CN115035070A

CN115035070A - Method and device for determining position of implant in CBCT image

Info

Publication number: CN115035070A
Application number: CN202210688799.2A
Authority: CN
Inventors: 黄志俊; 刘金勇; 钱坤; 陈家兴
Original assignee: Lancet Robotics Co Ltd
Current assignee: Lancet Robotics Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2022-09-09

Abstract

The invention discloses a method and a device for determining the position of an implant in a CBCT image, wherein the method comprises the following steps: obtaining a CBCT image after the implant is implanted; 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; in each view group, respectively determining a view with the minimum distance from the central tangent plane of the implant, and determining a first position of an implantation point of the implant and a first position of a root tip point; determining a second location of an implantation point of the implant and a second location of the apical point; determining an error between the implant implantation position and an expected position. The method can rapidly acquire the positions of the implantation point and the root tip point of the implant from the CBCT image, and improve the accuracy of the position precision calculation of the implant.

Description

Method and device for determining position of implant in CBCT image

Technical Field

The invention relates to the field of image processing, in particular to a method and a device for determining the position of an implant in a CBCT image.

Background

Robot-assisted oral implantation is a popular field in recent years, the robot-assisted implantation can improve the implantation accuracy of an implant, a matched surgical navigation system can display the implantation condition of the implant in real time, and objective and quantifiable data and indexes are provided for a doctor to judge the implantation accuracy of the implant. Evaluating the implantation accuracy of the implant requires performing fusion registration on a post-operative CBCT image and a pre-operative CBCT image, and finally calculating an angle and a distance deviation between the post-operative implant and the pre-operative implant from the fused image to evaluate the implantation accuracy of the robot, wherein the angle refers to an angle between a center line of the pre-operative implant and a center line of the post-operative implant, the distance includes a euclidean distance between an implantation point of the pre-operative implant and an implantation point of the post-operative implant, and a euclidean distance between a root tip of the pre-operative implant and a root tip of the post-operative implant.

The connecting line of the implantation point and the root tip point of the implant forms the central line of the implant. The implantation point and the apical point of the preoperative implant are recorded by the surgical navigation system when planning the implant implantation position. The positions of the implantation point and the root apex point of the implant after the operation need to be obtained from the CBCT image after the operation, and the traditional method generally uses a manual mode to search the section of the implant in the slice sequence of the CBCT image and manually mark the implantation point and the root apex point on the slice image. Manual marking is not only time consuming and labor intensive, and subjective factors are more influential, but it is often difficult to mark the exact location.

Disclosure of Invention

The invention provides a method and a device for determining the position of an implant in a CBCT image, which can solve the technical problems of low accuracy and low efficiency of the recognition of the position of the implant after the oral implantation is finished.

In the above embodiments of the method of the present invention, the method for determining the position of the implant in the CBCT image comprises:

step S1: obtaining a CBCT image after the implant is implanted;

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 set of sagittal plane views includes one or more sagittal plane views;

step S3: in each view group, respectively determining a view with the minimum distance from the central tangent plane of the implant, taking the view as a preferred view, forming a preferred view set by all the preferred views, and determining a first position of an implantation point of the implant and a first position of a root tip point based on the preferred view set;

step S4: determining a second position of an implantation point of the implant and a second position of a root tip point based on the first position of the implantation point and the first position of the root tip point of the implant;

step S5: determining an error of the implant implantation position from an expected position.

Optionally, the step S2, wherein:

setting the direction of the center line of the implant in the CBCT image as a Z axis, taking the circle center of the inner circle of the implant as an origin, and taking a plane which is vertical to the Z axis and comprises the circle center of the inner circle of the implant as a horizontal plane; the direction which passes through the circle center in the horizontal plane and is horizontally right in the horizontal plane is determined as an X axis, and a line which passes through the circle center in the horizontal plane and is vertical to the X axis in the horizontal plane is determined as a Y axis; cutting the three-dimensional image from a direction parallel to the Z axis to obtain two groups of views which are parallel to the Z axis and are mutually perpendicular, wherein the view group in the direction parallel to the XZ plane is a coronal view group, the coronal view group comprises one or more coronal views, and the view group in the direction parallel to the YZ plane is a sagittal view group; the central line of the implant is a connecting line which penetrates through the root tip point and the implantation point of the implant.

