Implant protrusion detection method and device and storage medium

Abstract

The invention relates to an implant protrusion detection method and device and a storage medium, and the method comprises the steps: obtaining the structure information of a target physiological part in a to-be-detected image; the target physiological part is a physiological part matched with the implant; determining a target space matched with the implant according to the structural information of the target physiological part; obtaining implantation position information of the implant; according to the structure information of the target physiological part and the implantation position information of the implant, whether the implant is located in the target space or not is detected. By means of the method and device, the problem that in the prior art, protrusion detection of implants such as the interbody fusion cage cannot be achieved, and consequently bad consequences are caused after the implantation position of the interbody fusion cage is inaccurate is solved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device and storage medium for detecting protrusion of an implant. Background Art

[0002] Lumbar diseases (such as lumbar disc herniation) are usually caused by factors such as rupture of the intervertebral disc annulus and degenerative displacement of the lumbar vertebrae. They are common clinical diseases that seriously affect patients' daily lives. In order to help patients with treatment, an intervertebral fusion device (cage) is usually implanted between the human lumbar vertebrae to replace the intervertebral disc. In clinical scenarios, if the model of the intervertebral fusion device selected or implanted is too large or the implantation position is incorrect, a part of the intervertebral fusion device will protrude outside the vertebral body. At this time, it is necessary to reselect a different model of intervertebral fusion device and perform multiple implants.

[0003] In the prior art, it is not possible to detect the protrusion of implants such as intervertebral fusion cages. Summary of the invention

[0004] The present application provides a method, device and storage medium for detecting protrusion of an implant, so as to solve the problem that the prior art fails to detect protrusion of implants such as intervertebral fusion cages.

[0005] In a first aspect, the present application provides a method for detecting protrusion of an implant, the method comprising:

[0006] Acquiring structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant;

[0007] Determining a target space for fitting the implant according to structural information of the target physiological part;

[0008] Acquiring implantation position information of the implant;

[0009] Whether the implant is located in the target space is detected according to the structural information of the target physiological part and the implantation position information of the implant.

[0010] In some embodiments, determining a target space for fitting the implant according to the structural information of the target physiological part includes:

[0011] Determining edge points of a target physiological structure of the target physiological part according to the structural information of the target physiological part; the target physiological structure is a physiological structure adjacent to at least two sides of the implant;

[0012] The target space is determined according to the edge points of the target physiological structure.

[0013] In some embodiments, determining edge points of a target physiological structure of the target physiological part according to the structural information of the target physiological part includes:

[0014] Determining a fitting surface of the target physiological structure according to the structural information of the target physiological part;

[0015] The edge point of the target physiological structure is determined according to the fitting surface of the target physiological structure and the center of the surface of the target physiological structure.

[0016] In some embodiments, determining the edge point of the target physiological structure according to the fitting surface of the target physiological structure and the center of the surface of the target physiological structure includes:

[0017] Taking a first vector and a second vector on the fitting surface of the target physiological structure through the center of the surface of the target physiological structure;

[0018] Determine a target plane according to the first vector and the second vector, wherein the target plane intersects with the fitting surface;

[0019] The edge points of the target physiological structure are determined according to the intersection point set between the surface of the target physiological structure and the target plane.

[0020] In some embodiments, determining the target plane according to the first vector and the second vector includes:

[0021] The first vector is rotated a preset number of times with a preset angle value as a step length to obtain a plurality of rotated first vectors; wherein the preset angle value×preset number=360°;

[0022] Determine a plurality of target planes according to the plurality of rotated first vectors and the second vector;

[0023] A plurality of intersection point sets are determined according to a plurality of target planes intersecting with the surface of the target physiological structure; and a plurality of edge points of the target physiological structure are determined according to the plurality of intersection point sets.

[0024] In some embodiments, determining the fitting surface of the target physiological structure according to the structural information of the target physiological part includes:

[0025] Performing image segmentation on the image to be detected to obtain a point set of the target physiological structure;

[0026] The point set of the surface of the target physiological structure is fitted to obtain a fitting surface of the target physiological structure.

