A method and device for determining implant position in CBCT image

Abstract

The present invention discloses a method and device for determining the position of an implant in a CBCT image, wherein the method comprises: obtaining a CBCT image after the implant is implanted; cutting a three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; in each view group, respectively determining the view with the smallest distance from the central section of the implant, determining the first position of the implantation point and the first position of the apex point of the implant; determining the second position of the implantation point and the second position of the apex point of the implant; and determining the error between the implantation position and the expected position of the implant. The method can quickly obtain the position of the implantation point and the apex point of the implant from the CBCT image, and improve the accuracy of the implantation position precision calculation.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a method and a device for determining the position of an implant in a CBCT image. Background Art

[0002] Robot-assisted oral implantation is a hot field in recent years. Robot-assisted implantation can improve the accuracy of implant placement. The accompanying surgical navigation system can display the implant placement status in real time, providing objective and quantifiable data and indicators for doctors to judge the accuracy of implant placement. To evaluate the implant placement accuracy, it is necessary to fuse and register the postoperative CBCT image with the preoperative CBCT image. Finally, the angle and distance deviation between the postoperative implant and the preoperative implant are calculated from the fused image to evaluate the robot's implant accuracy. The angle refers to the angle between the center line of the preoperative implant and the center line of the postoperative implant. The distance includes the Euclidean distance between the implant point of the preoperative implant and the implant point of the postoperative implant, and the Euclidean distance between the apex point of the preoperative implant and the apex point of the postoperative implant.

[0003] The line connecting the implant's insertion point and apex point constitutes the centerline of the implant. The implant's insertion point and apex point are recorded by the surgical navigation system when planning the implant's insertion position before surgery. The position of the implant's insertion point and apex point after surgery needs to be obtained from the postoperative CBCT image. The previous method usually uses a manual method to find the slice where the implant is located in the slice sequence of the CBCT image and manually mark the implant point and apex point on the slice image. Manual marking is not only time-consuming and labor-intensive, and is greatly affected by subjective factors, but it is also usually difficult to mark the exact position. Summary of the invention

[0004] The present invention provides a method and device for determining the position of an implant in a CBCT image, which can solve the technical problems of low accuracy and low efficiency in identifying the position of the implant after oral implantation.

[0005] In the above-mentioned method embodiments of the present invention, the method for determining the implant position in the CBCT image includes:

[0006] Step S1: Acquire a CBCT image after implantation;

[0007] Step S2: cutting the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; the sagittal view group includes one or more sagittal views;

[0008] Step S3: in each view group, respectively determine the view with the shortest distance from the central section of the implant, use the view as the preferred view, all the preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set;

[0009] Step S4: determining a second position of the implantation point of the implant and a second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point;

[0010] Step S5: determining the error between the implantation position of the implant and the expected position.

[0011] Optionally, in step S2, wherein:

[0012] The Cartesian coordinate system of the CBCT image is used as the reference coordinate system, the direction of the centerline of the implant in the CBCT image is set as the Z axis, the center of the inner circle of the implant is used as the origin, and the plane perpendicular to the Z axis and including the center of the inner circle of the implant is used as the horizontal plane; the direction passing through the center of the circle in the horizontal plane and horizontally to the right in the horizontal plane is determined as the X axis, and the line passing through the center of the circle in the horizontal plane and perpendicular to the X axis in the horizontal plane is determined as the Y axis; the three-dimensional image is cut from a direction parallel to the Z axis to obtain two groups of views parallel to the Z axis and perpendicular to each other, the view group in the direction parallel to the XZ plane is a coronal view group, the coronal view group includes one or more coronal views, and the view group in the direction parallel to the YZ plane is a sagittal view group; the centerline of the implant is a line running through the apex point and the implantation point of the implant.

[0013] Optionally, the step S3, in which in each view group, the view with the shortest distance from the central section of the implant is determined respectively and the view is used as the preferred view, comprises:

[0014] Step S31: obtaining a view group, and performing image processing on each view in the view group;

[0015] The acquired view group is a view group of the coronal view group and the sagittal view group for which a preferred view has not been determined;

[0016] Step S32: for the processed view group, filter the view without implant based on the actual width Width and length Length of the implant; for each view in the processed view group: calculate the bounding box of all contours in the view, if in the view, the length of all bounding boxes is outside the range [L*A, L*(2-A)], and the width of all bounding boxes is outside the range [W*A, W*(2-A)], then filter out the view; wherein W = Width / Spacing, L = Length / Spacing, A is the filtering accuracy, the range is (0, 1], Spacing is the pixel spacing in the CBCT image;

[0017] Step S33: for each view retained after filtering: obtain a bounding box with the smallest deviation from the actual size of the implant, use the contour area corresponding to the bounding box as the detection area S of the view, perform rotation correction and scaling on the detection area S to obtain a transformed detection area S', calculate the similarity between the detection area S' and the standard image, and record it as SSIM;

[0018] The SSIMs corresponding to the views retained after filtering are compared, and the view corresponding to the SSIM with the largest value is the preferred view of the view group.