Optionally, in step S3, the determining, in each view group, a view with the smallest distance from the central tangent plane of the implant, and regarding this view as a preferred view, includes:

step S31: acquiring a view group, and carrying out image processing on each view in the view group;

wherein, the acquired view group is a view group of which the preferred view is not determined in one of the coronal view group and the sagittal view group;

step S32: filtering, for the processed view set, views where no implant exists based on the actual Width and Length of the implant; for each view in the processed view group: computing bounding boxes for all contours in the view, filtering out the view if all bounding boxes in the view have lengths outside the range [ L A, L (2-A) ] and all bounding boxes have widths outside the range [ W A, W (2-A) ]; wherein, W is Width/Spacing, L is Length/Spacing, a is filtering precision, a range is (0, 1), and Spacing is pixel interval in the CBCT image;

step S33: for each view retained after filtering: acquiring a bounding box with the minimum deviation between the size and the actual size of the implant, taking a contour region corresponding to the bounding box as a detection region S of the view, performing rotation correction and scaling on the detection region S to obtain a converted detection region S ', calculating the similarity between the detection region S' and a standard image, and marking as SSIM;

comparing the SSIMs corresponding to the views retained after filtering, wherein the view corresponding to the SSIM with the largest value is the preferred view of the view group.

Optionally, the step S3, determining the first position of the implant point and the first position of the apical point of the implant based on the preferred view-set, comprises:

step S34: for each preferred image in the preferred view set: acquiring a detection area S of the preferred image; if the absolute value of the slope K of the detection area S is larger than 1, the detection area S is converted into a vertical direction, then the detection area S is divided into two areas, namely an upper area S _ up and a lower area S _ down, the number of non-empty pixels in the two areas S _ up and S _ down is calculated, the area with the small number of non-empty pixels is the area where the top opening of the implant is located, and the area with the 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, converting the detection area S into a horizontal orientation, dividing the detection area S into two areas, namely a left area S _ left and a right area S _ right, calculating the number of non-empty pixels in the two areas of the left area S _ left and the right area S _ right, wherein the area with less non-empty pixels is the area where the top opening of the implant is located, and the area with more non-empty pixels is the area where the bottom of the implant is located;

determining the coordinates of the implantation point and the root tip point of the implant in the preferred image respectively; the gray value of the pixel of the white area in the preferred image is 255, and the pixel is a non-empty area;

step S35: for each preferred image in the preferred view set: determining coordinate values of an implantation point and a apical point of the implant in a three-dimensional space based on the type of the preferred image in the corresponding view group, the sequence number of the preferred image in the view group corresponding to the preferred image and the pixel interval of the CBCT image, taking the coordinate values as first positions of the implantation point and the apical point of the implant, wherein a calculation formula of the first position of the implantation point of the implant is as follows:

(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 original point of the CBCT image, oy is the Y-axis physical coordinate value of the original point of the CBCT image, and oz is the Z-axis physical coordinate value of the original point of the CBCT image; the index coordinate is a serial number of the implantation point relative to a CBCT image origin, and the CBCT image origin is a physical coordinate value of a pixel with a serial number value of (0,0,0) in the CBCT image;

the calculation formula of the first position of the root tip point of the implant is as follows:

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

wherein, 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 original point of the CBCT image, oy is the Y-axis physical coordinate value of the original point of the CBCT image, and oz is the Z-axis physical coordinate value of the original point of the CBCT image; and the index coordinate is a serial number of the implantation point relative to the original point of the CBCT image.

Alternatively, step S5: determining an error of the implant implantation position from an expected position, comprising:

determining an error epsilon between the distance of the connecting line between the root apex point and the implantation point of the implant and the length L of the implant according to the second position (X3, Y3, Z3) of the implantation point of the implant and the second position (X4, Y4, Z4) of the root apex point;

and if the epsilon is smaller than the preset threshold, determining that the position of the implant is correctly identified and the implant implantation position is correct.

Alternatively, if the error is greater than or equal to the preset threshold, the CBCT image is re-captured, and step S1 is executed.

In the above embodiments of the method of the present invention, the apparatus for determining the position of the implant in the CBCT image comprises:

the method comprises the following steps:

an image acquisition module: the CBCT image acquisition method comprises the steps of configuring to obtain a CBCT image after the implant is implanted;

cutting the module: 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; the set of sagittal plane views includes one or more sagittal plane views;

a first position module: configured to determine, in each view group, a view having a minimum distance from a central tangent plane of the implant, as a preferred view, all preferred views constituting a preferred view set, and determine a first position of an implantation point of the implant and a first position of a apical point of the root based on the preferred view sets;

a second position module: configured to determine a second location of an implantation point of the implant and a second location of a root tip point based on the first location of the implantation point and the first location of the root tip point;

an error module: configured to determine an error of the implant implantation position from an expected position.

In the above method embodiments of the present invention, a computer-readable storage medium has stored therein a plurality of instructions for being loaded by a processor and executing the method as described above.

In the foregoing method embodiments of the present invention, an electronic device includes:

a processor for executing a plurality of instructions;

a memory to store a plurality of instructions;

wherein the plurality of instructions are for storage by the memory and for loading and execution by the processor of the method as previously described.

The invention can rapidly acquire the positions of the implantation point and the root tip point of the implant from the CBCT image, and improve the accuracy of the position precision calculation of the implant.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail embodiments of the present invention with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings, like reference numbers generally indicate like parts or steps.

