Bone nail marker point extraction method, device, processing equipment and storage medium

Abstract

The present application relates to a bone screw marker point extraction method, apparatus, processing equipment and storage medium, wherein the method comprises: acquiring a three-dimensional scanned image of a bone screw extraction object; identifying a bone screw image of a target bone screw in the three-dimensional scanned image according to physical parameters of the bone screw; determining a head image of the target bone screw according to the bone screw image; determining a center position of a head of the target bone screw according to the head image; and determining a marker point position of the target bone screw according to the center position of the head of the target bone screw and a radius of a probe.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a method, device, processing equipment and storage medium for extracting bone nail markers. Background Art

[0002] Bone screws are parts used in medicine to connect bones. For example, bone screws can be used to stabilize fracture sites, fuse joints, reconstruct small bones in the foot, ankle, and toes, etc. Some bone screws need to be removed from the human body after being placed in the body for a period of time. If the bone screw extraction operation is performed when the detected bone screw position deviates from its actual position, it may cause secondary bone damage to the patient. Therefore, accurately detecting the position of the bone screw in the body and removing the bone screw from the corresponding position is a highly technical medical process.

[0003] In the related art, doctors usually extract bone screws manually. The commonly used extraction method is that the doctor roughly locates the marking point of the bone screw in the three-dimensional scanned image. The marking point can be, for example, the extraction point of the bone screw extracted by a bone screw extraction device. Then, the plane image at the marking point can be jointly displayed, for example, based on the multi-planar reformation (MPR) view in three coordinate directions, and then the extraction point of the bone screw is fine-tuned. It can be seen that the method of extracting bone screws in the related art depends on the doctor's operation and judgment, the accuracy cannot be guaranteed, and it takes a long time.

[0004] Therefore, an accurate and efficient method for automatically extracting bone screw marker points is urgently needed in the relevant technology. Summary of the invention

[0005] The embodiments of the present application provide a bone nail detection method, apparatus, processing device, and storage medium to at least solve the problem of low efficiency in extracting bone nail markers in the related art.

[0006] In a first aspect, an embodiment of the present application provides a method for extracting bone nail markers, comprising:

[0007] Acquire a three-dimensional scanning image of the bone screw extraction object;

[0008] identifying a bone screw image of a target bone screw in the three-dimensional scan image according to physical parameters of the bone screw;

[0009] Determine the head image of the target bone screw according to the bone screw image;

[0010] Determining the center position of the head of the target bone screw according to the head image;

[0011] The position of the marking point of the target bone screw is determined according to the center position of the head of the target bone screw and the radius of the probe.

[0012] The embodiment of the present application processes the three-dimensional scanned image of the bone screw extraction object, and can accurately determine the position of the mark point of the bone screw in the bone screw extraction object. Specifically, first, the bone screw image of the target bone screw is identified based on the physical parameters of the bone screw. Since the bone screw has inherent properties, the bone screw image can be relatively accurately identified based on the physical parameters. After determining the bone screw object, the head image, the center position of the head and the mark point position of the bone screw can be gradually determined. By using this layer-by-layer progressive method to obtain the mark point position, the target nature of the mark point position can be continuously enhanced, and the accuracy of the mark point position can be improved.

[0013] Optionally, in one embodiment of the present application, the physical parameters include bone screw material, bone screw size, and bone screw shape.

[0014] Optionally, in one embodiment of the present application, identifying a bone screw image of a target bone screw in the three-dimensional scanned image according to physical parameters of the bone screw includes:

[0015] Obtaining an image pixel value corresponding to each voxel in the three-dimensional scanned image;

[0016] Determine the image pixel range corresponding to the bone screw;

[0017] A target image area is screened out from the three-dimensional scanned image according to the image pixel value and the image pixel range.

[0018] Optionally, in one embodiment of the present application, it further includes:

[0019] Acquire the volume of at least one first connected area in the target image area;

[0020] Determine the volume range corresponding to the bone screw;

[0021] At least one second connected region whose volume is within the volume range is screened out from the at least one first connected region.

[0022] Optionally, in one embodiment of the present application, it further includes:

[0023] Obtaining a proportion of singular values ​​of a first main direction in the at least one second connected region among the singular values ​​of the three main directions, wherein the first main direction corresponds to a direction having the largest singular value among the three main directions;

[0024] Determine a threshold value of the proportion of the singular value in the first main direction of the bone screw in the singular values ​​in the three main directions;

[0025] At least one target connected area whose proportion is greater than the proportion threshold is screened out from the at least one second connected area.