[0027] In some embodiments, the target physiological part includes a first physiological part and a second physiological part, and determining the target space according to edge points of the target physiological structure includes:

[0028] matching the edge point of the target physiological structure of the first physiological part with the edge point of the target physiological structure of the second physiological part according to the distance between the edge point of the target physiological structure of the first physiological part and the edge point of the target physiological structure of the second physiological part;

[0029] Connect the matched edge points of the target physiological structure of the first physiological part and the edge points of the target physiological structure of the second physiological part to generate a mesh plane;

[0030] The target space is determined according to the grid plane.

[0031] In some embodiments, detecting whether the implant is in the target space according to the target space and the implantation position information of the implant comprises:

[0032] Acquiring implantation position information of the implant in the image to be detected;

[0033] Whether the implant is in the target space is determined based on the positional relationship between the implantation position information of the implant and the plane where the grid plane is located.

[0034] In some embodiments, judging whether the implant is in the target space according to the positional relationship between the implantation position information of the implant and the plane where the grid plane is located includes:

[0035] Calculating a normal vector of the grid plane;

[0036] Constructing a plane equation of the grid plane according to the normal vector;

[0037] Determining the implantation position coordinates of the implant according to the implantation position information of the implant;

[0038] Substituting the implantation position coordinates of the implant into the plane equation of the grid plane to obtain a judgment value;

[0039] According to the judgment value, it is determined whether the implant is in the target space.

[0040] In a second aspect, the present application provides a device for detecting protrusion of an implant, the device comprising:

[0041] A first acquisition module is used to acquire structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant;

[0042] A determination module, used for determining a target space adapted to the implant according to the structural information of the target physiological part;

[0043] A second acquisition module is used to acquire implantation position information of the implant;

[0044] The detection module is used to detect whether the implant is located in the target space according to the structural information of the target physiological part and the implantation position information of the implant.

[0045] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the implant protrusion detection method described in the first aspect.

[0046] Compared with the prior art, the present application provides an implant protrusion detection method, device and storage medium, which obtain the structural information of the target physiological part and the implantation position information of the implant from the image to be detected, determine the target space for adapting the implant according to the structural information of the target physiological part and the implantation position information of the implant, and detect whether the implant is located in the target space according to the structural information of the target physiological part and the implantation position information of the implant, thereby realizing implant protrusion detection, which solves the problem that the prior art cannot realize protrusion detection of implants such as intervertebral fusion devices.

[0047] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 It is a hardware structure block diagram of a terminal for executing a method for detecting protrusion of an implant according to an embodiment of the present application;

[0050] Figure 2 is a flow chart of a method for detecting protrusion of an implant according to an embodiment of the present application;

[0051] Figure 3 is a flow chart of a method for detecting protrusion of an implant according to the present specific embodiment;

[0052] Figure 4 is a schematic diagram of the structure of an implant and a target physiological part of this specific embodiment;

[0053] Figure 5 is a schematic diagram of an edge point of this specific embodiment;

[0054] Figure 6 It is a structural block diagram of an implant protrusion detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0056] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0057] The method embodiments provided in this application can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 1 is a hardware structure block diagram of a terminal for executing a method for detecting protrusion of an implant according to an embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0058] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for detecting protrusion of an implant in the present embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0059] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0060] In the present application, a method for detecting protrusion of an implant is provided. Figure 2 is a flow chart of a method for detecting protrusion of an implant according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0061] Step S210, obtaining structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant.

[0062] Specifically, the image to be detected includes an implant and a physiological part that matches the implant, namely, a target physiological part. The image to be detected is segmented to obtain a mask of the target physiological part, and the structural information of the target physiological part is obtained according to the mask of the target physiological part. The structural information of the target physiological part here includes the position information of the target physiological part and the coordinate information of the target physiological part. The mask of the target physiological part includes at least information such as the category information of the target physiological part, the position information of the target physiological part, the coordinate information of the target physiological part, and the shape information of the target physiological part.