FIG. 1 is a schematic flow chart of a method for determining the position of an implant in a CBCT image according to the present invention;

FIG. 2 is a schematic flow chart of a method for determining an implantation point and a root tip point of an implant according to the present invention;

FIGS. 3(A) and 3(B) are schematic views of the apical point and the implantation point of the implant, respectively;

FIGS. 4(A) -4 (B) are schematic diagrams illustrating the operation of closing the implant on the image;

FIG. 5 is a schematic view illustrating the rotation of the image where the implant is located;

FIG. 6 is a schematic view of an image template of an implant;

FIG. 7 is a schematic view of an image area of an implant;

fig. 8(a) -8 (B) are schematic views of the selected section images with the largest SSIM index;

FIGS. 9(A) -9 (D) are schematic diagrams of the image coordinate system of OpenCV and the coordinate system of each set of slice images;

FIG. 10 is a schematic view of a bounding box detecting an implantation point and a root tip point of an implant;

FIGS. 11(A) -11 (B) are schematic views for distinguishing an implantation point and a apical point according to an opening of an implant;

FIG. 12 is a schematic diagram of a coordinate system of a CBCT image;

FIGS. 13(A) -13 (B) are schematic drawings of the CBCT image;

fig. 14(a) -14 (B) are schematic views of detected implantation points and apical points of the implant;

FIG. 15 is a schematic view of the apparatus for determining the position of an implant in a CBCT image according to the present invention;

FIG. 16 is a schematic structural diagram of an apparatus for determining the position of an implant in a CBCT image according to the present invention.

Detailed Description

Hereinafter, example embodiments according to the present invention will be described in detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of embodiments of the invention and not all embodiments of the invention, with the understanding that the invention is not limited to the example embodiments described herein.

It should be noted that: the relative arrangement of the 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.

It will be understood by those skilled in the art that the terms "first", "second", S1, S2, etc. in the embodiments of the present invention are used only for distinguishing between different steps, devices or modules, etc., and do not represent any specific technical meaning or necessarily logical order therebetween.

It should also be understood that in embodiments of the present invention, "a plurality" may refer to two or more and "at least one" may refer to one, two or more.

It is also to be understood that any reference to any component, data, or structure in the embodiments of the invention may be generally understood as one or more, unless explicitly defined otherwise or stated to the contrary hereinafter.

In addition, the term "and/or" in the present invention is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In the present invention, the character "/" generally indicates that the preceding and following related objects are in an "or" relationship.

It should also be understood that the description of the embodiments of the present invention emphasizes the differences between the embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

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.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Embodiments of the invention are operational with numerous other general purpose or special purpose computing system environments or configurations, and with numerous other electronic devices, such as terminal devices, computer systems, servers, etc. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as terminal devices, computer systems, servers, and the like, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Exemplary method

Fig. 1 is a flowchart illustrating a method for determining an implant position in a CBCT image according to an exemplary embodiment of the present invention. As shown in fig. 1, the method comprises the following steps:

step S1: acquiring a CBCT image after the implant is implanted;

step S3: in each view group, respectively determining a view with the minimum distance from the central tangent plane (tangent plane passing through the center line of the implant) of the implant, regarding the view as a preferred view, wherein all the preferred views form a preferred view set, and determining a first position of an implantation point of the implant and a first position of a apical point of the implant based on the preferred view set;

The step S1, wherein:

in order to evaluate and judge the implant position of the implant, a CBCT image is taken after the implant is implanted. For example, after planting, CBCT images are taken with an optical pointing device by the user receiving the planting. And removing artifacts from the CBCT image, namely performing smooth denoising operation, wherein the pixel interval of the CBCT image is less than 0.30 mm. The scanning pattern and coordinate system direction of CBCT imaging are shown in fig. 12, 13(a) -13 (B). The direction of the scan is from right to left, from sole to crown and from front to back. The open source software mitkWorkBench performs the viewing of the three-dimensional Volume rendering, and uses the function of Volume Visualization (Volume Visualization) in the software for visual viewing.

The step S2, wherein:

setting the direction of the center line of the implant in the CBCT image as a Z axis, taking the circle center of the inner circle of the implant as an origin, and taking a plane which is vertical to the Z axis and comprises the circle center of the inner circle of the implant as a horizontal plane; the direction which passes through the circle center in the horizontal plane and is horizontally right in the horizontal plane is determined as an X axis, and a line which passes through the circle center in the horizontal plane and is vertical to the X axis in the horizontal plane is determined as a Y axis; cutting the three-dimensional image from the direction parallel to the Z axis to obtain two groups of views which are parallel to the Z axis and are perpendicular to each other, wherein the view group parallel to the XZ plane is a coronal view group, the coronal view group comprises one or more coronal views, and the view group parallel to the YZ plane is a sagittal view group; the central line of the implant is a connecting line which penetrates through the root tip point and the implantation point of the implant.