[0026] Optionally, in one embodiment of the present application, determining the head image of the target bone screw according to the bone screw image includes:

[0027] Determine that the direction of the nail body of the target bone nail from the tail to the head is the positive direction;

[0028] The outermost region of the bone screw image distributed along the positive direction and occupying a preset proportion of the bone screw volume is used as the head image of the target bone screw.

[0029] Optionally, in one embodiment of the present application, determining the center position of the head of the target bone screw according to the head image includes:

[0030] Determine the outermost plane of the head image with the positive direction of the target bone screw as the normal vector, where the positive direction includes the direction of the nail body of the target bone screw from the tail to the head;

[0031] Projecting voxels contained in the head image into the outermost plane;

[0032] The center point of the projection point in the outermost plane is determined, and the center point is used as the center position of the head of the target bone screw.

[0033] Optionally, in one embodiment of the present application, determining the center point of the projection point in the outermost plane includes:

[0034] Step 1, randomly selecting a first projection point and a second projection point on the outermost plane, and determining a projection vector starting from the first projection point and pointing to the second projection point;

[0035] Step 2, determining multiple module values ​​of the projection point in the outermost plane on the projection vector, and determining the average value of the maximum value and the minimum value of the multiple module values ​​as the candidate center point of the projection point in the outermost plane;

[0036] Repeat step 1 and step 2 until the number of repetitions is not less than a preset threshold, and determine the center point of the projection point in the outermost plane based on the multiple candidate center points obtained.

[0037] Optionally, in one embodiment of the present application, determining the position of the marking point of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe includes:

[0038] Acquiring the radius of the probe and the head radius of the target bone screw;

[0039] Determining a marking distance of the target bone screw according to the radius of the probe and the radius of the head;

[0040] The position of the center of the head along the positive direction of the target bone screw at the distance from the marking is used as the marking point position of the target bone screw, and the positive direction includes the direction of the nail body of the target bone screw from the tail to the head.

[0041] In a second aspect, an embodiment of the present application provides a bone nail marker extraction device, comprising:

[0042] A three-dimensional scanning image acquisition module is used to acquire a three-dimensional scanning image of the bone screw extraction object;

[0043] A bone screw recognition module, used to recognize a bone screw image of a target bone screw in the three-dimensional scan image according to physical parameters of the bone screw;

[0044] A bone screw head recognition module, used to determine the head image of the target bone screw according to the bone screw image;

[0045] A head center determination module, used to determine the head center position of the target bone screw according to the head image;

[0046] The marking point determination module is used to determine the marking point position of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe.

[0047] In a third aspect, an embodiment of the present application provides a processing device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the bone nail marker point extraction method.

[0048] In a fourth aspect, an embodiment of the present application provides a computer storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute the bone nail marker point extraction method when running.

[0049] 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

[0050] 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:

[0051] Figure 1 is a method flow chart of a bone nail marker point extraction method provided in an embodiment of the present application;

[0052] Figure 2A This is a schematic diagram of a scenario provided by an embodiment of the present application;

[0053] Figure 2BThis is a schematic diagram of a scenario provided by an embodiment of the present application;

[0054] Figure 3 This is a schematic diagram of a scenario provided by an embodiment of the present application;

[0055] Figure 4 This is a schematic diagram of a scenario provided by an embodiment of the present application;

[0056] Figure 5 It is a schematic diagram of the module structure of the bone nail landmark extraction device provided in an embodiment of the present application;

[0057] Figure 6 It is a schematic diagram of the module structure of the processing device provided in the embodiment of the present application;

[0058] Figure 7 It is a conceptual partial view of the computer program product provided by the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0060] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0061] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or 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 direct or indirect. The "multiple" involved in this application refers to greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0062] The bone nail marker point extraction method described in the present application is described in detail below with reference to the accompanying drawings. Figure 1 It is a flow chart of an embodiment of the bone nail marker point extraction method provided by the present application. Although the present application provides the method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application. In the actual bone nail marker point extraction process or when the method is executed, the method can be executed in the method sequence shown in the embodiments or drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment).

[0063] Specifically, an embodiment of the bone nail marker extraction method provided in the present application is as follows: Figure 1 As shown, the method may include:

[0064] S101: Acquire a three-dimensional scanning image of a bone screw extraction object.