[0019] Optionally, the step S3, determining a first position of an implantation point and a first position of an apex point of the implant based on the preferred view set, comprises:

[0020] Step S34: for each preferred image in the preferred view set: obtain the detection area S of the preferred image; if the absolute value of the slope K of the detection area S is greater than 1, the detection area S is turned into a vertical orientation, and then the detection area S is divided into two areas from top to bottom, namely the upper area S_up and the lower area S_down, and the number of non-empty pixels in the two areas S_up and S_down is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located; if the absolute value of K of the detection area S is less than 1, the detection area S is turned into a horizontal orientation, and then the detection area S is divided into two areas from left to right, namely the left area S_left and the right area S_right, and the number of non-empty pixels in the two areas S_left and S_right is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located;

[0021] Determine the coordinates of the implantation point and the root apex point of the implant in the preferred image respectively; wherein the grayscale value of the pixels in the white area in the preferred image is 255, which is a non-empty area;

[0022] Step S35: for each preferred image in the preferred view set: based on the type of the preferred image in the corresponding view group, the serial number of the preferred image in the corresponding view group, and the pixel interval of the CBCT image, determine the coordinate values ​​of the implantation point and the apex point of the implant in the three-dimensional space, and use the coordinate values ​​as the first position of the implantation point and the apex point of the implant. The calculation formula for the first position of the implantation point of the implant is:

[0023] (V3*Spacing+ox,V1*Spacing+oy,V2*Spacing+oz)

[0024] Wherein, V1 is the index coordinate of the implantation point in the Y-axis direction, V2 is the index coordinate of the implantation point in the Z-axis direction, V3 is the index coordinate of the implantation point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image, and the origin of the CBCT image is the physical coordinate value of the pixel with the serial number value (0,0,0) in the CBCT image;

[0025] The calculation formula for the first position of the apex point of the implant is:

[0026] (V6*Spacing+ox,V4*Spacing+oy,V5*Spacing+oz)

[0027] Among them, V4 is the index coordinate of the apex point in the Y-axis direction, V5 is the index coordinate of the apex point in the Z-axis direction, V6 is the index coordinate of the apex point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image.

[0028] Optionally, step S5: determining the error between the implantation position of the implant and the expected position comprises:

[0029] Determine, according to the second position (X3, Y3, Z3) of the implantation point of the implant and the second position (X4, Y4, Z4) of the apex point, an error ε between the distance between the apex point and the implantation point of the implant and the length L of the implant;

[0030]

[0031] If ε is less than the preset threshold, it is determined that the implant position is correctly identified and the implant placement is correct.

[0032] Optionally, if the error is greater than or equal to a preset threshold, the CBCT image is retaken and step S1 is executed.

[0033] In the above-mentioned method embodiments of the present invention, the device for determining the position of an implant in a CBCT image includes:

[0034] include:

[0035] Image acquisition module: configured to acquire CBCT images after implantation;

[0036] A cutting module: configured to cut the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; the sagittal view group includes one or more sagittal views;

[0037] A first position module: configured to determine, in each view group, a view with the smallest distance from the central section of the implant, and use the view as a preferred view. All preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set;

[0038] A second position module: configured to determine a second position of the implantation point of the implant and a second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point;

[0039] The error module is configured to determine the error between the implantation position of the implant and the expected position.

[0040] In the above method embodiments of the present invention, a computer-readable storage medium is provided, wherein a plurality of instructions are stored in the storage medium, and the plurality of instructions are used for a processor to load and execute the above method.

[0041] In the above method embodiments of the present invention, an electronic device includes:

[0042] A processor, which is used to execute multiple instructions;

[0043] A memory for storing a plurality of instructions;

[0044] The plurality of instructions are used to be stored in the memory, and loaded and executed by the processor to implement the method as described above.

[0045] The present invention can quickly obtain the positions of the implantation point and the apex point of the implant from the CBCT image, thereby improving the accuracy of the implant position precision calculation.

[0046] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and other purposes, features and advantages of the present invention will become more apparent by describing the embodiments of the present invention in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0048] Figure 1 A schematic diagram of a method for determining the position of an implant in a CBCT image according to the present invention;

[0049] Figure 2 A schematic flow chart of a method for determining an implantation point and an apex point of an implant according to the present invention;

[0050] Figure 3 (A) and Figure 3 (B) are schematic diagrams of the apex and implantation point of the implant, respectively;

[0051] Figure 4(A)-Figure 4(B) A schematic diagram of using a closing operation on the image where the implant is located;

[0052] Figure 5 It is a rotation diagram of the image where the implant is located;

[0053] Figure 6 Schematic diagram of the image template of the implant;

[0054] Figure 7 It is a schematic diagram of the implant image area;

[0055] Figure 8(A)-Figure 8(B) This is a schematic diagram of the cross-sectional image with the largest SSIM index screened out;

[0056] Figure 9(A)-Figure 9(D) It is a schematic diagram of the image coordinate system of OpenCV and the coordinate system of each group of slice images;

[0057] Fig.10 Schematic diagram of the implantation point and apex point of the implant detected by the bounding box;

[0058] Figure 11(A)-Figure 11(B) This is a schematic diagram to distinguish the implantation point and the apex point according to the orientation of the implant opening;

[0059] Fig.12 Schematic diagram of the coordinate system of CBCT images;

[0060] Figure 13(A)-Figure 13(B) Schematic diagram of volume rendering of CBCT images;

[0061] Figure 14(A)-Figure 14(B) Schematic diagram of the implant placement point and root apex point detected;

[0062] Fig.15 A schematic diagram of the structure of a device for determining the position of an implant in a CBCT image according to the present invention;

[0063] Fig.16 The schematic diagram of the structure of the device for determining the implant position in the CBCT image according to the present invention. DETAILED DESCRIPTION

[0064] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0065] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0066] Those skilled in the art can understand that the terms "first", "second", S1, S2, etc. in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0067] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0068] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0069] In addition, the term "and / or" in the present invention is only a description of the association relationship of the 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. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0070] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0071] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0072] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0073] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0074] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0075] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0076] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0077] Exemplary Methods

[0078] Figure 1 FIG. 1 is a flow chart of a method for determining the position of an implant in a CBCT image provided by an exemplary embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0079] Step S1: Acquire a CBCT image after implantation;

[0080] Step S2: cutting the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; the sagittal view group includes one or more sagittal views;

[0081] Step S3: in each view group, respectively determine the view with the shortest distance from the central section plane of the implant (the section plane passing through the center line of the implant), use the view as the preferred view, all the preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set;

[0082] Step S4: determining a second position of the implantation point of the implant and a second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point;

[0083] Step S5: determining the error between the implantation position of the implant and the expected position.