[0063] The implant here may be an implanted intervertebral fusion device, and the target physiological part here may be a physiological part compatible with or adjacent to the implanted intervertebral fusion device, such as a vertebral body of the spine adjacent to the implanted intervertebral fusion device above the implanted intervertebral fusion device and a vertebral body of the spine adjacent to the implanted intervertebral fusion device below the implanted intervertebral fusion device. The image to be detected here may be a magnetic resonance imaging (MRI) image, a computed tomography (CT) image, a positron emission computed tomography (PET) image, etc., which is not specifically limited here.

[0064] Step S220, determining a target space for fitting the implant according to the structural information of the target physiological part.

[0065] Specifically, according to the structural information of the target physiological part obtained in step S210, a target space adapted to the implant is determined, and the target space is the spatial position where the implant needs to be implanted. The target physiological part here can be multiple physiological parts adapted to the implant, and the target space here can be a space determined according to the structural information of the multiple target physiological parts.

[0066] Step S230, obtaining implantation position information of the implant.

[0067] Specifically, the implantation position information of the implant in the image to be detected is obtained, and the image to be detected is segmented to obtain the implant in the image to be detected and the implantation position information of the implant.

[0068] Step S240, detecting whether the implant is located in the target space based on the structural information of the target physiological part and the implantation position information of the implant.

[0069] Specifically, based on the structural information of the target physiological part obtained in step S210 and the implantation position information of the implant obtained in step S230, it is detected whether the implant is located in the target space.

[0070] In this embodiment, the structural information of the target physiological part and the implantation position information of the implant are obtained from the image to be detected, the target space for fitting the implant is determined according to the structural information of the target physiological part and the implantation position information of the implant, and based on the structural information of the target physiological part and the implantation position information of the implant, it is detected whether the implant is located in the target space, thereby realizing protrusion detection of the implant, which solves the problem in the prior art that the protrusion detection of implants such as intervertebral fusion devices cannot be realized, resulting in inaccurate implantation position of the intervertebral fusion devices and causing adverse consequences.

[0071] In some of the embodiments, a target space for fitting the implant is determined based on structural information of the target physiological part, including: determining edge points of a target physiological structure of the target physiological part based on the structural information of the target physiological part; the target physiological structure is a physiological structure adjacent to at least two sides of the implant; and determining the target space based on the edge points of the target physiological structure.

[0072] In some of the embodiments, the edge points of the target physiological structure of the target physiological part are determined according to the structural information of the target physiological part, including: determining the fitting surface of the target physiological structure according to the structural information of the target physiological part; determining the edge points of the target physiological structure according to the fitting surface of the target physiological structure and the center of the surface of the target physiological structure. The target physiological structure here can be the end plate of the target physiological part, such as when the target physiological part is a vertebral body of the spine adjacent to the implanted intervertebral fusion device and above the implanted intervertebral fusion device, the target physiological structure can be the lower end plate of the vertebral body; for example, when the target physiological part is a vertebral body of the spine adjacent to the implanted intervertebral fusion device and below the implanted intervertebral fusion device, the target physiological structure can be the upper end plate of the vertebral body. The edge of the upper end plate and the edge of the lower end plate constitute the target space as a whole.

[0073] In some of the embodiments, edge points of the target physiological structure are determined based on a fitting surface of the target physiological structure and the center of the surface of the target physiological structure, including: taking a first vector and a second vector passing through the center of the surface of the target physiological structure on the fitting surface of the target physiological structure; determining a target plane based on the first vector and the second vector, where the target plane intersects with the fitting surface; and determining edge points of the target physiological structure based on a set of intersection points between the surface of the target physiological structure and the target plane.

[0074] Specifically, the first vector and the second vector are multiplied to obtain a target plane intersecting with the fitting surface, and the edge points of the target physiological structure are determined according to the intersection point set of the surface of the target physiological structure and the target plane. Further specifically, the two points with the farthest distance from each other are selected in the intersection point set as the two edge points of the target physiological structure.

