPU, the GPU can be a single-core GPU or a multi-core GPU. Optionally, the processor 21 can be a processor group composed of multiple GPUs, and the multiple processors are coupled to each other through one or more buses. Optionally, the processor can also be other types of processors, etc. The embodiments of the present application do not make any limitation.

[0096] The memory 22 can be used to store computer program instructions, and various computer program codes including program codes for implementing the schemes of the present application. Optionally, the memory includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read only memory (EPROM), or a compact disc read-only memory (CD-ROM), which is used for storing relevant instructions and data.

[0097] The input device 23 is used for inputting data and / or signals, and the output device 24 is used for outputting data and / or signals. The input device 23 and the output device 24 can be independent devices, or can be an integral device.

[0098] It can be understood that, in the embodiments of the present application, the memory 22 can be used not only for storing relevant instructions, but also for storing relevant data, and the embodiments of the present application do not limit the data stored in the memory.

[0099] It can be understood that, Figure 5 Only a simplified design of an electronic device is shown. In actual applications, the electronic device can also include other necessary elements, including but not limited to any number of input / output devices, processors, memories, etc., and all electronic devices that can implement the embodiments of the present application are within the protection scope of the present application.

[0100] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solutions. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0101] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here. Those skilled in the art can also clearly understand that each embodiment of the present application describes each with emphasis, and for the convenience and brevity of description, the same or similar parts can not be described in different embodiments. Therefore, the parts not described or not described in detail in a certain embodiment can refer to the description in other embodiments.

[0102] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is only a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0103] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0104] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0105] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a digital versatile disc (DVD)), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned method embodiments can be implemented by a computer program instructing relevant hardware to complete, the program can be stored in a computer readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The aforementioned storage medium includes read-only memory (ROM) or random access memory (RAM), a magnetic disc or an optical disc, and various media that can store program codes.

Claims

1. A cluster-based path planning method, characterized in that, The cluster-based path planning method comprises: obtaining a first three-dimensional CT image, the first three-dimensional CT image comprising a skin region of a target object, a first tissue of the target object; determining a terminal point of a target path from the first tissue; determining at least two first candidate points of the target path from the skin region; determining at least two first candidate paths based on the at least two first candidate points and the terminal point of the target path; clustering the at least two first candidate paths to obtain at least one first path set, the distance between any two first candidate paths in the same first path set being less than or equal to a first threshold, the distance between any two first candidate paths belonging to different first path sets being greater than or equal to the first threshold; determining a second path set from the at least one first path set, the number of first candidate paths in the second path set being greater than or equal to a second threshold; determining the target path based on the second path set.

2. The cluster-based path planning method of claim 1, wherein, The method further comprises: determining at least two second candidate paths based on the at least two skin points in the skin region and the terminal point of the target path, the starting point of the second candidate path in the at least two second candidate paths being the skin point in the at least two skin points, and the terminal point of the second candidate path in the at least two second candidate paths being the terminal point of the target path; determining at least two first normal vectors of the at least two skin points based on the first three-dimensional CT image; determining at least two first angles between the second candidate path in the at least two second candidate paths and the corresponding first normal vector in the at least two first normal vectors; in a case where the number of first angles less than or equal to a third threshold in the at least two first angles is greater than or equal to 2, determining the at least two first candidate points based on the skin points in the at least two skin points corresponding to the first angles less than or equal to the third threshold; in a case where the number of first angles less than or equal to the third threshold in the at least two first angles is less than 2, determining the at least two first candidate points based on the skin points in the at least two skin points corresponding to the n smallest first angles in the at least two first angles, the n being an integer greater than or equal to 2.

3. The cluster-based path planning method of claim 2, wherein, Before the step of determining at least two second candidate paths based on the at least two skin points in the skin region and the terminal point of the target path, the cluster-based path planning method further comprises: determining a reference sphere based on the terminal point of the target path and a preset radius, the center of the reference sphere being the terminal point of the target path, and the radius of the reference sphere being the preset radius; determining at least two second candidate points based on the skin points in the skin region within the reference sphere; determining the at least two skin points based on the at least two second candidate points.