[0084] The step S1, wherein:

[0085] In order to evaluate and determine the implantation position of the implant, a CBCT image is taken after the implant is implanted. For example, after implantation, the user who receives the implant takes a CBCT image with an optical positioning device. The pixel interval of the CBCT image is less than 0.30 mm, and then the CBCT image is de-artifacted, that is, a smoothing and denoising operation is performed. The scanning mode and coordinate system direction of CBCT imaging, such as Fig.12 , Figure 13 (A) - Figure 13 (B) As shown. The scanning direction is from right to left, from the soles of the feet to the top of the head, and from front to back. The open source software MitkWorkBench is used to view the three-dimensional volume rendering, using the volume visualization function in the software.

[0086] The step S2, wherein:

[0087] The Cartesian coordinate system of the CBCT image is used as the reference coordinate system, the direction of the centerline of the implant in the CBCT image is set as the Z axis, the center of the inner circle of the implant is used as the origin, and the plane perpendicular to the Z axis and including the center of the inner circle of the implant is used as the horizontal plane; the direction passing through the center of the circle in the horizontal plane and horizontally to the right in the horizontal plane is determined as the X axis, and the line passing through the center of the circle in the horizontal plane and perpendicular to the X axis in the horizontal plane is determined as the Y axis; the three-dimensional image is cut from a direction parallel to the Z axis to obtain two groups of views parallel to the Z axis and perpendicular to each other, the view group in the direction parallel to the XZ plane is a coronal view group, the coronal view group includes one or more coronal views, and the view group in the direction parallel to the YZ plane is a sagittal view group; the centerline of the implant is a line running through the apex point and the implantation point of the implant.

[0088] In the present invention, the Cartesian coordinate system of the CBCT image is used as the reference coordinate system (the concept of coordinate system is https: / / www.slicer.org / wiki / Coordinate_systems). The acquired CBCT image includes multiple images numbered from 0 to N. The image number is automatically generated when the CBCT is taken. The number represents the position of the image in the Z-axis direction in the space of the CBCT image. The plane where each image is located is a plane parallel to the X-axis and the Y-axis. Therefore, the CBCT image group corresponds to a three-dimensional image. When the center line of the implant is parallel to the Z axis, the coronal view (parallel to the YZ plane) and the sagittal plane (parallel to the XZ plane) are parallel to the Z axis, that is, the center line of the implant is perpendicular to the normals of the two views.

[0089] The multiple image sequences included in the CBCT image are usually sequences of various sections, and each image is square. Therefore, assuming that the size of each image is D×D, the corresponding size of the three-dimensional image formed by the combination of all images is D×D×N. After slicing the three-dimensional image, the coronal view group includes D coronal views, and the size of each coronal view is D×N; the sagittal view group includes D sagittal views, and the size of each sagittal view is D×N.

[0090] CBCT images are usually in DICOM format, and the grayscale value (also called CT value or HU value) of the pixels of DICOM format images is usually [-1024, 3071]. This range exceeds the limit of human eye recognition. The present invention converts the three-dimensional CBCT image into a coronal view group and a sagittal view group in the range of [0-255]. The views in the coronal view group and the sagittal view group are PNG images or JPEG images. In other words, the corresponding window width and window level are set to convert the three-dimensional CBCT image into a PNG image or a JPEG image for storage.

[0091] In this embodiment, the corresponding window width and window level are set according to the CT value corresponding to the implant material, and the grayscale value range of the image is linearly mapped from [-1024, 3071] to [0, 255], so that only objects with a density similar to that of the implant are displayed on the two-dimensional image.

[0092] like Figure 2 3(A) and 3(B), in step S3: in each view group, respectively determine the view with the smallest distance from the central section of the implant, use the view as the preferred view, all the preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set, wherein:

[0093] The method of determining in each view group a view with the smallest distance from the central section of the implant and taking the view as the preferred view comprises:

[0094] Step S31: obtaining a view group, and performing image processing on each view in the view group;

[0095] The acquired view group is a view group for which a preferred view has not been determined among the coronal view group and the sagittal view group.

[0096] The image processing includes graying the view, binarizing it, and then using a closing operation. Due to the existence of the volume effect, some closed smaller objects will be disconnected, so it is necessary to use an image processing algorithm for preprocessing operations. First, gray the two-dimensional PNG image and JPEG image, then binarize it, and finally use a closing operation (expand first and then erode) to connect the separated objects at the thin parts and smooth the boundaries of larger objects. Figure 4(A)-Figure 4(B) As shown, a closed operation is performed on the implant to connect the disconnected small parts. FIG4(A) is an image before the closed operation, and FIG4(B) is an image after the closed operation.

[0097] Step S32: for the processed view group, filter the views without implants based on the actual width Width and length Length of the implants; for each view in the processed view group: calculate the bounding boxes of all contours in the view, if in the view, the lengths of all bounding boxes are outside the range [L*A, L*(2-A)], and the widths of all bounding boxes are outside the range [W*A, W*(2-A)], filter out the view; where W = Width / Spacing, L = Length / Spacing, A is the filtering accuracy, ranging from (0, 1], and Spacing is the pixel spacing in the CBCT image.