[0075] In some of the embodiments, determining the target plane according to the first vector and the second vector includes:

[0076] The first vector is rotated a preset number of times with a preset angle value as a step size to obtain multiple rotated first vectors; wherein, the preset angle value×preset number of times=360°; multiple target planes are determined based on the multiple rotated first vectors and second vectors; multiple intersection point sets are determined based on the multiple target planes intersecting with the surface of the target physiological structure; multiple edge points of the target physiological structure are determined based on the multiple intersection point sets.

[0077] Specifically, the preset angle value step length h=180 / n, where 1<=n<=180, the preset angle value step length h is the angle of each rotation of the first vector, the first vector rotates with the preset angle value step length h until it rotates once, the number of rotations m=360 / h, that is, m first vectors are generated by rotation, the m first vectors and the second vector are respectively multiplied to obtain m target planes intersecting with the fitting surface, and the m groups of edge points of the target physiological structure are determined according to the surface of the target physiological structure and the m groups of intersection points of the m target planes. The target space is subsequently determined according to the m groups of edge points.

[0078] In some embodiments, determining edge points of the target physiological structure based on a set of intersections between a surface of the target physiological structure and a target plane includes: determining multiple edge points of the target physiological structure based on multiple sets of intersections between the surface of the target physiological structure and multiple target planes.

[0079] Specifically, according to the multiple intersection points of the surface of the target physiological structure and the multiple target planes, the two points with the farthest distance in each intersection point set are taken as two edge points of the target physiological structure, thereby determining the multiple edge points of the target physiological structure. In some embodiments, according to the structural information of the target physiological part, the fitting surface of the target physiological structure is determined, including: performing image segmentation on the image to be detected to obtain the point set of the target physiological structure; fitting the point set of the surface of the target physiological structure to obtain the fitting surface of the target physiological structure.

[0080] Specifically, the image to be detected is segmented to obtain a mask of the target physiological part, the mask of the target physiological part includes coordinate information of the target physiological part, and a point set of the target physiological structure corresponding to the target physiological part is obtained according to the coordinate information of the target physiological part.

[0081] In some of the embodiments, the target physiological part includes a first physiological part and a second physiological part, and the target space is determined according to the edge points of the target physiological structure, including: matching the edge points of the target physiological structure of the first physiological part and the edge points of the target physiological structure of the second physiological part according to the distance between the edge points of the target physiological structure of the first physiological part and the edge points of the target physiological structure of the second physiological part; connecting the matched edge points of the target physiological structure of the first physiological part and the edge points of the target physiological structure of the second physiological part to generate a grid plane; and determining the target space according to the grid plane.

[0082] In some of the embodiments, detecting whether the implant is in the target space is performed based on the target space and the implantation position information of the implant, including: acquiring the implantation position information of the implant in the image to be detected; and judging whether the implant is in the target space based on the positional relationship between the implantation position information of the implant and the plane where the grid plane is located.

[0083] In some of the embodiments, whether the implant is in the target space is determined based on the positional relationship between the implant position information of the implant and the plane where the grid plane is located, including: calculating the normal vector of the grid plane based on the points on the grid plane; constructing the plane equation of the grid plane based on the normal vector; determining the implant position coordinates of the implant based on the implant position information of the implant; substituting the implant position coordinates of the implant into the plane equation of the grid plane to obtain a judgment value; and determining whether the implant is in the target space based on the judgment value.

[0084] Specifically, according to the direction of the normal vector, a judgment rule is determined, and according to the judgment value and the determined judgment rule, it is determined whether the implant is in the target space. For example, when the normal vector points to the outside of the target space, the implant position coordinates of the implant are substituted into the plane equation of the grid plane to obtain a judgment value. When the judgment value is greater than or equal to 0, it is determined that the implant is outside the target space or on the boundary of the target space. When the judgment value is less than 0, it is determined that the implant is in the target space; when the normal vector points to the inside of the target space, the implant position coordinates of the implant are substituted into the plane equation of the grid plane to obtain a judgment value. When the judgment value is less than or equal to 0, it is determined that the implant is outside the target space or on the boundary of the target space. When the judgment value is greater than 0, it is determined that the implant is in the target space.

