Plate-shaped object CT image reconstruction method based on diffusion model
Through the iterative reconstruction method based on the diffusion model, the problem of finite angle artifacts in plate-like CT images is solved, image edge protection and numerical diffusion are achieved, and image quality is improved.
Patent Information
- Application Number
- CN202411084718.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-20
AI Technical Summary
The prior art is difficult to eliminate image quality degradation due to finite angle artifacts in plate-like CT images, especially when the long side size of the plate-like object is large or thick side size leads to missing projection data.
The iterative reconstruction method based on the diffusion model is adopted, and the projection data is obtained through the CT system, and multiple iterative solutions are performed using the preset reconstruction method and diffusion model, and the reconstruction image value is updated until the number of iterations is converged or the number of iterations is reached to remove finite angle artifacts.
The finite angle artifacts in the plate-like CT images are effectively removed, the image edges are protected, and the image quality is improved. Compared with the traditional method, high-quality reconstruction images are obtained with a small number of iterations.
Smart Images
Figure CN119169121A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to a plate-like object CT image reconstruction method based on a diffusion model. Background Art
[0002] X-ray computed tomography (X-Ray CT) is an important method for non-destructive testing of plate-like objects. In theory, images can be accurately reconstructed if the projection data is complete. However, in actual plate-like object detection scenarios, it is often impossible to obtain complete projection data; for example, in order to obtain high-resolution reconstruction results, the distance between the plate-like object and the radiation source in the CT system is shortened. At this time, the long side of the plate-like object is too large, which will cause a collision with the radiation source, or the edge of the plate-like object is too thick, which makes it impossible for X-rays to penetrate, resulting in partial loss of projection data. If the partially missing projection data with limited scanning conditions is directly reconstructed, the final projection data will produce obvious limited angle artifacts.
[0003] Therefore, the prior art needs to be improved. Summary of the invention
[0004] In view of the defects of the prior art, the present invention provides a method for reconstructing CT images of plate-like objects based on a diffusion model, aiming to solve the technical problem that the current method for detecting plate-like objects is difficult to eliminate limited angle artifacts in projection data.
[0005] The technical solution adopted by the present invention to solve the above technical problems is as follows.
[0006] In a first aspect, the present invention provides a method for reconstructing a plate-like object CT image based on a diffusion model, comprising the steps of:
[0007] Scanning the plate-shaped object using a CT system to obtain projection data of the plate-shaped object;
[0008] Based on a preset reconstruction method, image reconstruction processing is performed using a preset initial value of the reconstructed image and the projection data to obtain a reconstructed image value after reconstruction;
[0009] Substituting the reconstructed image value after reconstructing into a preset diffusion model for solving, to obtain an updated reconstructed image value; based on the reconstruction method, performing the image reconstruction process using the updated reconstructed image value and the projection data, to obtain a final reconstructed image.
[0010] In some embodiments, based on the reconstruction method, the step of performing the image reconstruction process using the updated reconstructed image value and the projection data to obtain a final reconstructed image includes:
[0011] The step of updating the initial reconstructed image value by using the updated reconstructed image value, repeating the steps of performing image reconstruction processing based on a preset reconstruction method by using the preset initial reconstructed image value and the projection data to obtain a reconstructed image value after reconstruction, and repeating the step of substituting the reconstructed image value after reconstruction into a preset diffusion model for solving to obtain an updated reconstructed image value, until the number of repetitions reaches a preset number of iterations or the updated reconstructed image value converges, thereby obtaining the final reconstructed image.
[0012] In some embodiments, the diffusion model is:
[0013]
[0014] Wherein, t represents time; x represents the horizontal direction of space; function φ represents the reconstructed image value after the reconstruction; function φ xx represents the second-order partial derivative of the function φ in the horizontal direction of the space; Ω represents the position set of all points on the image, represents the position set of edge points on the image, Ω′ is the position set of non-edge points on the reconstructed image, wherein all points include the edge points and the non-edge points; function u represents the updated reconstructed image value; function u t represents the partial derivative of function u with respect to the time; function u xx represents the second-order partial derivative of the function u in the horizontal direction of the space; μ represents a constant coefficient.
[0015] In some embodiments, the solution method is a finite element method or a finite difference method.
[0016] In some embodiments, the step of scanning the plate-shaped object using a CT system to obtain projection data of the plate-shaped object comprises the steps of:
[0017] The CT system is used to perform limited-angle CT scanning on the plate-like object to obtain the projection data of the plate-like object corresponding to a preset limited angle α.
[0018] In some embodiments,
[0019] In some embodiments, the reconstruction method is an ART method or a SART method, the initial reconstructed image value, the reconstructed image value after reconstruction, and the updated reconstructed image value are all grayscale values of pixels of the image, and the initial reconstructed image value is 0.
