CBCT system bed board artifact correction method, device and equipment and storage medium

Abstract

The invention discloses a CBCT system bed board artifact correction method, device and equipment and a storage medium, and relates to the technical field of computed tomography. The method comprises the following steps: scanning first object projection data of an object by a bed board; performing three-dimensional reconstruction on the first object projection data to obtain a first CBCT image; constructing a three-dimensional digital image of the bed board according to the first CBCT image; forward projecting the three-dimensional digital image of the bed board to obtain an independent bed board projection; according to the independent bed board projection, separating the contribution of the bed board from the first object projection data to obtain second object projection data; performing three-dimensional reconstruction on the second object projection data to obtain a second CBCT image; and carrying out image evaluation index judgment until the evaluation index is greater than or equal to a preset threshold value, and obtaining an image without the bed board artifact. According to the method, the three-dimensional digital image of the bed board is constructed through one-time scanning to achieve artifact removal, related problems of secondary scanning are avoided, low-complexity forward projection is adopted to separate bed board contribution, and higher robustness and convenience are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer tomography, in particular to a CBCT system bed plate artifact correction method, device, equipment and storage medium. BACKGROUND

[0002] Cone beam tomography technology (CBCT) uses one or more sets of radiation sources and flat panel detectors to rotate around the treatment bed for scanning, which can reconstruct the three-dimensional volume data of the object on the bed at one time, and is widely used in dental specialties, image-guided and pet medical fields. FDK reconstruction algorithm is the most widely used FBP type reconstruction algorithm in the field of CBCT, but this algorithm is prone to ring effect when dealing with the edge area with severe image gray scale change (such as the edge of the bed plate), which leads to the appearance of radial stripe artifacts.

[0003] In order to solve the problem of artifacts introduced by the bed plate and other angular objects, two processing schemes are proposed in the industry. The first scheme requires two scans for each object, one normal scan and one scan of the bed plate only, and then the bed plate part in the object scan data is removed through a formula, and then the reconstruction is carried out, so as to remove the artifacts caused by the bed plate. However, this scheme requires two scans, which increases the scanning cost and time, and it is difficult to ensure the consistency of each scan angle of the gantry, and the deformation of the bed plate is inconsistent under the conditions of weight and no object, which leads to the fact that the bed plate data cannot be completely separated, and the artifacts are difficult to completely remove. The second scheme is to pre-scan the bed plate data, and to perform image registration between the bed plate projection and the object projection during the object scan, so that they are located at the same scanning position, and then the bed plate part is removed from the object scan data for reconstruction, and finally the artifacts are removed. However, this scheme still cannot avoid the problem of inconsistent deformation of the bed plate under the weight, and involves a large number of projection image registrations, and needs to correct the dose difference between pre-scanning and actual scanning, which increases the complexity of the algorithm and cannot meet the requirements of real-time image reconstruction. Therefore, the second scheme also cannot completely remove the bed plate artifacts in practical application. SUMMARY

[0004] Based on the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a CBCT system bed plate artifact correction method, device, equipment and storage medium to solve the above technical problems.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a CBCT system bed plate artifact correction method, comprising:

[0006] scanning the first object projection data of the object with the bed plate;

[0007] performing three-dimensional reconstruction on the first object projection data to obtain a first CBCT image;

[0008] constructing a bedplate three-dimensional digital image according to the first CBCT image;

[0009] forward projecting the bedplate three-dimensional digital image to obtain a single bedplate projection;

[0010] separating the contribution of the bedplate from the first object projection data according to the single bedplate projection to obtain second object projection data;

[0011] performing three-dimensional reconstruction on the second object projection data to obtain a second CBCT image;

[0012] performing image evaluation index judgment on the second CBCT image until the evaluation index is greater than or equal to a preset threshold to obtain a final CBCT image with bedplate artifacts removed.