[0085] The embodiments of the present application are described and illustrated below through specific examples.

[0086] Figure 3 FIG. 4 is a flow chart of a method for detecting protrusion of an implant according to this specific embodiment. Figure 3 and Figure 4 As shown, the process includes the following steps:

[0087] Step S310, segmenting the original CT spinal column image in which the intervertebral fusion cage B is implanted to obtain a first vertebral body A1 above the intervertebral fusion cage B and a second vertebral body A2 below the intervertebral fusion cage.

[0088] Specifically, the original CT spine image is segmented to obtain the first vertebra A1 above the intervertebral fusion cage B and the second vertebra A2 below the intervertebral fusion cage. Further specifically, the original CT spine image is segmented to obtain the mask of the first vertebra A1 above the intervertebral fusion cage B and the mask of the second vertebra A2 below the intervertebral fusion cage, the mask of the first vertebra A1 at least includes the category information of the first vertebra A1, the position information of the first vertebra A1, the coordinate information of the first vertebra A1, the shape information of the first vertebra A1 and other information, and the mask of the second vertebra A2 at least includes the category information of the second vertebra A2, the position information of the second vertebra A2, the coordinate information of the second vertebra A2, the shape information of the second vertebra A2 and other information.

[0089] The original CT spine image here is the image to be detected described in the aforementioned embodiment, the first vertebral body and the second vertebral body here are the target physiological parts described in the aforementioned embodiment, and the intervertebral fusion device here is the implant described in the aforementioned embodiment.

[0090] Step S320: extracting coordinate information of the surface of the lower end plate of the first vertebral body A1 and coordinate information of the surface of the upper end plate of the second vertebral body A2.

[0091] Specifically, the coordinate information of the surface of the lower end plate of the first vertebra A1 is extracted according to the mask of the first vertebra A1, and the coordinate information of the surface of the upper end plate of the second vertebra A2 is extracted according to the mask of the second vertebra A2, and the center C1 of the surface of the lower end plate of the first vertebra A1 and the center C2 of the surface of the upper end plate of the second vertebra A2 are obtained.

[0092] The surface of the lower end plate of the first vertebral body A1 and the surface of the upper end plate of the second vertebral body A2 are the surfaces of the target physiological structures described in the above examples.

[0093] Step S330: determine a point set on the surface of the lower end plate of the first vertebral body A1, and fit the point set on the surface of the lower end plate of the first vertebral body A1 to obtain a fitting surface L1.

[0094] Specifically, the original CT spine image is segmented to obtain the first vertebra A1 and the lower end plate of the first vertebra A1. More specifically, the original CT spine image is segmented to obtain the mask of the first vertebra A1 above the intervertebral fusion device B, and the point set on the surface of the lower end plate of the first vertebra A1 is determined based on the mask of the first vertebra A1. Alternatively, more specifically, the original CT spine image is segmented to obtain the mask of the lower end plate of the first vertebra A1, and the point set on the surface of the lower end plate of the first vertebra A1 is determined based on the mask of the lower end plate of the first vertebra A1. The mask of the lower end plate of the first vertebra A1 here includes at least information such as category information of the lower end plate of the first vertebra A1, position information of the lower end plate of the first vertebra A1, coordinate information of the lower end plate of the first vertebra A1, and shape information of the lower end plate of the first vertebra A1. A point set on the surface of the lower end plate of the first vertebral body A1 is fitted to obtain a fitting surface L1 , which passes through the center C1 of the surface of the lower end plate of the first vertebral body A1 .

[0095] Step S340, within the fitting surface L1, randomly select a direction vector V1 and a fixed vector V2 through the center C1, determine a first plane L2 according to the direction vector V1, the fixed vector V2 and the center C1, and determine an intersection point set according to the first plane L2.