[0098] In this embodiment, the value of Spacing is 0.25.

[0099] In this embodiment, the purpose of this step is to filter out views without implants. Each view is a two-dimensional image, and the bounding boxes of all contours in each view are calculated, for example, using the minAreaRect function in OpenCV for calculation. The two-dimensional image is then filtered based on the actual width width and length length of the implant. If the voxels of the CBCT image are cubes, that is, the spacings in the three directions of XYZ are the same, then the width W of the implant in the two-dimensional image is Width / Spacing, and the length L is Length / Spacing. The filtering accuracy A (range 0 to 1) is specified, and contours whose width is not in [W*A, W*(2-A)] and whose length is not in [L*A, L*(2-A)] are filtered. If all contours in a certain view are not within the specified filtering range, the image is filtered out.

[0100] Step S33: for each view retained after filtering: obtain a bounding box with the smallest deviation from the actual size of the implant, use the contour area corresponding to the bounding box as the detection area S of the view, perform rotation correction and scaling on the detection area S to obtain a transformed detection area S', calculate the similarity between the detection area S' and the standard image, and record it as SSIM;

[0101] The SSIMs corresponding to the views retained after filtering are compared, and the view corresponding to the SSIM with the largest value is the preferred view of the view group.

[0102] In this embodiment, the purpose of this step is to select the view closest to the center section of the implant. The same implant will form multiple section images in the DICOM image, and the implantation point and the root apex point are both located on the center section image. Therefore, as shown in Figures 3(A), 3(B), Figure 6 As shown, the apex point is the lowest point of the bottom arc, and the implantation point is the center of the topmost open circle. The implant is identified and filtered based on the contour of the front view (side view), that is, it is detected whether there is an area similar to the shape of the implant front view (side view) in the image of each slice view group in the CBCT image (corresponding to the non-zero area in the binary image). Figure 6 The image template of the implant is shown. A variety of image templates for calculating SSIM are set according to the implant area, diameter and length of the implant. A central section image of the implant is produced based on the image template as a comparison benchmark. In this embodiment, a standard STL model of the implant is used to produce the central section image of the implant, and the central section image of the implant is the benchmark image. For each view that is not filtered out, the bounding box of all non-empty areas in the view is calculated, and the area whose bounding box length L1 and width W1 are closest to the actual length L and width W of the implant is extracted as the detection area S of the image, as shown in FIG. Figure 7 As shown, Figure 7 This is an example of the implant tomographic image area, which is the implant area in the sagittal tomographic image obtained by screening according to the aspect ratio and actual length of the implant. There are multiple ways to compare the bounding box with the smallest deviation between the size and the actual size of the implant. For example, the contour area corresponding to the bounding box with the smallest deviation between the bounding box length L1 and the actual length of the implant is used as the detection area S of the view; the contour area corresponding to the bounding box with the smallest deviation between the bounding box width W1 and the actual width of the implant is used as the detection area S of the view; the deviation between the bounding box length L1 and the actual length of the implant, and the deviation between the bounding box width W1 and the actual width of the implant are weighted to obtain the contour area corresponding to the bounding box with the smallest size deviation as the detection area S of the view. The actual length size of the implant is determined based on the central section image of the implant. In the present invention, the grayscale value of the pixels in the white area of ​​the image is 255, which is a non-empty area; the grayscale value of the pixels in the black background area is 0, which is an empty area.

[0103] The rotation angle of the detection area S can be determined based on the slope of the detection area S, and then the rotation correction is performed based on the area where the implant is located (maxillary bone or mandibular bone), such as Figure 5 As shown, if the implant is planted in the upper jaw area, the implant opening is vertically downward; if the implant is planted in the lower jaw area, the implant opening is vertically upward. The scaling scale of the detection area S is determined with the number of pixels in the scaled detection area S' being the same as the number of pixels in the center section image of the implant, and then the detection area S is scaled, the similarity between the detection area S' and the standard image is calculated, and the two-dimensional image of the detection area S with the largest SSIM index is used as the final section image of the implant. The SSIMs corresponding to the views retained after filtering are compared, and the view corresponding to the SSIM with the largest value is the preferred view of the view group.

[0104] All the preferred views constitute a preferred view set, including: extracting a preferred view from each view group, naming and saving the preferred view using the name of the view group to which the preferred view belongs and the sequence number of the preferred view in the view group; the preferred views corresponding to the two view groups respectively constitute a preferred view set.

[0105] In this embodiment, for example, if the SSIM index of the image with the sequence number YYY in the sagittal view group is the largest, the image is extracted and named Sagittal_YYY; if the SSIM index of the image with the sequence number ZZZ in the coronal view group is the largest, the image is extracted and named Coronal_ZZZ. The implantation point and the apex point of the implant are detected from the front view and the side view, so the two images with the largest SSIM index are extracted, and the two images are extracted to enter the next detection step, such as Figure 8(A)-Figure 8(B) , Figure 9(A)-Figure 9(D) As shown. Figure 8(A)-Figure 8(B) The screened slice image with the largest SSIM is shown. According to the image name, the view group to which the image belongs and the slice number of the image in the view group can be determined. Figure 9(A)-Figure 9(D) is a schematic diagram of the image coordinate system and the coordinate system of each group of slice images. Figure 9(A)-Figure 9(D) As shown, the sagittal section image is parallel to the YZ plane; the coronal section image is parallel to the XZ plane.