4. The cluster-based path planning method according to claim 2 or 3, characterized in that, The determining the at least two first candidate points based on the skin points among the at least two skin points corresponding to the first angle that is less than or equal to the third threshold comprises: determining, based on the skin point among the at least two skin points corresponding to the first angle less than or equal to the third threshold and the end point of the target path, at least two third candidate paths, where the starting point of the third candidate path among the at least two third candidate paths is the skin point among the at least two skin points corresponding to the first angle less than or equal to the third threshold, and the end point of the third candidate path among the at least two third candidate paths is the end point of the target path; clustering the at least two third candidate paths to obtain at least one third path set, wherein a distance between any two third candidate paths in the same third path set is less than or equal to a fourth threshold, and a distance between any two third candidate paths in different third path sets is greater than or equal to the fourth threshold; determining a fourth path set from the at least one third path set, wherein the number of the third candidate paths in the fourth path set is greater than or equal to a fifth threshold; The at least two first candidate points are determined based on a starting point of the third candidate path in the fourth path set.

5. The cluster-based path planning method according to any one of claims 1 to 3, characterized in that, Before determining at least two first candidate paths based on the at least two first candidate points and the end point of the target path, the clustering-based path planning method further includes: determining a second tissue from the first three-dimensional CT image, the second tissue being different from the first tissue; The determining of at least two first candidate paths based on the at least two first candidate points and the end point of the target path includes: determining, based on the at least two first candidate points and the end point of the target path, at least two fourth candidate paths, wherein a starting point of the fourth candidate path in the at least two fourth candidate paths is the candidate point among the at least two first candidate points, and an end point of the fourth candidate path in the at least two fourth candidate paths is the end point of the target path; determining a minimum distance between the fourth candidate path among the at least two fourth candidate paths and the second tissue to obtain at least two first distances; Obtaining the at least two first candidate paths based on the fourth candidate path among the at least two fourth candidate paths corresponding to the first distance that is greater than or equal to the sixth threshold, when the first distance among the at least two first distances is greater than or equal to 2; When the first distance greater than or equal to the sixth threshold among the at least two first distances is less than 2, the at least two first candidate paths are obtained based on s fourth candidate paths having the largest first distance among the at least two fourth candidate paths, where s is an integer greater than or equal to 2.

6. The cluster-based path planning method of claim 5, wherein, The determining of the second tissue from the first three-dimensional CT image includes: determine at least one first enclosing region based on the at least two first candidate points, the first enclosing region in the at least one first enclosing region including the at least two first candidate points; determine a second enclosing region from the first enclosing region with the smallest area in the at least one first enclosing region; determine a normal vector of the first candidate point in the second enclosing region based on the first three-dimensional CT image, to obtain at least one second normal vector; determine a third tissue of the target object from the first three-dimensional CT image, the third tissue being different from the first tissue; determine the second tissue based on a point in the third tissue that is determined to be at a distance less than or equal to a seventh threshold value from the at least one second normal vector.

7. A cluster-based path planning apparatus, characterized by comprising: The clustering-based path planning device comprises: an acquisition unit configured to acquire a first three-dimensional CT image, the first three-dimensional CT image including a skin region of a target object and a first tissue of the target object; a determination unit configured to determine a terminal point of a target path from the first tissue; the determination unit is further configured to determine at least two first candidate points of the target path from the skin region; the determination unit is further configured to determine at least two first candidate paths based on the at least two first candidate points and the terminal point of the target path; a clustering unit configured to cluster the at least two first candidate paths to obtain at least one first path set, any two first candidate paths in a same first path set being at a distance less than or equal to a first threshold value, and any two first candidate paths belonging to different first path sets being at a distance greater than or equal to the first threshold value; the determination unit is further configured to determine a second path set from the at least one first path set, the number of first candidate paths in the second path set being greater than or equal to a second threshold value; the determination unit is further configured to determine the target path based on the second path set.

8. A surgical robot, characterized by The surgical robot comprises the clustering-based path planning device according to claim 7.

9. An electronic device, comprising: comprise: a processor and a memory, the memory being configured to store computer program code, the computer program code comprising computer instructions, in a case where the processor executes the computer instructions, the electronic device executes the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program comprising program instructions, in a case where the program instructions are executed by a processor, the processor executes the method according to any one of claims 1 to 6.

Images