[0013] The application is further provided that the bedplate three-dimensional digital image is constructed according to the first CBCT image, and the bedplate three-dimensional digital image comprises:

[0014] performing image segmentation and morphological operation on the first CBCT image to generate a bedplate mask image;

[0015] multiplying the first CBCT image and the bedplate mask image to separate the bedplate three-dimensional digital image.

[0016] The application is further provided that the image segmentation and morphological operation comprises:

[0017] segmenting the first CBCT image by using a 3DU-Net neural network to obtain a first CBCT initial bedplate mask;

[0018] performing morphological dilation operation on the first CBCT initial bedplate mask to expand the mask edge by a preset number of pixels to generate a first CBCT bedplate mask image.

[0019] The application is further provided that the forward projection is realized by using an energy-dependent physical model, and the single bedplate projection data is generated by performing energy-weighted path integral operation on the radiation path from the ray source to the detector pixel based on the voxel gray value of the bedplate three-dimensional digital image, in combination with the ray source energy spectrum function and the flat panel detector energy absorption function.

[0020] The application is further provided that the contribution of the bedplate is separated from the first object projection data by subtracting the single bedplate projection from the first object projection data in a projection subtraction manner to obtain the second object projection data.

[0021] The application is further configured that the image evaluation index is an information entropy of the second CBCT image, the information entropy is calculated based on a gray scale statistical distribution of the second CBCT image, the information entropy value is obtained as the image evaluation index by performing a negative accumulation sum operation on a probability value of each gray scale and a binary logarithm product of the probability value and a normalized probability distribution function of all gray scales of the second CBCT image.

[0022] The application is further configured that when the image evaluation index is less than a preset threshold value, the ray source spectrum function and the flat panel detector energy absorption function are updated;

[0023] Based on the updated ray source spectrum function and the flat panel detector energy absorption function, the updated individual bed plate projection is regenerated, and the newly generated bed plate projection contribution is separated from the first object projection data to generate updated second object projection data;

[0024] The updated second object projection data is subjected to three-dimensional reconstruction to generate an updated second CBCT image;

[0025] The updated second CBCT image is subjected to image evaluation index judgment until the image evaluation index meets the preset threshold value requirement.

[0026] The application also provides a CBCT system bed plate artifact correction device for implementing the CBCT system bed plate artifact correction method.

[0027] The image scanning module is configured to scan the object with the bed plate to obtain the first object projection data.

[0028] The image reconstruction module is configured to perform three-dimensional reconstruction on the first object projection data to obtain the first CBCT image, and perform three-dimensional reconstruction on the second object projection data to obtain the second CBCT image.

[0029] The model construction module is configured to construct a bed plate three-dimensional digital image based on the first CBCT image.

[0030] The forward projection module is configured to perform forward projection on the bed plate three-dimensional digital image to obtain the individual bed plate projection.

[0031] The projection separation module is configured to separate the contribution of the bed plate from the first object projection data based on the individual bed plate projection to obtain the second object projection data.

[0032] The image evaluation module is configured to perform image evaluation index judgment on the second CBCT image until the evaluation index is greater than or equal to the preset threshold value to obtain the final CBCT image with the bed plate artifact removed.

[0033] The application also provides an electronic device, which comprises:

[0034] one or more processors;

[0035] a storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement a CBCT system bed board artifact correction method according to any one of the preceding.

[0036] The present application also provides a computer-readable storage medium having a computer program stored thereon, which when executed by a processor of a computer, causes the computer to perform a CBCT system bed board artifact correction method according to any one of the preceding.