[0065] In the embodiment of the present application, the three-dimensional scanned image of the bone screw extraction object may include three-dimensional data obtained by scanning using a computed tomography (CT) device, a magnetic resonance imaging (MRI) device, a positron emission computed tomography (PET) device, an ultrasound device, etc., and the present application does not limit this. In addition, the bone screw extraction object is not limited to a human body, and may also include an animal, such as a pet that has undergone bone setting surgery.

[0066] S103: Identifying a bone screw image of a target bone screw in the three-dimensional scan image according to the physical parameters of the bone screw.

[0067] In the embodiment of the present application, in the bone screw extraction object, the bone screw often has a unique physical property. Therefore, based on the physical parameters of the bone screw, the position of the target bone screw in the three-dimensional scan image can be more accurately identified. Among them, the physical parameters may include the material of the bone screw, the size of the bone screw, the shape of the bone screw, etc. The bone screw material may include metal (such as ordinary steel, stainless steel, titanium, titanium alloy, etc.), and may also include chemical composite materials (such as chitin microfiber, chitosan fiber, polylactic acid fiber, etc.). In addition, the bone screw also has a fixed size and shape, typically, such as 32mm threaded nails, 16mm threaded nails and other specifications.

[0068] Considering the physical parameters of the bone screw material, the size of the bone screw, and the shape of the bone screw, from the perspective of screening capability, the material of the bone screw is greater than the size of the bone screw, and the size of the bone screw is greater than the shape of the bone screw. Therefore, the screening order of the bone screws can be set as the material of the bone screw, the size of the bone screw, and the shape of the bone screw. Based on this, the identification of the bone screw image of the target bone screw in the three-dimensional scanned image according to the physical parameters of the bone screw may include:

[0069] S201: Obtaining an image pixel value corresponding to each voxel in the three-dimensional scanned image;

[0070] S203: Determine the image pixel range corresponding to the bone screw;

[0071] S205: Filtering out a target image area from the three-dimensional scanned image according to the image pixel value and the image pixel range.

[0072] In the embodiment of the present application, the bone screws can be first screened based on the material of the bone screws, and specifically, the bone screw materials can be screened based on the image pixel value. Since the bone screws are used to connect bones, their hardness needs to be higher than that of bones. Therefore, the image pixel value of the bone screw material is significantly different from the image pixel value of the bones, other organs or tissues in the bone screw extraction object. For example, in a CT three-dimensional scanning image, the CT value of the bone screw material is much higher than the CT value of other organs or tissues. In addition, the image pixel range of the bone screw material can also be determined as [G min , G max ], where G min is the minimum value of image pixels, G max Of course, for different bone screw materials, the image pixel range may be different, which can be determined according to actual conditions.

[0073] After determining the image pixel value corresponding to each voxel in the three-dimensional scanned image and the image pixel range corresponding to the bone nail, the target image area can be screened out from the three-dimensional scanned image according to the image pixel value and the image pixel range. In one embodiment of the present application, the image area constituted by the voxels whose image pixel values ​​are within the image pixel range can be used as the target image area. In another embodiment of the present application, a dynamic threshold can also be set according to the image pixel range, and the voxels greater than or equal to the dynamic threshold constitute the target image area. In one example, the dynamic threshold T can be determined using the following formula:

[0074] T=G min +R*(G max –G min )

[0075] Among them, R is the threshold ratio, and its value range is [0, 1]. Then T g The value range is [G min , G max ]. By adjusting the value of R, the value of T can be dynamically adjusted to change the degree of screening. The specific screening result M(x,y,z) is expressed as:

[0076]

[0077] Where I(x,y,z) represents the image pixel value of the voxel with coordinates (x,y,z).

[0078] In the embodiment of the present application, the target image area obtained by screening according to the material of the bone screw can be further screened, and can be screened according to the size of the bone screw. Based on this, after S305, the following may also be included:

[0079] S301: Acquire the volume of at least one first connected region in the target image region;

[0080] S303: Determine the volume range corresponding to the bone screw;

[0081] S305: Filter out at least one second connected region whose volume is within the volume range from the at least one first connected region.