[0096] Specifically, Figure 5 As shown, in the fitting surface L1, through the center C1, any direction vector V1 and fixed vector V2 are taken. According to the direction vector V1, the fixed vector V2 and the center C1, the first plane L2 is determined, wherein the first plane L2 is perpendicular to the fitting surface L1, and the intersection set of the first plane L2 and the surface of the lower end plate of the first vertebral body A1 is taken, and the intersection set is as follows Figure 5 The dotted part in the figure. The direction vector V1 and the fixed vector V2 are multiplied to determine the first plane L2.

[0097] Step S350: determining edge points according to the intersection point set.

[0098] Specifically, select the two points with the farthest distance from each other from the intersection point set, such as Figure 5 There are two points C3 in the middle, which are the two edge points of the lower end plate of the first vertebra A1.

[0099] Step S360: determining the edge point set P1 of the lower end plate of the first vertebral body A1 according to the edge points.

[0100] Specifically, the preset angle value step length h is set to 180 / n, 1<=n<=180, the direction vector V1 in step S350 is rotated by an angle of h, and steps S340 and S350 are executed to obtain the other two edge points. By analogy, the edge point set P1 of the lower end plate of the first vertebra A1 is finally obtained. The preset angle value step length h is the angle of each rotation of the direction vector V1. The direction vector V1 is rotated with the preset angle value step length h until it rotates one circle. The number of rotations m=360 / h, that is, m direction vectors V1 are generated by rotation. The m direction vectors V1 are respectively multiplied by the fixed vector V2 to obtain m first planes L2 intersecting with the fitting surface. According to the m groups of intersection points of the first plane L2 and the surface of the lower end plate of the first vertebra A1, the m groups of edge points of the lower end plate of the first vertebra A1 are determined, and the target space is subsequently determined according to the m groups of edge points. Regarding the selection of the preset angle value step h, if the preset angle value step h is too large (or the smaller n is), it will lead to the inability to extract enough edge point sets, and thus the inability to form an effective grid, which will affect the effect of the intervertebral fusion cage protrusion detection algorithm; and if the preset angle value step h is too small (or the larger n is), it will lead to a relatively large amount of calculation. Therefore, it is recommended to set n between 10<=n<=180.

[0101] Here, the direction vector V1 is the first vector described in the aforementioned embodiment, the fixed vector V2 is the second vector described in the aforementioned embodiment, and the first plane L2 is the target plane described in the aforementioned embodiment.

[0102] Step S370: determine the edge point set P2 of the upper end plate of the second vertebral body A2.

[0103] Specifically, similar to the determination method of the edge point set P1 of the lower end plate of the first vertebra A1, for the upper end plate of the second vertebra A2, a plane is fitted based on the point set on the surface of the end plate, and the plane passes through the center C2 of the surface of the upper end plate of the second vertebra A2. In the plane, a direction vector V3 is randomly selected through the center C2, and steps S340, S350 and S360 are executed to obtain the edge point set P2 of the upper end plate of the second vertebra A2. The preset angle value step length for determining the edge point set P1 of the lower end plate of the first vertebra A1 is equal to the preset angle value step length for determining the edge point set P2 of the upper end plate of the second vertebra A2, and the number of points in the edge point set P1 is equal to the number of points in the edge point set P2.

[0104] Step S380: Match the edge point set P1 and the edge point set P2 to determine a closed grid.

[0105] Specifically, we obtain the edge point set P1 and the edge point set P2. At this time, the number of points in the two edge point sets is equal. We need to match the two point sets one by one according to the distance to make a closed grid. And the implanted intervertebral fusion device is closed in the intervertebral space. The closed grid is formed by connecting multiple adjacent triangular facets in sequence, such as Figure 4 As shown, for example, the point P21 in the edge point set P2 that is closest to the point P11 in the edge point set P1 is determined, a triangular patch is determined based on the point P11, the point P21, and the point P12 adjacent to the point P11, and a triangular patch is determined based on the point P11, the point P21, and the point P22 adjacent to the point P21. The space formed by the closed grid here is the target space of the adaptive implant described in the above embodiments.