[0037] The present application provides a CBCT system bed board artifact correction method, device, equipment and storage medium, the method is through the first object projection data of the object scanned with the bed board;The first object projection data is three-dimensionally reconstructed, and the first CBCT image is obtained;The bed board three-dimensional digital image is constructed according to the first CBCT image;The bed board projection is obtained by forward projection to the bed board three-dimensional digital image;The contribution of the bed board is separated from the first object projection data according to the bed board projection alone, and the second object projection data is obtained;The second object projection data is three-dimensionally reconstructed, and the second CBCT image is obtained;The image evaluation index is judged to the second CBCT image, until the evaluation index is greater than or equal to the preset threshold, and the CBCT image of the bed board artifact is finally removed, and the beneficial effects include:

[0038] 1、the present application only needs to scan the object with the bed board once, does not need to scan the bed board alone twice, avoids the inconsistent dose of secondary scanning, the inconsistent angle of secondary scanning and the inconsistent deformation of the bed board under load and without object, etc.

[0039] 2、the present application realizes artifact removal by constructing the bed board three-dimensional digital image, which is fundamentally different from the two common processing schemes in the industry, respectively scans the object and the bed board twice and removes the bed board interference reconstruction, or pre-scans the bed board and removes the bed board part after registration with the object scanning data, exhibits higher robustness and convenience, and the present application can also be used for bed board separation.

[0040] 3、the present application separates the contribution of the bed board projection by using forward projection mode, and the algorithm complexity is low, so that real-time processing can be realized, and actual clinical application is met.

[0041] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, which can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application. Other drawings can be obtained by those skilled in the art without any creative effort, based on these drawings. In the drawings:

[0043] Figure 1 A flow chart of the CBCT system bed board artifact correction method shown in an exemplary embodiment of the present application;

[0044] Figure 2 A structural diagram of a circular orbit CBCT system;

[0045] Figure 3 A structural schematic diagram of the CBCT system bed board artifact correction device shown in an exemplary embodiment of the present application;

[0046] In the drawings, 201 is an X-ray generating device, 202 is a flat panel detector, 203 is a bearing bed board, and 204 is a scanning object. DETAILED DESCRIPTION

[0047] The embodiments of the present application will be described hereinafter with reference to the drawings and preferred embodiments in detail, and other advantages and effects of the present application can be easily understood by those skilled in the art from the contents disclosed in the present specification. The present application can also be implemented or applied by other different specific embodiments, and each detail in the present specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0048] It should be noted that the drawings provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the drawings, but not the number, shape and size of the components when actually implemented. The type, number and proportion of each component when actually implemented can be arbitrarily changed, and the layout type of the components can also be more complex.

[0049] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application, however, it is obvious for those skilled in the art that the embodiments of the present application can be implemented without these specific details, and in other embodiments, the known structures and devices are shown in the form of block diagrams instead of details, to avoid making the embodiments of the present application difficult to understand.

[0050] Embodiment one

[0051] A CBCT system bed plate artifact correction method, as shown in Figure 1 comprises:

[0052] First object projection data of a scanned object with a bed plate;

[0053] Three-dimensional reconstruction is performed on the first object projection data to obtain a first CBCT image;

[0054] A bed plate three-dimensional digital image is constructed according to the first CBCT image;

[0055] Forward projection is performed on the bed plate three-dimensional digital image to obtain a single bed plate projection;

[0056] According to the single bed plate projection, the contribution of the bed plate is separated from the first object projection data to obtain second object projection data;

[0057] Three-dimensional reconstruction is performed on the second object projection data to obtain a second CBCT image;

[0058] Image evaluation index judgment is performed on the second CBCT image until the evaluation index is greater than or equal to a preset threshold value, to obtain a final CBCT image with bed plate artifact removed.