In the present invention, the Cartesian Coordinate system of the CBCT image is used as a reference Coordinate system (concept of Coordinate system https:// www.slicer.org/wiki/Coordinate _ systems). The CBCT images obtained comprise a plurality of images with the sequence numbers from 0 to N, the image sequence numbers are automatically generated when the CBCT images are shot, the sequence numbers represent the positions of the images in the Z-axis direction in the space of the CBCT images, and the plane of each image is a plane parallel to the X-axis and the Y-axis, so that the CBCT image group corresponds to a three-dimensional image. When the center line of the implant is parallel to the Z-axis, then the coronal (parallel to the YZ plane) and sagittal (parallel to the XZ plane) views are parallel to the Z-axis, i.e. the center line of the implant is perpendicular to the normal of the two views.

The CBCT image includes a plurality of image sequences, which are usually sequences of various cross-sections, each image is a square, and therefore, assuming that the size of each image is D × D, the size corresponding to a three-dimensional image formed by combining all the images is D × N, after the three-dimensional image is sliced, a coronal view set includes D coronal views, and the size of each coronal view is D × N; the set of sagittal plane views includes D sagittal plane views, each having dimensions D × N.

The CBCT image is generally in DICOM format, the gray value (also called CT value or HU value) of the pixel of the DICOM format image is generally [ -1024,3071], the range exceeds the limit of human eye identification, and the invention converts the three-dimensional CBCT image into a coronal view group and a sagittal view group in the range of [0-255], wherein the views in the coronal view group and the sagittal view group are PNG images or JPEG images. That is, the three-dimensional CBCT image is converted into a PNG image or a JPEG image and stored by setting the corresponding window width and level.

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

As shown in fig. 2, 3(a), and 3(B), the step S3: in each view group, respectively determining a view with the minimum distance from the central tangent plane of the implant, regarding the view as a preferred view, wherein all the preferred views form a preferred view set, and determining a first position of an implantation point of the implant and a first position of a root tip point based on the preferred view set, wherein:

in each view group, determining the view with the minimum distance from the central tangent plane of the implant, and taking the view as a preferred view, including:

and the acquired view group is a view group of which the preferred view is not determined in one of the coronal view group and the sagittal view group.

The image processing comprises graying the view, then carrying out binarization and then using a closing operation. Due to the volume effect, the partially enclosed small objects are disconnected, so that the preprocessing operation using the image processing algorithm is required. Graying a two-dimensional PNG image and a JPEG image, binarizing, and connecting separated objects at a fine position and smoothing the boundary of a larger object by using a closing operation (expansion and corrosion). As shown in fig. 4(a) -4 (B), the implant is closed and the connection is broken at the small point. Fig. 4(a) is an image before the closing operation is performed, and fig. 4(B) is an image after the closing operation is performed.

Step S32: filtering, for the processed view set, views where no implant exists based on the actual Width and Length of the implant; for each view in the processed view group: calculating all bounding boxes of the contours in the view, and filtering out the view if all bounding boxes in the view have a length outside the range [ L A, L (2-A) ] and all bounding boxes have a width outside the range [ W A, W (2-A) ]; where, W is Width/Spacing, L is Length/Spacing, a is filtering precision, a range is (0, 1), and Spacing is a pixel interval in the CBCT image.

In this embodiment, Spacing takes on a value of 0.25.

In this embodiment, the purpose of this step is to filter out the view without implants. Each view is a two-dimensional image, and the bounding boxes of all contours in each view are computed, for example, using the minareact function in OpenCV. And then filtering the two-dimensional image based on the actual width and length of the implant. If the voxel of the CBCT image is a cube, namely the intervals Spacing in the three directions of XYZ are the same, the Width W of the implant in the two-dimensional image is Width/Spacing, the Length L is Length/Spacing, the filtering precision A (range 0 to 1) is specified, the contour with the Width not being [ W A, W (2-A) ] and the Length not being [ L A, L (2-A) ] is filtered, and if all the contours in a certain view are not in the specified filtering range, the image is filtered.