[0082] In the embodiment of the present application, considering that the bone nail belongs to a connected area in the three-dimensional scanning image, at least one first connected area can be firstly screened out from the target image area, and the volume of each first connected area can be obtained. The bone nail can also have a certain volume range, and the volume range can be expressed as the number range of voxels contained in the bone nail. For example, the range of the volume V of the bone nail is determined to be [V min , V max ], then we can get the screening result M(O i )for:

[0083]

[0084] Among them, O i is the coordinate set of voxels contained in the i-th first connected region.

[0085] In the embodiment of the present application, the at least one second connected area obtained by screening according to the size of the bone screw can be further screened, and can be screened according to the shape of the bone screw. Based on this, after step S405, the following may also be included:

[0086] S401: Obtain a proportion of singular values ​​of a first main direction in the singular values ​​of three main directions in the at least one second connected region, wherein the first main direction corresponds to a direction having the largest singular value among the three main directions;

[0087] S403: Determine a threshold value of the proportion of the singular value in the first main direction of the bone screw in the singular values ​​in the three main directions;

[0088] S405: Filter out at least one target connected area whose proportion is greater than the proportion threshold from the at least one second connected area.

[0089] In the embodiment of the present application, considering that the shape of the bone nail is slender, the at least one second connected region can be further screened according to the shape feature. The embodiment of the present application can use the singular value decomposition (SVD) algorithm for screening. First of all, the singular value decomposition can be performed on each second connected region to determine the three main directions of distribution of each second connected region in the three-dimensional space and the singular values ​​corresponding to the three main directions. According to the definition of the singular value, the larger the singular value, the greater the proportion of the distribution direction corresponding to the singular value of the second connected region in the three main directions. According to the shape feature of the bone nail, the distribution direction of the bone nail body should be the first main direction, and the first main direction is the direction with the largest singular value in the three main directions. Based on this, in the screening process, it can be verified whether the proportion of the singular value corresponding to the first main direction in the singular values ​​of the three main directions is large enough. If it is large enough, it can be determined that the second connected region to be verified meets the shape feature of the bone nail. Specifically, a threshold value T of the proportion of the singular value in the first main direction of the bone nail in the singular values ​​in the three main directions can be set. R , if we determine the proportion of the singular values ​​of the first main direction in the second connected region to the singular values ​​of the three main directions R v Greater than or equal to the proportion threshold T R , it can be determined that the second connected area meets the shape characteristics of the bone screw. v It can be calculated according to the following formula:

[0090]

[0091] Among them, V1 is the singular value in the first main direction in the second connected region, and V2 and V3 are the singular values ​​in the other two main directions respectively.

[0092] In the above embodiments, the determined target connected area can be used as the bone screw image of the target bone screw. By screening the bone screw image of the target bone screw in the order of bone screw material, bone screw size, and bone screw shape, the screening efficiency and screening accuracy can be maximized.

[0093] It should be noted that, in other embodiments, the bone screw image of the target bone screw can be obtained by screening according to any one or more of the bone screw material, bone screw size, and bone screw shape. The embodiment of the present application does not limit the physical parameters and screening order based on which the screening is based.

[0094] S105: Determine the head image of the target bone screw according to the bone screw image.

[0095] In the embodiment of the present application, since the extraction position of the bone screw is located at the head of the bone screw, the head image of the target bone screw can be determined first, and then the extraction position of the target bone screw can be determined from the head image. The proportion of the volume of the bone screw head to the volume of the entire bone screw can be a fixed value. Based on this, determining the head image of the target bone screw based on the bone screw image can include:

[0096] S501: Determine that the direction of the nail body of the target bone nail from the tail to the head is a positive direction;

[0097] S503: Using the outermost region of the bone screw image distributed along the positive direction and occupying a preset proportion of the bone screw volume as the head image of the target bone screw.