[0059] Specifically, a CBCT system bed plate artifact correction method is applied to a circular orbit CBCT system as shown in Figure 2 The circular orbit CBCT system comprises an X-ray generating device 201, a flat panel detector 202, and a bearing bed plate 203; the X-ray generating device 201 is arranged at the top of the circular orbit CBCT system, the flat panel detector 202 is arranged at the bottom of the circular orbit CBCT system, and the bearing bed plate 203 is arranged between the X-ray generating device 201 and the flat panel detector 202; the X-ray generating device 201 is 650 mm away from the rotation center and 1060 mm away from the flat panel detector 202; the X-ray generating device 201 and the flat panel detector 202 rotate at a speed of 10 degrees per second around the rotation center of the CBCT system 20 (which can be approximately regarded as the center point of the scanned object 204 placed on the bearing bed plate 203) at a uniform speed, and the angle range of rotation is 0 to 360 degrees; during rotation, the X-ray generating device 201 emits X-rays, the X-rays pass through the scanned object 204 and the bearing bed plate 203 and are partially attenuated, and then are captured by the flat panel detector 202 at an acquisition rate of 20 frames per second and converted into image signals, i.e. projection data.

[0060] Specifically, the acquisition process of the first object projection data scanned with the bed plate is as follows: the scanned object 204 is placed on the bearing bed plate 203, the CBCT system 20 is started to perform full circle scanning at a uniform rotation speed of 10 degrees per second, and a total of 720 frames of first object projection data are acquired, which is denoted as P mix; During the entire rotation scanning phase, the scanning object 204 and the bearing bed plate 203 are always located within the X-ray coverage area, thereby ensuring complete acquisition of the projection data of the scanning object 204 and the bearing bed plate 203.

[0061] Specifically, the first object projection data is subjected to three-dimensional reconstruction to obtain a first CBCT image, in this embodiment, the first object projection data P mix is subjected to three-dimensional reconstruction to obtain a first CBCT image, denoted as I mix ; It needs to be particularly pointed out that the three-dimensional reconstruction algorithm is not limited in this embodiment, therefore, a person skilled in the art can select other suitable reconstruction algorithms according to the specific application requirements, for example, iterative reconstruction algorithms such as algebraic reconstruction technique SART and maximum likelihood expectation maximization algorithm MLEM, or image reconstruction methods based on deep learning network; the reason why the FDK analytical reconstruction algorithm is selected in this example is that the algorithm has been widely applied in the field of CBCT, and through GPU parallel processing, the analytical reconstruction algorithm FDK can improve the running efficiency, shorten the calculation time, thereby reducing the time cost, and meet the needs of real-time or high-frequency image reconstruction.

[0062] The application further provides that the construction of the bed plate three-dimensional digital image according to the first CBCT image comprises: performing image segmentation and morphological operation on the first CBCT image to generate a bed plate mask image; and multiplying the first CBCT image and the bed plate mask image to separate the bed plate three-dimensional digital image; the application further provides that the image segmentation and morphological operation comprises: segmenting the first CBCT image by using a 3DU-Net neural network to obtain a first CBCT initial bed plate mask; and performing morphological dilation operation on the first CBCT initial bed plate mask to expand the mask edge by a preset number of pixels to generate a first CBCT bed plate mask image; specifically, in this embodiment, the first CBCT image I mix is segmented by using a 3DU-Net neural network to obtain a first CBCT initial bed plate mask image, denoted as I inmask; the bed plate mask image is a binary image, wherein 1 represents a bed plate region and 0 represents other regions; the 3D U-Net neural network is trained by using a simulated three-dimensional reconstruction image, and the simulated three-dimensional reconstruction image includes a single bed plate, a single object and a three-dimensional image of a combination of a bed plate and an object; a three-dimensional forward projection algorithm is used to perform virtual projection on a CAD three-dimensional design image of a bed body and a three-dimensional digital image of an object, to obtain projection data of a single bed plate, projection data of a single object and projection data of a combination of a bed plate and an object respectively; a FDK analytical reconstruction algorithm is used to reconstruct the three groups of simulated projection data, to generate a simulated three-dimensional reconstruction image required for training of the 3D U-Net neural network; after the first CBCT initial bed plate mask image I inmask is obtained, a morphological dilation operation is used to expand the mask edge outward by a preset number of pixels, to obtain a first CBCT bed plate mask image, and the first CBCT bed plate mask image is denoted as I mask ; in the present example, the preset number of pixels is set to 5; the morphological dilation operation can effectively reduce missegmentation regions and improve the robustness of the system; the obtained first CBCT bed plate mask image I mask is multiplied by a first CBCT image I mix , to separate the bed plate part in the first CBCT image I mix , and further obtain a bed plate three-dimensional digital image, and the bed plate three-dimensional digital image is denoted as I model ; it needs to be further explained that the three-dimensional forward projection algorithm is not limited in the present example, and a person skilled in the art can select different types of forward projection algorithms according to requirements, for example, virtual projection algorithms such as distance driving, pixel driving and grid driving, and these methods are all included in the protection scope of the present application.