[0106] Step S390, determining whether the intervertebral fusion cage is beyond the range of the vertebral body by determining whether the coordinates of the intervertebral fusion cage are inside or outside the grid.

[0107] Specifically, the judgment principle is as follows: for any triangular face, calculate the normal vector of the face, and determine whether the intervertebral fusion cage breaks through the vertebral body by judging whether the plane equation of a point outside the plane is greater than 0 or less than 0. j And the corresponding normal vector, the plane equation is A j *x+B j *y+C j *z+D j = 0. For any volume data (or mesh data) V of the implanted three-dimensional intervertebral fusion cage i = {Xi,Yi,Zi}, V i Substitute it into the plane equation and get the judgment value Value = A j *Xi+B j *Yi+C j *Zi+D j When the triangle F j When the direction of the normal vector points to the outside of the space enclosed by the grid, if Value>0, it means that point V i Not in the grid, Value<0, then point V i In the grid, Value = 0, which means point V i On the plane. Among them, i represents the subscript of the volume data, Xi, Yi, Zi represent the volume data V i The coordinate position of the surface patch. j represents the subscript of the fitted surface patch, A j , B j . C j D j It is a patch F j Plane parameters, where (A j , Bj . C j ) is the triangular patch F j Normal vector, first of all, the face is a plane formed by 3 points (point a, point b and point c), then the vector (ac) is cross-producted with the vector (ab) to get the normal vector. For any point of the intervertebral fusion device, only when the value of the point and all facets is less than 0, the point is considered to be within the space surrounded by the grid. If there is a facet whose value is greater than 0, the point is considered to be outside the space surrounded by the grid. The above operation is traversed for all volume data of the intervertebral fusion device. Only when the value of all volume data of the intervertebral fusion device is less than 0, the intervertebral fusion device is considered to have not broken through the vertebral body.

[0108] In this embodiment, the structural information of the vertebral body and the implantation position information of the implant are obtained from the original CT spine image, the target space for fitting the implant is determined based on the structural information of the vertebral body and the implantation position information of the implant, and whether the implant is located in the target space is detected based on the structural information of the end plate and the implantation position information of the implant, thereby realizing protrusion detection of the implant, which solves the problem in the prior art that the protrusion detection of implants such as intervertebral fusion devices cannot be realized, thereby causing adverse consequences due to inaccurate implantation position of the intervertebral fusion devices.

[0109] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0110] The present application also provides an implant protrusion detection device, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated here. The terms "module", "unit", "subunit", etc. used below can be a combination of software and / or hardware that implements the predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0111] Figure 6 is a structural block diagram of an implant protrusion detection device according to an embodiment of the present application, such as Figure 6 As shown, the device comprises:

[0112] The first acquisition module 710 is used to acquire structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant;

[0113] A determination module 720 is used to determine a target space for fitting the implant based on the structural information of the target physiological part;

[0114] The second acquisition module 730 is used to acquire implantation position information of the implant;

[0115] The detection module 740 is used to detect whether the implant is located in the target space based on the structural information of the target physiological part and the implantation position information of the implant.

[0116] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0117] The present application also provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0118] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0119] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0120] S1, obtaining structural information of a target physiological part in an image to be detected; the target physiological part is a physiological part that matches the implant;

[0121] S2, determining the target space of the adaptive implant according to the structural information of the target physiological part;

[0122] S3, obtaining implantation position information of the implant;

[0123] S4, detecting whether the implant is located in the target space according to the structural information of the target physiological part and the implantation position information of the implant.

[0124] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0125] In addition, in combination with the implant protrusion detection method provided in the above embodiment, a storage medium can also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, the steps of any implant protrusion detection method in the above embodiment are implemented.

[0126] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0127] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0128] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0129] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for detecting protrusion of an implant, characterized in that: The method comprises: Acquiring structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant; Determining a target space for fitting the implant according to structural information of the target physiological part; Acquiring implantation position information of the implant; Whether the implant is located in the target space is detected according to the structural information of the target physiological part and the implantation position information of the implant.