[0098] In the embodiment of the present application, the positive direction of the target bone screw can be determined, and the positive direction is the direction of the nail body of the target bone screw from the tail to the head. Figure 2A , Figure 2B Describe how to determine the positive direction. Figure 2A A three-dimensional scanned image 201 of a head skull is shown, and the three-dimensional scanned image 201 includes a plurality of bone screw images 202. Then, the center point O (Xc, Yc, Zc) of the three-dimensional scanned image 201 can be determined. In one example, assuming that the length, width, and height of the three-dimensional scanned image 201 are W, H, and D, respectively, the coordinates of the center point O can be (W / 2, H / 2, D / 2). Since the bone screw is inserted into the skull with the tail inside and the head outside, based on this, the first principal direction, any point on the bone screw, and the center point O can be used to determine the positive direction of the target bone screw. Specifically, Figure 2B is from Figure 2A The extracted bone screw image. Figure 2B As shown, select point P on the bone screw image of any target bone screw, vector The direction is parallel to the first principal direction of the target bone screw, and it is assumed that the vector is the positive direction of the target bone screw. Then, a line is drawn from the center point O to the point P to generate a vector If the vector If the angle between the assumed positive direction and the current assumed positive direction is an acute angle, the assumed positive direction is considered to be the positive direction; otherwise, the assumed positive direction is flipped 180 degrees and used as the positive direction of the target bone screw. Figure 2B As shown, due to the vector With vector The angle between them is an obtuse angle, so the vector The opposite direction of is taken as the positive direction of the target bone screw.

[0099] After determining the positive direction of the target bone screw, the outermost region of the bone screw image distributed along the positive direction and occupying a preset proportion of the bone screw volume can be used as the head image of the target bone screw. The preset proportion can be set to 10%, 15%, etc.

[0100] S107: Determine the center position of the head of the target bone screw according to the head image.

[0101] In an embodiment of the present application, the position of the mark point of the bone screw is related to the position of the head of the bone screw. Therefore, after determining the head image of the target bone screw, the center position of the head of the target bone screw can be determined in the head image. In an embodiment of the present application, the center position of the head can include the projection center point position of the head image in the outermost plane of the target bone screw. Specifically, determining the center position of the head of the target bone screw based on the head image includes:

[0102] S601: Determine the outermost plane of the head image with the positive direction of the target bone screw as the normal vector, where the positive direction includes the direction of the nail body of the target bone screw from the tail to the head;

[0103] S605: Projecting the voxels included in the head image onto the outermost plane;

[0104] S605: Determine the center point of the projection point in the outermost plane, and use the center point as the center position of the head of the target bone screw.

[0105] In the embodiment of the present application, the outermost plane has the positive direction of the target bone screw as a normal vector, and the positive direction includes the direction from the tail to the head of the nail body of the target bone screw. Figure 3 To illustrate this embodiment, Figure 3 As shown, the head image 301 is obtained by using the above embodiment, and then the voxels in the head image 301 can be projected into the outermost plane. Figure 3 The middle right figure shows a schematic diagram of the outermost plane observed along the positive direction of the target bone screw and the projection point in the outermost plane. Then, the center point of the projection point in the outermost plane is the center position of the head of the target bone screw.

[0106] In one embodiment of the present application, the center point of the projection point in the outermost plane may be determined by seeking candidate center points multiple times. Specifically, determining the center point of the projection point in the outermost plane may include:

[0107] Step 1, randomly selecting a first projection point and a second projection point on the outermost plane, and determining a projection vector starting from the first projection point and pointing to the second projection point;

[0108] Step 2, determining multiple module values ​​of the projection point in the outermost plane on the projection vector, and determining the average value of the maximum value and the minimum value of the multiple module values ​​as the candidate center point of the projection point in the outermost plane;

[0109] Step 3, repeating steps 1 and 2 until the number of repetitions is not less than a preset threshold, and determining the center point of the projection point in the outermost plane based on the multiple candidate center points obtained.

[0110] In the embodiment of the present application, the preset threshold value can be set to a value such as 100, 200, or 250, and the present application does not limit this. When multiple candidate center points are determined, the positions of the multiple candidate center points can be averaged, and the average value can be used as the center point of the projection point in the outermost plane, such as Figure 3 As shown, the center point is determined to be point C. In this embodiment, due to the small size of the bone screw, and the high accuracy of the extraction point position when extracting the bone screw from the bone screw extraction object, that is, the position accuracy of the center point of the projection point in the outermost plane has high requirements. By using multiple projections to obtain the position of the center point, the accuracy of the center point can be greatly improved. It should be noted that the method for determining the center point is not limited to the above examples. For example, other projection methods can also be used to determine the center point. Under the inspiration of the technical essence of this application, technical personnel in the relevant field may also make other changes, but as long as the functions and effects achieved are the same or similar to those of this application, they should be covered within the scope of protection of this application.

[0111] S109: Determine the position of the marking point of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe.