[0063] The present application is further provided that the forward projection is realized by using an energy-dependent physical model, based on a voxel gray value of the bed plate three-dimensional digital image, combined with a ray source energy spectrum function and a flat panel detector energy absorption function, energy-weighted path integral operation is performed on a radiation path from a ray source to a detector pixel, to generate the single bed plate projection data; specifically, the bed plate three-dimensional digital image I model is subjected to forward projection, to obtain a single bed plate projection, and the single bed plate projection is denoted as P model ; in the present example, the forward projection algorithm is consistent with the three-dimensional forward projection algorithm described in the previous step; in the present example, the specific process of the forward projection algorithm is described by the following formula: Wherein, E is an energy variable, φ (E) is a ray source spectrum function, r (E) is a flat panel detector energy absorption function, μ (E) is a linear attenuation coefficient function, and L is a path length from the ray source to a pixel deposition point of the flat panel detector;φ (E) is used to describe the intensity distribution of each energy component emitted by the ray source, reflecting the emission characteristics of the ray source at different energies, r (E) is used to describe the absorption ability of the detector to rays of different energies, and both φ (E) and r (E) need to be determined or estimated through experiments;The linear attenuation coefficient function μ (E) is calculated based on a preset conversion relationship between the voxel grayscale value of the bedplate three-dimensional digital image I model and the linear attenuation coefficient function of water, and the specific conversion calculation formula is as follows: Wherein, μ w (E) is the linear attenuation coefficient function of water, which can be obtained from a known physical database; is used to convert the voxel grayscale value in the bedplate three-dimensional digital image I model into a scale compatible with the linear attenuation coefficient function μ w (E) of water, and the grayscale value of the bedplate three-dimensional digital image I model is standardized so that the corresponding linear attenuation coefficient function μ (E) can be calculated;It should be particularly pointed out that the ray source spectrum function φ (E) and the energy absorption function r (E) of the detector will change with different experimental conditions, so the single bedplate projection P model will also be affected.

[0064] The application further provides that the bedplate contribution is separated from the first object projection data by subtracting the single bedplate projection from the first object projection data to obtain second object projection data;Specifically, the bedplate contribution is separated from the first object projection data P model to obtain second object projection data P′ mix , and the second object projection data is denoted as P′ mix ;The separation method is projection subtraction, and the calculation formula is as follows: P′ mix = P mix -P model In order to make the transition of the subtracted projection more natural and smooth, the second object projection data P′ mix may be further subjected to smoothing filtering, image denoising or Gaussian blurring operations, and the above image filtering operations are not described in detail in this embodiment for the purpose of simplifying the description, but it should be understood that the related filtering operations still belong to the protection scope of the application;The second object projection data is denoted as P′ mix for three-dimensional reconstruction to obtain a second CBCT image, and the second CBCT image is denoted as I objectThe reconstruction algorithm used has been described in detail in the preceding steps and will not be repeated here. It should be noted that, given the projection data P′ of the second object... mix The contribution of the separated bed plate is thus obtained in the second CBCT image I. object The images are mainly reconstructed images of the object parts.