[0106] Determining a first position of an implantation point and a first position of an apex point of the implant based on the preferred view set comprises:

[0107] Step S34: for each preferred image in the preferred view set: obtain the detection area S of the preferred image; if the absolute value of the slope K of the detection area S is greater than 1, the detection area S is turned into a vertical orientation, and then the detection area S is divided into two areas from top to bottom, namely the upper area S_up and the lower area S_down, and the number of non-empty pixels in the two areas S_up and S_down is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located; if the absolute value of K of the detection area S is less than 1, the detection area S is turned into a horizontal orientation, and then the detection area S is divided into two areas from left to right, namely the left area S_left and the right area S_right, and the number of non-empty pixels in the two areas S_left and S_right is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located;

[0108] Determine the coordinates of the implantation point and the root apex point of the implant in the preferred image respectively; wherein the grayscale value of the pixels in the white area in the preferred image is 255, which is a non-empty area;

[0109] Step S35: for each preferred image in the preferred view set: based on the type of the preferred image in the corresponding view group, the serial number of the preferred image in the corresponding view group, and the pixel interval of the CBCT image, determine the coordinate values ​​of the implantation point and the apex point of the implant in the three-dimensional space, and use the coordinate values ​​as the first position of the implantation point and the apex point of the implant. The calculation formula for the first position of the implantation point of the implant is:

[0110] (V3*Spacing+ox,V1*Spacing+oy,V2*Spacing+oz)

[0111] Among them, V1 is the index coordinate of the implantation point in the Y-axis direction, V2 is the index coordinate of the implantation point in the Z-axis direction, V3 is the index coordinate of the implantation point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image, and the origin of the CBCT image is the physical coordinate value of the pixel with the serial number value (0,0,0) in the CBCT image.

[0112] The calculation formula for the first position of the apex point of the implant is:

[0113] (V6*Spacing+ox,V4*Spacing+oy,V5*Spacing+oz)

[0114] Among them, V4 is the index coordinate of the apex point in the Y-axis direction, V5 is the index coordinate of the apex point in the Z-axis direction, V6 is the index coordinate of the apex point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image.

[0115] In this embodiment, the origin of the CBCT image is recorded in the Tag in the DICOM image, and the Image Position with the Tag ID (0020, 0032) records the physical coordinate value of the origin of the image.

[0116] In this embodiment, the purpose of this step is to calculate the first position of the implantation point and the apex point of the implant. The two selected preferred images are detected to calculate the positions of the implantation point and the apex point of the implant. The detection area S of the preferred image is obtained. Fig.10, the midpoints of the two shortest sides of the bounding box are the implantation point and the apex point of the implant. In order to distinguish the implantation point and the apex point of the implant, it is necessary to determine the opening direction of the implant, that is, determine which short side is close to the opening area and which short side is close to the bottom area. Calculate the slope K of the detection area S. If the absolute value of the slope K is greater than 1, the implant is turned to a vertical orientation, and then the implant is divided into two areas S_up and S_down from top to bottom. Calculate the number of non-empty pixels in the two areas S_up and S_down. The area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located. As shown in Figure 11 (A), the number of non-empty pixels in S_up is less than that in S_down, that is, the implant opening is facing upward, and the middle of the short side of the top of the bounding box (the smallest Y value in the OpenCV coordinate system) is The point is the implantation point of the implant, and the midpoint of the bottom short side is the apex point of the implant; if the absolute value of the slope K is less than 1, the implant is turned to a horizontal orientation, and then the implant is divided into two areas S_left and S_right. Similarly, the area with fewer non-empty pixels is the area where the top of the implant is located, as shown in Figure 11 (B), the number of non-empty pixels in S_right is less than the number of non-empty pixels in S_left, the implant opening faces right, the midpoint of the short side on the right side (the largest X value in the OpenCV coordinate system) of the bounding box is the implantation point, and the midpoint of the short side on the left is the apex point of the implant.

[0117] Based on the type of the preferred image in the corresponding view group, the sequence number of the preferred image in the corresponding view group, and the pixel interval of the CBCT image, the coordinate values ​​of the implantation point and the apex point of the implant in the three-dimensional space are determined, and the coordinate values ​​are used as the first positions of the implantation point and the apex point of the implant. The relationship between the OpenCV coordinate system and each group of section view groups formed by the CBCT image is shown in FIG9, and the coordinate values ​​detected by OpenCV need to be mapped back to the three-dimensional coordinate space where the CBCT image is located. Take the coordinate value of the implant point of the image Sagittal_V3 for example. The sagittal plane corresponds to the YZ plane of the CBCT image. The X coordinate value V1 measured by the OpenCV function corresponds to the Y index coordinate value of the CBCT image. The index coordinate value V2 of the implant in the Z axis direction in the CBCT image is obtained by subtracting the Y coordinate value measured by the OpenCV function from the size of the image Y axis dimension (the image is a two-dimensional array, and the dimension here also refers to the number of rows of the two-dimensional array). The index coordinate value of the implant in the X axis direction is the serial number of the PNG image (generated when re-slicing) V3. Therefore, the index coordinate value of the implant detected from the image Sagittal_V3 is (V3, V1, V2). The index coordinate value is multiplied by the pixel spacing Spacing of the CBCT image and the offset (ox, oy, oz) relative to the origin of the 3D image space coordinate system to obtain the coordinate value of the implant point in the 3D image space, that is, (V3*Spacing+ox, V1*Spacing+oy, V2*Spacing+oz).

[0118] The step S4: determines the second position of the implantation point of the implant and the second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point, including: taking the coordinate mean of the first position of the implantation point of the implant corresponding to each of the preferred images as the second position of the implantation point of the implant, and taking the coordinate mean of the first position of the apex point of the implant corresponding to each of the preferred images as the second position of the apex point of the implant.