2. The implant protrusion detection method according to claim 1, characterized in that: Determining a target space for adapting the implant according to the structural information of the target physiological part includes: Determining edge points of a target physiological structure of the target physiological part according to the structural information of the target physiological part; the target physiological structure is a physiological structure adjacent to at least two sides of the implant; The target space is determined according to the edge points of the target physiological structure.

3. The implant protrusion detection method according to claim 2, characterized in that: The step of determining edge points of a target physiological structure of the target physiological part according to the structural information of the target physiological part comprises: Determining a fitting surface of the target physiological structure according to the structural information of the target physiological part; The edge point of the target physiological structure is determined according to the fitting surface of the target physiological structure and the center of the surface of the target physiological structure.

4. The method for detecting implant protrusion according to claim 3, characterized in that: The step of determining the edge point of the target physiological structure according to the fitting surface of the target physiological structure and the center of the surface of the target physiological structure comprises: Taking a first vector and a second vector on the fitting surface of the target physiological structure through the center of the surface of the target physiological structure; Determine a target plane according to the first vector and the second vector, wherein the target plane intersects with the fitting surface; The edge points of the target physiological structure are determined according to the intersection point set between the surface of the target physiological structure and the target plane.

5. The method for detecting implant protrusion according to claim 4, characterized in that: The step of determining a target plane according to the first vector and the second vector includes: The first vector is rotated a preset number of times with a preset angle value as a step length to obtain a plurality of rotated first vectors; wherein the preset angle value×preset number of times=360°; Determine a plurality of target planes according to the plurality of rotated first vectors and the second vector; A plurality of intersection point sets are determined according to a plurality of target planes intersecting with the surface of the target physiological structure; and a plurality of edge points of the target physiological structure are determined according to the plurality of intersection point sets.

6. The method for detecting implant protrusion according to claim 3, characterized in that: Determining the fitting surface of the target physiological structure according to the structural information of the target physiological part includes: Performing image segmentation on the image to be detected to obtain a point set of the target physiological structure; The point set of the surface of the target physiological structure is fitted to obtain a fitting surface of the target physiological structure.

7. The method for detecting implant protrusion according to claim 2, characterized in that: The target physiological part includes a first physiological part and a second physiological part, and the target space is determined according to the edge points of the target physiological structure, including: matching the edge point of the target physiological structure of the first physiological part with the edge point of the target physiological structure of the second physiological part according to the distance between the edge point of the target physiological structure of the first physiological part and the edge point of the target physiological structure of the second physiological part; Connect the matched edge points of the target physiological structure of the first physiological part and the edge points of the target physiological structure of the second physiological part to generate a mesh plane; The target space is determined according to the grid plane.

8. The method for detecting implant protrusion according to claim 7, characterized in that: The step of detecting whether the implant is in the target space according to the target space and the implantation position information of the implant comprises: Acquiring implantation position information of the implant in the image to be detected; Whether the implant is in the target space is determined based on the positional relationship between the implantation position information of the implant and the plane where the grid plane is located.

9. The method for detecting implant protrusion according to claim 8, characterized in that: The step of judging whether the implant is in the target space according to the positional relationship between the implantation position information of the implant and the plane where the grid plane is located comprises: Calculating a normal vector of the grid plane; Constructing a plane equation of the grid plane according to the normal vector; Determining the implantation position coordinates of the implant according to the implantation position information of the implant; Substituting the implantation position coordinates of the implant into the plane equation of the grid plane to obtain a judgment value; According to the judgment value, it is determined whether the implant is in the target space.

10. An implant protrusion detection device, characterized in that: The device comprises: A first acquisition module is used to acquire structural information of a target physiological part in the image to be detected; the target physiological part is a physiological part that matches the implant; A determination module, used for determining a target space adapted to the implant according to the structural information of the target physiological part; A second acquisition module is used to acquire implantation position information of the implant; The detection module is used to detect whether the implant is located in the target space according to the structural information of the target physiological part and the implantation position information of the implant.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the implant protrusion detection method according to any one of claims 1 to 9 are implemented.

Images