In this embodiment, the purpose of this step is to screen out the view closest to the central section of the implant. The same implant can form a plurality of section images in the DICOM image, and the implantation point and the root tip point are both positioned on the most central section image. Therefore, as shown in fig. 3(a), 3(B) and 6, the apex point is the lowest point of the bottom arc, and the implantation point is the center of the top opening circle. The identification of the implant is identified and filtered by the contour of the front view (side view), i.e. whether there is an area (corresponding to a non-zero area in the binary image) approximating the shape of the front view (side view) of the implant in the image of each slice view group in the CBCT image is detected. Fig. 6 shows an image template of an implant. And setting a plurality of image templates for calculating SSIM according to the planting area, the diameter and the length of the implant. In this embodiment, a standard STL model of the implant is used to make the center section image of the implant, which is a reference image. For each unfiltered view, calculating bounding boxes of all non-empty regions in the view, and extracting the regions with the length L1 and the width W1 of the bounding boxes closest to the actual length L and the width W of the implant as a detection region S of the image, as shown in FIG. 7, wherein FIG. 7 is an implant sectional image region example, and the implant region in the sagittal plane sectional image obtained by screening according to the length-width ratio and the actual length of the implant is extracted. There are various comparison methods for the bounding box with the smallest deviation between the size and the actual size of the implant, for example, the contour region 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 region S of the view; the outline area of the bounding box with the width W1 smallest deviation with the actual width dimension of the implant corresponding to the bounding box is used as the detection area S of the view; the bounding box length L1 and the actual implant length dimensional deviation, and the bounding box width W1 and the actual implant width dimensional deviation are weighted to obtain the outline area corresponding to the bounding box with the minimum dimensional deviation as the detection area S of the view. The actual length dimension of the implant is determined based on the center section image of the implant. In the invention, the gray value of the pixel of the white area in the image is 255, and the pixel is a non-empty area; the gray scale value of the pixel in the black background region is 0, and the pixel is an empty region.

The rotation angle of the detection area S can be determined based on the slope of the detection area S, and then rotation correction is performed based on the area (maxillary or mandibular) where the implant is located, as shown in fig. 5, if the implant is implanted in the maxillary area, the opening of the implant is directed vertically downward; if the implant is implanted in the lower jaw area, the implant opening is directed vertically upwards. And determining the scaling scale of the detection area S by taking the same pixel number of the scaled detection area S 'as the pixel number of the central section image of the implant as a target, then carrying out scaling operation on the detection area S, calculating the similarity between the detection area S' and a standard image, and taking a two-dimensional image of the detection area S with the largest SSIM index as a final section image of the implant. Comparing the SSIMs corresponding to the views retained after filtering, wherein the view corresponding to the SSIM with the largest value is the preferred view of the view group.

The all preferred views constitute a preferred view set comprising: extracting a preferred view from each view group, and naming and storing the preferred view by using the name of the view group where the preferred view is located and the sequence number of the preferred view in the view group; the preferred views corresponding to the two view groups respectively form a preferred view set.

In this embodiment, for example, if the SSIM index of the image with the serial number YYY in the Sagittal view group is the largest, the image is extracted and named as Sagittal _ YYY; the image with sequence number ZZZ in the Coronal view set has the largest SSIM index, and is extracted and named Coronal _ ZZZ. The detection of the implantation point and the apical point of the implant is performed from the front view and the side view, and thus two images having the largest SSIM index are extracted and then the two images are extracted to be subjected to the next detection step, as shown in fig. 8(a) -8 (B) and 9(a) -9 (D). Fig. 8(a) -8 (B) show the section images with the largest SSIM screened out. And determining the view group where the image is located according to the image name, wherein the serial number of the image in the view group is the same as the serial number of the image in the view group. Fig. 9(a) -9 (D) are schematic diagrams of the image coordinate system and the coordinate system in which each set of slice images is located. As shown in fig. 9(a) -9 (D), the sagittal plane sectional images are parallel to the YZ plane; the slice images of the coronal plane are parallel to the XZ plane.

Determining a first location of an implant point and a first location of a apical point of the implant based on the set of preferred views, comprising:

determining the coordinates of the implantation point and the root tip point of the implant in the preferred image respectively; the gray value of a pixel of a white area in the preferred image is 255, and the pixel is a non-empty area;

(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 original point of the CBCT image, oy is the Y-axis physical coordinate value of the original point of the CBCT image, and oz is the Z-axis physical coordinate value of the original point of the CBCT image; the index coordinate is a serial number of the implantation point relative to a CBCT image origin, and the CBCT image origin is a physical coordinate value of a pixel with a serial number value of (0,0,0) in the CBCT image.

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

wherein, 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 original point of the CBCT image, oy is the Y-axis physical coordinate value of the original point of the CBCT image, and oz is the Z-axis physical coordinate value of the original point of the CBCT image; and the index coordinates are the serial numbers of the implantation points relative to the original point of the CBCT image.