[0119] In this embodiment, the average is taken to obtain the accurate position of the implantation point and the apex point of the implant. The coordinate values ​​in the three-dimensional space obtained by the two preferred images Picture1 and Picture2 are (X1, Y1, Z1) and (X2, Y2, Z2) respectively, and the average ((X1+X2) / 2, (Y1+Y2) / 2, (Z1+Z2) / 2) is taken as the second position.

[0120] Step S5: determining the error between the implantation position of the implant and the expected position, including:

[0121] Determine, according to the second position (X3, Y3, Z3) of the implantation point of the implant and the second position (X4, Y4, Z4) of the apex point, an error ε between the distance between the apex point and the implantation point of the implant and the length L of the implant;

[0122]

[0123] If ε is less than the preset threshold, it is determined that the implant position is correctly identified and the implant placement is correct.

[0124] In this embodiment, the error between the distance between the apex point and the implantation point of the implant and the actual length of the implant is used as the calculation error of the algorithm of the present invention. Assuming that the coordinate value of the implantation point of the implant is (X3, Y3, Z3), the coordinate value of the apex point is (X4, Y4, Z4), and the actual length of the implant is L mm, the overall error is

[0125]

[0126] The error ε is calculated as a percentage. If ε is less than 1%, the recognition is considered to be relatively accurate.

[0127] Furthermore, after step S5, step S6 is also included.

[0128] Step S6: If the error is greater than or equal to the preset threshold, retake the CBCT image and execute step S1.

[0129] In this embodiment, if the error is greater than or equal to the preset threshold, it is considered that there is a large artifact in the CBCT, resulting in deformation of the implant. The CBCT image can be re-photographed to reduce the impact of the CBCT artifact in the original image on the implant image.

[0130] Another embodiment of the present invention provides a method for determining the position of an implant in a CBCT image. The embodiment comprises the following steps:

[0131] Taking CBCT images

[0132] The patient wore a positioning guide to take preoperative CBCT images and perform artifact removal. In this case, the pixel interval of the CBCT image in the X, Y, and Z directions was 0.3 mm.

[0133] Convert CBCT images to PNG images

[0134] The CBCT image in this example is composed of a total of 402 slice sequences, and the size of each slice image is 512X512. The size of the combined 3D image is 512X512X402. The centerline of the implant is parallel to the YZ plane and the XZ plane. Therefore, the 3D image is re-sliced ​​from the coronal plane and the sagittal plane to obtain 512 coronal planes (image size is 512X402) and 512 sagittal planes (image size is 512X402).

[0135] The implant used in this example is made of titanium, and the CT value of titanium is 2900. Set the window level to 2900 and the window width to 500, and linearly map the grayscale values ​​in the range of [2900-500 / 2, 2900+500 / 2] to the range of 0-255. The grayscale values ​​of pixels below 2900-500 / 2 are set to 0, and the grayscale values ​​of pixels above 2900+500 / 2 are set to 255. By setting the window width and window level, only the area formed by objects with a density similar to that of the implant material titanium can be retained in the PNG image.

[0136] Calculate the implant placement point and apex position in each set of section views

[0137] ① Image preprocessing. First, grayscale the PNG image and convert the RBG image into a grayscale image; then perform binarization to convert the grayscale image into a binary image, set the threshold to 127, set the grayscale value of pixels greater than the threshold to 255, and set the grayscale value of pixels less than the threshold to 0; finally, use the closing operation (expansion followed by erosion) to connect the separated objects at the thin parts and smooth the boundaries of the larger objects. The convolution kernel of the closing operation is 5X5.

[0138] ② Filter out images without implants. The width of the implant used in this example is 4.8 mm and the length is 10 mm. Calculate the bounding box of the contours of all non-empty areas in each image, using the minAreaRect function in OpenCV. Filter the PNG image based on the actual width width and length length of the implant. If the voxels of the CBCT image are cubes, that is, the spacing in the three directions of XYZ is the same, then the width W of the implant in the PNG image is 4.8 / 0.3=16, and the length L is 10 / 0.3=34, both of which are rounded up. Specify the filtering accuracy of 0.8, and filter the contours whose width is not in [16*0.8,16*(2-0.8)] and whose length is not in [34*0.8,34*(2-0.8)]. If the length and width of all contours in the image do not meet the requirements, the image is filtered out.

[0139] ③ Filter out the image closest to the center section of the implant. Use the SSIM index to filter and screen the PNG images in the coronal view group and the sagittal view group, select the PNG images with the largest SSIM index in each group, and retain the two PNG images with the largest SSIM index, as shown in Figure 8. The SSIM index of the section image with the serial number 0202 in the sagittal view group is the largest, which is 0.7765. The PNG image is extracted and renamed to Sagittal_0202.png; the SSIM index of the section image with the serial number 0129 in the coronal view group is the largest, which is 0.7709. The PNG image is extracted and renamed to Coronal_0129.png.