[0112] In an embodiment of the present application, the probe is a spherical tool for extracting bone screws, and correspondingly, the head of the bone screw is provided with a recess, which matches at least part of the probe. The position of the marking point may include the center position of the sphere when the probe extracts the target bone screw. Based on this, in an embodiment of the present application, the position of the marking point of the target bone screw is determined according to the center position of the head of the target bone screw and the radius of the probe, including:

[0113] S701: Acquire the radius of the probe and the head radius of the target bone screw;

[0114] S703: Determine a marking distance of the target bone screw according to the radius of the probe and the radius of the head;

[0115] S705: The position of the center of the head of the target bone screw at a distance from the marking in the positive direction of the target bone screw is used as the marking point position of the target bone screw, where the positive direction includes the direction of the nail body of the target bone screw from the tail to the head.

[0116] Combine the following Figure 4 The above embodiments are described in detail. Figure 4 As shown, the center of the head of the target bone screw is determined to be C, and the radius R of the probe and the radius CM of the head of the target bone screw can be obtained. Then, the marking distance of the target bone screw can be determined according to the Pythagorean theorem of the triangle EMC: Point E is the mark point position of the target bone screw. Specifically, point E can be found by taking the center C of the head as the starting point and along the length of the positive direction EC.

[0117] Combined with the above Figures 1 to 4 The bone screw marker point extraction method provided by the present application is described in detail. Figure 5 , describing the bone nail landmark extraction device 500 provided in the present application, including:

[0118] A three-dimensional scanning image acquisition module 501 is used to acquire a three-dimensional scanning image of a bone screw extraction object;

[0119] A bone screw recognition module 503, used to recognize a bone screw image of a target bone screw in the three-dimensional scan image according to physical parameters of the bone screw;

[0120] A bone screw head recognition module 505, configured to determine the head image of the target bone screw according to the bone screw image;

[0121] A head center determination module 507, used to determine the head center position of the target bone screw according to the head image;

[0122] The marking point determination module 509 is used to determine the position of the marking point of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe.

[0123] Optionally, in one embodiment of the present application, the physical parameters include bone screw material, bone screw size, and bone screw shape.

[0124] Optionally, in one embodiment of the present application, the bone nail identification module is specifically used to:

[0125] Obtaining an image pixel value corresponding to each voxel in the three-dimensional scanned image;

[0126] Determine the image pixel range corresponding to the bone screw;

[0127] A target image area is screened out from the three-dimensional scanned image according to the image pixel value and the image pixel range.

[0128] Optionally, in one embodiment of the present application, the bone nail identification module is specifically used to:

[0129] Acquire the volume of at least one first connected area in the target image area;

[0130] Determine the volume range corresponding to the bone screw;

[0131] At least one second connected region whose volume is within the volume range is screened out from the at least one first connected region.

[0132] Optionally, in one embodiment of the present application, the bone nail identification module is specifically used to:

[0133] Obtaining a proportion of singular values ​​of a first main direction in the at least one second connected region among the singular values ​​of the three main directions, wherein the first main direction corresponds to a direction having the largest singular value among the three main directions;

[0134] Determine a threshold value of the proportion of the singular value in the first main direction of the bone screw in the singular values ​​in the three main directions;

[0135] At least one target connected area whose proportion is greater than the proportion threshold is screened out from the at least one second connected area.

[0136] Optionally, in one embodiment of the present application, the bone nail head recognition module is specifically used to:

[0137] Determine that the direction of the nail body of the target bone nail from the tail to the head is the positive direction;

[0138] The outermost region of the bone screw image distributed along the positive direction and occupying a preset proportion of the bone screw volume is used as the head image of the target bone screw.

[0139] Optionally, in one embodiment of the present application, the head center determination module is specifically used to:

[0140] Determine the outermost plane of the head image with the positive direction of the target bone screw as the normal vector, where the positive direction includes the direction of the nail body of the target bone screw from the tail to the head;

[0141] Projecting voxels contained in the head image into the outermost plane;

[0142] The center point of the projection point in the outermost plane is determined, and the center point is used as the center position of the head of the target bone screw.

[0143] Optionally, in one embodiment of the present application, the head center determination module is specifically used to:

[0144] Step 1, randomly selecting a first projection point and a second projection point on the outermost plane, and determining a projection vector starting from the first projection point and pointing to the second projection point;

[0145] Step 2, determining multiple module values ​​of the projection point in the outermost plane on the projection vector, and determining the average value of the maximum value and the minimum value of the multiple module values ​​as the candidate center point of the projection point in the outermost plane;

[0146] Repeat step 1 and step 2 until the number of repetitions is not less than a preset threshold, and determine the center point of the projection point in the outermost plane based on the multiple candidate center points obtained.