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

In this embodiment, the purpose of this step is to calculate the first position of the implant point and the apical point of the implant. And detecting the two screened preferable images, and calculating the positions of an implantation point and a root tip point of the implant. The detection region S of the preferred image is acquired. Referring to fig. 10, the midpoint of the two shortest sides of the bounding box is the implantation point and the root tip point of the implant, and in order to distinguish the implantation point and the root tip point of the implant, the opening direction of the implant needs to be determined, i.e., which short side is close to the opening region and which short side is close to the bottom region. Calculating the slope K of the detection area S, if the absolute value of the slope K is greater than 1, converting the implant into a vertical direction, dividing the implant into two areas S _ up and S _ down in an up-and-down manner, and calculating the number of non-empty pixels in the two areas S _ up and S _ down, wherein the area with a small number of non-empty pixels is the area where the top opening of the implant is located, 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 S _ down, namely the opening of the implant is upward, the middle point of the top of a bounding box (the minimum Y value short side in an OpenCV coordinate system) is the implantation point of the implant, and the middle point of the short side of the bottom is the root tip point of the implant; if the absolute value of the slope K is smaller than 1, the implant is turned to be in a horizontal orientation, then the implant is divided into two areas S _ left and S _ right in a left-right halving mode, and similarly, the area with the smaller number of the non-empty pixels is the area where the top of the implant is located, as shown in fig. 11(B), the number of the S _ right non-empty pixels is smaller than the number of the S _ left non-empty pixels, the opening of the implant faces to the right, the midpoint of the short side of the right side (with the largest X value in an OpenCV coordinate system) of the bounding box is the implantation point of the implant, and the midpoint of the short side of the left side is the root tip point of the implant.

And determining coordinate values of the implantation point and the apical point of the implant in a three-dimensional space 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, and taking the coordinate values as the first positions of the implantation point and the apical point of the implant. The relationship between the coordinate system of OpenCV and each group of sectional view sets formed by CBCT images is shown in fig. 9, and it is necessary to map the coordinate values detected by OpenCV back to the three-dimensional coordinate space where the CBCT images are located. Taking the coordinate value of the implantation point of the image Sagittal _ V3 for detecting the Sagittal plane as an 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 (Index) coordinate value of the CBCT image, the Index (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 Y-axis direction dimension of the image (the image is a two-dimensional array, where the dimension also refers to the number of lines in the two-dimensional array), and the Index (Index) coordinate value in the X-axis direction of the implant is the serial number (generated during re-slicing) V3 of the PNG image. Therefore, the detected index coordinate value of the implant from the image Sagittal _ V3 is (V3, V1, V2), and the coordinate value of the implant in the 3D image space, that is, (V3 Spacing + ox, V1 Spacing + oy, V2 Spacing + oz), can be obtained by multiplying the index coordinate value by the pixel Spacing of the CBCT image and the offset (ox, oy, oz) from the origin of the coordinate system in the 3D image space.

The step S4: determining a second position of the implantation point of the implant and a second position of the apical point based on the first position of the implantation point of the implant and the first position of the apical point, comprising: and taking the coordinate mean value of the first position of the implantation point of the implant corresponding to each preferred image as the second position of the implantation point of the implant, and taking the coordinate mean value of the first position of the root tip point of the implant corresponding to each preferred image as the second position of the root tip point of the implant.

In this embodiment, the mean value is taken to obtain the exact position of the implantation point and the root tip 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 value ((X1+ X2)/2, (Y1+ Y2)/2, (Z1+ Z2)/2) is taken as the second position.

Step S5: determining an error of the implant implantation position from an expected position, comprising:

In this embodiment, an error between the distance between the connection line between the root tip and the implantation point of the implant and the actual length of the implant is calculated as a calculation error of the algorithm of the present invention. Assuming that the coordinate values of the implantation point of the implant are (X3, Y3, Z3), the coordinate values of the apical point are (X4, Y4, Z4), and the actual length of the implant is L mm, the overall error is

The error ε is calculated as a percentage, and if ε is less than 1%, the recognition is considered more accurate.

Further, after the step S5, a step S6 is also included.

Step S6: if the error is greater than or equal to the preset threshold, the CBCT image is re-captured, and step S1 is executed.

In this embodiment, if the error is greater than or equal to the preset threshold, it is determined that a large artifact exists in the CBCT, resulting in deformation of the implant. The CBCT image can be re-shot, and the influence of the CBCT artifact in the original image on the implant image is reduced.

In yet another embodiment of the present invention, a method for determining the position of an implant in a CBCT image is provided. The embodiment comprises the following steps:

taking CBCT images

The patient takes a preoperative CBCT image with the positioning guide plate and performs artifact removing operation, and the pixel interval X, Y, Z direction of the CBCT image is 0.3mm in the example.

Converting CBCT image into PNG image

The CBCT image in this example consists of a total of 402 slice sequences, each slice image being 512X 512 in size, and after being combined into a 3D image being 512X 402 in size, the centerline of the implant is parallel to the YZ plane and the XZ plane, so that the 3D image is re-sliced from the coronal and sagittal planes to obtain 512 coronal planes (512X 402 in image size) and 512 sagittal planes (512X 402 in image size).

The material of the implant used in this example was titanium, and the CT value of titanium was 2900. The window level 2900 and the window width 500 are set, and the gradation values in the range of [2900 to 500/2,2900+500/2] are linearly mapped in the range of 0 to 255, the gradation values of the pixels lower than 2900 to 500/2 are set to 0, and the gradation values of the pixels higher than 2900+500/2 are set to 255. Only the area formed by the object with the titanium density close to that of the material of the implant can be reserved in the PNG image by setting the window width and the window level.