[0065] The present invention is further configured such that the image evaluation index is the information entropy of the second CBCT image, which is calculated based on the gray-level statistical distribution of the second CBCT image. This is achieved by statistically analyzing the normalized probability distribution function of all gray levels in the second CBCT image, performing a negative cumulative summation operation on the probability value of each gray level and the binary logarithmic product of that probability value, and obtaining the information entropy value as the image evaluation index. The present invention is further configured such that when the image evaluation index is less than a preset threshold, the X-ray source energy spectrum function and the flat panel detector energy absorption function are updated; based on the updated X-ray source energy spectrum function and the flat panel detector energy absorption function, an updated individual bed projection is regenerated, and the newly generated bed projection contribution is separated from the first object projection data to generate updated second object projection data; three-dimensional reconstruction is performed on the updated second object projection data to generate an updated second CBCT image; the updated second CBCT image is then judged based on the image evaluation index until the image evaluation index meets the preset threshold requirement; specifically, based on the second CBCT image I... object The image evaluation metric is calculated, which can be measured by information entropy. The formula for calculating information entropy is: Where f is the information entropy, and K is the second CBCT image I. object The total number of gray levels, k is the second CBCT image I object For each gray level in the image, g(k) represents the second CBCT image I. object The ratio of the number of pixels with a grayscale value of k to the total number of pixels is the grayscale probability function; the larger the information entropy f value, the smaller the artifacts in the image; in this embodiment, the information entropy threshold is preset to δ. When f ≥ δ, that is, when the image evaluation index is greater than or equal to the threshold, the final CBCT image I with bed board artifacts removed is obtained. final Otherwise, update the X-ray source energy spectrum function and the flat panel detector energy absorption function, regenerate individual bed plate projection data based on the updated X-ray source energy spectrum function and the flat panel detector energy absorption function, separate the bed plate contribution from the first object projection data to obtain the updated second object projection data, perform three-dimensional reconstruction on the updated second object projection data to generate the updated second CBCT image, and recalculate the image evaluation index until the image evaluation index meets the preset threshold requirements.

[0066] Example 2

[0067] Please see Figure 3The example CBCT system bed board artifact correction device includes:

[0068] An image scanning module: used for scanning a first object projection data of an object with a bed board;

[0069] An image reconstruction module: used for three-dimensional reconstruction of the first object projection data to obtain a first CBCT image, and three-dimensional reconstruction of the second object projection data to obtain a second CBCT image;

[0070] A model construction module: used for constructing a bed board three-dimensional digital image according to the first CBCT image;

[0071] A forward projection module: used for forward projection of the bed board three-dimensional digital image to obtain a single bed board projection;

[0072] A projection separation module: used for separating a contribution of the bed board from the first object projection data according to the single bed board projection to obtain the second object projection data;

[0073] An image evaluation module: used for image evaluation index judgment of the second CBCT image until the evaluation index is greater than or equal to a preset threshold to obtain a final CBCT image with bed board artifacts removed.

[0074] It should be noted that the CBCT system bed board artifact correction device provided in the above embodiment and the CBCT system bed board artifact correction method provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment, which will not be repeated here. The CBCT system bed board artifact correction device provided in the above embodiment can be used in actual application, and the above functions can be completed by different functional modules according to needs, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above, and this is not limited herein.

[0075] Embodiments of the present application also provide an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements a CBCT system bed board artifact correction method provided in each of the above embodiments.

[0076] Another aspect of the present application also provides a computer readable storage medium having a computer program stored thereon, which is executed by a processor to implement a CBCT system bed board artifact correction method as described above. The computer readable storage medium can be included in the electronic device described in the above embodiments, or can exist separately and not be assembled into the electronic device.

[0077] The above embodiments merely illustrate the principles of the present application and its efficacy, and are not intended to limit the present application. Any modification or change made by those skilled in the art without departing from the spirit and scope of the present application shall be covered by the claims of the present application.