[0147] Optionally, in one embodiment of the present application, the marking point determination module is specifically used to:

[0148] Acquiring the radius of the probe and the head radius of the target bone screw;

[0149] Determining a marking distance of the target bone screw according to the radius of the probe and the radius of the head;

[0150] The position of the center of the head along the positive direction of the target bone screw at the distance from the marking is used as the marking point position of the target bone screw, and the positive direction includes the direction of the nail body of the target bone screw from the tail to the head.

[0151] The embodiment of the present application further provides a processing device 600, which can be a physical device or a cluster of physical devices, or a virtualized cloud device, such as at least one cloud computing device in a cloud computing cluster. For ease of understanding, the present application uses the processing device 600 as an independent physical device to illustrate the structure of the processing device 600.

[0152] like Figure 6As shown, the processing device 600 includes: a processor and a memory for storing processor executable instructions; wherein the processor is configured to implement the above-mentioned apparatus when executing the instructions. The processing device 600 includes a memory 601, a processor 603, a bus 605 and a communication interface 607. The memory 601, the processor 603 and the communication interface 607 communicate with each other through the bus 601. The bus 605 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The communication interface 607 is used for communicating with the outside.

[0153] The processor 603 may be a central processing unit (CPU). The memory 601 may include a volatile memory, such as a random access memory (RAM). The memory 601 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a HDD or a SSD.

[0154] The memory 601 stores executable codes, and the processor 603 executes the executable codes to perform the aforementioned test scenario construction method.

[0155] An embodiment of the present application provides a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0156] An embodiment of the present application provides a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0157] In some embodiments, the disclosed methods may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture. Figure 7Schematically illustrates a conceptual partial view of an example computer program product arranged according to at least some embodiments presented herein, the example computer program product comprising a computer program for executing a computer process on a computing device. In one embodiment, the example computer program product 700 is provided using a signal bearing medium 701. The signal bearing medium 701 may include one or more program instructions 703, which when executed by one or more processors may provide the above-described Figure 1 The functions or parts of the functions described. In addition, Figure 7 Program instructions 703 in also describe example instructions.

[0158] In some examples, the signal bearing medium 701 may include a computer readable medium 705, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM) or a random access memory (RAM), etc. In some embodiments, the signal bearing medium 701 may include a computer recordable medium 707, such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, etc. In some embodiments, the signal bearing medium 701 may include a communication medium 705, such as, but not limited to, a digital and / or analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communication link, a wireless communication link, etc.). Thus, for example, the signal bearing medium 701 may be communicated by a wireless form of the communication medium 705 (e.g., a wireless communication medium that complies with the IEEE 802.11 standard or other transmission protocols). One or more program instructions 703 may be, for example, computer executable instructions or logic implementation instructions. In some examples, a computing device such as the computing device described for Figure 2 may be configured to provide various operations, functions, or actions in response to program instructions 703 communicated to the computing device by one or more of a computer-readable medium 705, a computer-recordable medium 707, and / or a communication medium 705. It should be understood that the arrangement described herein is only for the purpose of example. Thus, it will be appreciated by those skilled in the art that other arrangements and other elements (e.g., machines, interfaces, functions, sequences, and functional groups, etc.) can be used instead, and some elements can be omitted together according to the desired result. In addition, many of the elements described are functional entities that can be implemented as discrete or distributed components or in any appropriate combination and position in conjunction with other components.

[0159] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, system and computer program product according to multiple embodiments of the present application. In this regard, each square frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the function marked in the square frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square frames can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the function involved.

[0160] It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented by hardware (such as a circuit or ASIC (Application Specific Integrated Circuit)) that performs the corresponding function or action, or can be implemented by a combination of hardware and software, such as firmware.

[0161] Although the invention is described herein in conjunction with various embodiments, in the process of practicing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. A single processor or other unit may implement several functions listed in the claims. The fact that certain measures are recited in mutually different dependent claims does not mean that these measures cannot be combined to produce good results.