[0140] ④ Calculate the position of the implantation point and the apex point of the implant. Take the detection of the implantation point and the apex point of the implant in the PNG image Sagittal_0202 as an example. It is detected that the absolute value of the slope K = -152 of the implant area is greater than 1. The implant is rotated to a vertical orientation and the implant is divided into two halves. The number of non-empty pixels of S_up is 101, and the number of non-empty pixels of S_down is 204. S_up is smaller than S_down. Therefore, the implant opening faces upward. The midpoint of the top short side of the bounding box (coordinate value is (130,341)) is the implantation point of the implant, and the midpoint of the bottom short side of the bounding box (coordinate value is (130,375)) is the apex point of the implant. Combined with the coordinate system conversion relationship of FIG. 9 and the dimension 402 of the Z axis of the CBCT image, the index coordinate value of the implant placement point is obtained to be (202, 130, 402-341), i.e. (202, 130, 61), and the coordinate value of the apex point is (202, 130, 402-375), i.e. (202, 130, 27). Then, combined with the pixel interval of the CBCT image of 0.3 and the offset relative to the origin (-76.95, -76.95, -60.15), the coordinate values ​​of the implant placement point and the apex point in the CBCT image space are obtained to be (202*0.3-76.95, 130*0.3-76.95, 61*0.3-60.15) and (202*0.3-76.95, 130*0.3-76.95, 27*0.3-60.15), respectively.

[0141] The average was taken to obtain the accurate position of the implantation point and apex point of the implant in the CBCT image.

[0142] like Figure 14(A)-Figure 14(B) As shown, FIG14(A) is a side view of the implant and its center line (the line between the implantation point and the apex point), and FIG14(B) is a top view of the implant and its center line.

[0143] In the previous step, the coordinate values ​​of the implantation point and apex point obtained from the Sagittal_0202 image are (-16.35, -37.95, -41.85) and (-16.35, -37.95, -52.05), respectively; the coordinate values ​​of the implantation point and apex point obtained from the Coronal_0129 image are (-15.90, -38.25, -42.05) and (-15.90, -38.25, -52.05), respectively. After taking the average, the coordinate values ​​of the final implantation point can be obtained as (-16.125, -38.10, -41.95) and (-16.125, -38.10, -52.05).

[0144] Evaluation of detection error

[0145] The Euclidean distance between the implant insertion point and the root apex is calculated to be 10.1. Combined with the actual length of the implant, which is 10 mm, the overall error of the algorithm is The error is less than or equal to 1%, and the recognition accuracy of this method is relatively high.

[0146] Exemplary Devices

[0147] Fig.15 FIG. 1 is a schematic diagram of a device for determining the position of an implant in a CBCT image provided by an exemplary embodiment of the present invention. Fig.15 As shown, this embodiment includes:

[0148] Image acquisition module: configured to acquire CBCT images after implantation;

[0149] A cutting module: configured to cut the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; the sagittal view group includes one or more sagittal views;

[0150] A first position module: configured to determine, in each view group, a view with the smallest distance from the central section of the implant, and use the view as a preferred view. All preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set;

[0151] A second position module: configured to determine a second position of the implantation point of the implant and a second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point;

[0152] The error module is configured to determine the error between the implantation position of the implant and the expected position.

[0153] Exemplary Electronic Devices

[0154] Fig.16 This is the structure of the electronic device 160 provided by an exemplary embodiment of the present invention. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signals from them. Fig.16 FIG. 1 is a block diagram of an electronic device according to an embodiment of the present disclosure. Fig.16 As shown, the electronic device includes one or more processors 161 and memory 162 .

[0155] The processor 161 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0156] The memory 162 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 161 may run the program instructions to implement the method of determining the implant position in the CBCT image and / or other desired functions of the software program of each embodiment of the present disclosure described above. In one example, the electronic device may also include: an input device 163 and an output device 164, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0157] In addition, the input device 163 may also include, for example, a keyboard, a mouse, and the like.

[0158] The output device 164 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0159] Of course, to simplify, Fig.16 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0160] Exemplary computer program products and computer-readable storage media

[0161] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for determining the implant position in a CBCT image according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0162] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0163] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, causes the processor to execute the steps of the method for determining the position of an implant in a CBCT image according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0164] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0165] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0166] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0167] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0168] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0169] It should also be noted that in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present disclosure. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest scope consistent with the principles and novel features disclosed herein.

[0170] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for determining the position of an implant in a CBCT image, characterized in that: include: Step S1: Acquire a CBCT image after implantation; Step S2: cutting the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image, wherein the sagittal view group includes one or more sagittal views; Step S3: in each view group, respectively determine the view with the shortest distance from the central section of the implant, use the view as the preferred view, all the preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set; Step S4: determining the second position of the implantation point of the implant and the second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point, comprising: taking the coordinate mean of the first position of the implantation point of the implant corresponding to each preferred image in the preferred view set as the second position of the implantation point of the implant, and taking the coordinate mean of the first position of the apex point of the implant corresponding to each preferred image as the second position of the apex point of the implant; Step S5: determining the error between the implantation position of the implant and the expected position.

2. The method according to claim 1, characterized in that The step S2, wherein: The Cartesian coordinate system of the CBCT image is used as the reference coordinate system, the direction of the centerline of the implant in the CBCT image is set as the Z axis, the center of the inner circle of the implant is used as the origin, and the plane perpendicular to the Z axis and including the center of the inner circle of the implant is used as the horizontal plane; the direction passing through the center of the circle in the horizontal plane and horizontally to the right in the horizontal plane is determined as the X axis, and the line passing through the center of the circle in the horizontal plane and perpendicular to the X axis in the horizontal plane is determined as the Y axis; the three-dimensional image is cut from a direction parallel to the Z axis to obtain two groups of views parallel to the Z axis and perpendicular to each other, the view group in the direction parallel to the XZ plane is a coronal view group, the coronal view group includes one or more coronal views, and the view group in the direction parallel to the YZ plane is a sagittal view group; the centerline of the implant is a line running through the apex point and the implantation point of the implant.