Claims

1. A CBCT system bedplate artifact correction method, characterized in that, The method comprises the following steps: scanning an object with a bed plate to obtain first object projection data; performing three-dimensional reconstruction on the first object projection data to obtain a first CBCT image; constructing a three-dimensional digital image of the bed plate according to the first CBCT image; performing forward projection on the three-dimensional digital image of the bed plate to obtain a single bed plate projection; separating the contribution of the bed plate from the first object projection data according to the single bed plate projection to obtain second object projection data; performing three-dimensional reconstruction on the second object projection data to obtain a second CBCT image; performing image evaluation index judgment on the second CBCT image until the evaluation index is greater than or equal to a preset threshold to obtain a final CBCT image with bed plate artifacts removed.

2. The CBCT system bedplate artifact correction method of claim 1, wherein, The method comprises the following steps: performing image segmentation and morphological operation on the first CBCT image to generate a bed plate mask image; multiplying the first CBCT image and the bed plate mask image to separate the three-dimensional digital image of the bed plate.

3. The CBCT system bedplate artifact correction method of claim 2, wherein, The image segmentation and morphological operation comprises the following steps: segmenting the first CBCT image by using a 3D U-Net neural network to obtain a first CBCT initial bed plate mask; performing morphological dilation operation on the first CBCT initial bed plate mask to expand the mask edge by a preset number of pixels to generate a first CBCT bed plate mask image.

4. The CBCT system bedplate artifact correction method of claim 1, wherein, The forward projection is realized by using an energy-dependent physical model, based on the voxel gray value of the three-dimensional digital image of the bed plate, combined with the ray source energy spectrum function and the flat panel detector energy absorption function, the energy-weighted path integral operation is performed on the radiation path from the ray source to the detector pixel to generate the single bed plate projection data.

5. The CBCT system bedpan artifact correction method of claim 1, wherein, The contribution of the bed plate is separated from the first object projection data by subtracting the single bed plate projection from the first object projection data to obtain the second object projection data.

6. The CBCT system bedpan artifact correction method of claim 1, wherein, The image evaluation index is the information entropy of the second CBCT image, which is calculated based on the gray scale statistical distribution of the second CBCT image, by calculating the negative cumulative sum of the probability value of each gray scale and the binary logarithm product of the probability value, the information entropy value is obtained as the image evaluation index.

7. The CBCT system bedplate artifact correction method of claim 6, wherein, When the image evaluation index is less than the preset threshold, update the ray source energy spectrum function and the flat panel detector energy absorption function; based on the updated ray source energy spectrum function and the flat panel detector energy absorption function, regenerate the updated single bed plate projection, and separate the newly generated bed plate projection contribution from the first object projection data to generate the updated second object projection data; performing three-dimensional reconstruction on the updated second object projection data to generate an updated second CBCT image; performing image evaluation index judgment on the updated second CBCT image until the image evaluation index meets the preset threshold requirement.

8. A CBCT system couch top artifact correction apparatus for implementing the CBCT system couch top artifact correction method of any one of claims 1-7, characterized in that, The method comprises the following steps: an image scanning module for scanning an object with a bed plate to obtain first object projection data; An image reconstruction module is configured to reconstruct the first object projection data to obtain a first CBCT image and reconstruct the second object projection data to obtain a second CBCT image; A model construction module is configured to construct a bedplate three-dimensional digital image according to the first CBCT image; A forward projection module is configured to perform forward projection on the bedplate three-dimensional digital image to obtain individual bedplate projections; A projection separation module is configured to separate the bedplate contribution from the first object projection data according to the individual bedplate projections to obtain the second object projection data; An image evaluation module is configured to perform image evaluation index judgment on the second CBCT image until the evaluation index is greater than or equal to a preset threshold to obtain a final CBCT image with bedplate artifacts removed.

9. An electronic device, comprising: The electronic device includes: one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the CBCT system bedplate artifact correction method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, a computer program is stored thereon, when the computer program is executed by the processor of the computer, the computer executes the CBCT system bedplate artifact correction method of any one of claims 1 to 7.

Images