[0162] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for extracting bone screw marker points, characterized in that: include: Acquire a three-dimensional scanning image of the bone screw extraction object; identifying a bone screw image of a target bone screw in the three-dimensional scan image according to physical parameters of the bone screw; Determine the head image of the target bone screw according to the bone screw image; Determining the center position of the head of the target bone screw according to the head image; Determining the position of the marking point of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe; These include: Obtaining the radius of the probe and the head radius of the target bone screw; the probe is a spherical tool; Determining a marking distance of the target bone screw according to the radius of the probe and the radius of the head; The position of the center of the head along the positive direction of the target bone screw at the distance from the marking is used as the marking point position of the target bone screw, and the positive direction includes the direction of the nail body of the target bone screw from the tail to the head.

2. The bone nail marker extraction method according to claim 1, characterized in that: The physical parameters include bone screw material, bone screw size, and bone screw shape.

3. The bone nail marker extraction method according to claim 2, characterized in that: The step of identifying a bone screw image of a target bone screw in the three-dimensional scanned image according to the physical parameters of the bone screw comprises: Obtaining an image pixel value corresponding to each voxel in the three-dimensional scanned image; Determine the image pixel range corresponding to the bone screw; A target image area is screened out from the three-dimensional scanned image according to the image pixel value and the image pixel range.

4. The bone nail marker extraction method according to claim 3, characterized in that: Also includes: Acquire the volume of at least one first connected area in the target image area; Determine the volume range corresponding to the bone screw; At least one second connected region whose volume is within the volume range is screened out from the at least one first connected region.

5. The bone nail marker extraction method according to claim 4, characterized in that: Also includes: Obtaining a proportion of singular values ​​of a first main direction in the at least one second connected region to the singular values ​​of the three main directions, wherein the first main direction corresponds to a direction having the largest singular value among the three main directions; Determine a threshold value of the proportion of the singular value in the first main direction of the bone screw in the singular values ​​in the three main directions; At least one target connected area whose proportion is greater than the proportion threshold is screened out from the at least one second connected area.

6. The bone nail marker extraction method according to claim 1, characterized in that: The step of determining the head image of the target bone screw according to the bone screw image includes: Determine that the direction of the nail body of the target bone nail from the tail to the head is the positive direction; The outermost region of the bone screw image distributed along the positive direction and occupying a preset proportion of the bone screw volume is used as the head image of the target bone screw.

7. The bone nail marker extraction method according to claim 1, characterized in that: The step of determining the center position of the head of the target bone screw according to the head image includes: Determine the outermost plane of the head image with the positive direction of the target bone screw as the normal vector, where the positive direction includes the direction of the nail body of the target bone screw from the tail to the head; Projecting voxels contained in the head image into the outermost plane; The center point of the projection point in the outermost plane is determined, and the center point is used as the center position of the head of the target bone screw.

8. The bone nail marker extraction method according to claim 7, characterized in that: Determining the center point of the projection point in the outermost plane includes: Step 1, randomly selecting a first projection point and a second projection point on the outermost plane, and determining a projection vector starting from the first projection point and pointing to the second projection point; Step 2, determining multiple module values ​​of the projection point in the outermost plane on the projection vector, and determining the average value of the maximum value and the minimum value of the multiple module values ​​as the candidate center point of the projection point in the outermost plane; Repeat step 1 and step 2 until the number of repetitions is not less than a preset threshold, and determine the center point of the projection point in the outermost plane based on the multiple candidate center points obtained.

9. A bone screw marker point extraction device, characterized in that: include: A three-dimensional scanning image acquisition module is used to acquire a three-dimensional scanning image of the bone screw extraction object; A bone screw recognition module, used to recognize a bone screw image of a target bone screw in the three-dimensional scan image according to physical parameters of the bone screw; A bone screw head recognition module, used to determine the head image of the target bone screw according to the bone screw image; A head center determination module, used to determine the head center position of the target bone screw according to the head image; A marking point determination module, used to determine the position of the marking point of the target bone screw according to the center position of the head of the target bone screw and the radius of the probe; These include: Obtaining the radius of the probe and the head radius of the target bone screw; the probe is a spherical tool; Determining a marking distance of the target bone screw according to the radius of the probe and the radius of the head; The position of the center of the head along the positive direction of the target bone screw at the distance from the marking is used as the marking point position of the target bone screw, and the positive direction includes the direction of the nail body of the target bone screw from the tail to the head.

10. A processing device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the bone nail landmark extraction method according to any one of claims 1 to 8.

11. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the bone nail marker extraction method according to any one of claims 1 to 8 when running.

Images