3. The method according to any one of claims 1 to 2, characterized in that: In step S3, in each view group, respectively determining a view with the smallest distance from the central section of the implant and taking the view as the preferred view includes: Step S31: obtaining a view group, and performing image processing on each view in the view group; The acquired view group is a view group of the coronal view group and the sagittal view group for which a preferred view has not been determined; Step S32: for the processed view group, filter the view without implant based on the actual width Width and length Length of the implant; for each view in the processed view group: calculate the bounding box of all contours in the view, if in the view, the length Length of all bounding boxes is outside the range [L*A, L*(2-A)], and the width Width of all bounding boxes is outside the range [W*A, W*(2-A)], then filter out the view; where W=Width / Spacing, L=Length / Spacing, A is the filtering accuracy, the range is (0,1], Spacing is the pixel spacing in the CBCT image; Step S33: for each view retained after filtering: obtain a bounding box with the smallest deviation from the actual size of the implant, use the contour area corresponding to the bounding box as the detection area S of the view, perform rotation correction and scaling on the detection area S to obtain a transformed detection area S', calculate the similarity between the detection area S' and the standard image, and record it as SSIM; The SSIMs corresponding to the views retained after filtering are compared, and the view corresponding to the SSIM with the largest value is the preferred view of the view group.

4. The method according to claim 3, characterized in that In step S3, determining the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set includes: Step S34: for each preferred image in the preferred view set: obtain the detection area S of the preferred image; if the absolute value of the slope K of the detection area S is greater than 1, the detection area S is turned into a vertical orientation, and then the detection area S is divided into two areas from top to bottom, namely the upper area S_up and the lower area S_down, and the number of non-empty pixels in the two areas S_up and S_down is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located; if the absolute value of K of the detection area S is less than 1, the detection area S is turned into a horizontal orientation, and then the detection area S is divided into two areas from left to right, namely the left area S_left and the right area S_right, and the number of non-empty pixels in the two areas S_left and S_right is calculated, and the area with a small number of non-empty pixels is the area where the top opening of the implant is located, and the area with a large number of non-empty pixels is the area where the bottom of the implant is located; Determine the coordinates of the implantation point and the root apex point of the implant in the preferred image respectively; wherein the grayscale value of the pixels in the white area in the preferred image is 255, which is a non-empty area; Step S35: for each preferred image in the preferred view set: based on the type of the preferred image in the corresponding view group, the serial number of the preferred image in the corresponding view group, and the pixel interval of the CBCT image, determine the coordinate values ​​of the implantation point and the apex point of the implant in the three-dimensional space, and use the coordinate values ​​as the first position of the implantation point and the apex point of the implant. The calculation formula for the first position of the implantation point of the implant is: (V3*Spacing+ox,V1*Spacing+oy,V2*Spacing+oz), Wherein, V1 is the index coordinate of the implantation point in the Y-axis direction, V2 is the index coordinate of the implantation point in the Z-axis direction, V3 is the index coordinate of the implantation point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image, and the origin of the CBCT image is the physical coordinate value of the pixel with the serial number value (0,0,0) in the CBCT image; The calculation formula for the first position of the apex point of the implant is: (V6*Spacing+ox,V4*Spacing+oy,V5*Spacing+oz), Among them, V4 is the index coordinate of the apex point in the Y-axis direction, V5 is the index coordinate of the apex point in the Z-axis direction, V6 is the index coordinate of the apex point in the X-axis direction, ox is the X-axis physical coordinate value of the origin of the CBCT image, oy is the Y-axis physical coordinate value of the origin of the CBCT image, and oz is the Z-axis physical coordinate value of the origin of the CBCT image; the index coordinate is the serial number of the implantation point relative to the origin of the CBCT image.

5. The method according to any one of claims 1 to 2, characterized in that: The step S5: determining the error between the implantation position of the implant and the expected position, comprises: Determine an error ε between a distance between a line between the apex point and the implantation point of the implant and a length L of the implant according to a second position (X3, Y3, Z3) of the implantation point and a second position (X4, Y4, Z4) of the apex point of the implant; , If ε is less than the preset threshold, it is determined that the implant position is correctly identified and the implant placement is correct.

6. The method according to any one of claims 1 to 2, characterized in that: If the error is greater than or equal to the preset threshold, the CBCT image is retaken and step S1 is executed.

7. A device for determining the position of an implant in a CBCT image, characterized in that: include: Image acquisition module: configured to acquire CBCT images after implantation; A cutting module: configured to cut the three-dimensional image corresponding to the CBCT image to obtain a coronal view group and a sagittal view group of the three-dimensional image; the sagittal view group includes one or more sagittal views; A first position module: configured to determine, in each view group, a view with the smallest distance from the central section of the implant, and use the view as a preferred view. All preferred views form a preferred view set, and determine the first position of the implantation point and the first position of the apex point of the implant based on the preferred view set; A second position module: configured to determine the second position of the implantation point of the implant and the second position of the apex point based on the first position of the implantation point of the implant and the first position of the apex point, comprising: taking the coordinate mean of the first position of the implantation point of the implant corresponding to each preferred image in the preferred view set as the second position of the implantation point of the implant, and taking the coordinate mean of the first position of the apex point of the implant corresponding to each preferred image as the second position of the apex point of the implant; An error module is configured to determine the error between the implantation position of the implant and the expected position.

8. A computer-readable storage medium, wherein a plurality of instructions are stored in the storage medium, and the plurality of instructions are used for a processor to load and execute the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The electronic device comprises: A processor, which is used to execute multiple instructions; A memory for storing a plurality of instructions; The plurality of instructions are used to be stored in the memory, and loaded and executed by the processor to execute the method as described in any one of claims 1 to 6.

Images