Calculating implant implantation point and root apex position in each group of section views

Preprocessing an image. Firstly, carrying out gray level processing on a PNG image, and converting an RBG image into a gray level image; then, carrying out binarization processing, converting the gray map into a binary map, setting a threshold 127, setting the gray value of the pixel point which is larger than the threshold 127 as 255, and setting the gray value of the pixel point which is smaller than the threshold 127 as 0; finally, the separated objects are connected at the slimmer and the boundaries of the larger objects are smoothed using a close operation (dilation followed by erosion) with a convolution kernel of 5X 5.

Filtering out the images without the implant. The implant used in this example had a width of 4.8mm and a length of 10 mm. The bounding boxes of the contours of all non-empty regions in each image were computed using the minAreaRect function in OpenCV. The PNG image is filtered based on the actual width and length of the implant. If the voxels of the CBCT image are cubes, that is, the intervals Spacing in the three XYZ directions are the same, 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, which are rounded up. The filtering accuracy is specified to be 0.8, the filtering is performed on the contours with the widths not being [16 × 0.8,16 × 2-0.8 ] and the lengths not being [34 × 0.8,34 × 2-0.8 ], and if the length and the width of all the contours in the image are not satisfactory, the image is filtered.

And thirdly, screening out the image closest to the central tangent plane of the implant. Filtering and screening the PNG images in the coronal view group and the sagittal view group by using the SSIM indexes, selecting the PNG image with the largest SSIM index in each group, and keeping 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 of 0202 in the Sagittal plane view group is maximum and is 0.7765, and the PNG image is extracted and renamed to Sagittal _0202. PNG; the slice image with index 0129 in the Coronal view group had the largest SSIM index of 0.7709, and the PNG image was extracted and renamed Coronal _0129. PNG.

And fourthly, calculating the positions of the implantation point and the root tip point of the implant. Taking the detection of the implant point and the root tip point of the implant in the PNG image Sagittal _0202 as an example, the absolute value of the slope K of the area where the implant is detected to be-152 is greater than 1, the implant is rotated to the vertical direction, the implant is divided into the upper and lower parts, the number of non-empty pixels of S _ up is 101, the number of non-empty pixels of S _ down is 204, and S _ up is smaller than S _ down, so that the implant opening is upward, the midpoint of the short side of the bounding box top (coordinate value is (130,341)) is the implant point of the implant, and the midpoint of the short side of the bounding box bottom (coordinate value is (130,375)) is the root tip point of the implant. Combining the coordinate system transformation relationship of FIG. 9 and the Z-axis dimension 402 of the CBCT image, the index coordinate values of the implant implantation point are found to be (202,130,402- & 341) (202,130,61), the coordinate values of the root tip point are found to be (202,130,402- & 375) (202,130,27), and then the coordinate values of the implant implantation point and the root tip point in the CBCT image space are found to be (202X 0.3-76.95,130X 0.3-76.95, 61X 0.3-60.15) and (202X 0.3-76.95,130X 0.3-76.95, 27X 0.3-60.15), respectively, combining the pixel interval of the CBCT image 0.3 and the offset (-76.95, -76.95, -60.15) with the origin.

And taking the mean value to obtain the accurate positions of the implantation point and the root tip point of the implant in the CBCT image.

As shown in fig. 14(a) -14 (B), fig. 14(a) is a side view of the implant and its center line (a line between the implantation point and the apical point), and fig. 14(B) is a top view of the implant and its center line.

In the previous step, the coordinate values of the implant point and the apical point of the implant 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 implant insertion point and the apical point of the implant obtained from the Coronal _0129 image are (-15.90, -38.25, -42.05) and (-15.90, -38.25, -52.05), respectively. After the averaging, the coordinate values of the last implantation points of the implant are obtained as (-16.125, -38.10, -41.95) and (-16.125, -38.10, -52.05).

Evaluation of detection error

Calculating the Euclidean distance between an implant implantation point and a root tip point to obtain a value of 10.1, and combining the actual length of the implant of 10mm, the total error of the algorithm is

The error is less than or equal to 1 percent, and the identification accuracy of the method is higher.

Exemplary devices

Fig. 15 is a schematic structural diagram of an apparatus for determining an implant position in a CBCT image according to an exemplary embodiment of the present invention. As shown in fig. 15, the present embodiment includes:

Exemplary electronic device

Fig. 16 shows a structure of an electronic device 160 according to an exemplary embodiment of the present invention. The electronic device may be either or both of the first device and the second device, or a stand-alone device separate from them, which stand-alone device may communicate with the first device and the second device to receive the acquired input signals therefrom. FIG. 16 illustrates a block diagram of an electronic device in accordance with an embodiment of the disclosure. As shown in fig. 16, the electronic device includes one or more processors 161 and memory 162.

The processor 161 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

Memory 162 may include one or more computer program products that 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), cache memory (cache), and/or the like. 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 executed by the processor 161 to implement the method of determining the position of an implant in a CBCT image and/or other desired functions of the software program of the various embodiments of the present disclosure described above. In one example, the electronic device may further include: an input device 163 and an output device 164, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

The input device 163 may also include, for example, a keyboard, a mouse, and the like.

The output device 164 can output various information to the outside. The output devices 164 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.

Of course, for simplicity, only some of the components of the electronic device relevant to the present disclosure are shown in fig. 16, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device may include any other suitable components, depending on the particular application.

Exemplary computer program product and computer-readable storage Medium

In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in a method of determining an implant position in a CBCT image according to various embodiments of the present disclosure as described in the "exemplary methods" section of this specification, supra.

The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps in the method of determining the position of an implant in a CBCT image according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.

The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The foregoing describes the general principles of the present disclosure in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present disclosure are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure is not intended to be limited to the specific details so described.

In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same or similar parts in each embodiment are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by one skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".

The method and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of 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 specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure. The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.

Claims

1. A method of determining implant location in a CBCT image, comprising:

step S1: acquiring a CBCT image after the implant is implanted;

step S2: cutting a three-dimensional image corresponding to the CBCT image to obtain a coronal plane view group and a sagittal plane view group of the three-dimensional image, wherein the sagittal plane view group comprises one or more sagittal plane views;

step S4: determining a second position of an implantation point of the implant and a second position of a root tip point based on the first position of the implantation point and the first position of the root tip point of the implant; and

2. The method of claim 1, wherein said step S2, wherein:

3. The method of any one of claims 1-2, wherein in step S3, the determining the view with the smallest distance from the central tangent plane of the implant in each view group as the preferred view comprises:

step S32: filtering, for the processed view set, views where no implant exists based on the actual Width and Length of the implant; for each view in the processed view group: calculating bounding boxes for all contours in the view, filtering out the view if the Length of all bounding boxes in the view is outside the range [ L A, L (2-A) ] and the Width of all bounding boxes in the view is outside the range [ W A, W (2-A) ]; wherein, W is Width/Spacing, L is Length/Spacing, a is filtering precision, a range is (0, 1), and Spacing is pixel interval in the CBCT image;

4. The method of claim 3, wherein the step S3 of determining the first location of the implant point and the first location of the apical point of the implant based on the set of preferred views comprises:

step S34: for each preferred image in the preferred view set: acquiring a detection area S of the preferred image; if the absolute value of the slope K of the detection area S is larger than 1, the detection area S is converted into a vertical direction, then the detection area S is divided into two areas, namely an upper area S _ up and a lower area S _ down, the number of non-empty pixels in the two areas S _ up and S _ down is calculated, the area with the small number of non-empty pixels is the area where the top opening of the implant is located, and the area with the 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 smaller than 1, the detection area S is converted into a horizontal direction, then the detection area S is divided into two areas, namely a left area S _ left and a right area S _ right, the number of non-empty pixels in the two areas of the left area S _ left and the right area S _ right is calculated, the area with the small number of non-empty pixels is the area where the top opening of the implant is located, and the area with the large number of non-empty pixels is the area where the bottom of the implant is located;

(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 CBCT image origin, oy is the Y-axis physical coordinate value of the CBCT image origin, and oz is the Z-axis physical coordinate value of the CBCT image origin; the index coordinate is a serial number of the implantation point relative to a CBCT image origin, and the CBCT image origin is a physical coordinate value of a pixel with a serial number value of (0,0,0) in the CBCT image;

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

5. The method according to any of claims 1-2, wherein the step S5: determining an error of the implant implantation position from an expected position, comprising:

determining an error epsilon between the distance of a connecting line between the apical apex of the implant and the implantation point and the length L of the implant according to the second position (X3, Y3, Z3) of the implantation point of the implant and the second position (X4, Y4, Z4) of the apical apex;

and if the epsilon is smaller than the preset threshold value, determining that the position of the implant is correctly identified and the implant implantation position is correct.

6. The method as claimed in any one of claims 1-2, wherein if the error is greater than or equal to the preset threshold, the CBCT image is re-captured, and the step S1 is performed.

7. An apparatus for determining the position of an implant in a CBCT image, comprising:

8. A computer-readable storage medium having stored therein a plurality of instructions for loading by a processor and executing the method of any of claims 1-6.

9. An electronic device, characterized in that the electronic device comprises:

a processor for executing a plurality of instructions;

a memory for storing a plurality of instructions;

wherein the plurality of instructions are for storage by the memory and for loading and execution by the processor of the method of any of claims 1-6.