[0020] In a second aspect, the present invention provides a plate-like object CT image reconstruction device based on a diffusion model, comprising:
[0021] A projection data acquisition unit, used for scanning the plate-like object using a CT system to obtain projection data of the plate-like object;
[0022] A reconstructed image value acquisition unit is used to perform image reconstruction processing based on a preset reconstruction method, using a preset reconstructed image initial value and the projection data to obtain a reconstructed image value after reconstruction;
[0023] The updated reconstructed image value acquisition unit is used to substitute the reconstructed reconstructed image value into a preset diffusion model for solving to obtain an updated reconstructed image value; the final reconstructed image acquisition unit is used to perform the image reconstruction processing based on the reconstruction method using the updated reconstructed image value and the projection data to obtain a final reconstructed image.
[0024] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-mentioned diffusion model-based plate-like object CT image reconstruction method.
[0025] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for reconstructing CT images of plate-like objects based on a diffusion model.
[0026] Beneficial effect: The plate-like object CT image reconstruction method based on the diffusion model proposed in the present invention obtains the updated reconstructed image value by solving the diffusion model, and obtains the final reconstructed image by using the updated reconstructed image value and the projection data of the plate-like object for image reconstruction processing, so that the method can realize edge protection and numerical diffusion of the final reconstructed image, that is, effectively remove the limited angle artifacts in the final reconstructed image. Therefore, compared with the prior art, the method solves the technical problem that it is difficult to obtain complete projection data for the current plate-like object detection method, and thus it is difficult to eliminate the limited angle artifacts in the projection data. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative work.
[0028] Figure 1 A flowchart of the steps of a method for reconstructing CT images of a plate-like object based on a diffusion model provided by the present invention.
[0029] Figure 2 The present invention provides a plate-like object: a simulated circuit board containing noise, and a plane model diagram of the plate-like object.
[0030] Figure 3 A schematic diagram of a CT scanning system provided by the present invention for performing limited-angle CT scanning on a plate-like object to acquire projection data of the plate-like object.
[0031] Figure 4 (a) is the traditional SART method for Figure 2 A first reconstructed image is obtained by directly reconstructing the projection data of the simulated circuit board in the image, Figure 4 (b) is a plate-like object CT image reconstruction method based on a diffusion model provided by the present invention. Figure 2 A second reconstructed image is obtained by performing image reconstruction processing on projection data of the simulated circuit board.
[0032] Figure 5 A principle block diagram of a plate-like object CT image reconstruction device based on a diffusion model provided by the present invention.
[0033] Figure 6 The present invention provides a block diagram of the principles of a computer device. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0035] Those skilled in the art will appreciate that, unless expressly stated, the singular forms "one", "above", "aforesaid", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when an element is referred to as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.
[0036] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.
[0037] Those skilled in the art will appreciate that the terms "first", "second", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, "plurality" means two or more, unless otherwise clearly and specifically defined.
[0038] It should be understood that the sequence numbers and sizes of the steps in the present invention do not mean the order of execution. The execution order of each process is determined by its function and internal logic, and should not constitute any limitation to the present invention.
[0039] like Figure 1 As shown, the present invention provides a plate-like object CT image reconstruction method based on a diffusion model, and the method comprises the steps of:
[0040] S100: Scan a plate-like object using a CT system to obtain projection data of the plate-like object.
[0041] Furthermore, the CT system includes a ray source for emitting X-rays onto the plate-like object and a detector for acquiring projection data of the plate-like object; the CT system can be selected from common CT systems on the market and is not limited here.
[0042] Further, the plate-like object includes electronic packaging components (e.g., chips and circuit boards), etc.; Figure 2 Shown are the plate-like object used in the numerical experiment of the present invention: a simulated circuit board containing noise, and a plane model diagram of the plate-like object.
[0043] Furthermore, the CT system is used to perform limited-angle CT scanning on the plate-like object to obtain the projection data of the plate-like object corresponding to a preset limited angle α.
[0044] Figure 3The figure shows a schematic diagram of a CT scanning system provided by the present invention for performing limited angle CT scanning on a plate-like object to obtain projection data of the plate-like object. Point O is the rotation center of the plate-like object to be measured, the arrow is the rotation direction of the plate-like object to be measured, and α is a preset limited angle. When the ray source and the detector are turned on at the same time, the ray source emits X-rays to the plate-like object to be measured, and the plate-like object to be measured rotates around point O in the rotation direction indicated by the arrow, and the detector obtains X-ray projection data of the plate-like object to be measured corresponding to α, and the X-ray projection data is the CT projection data to be reconstructed of the plate-like object to be measured in step S100.
[0045] Further, That is to say, the plate-like object to be measured can be rotated 120° around point O, so that the detector obtains 120° X-ray projection data of the plate-like object to be measured.
[0046] like Figure 1 As shown, the method also includes the steps of:
[0047] S200 , based on a preset reconstruction method, performing image reconstruction processing using a preset reconstructed image initial value and the projection data to obtain a reconstructed image value after reconstruction.
[0048] Furthermore, the preset reconstruction method is the ART method or the SART method, but is not limited thereto, and may be other reconstruction methods; the initial value of the reconstructed image and the reconstructed image value after reconstruction are both grayscale values of the pixels of the image, and the initial value of the reconstructed image may be set to 0.
[0049] like Figure 1 As shown, the method also includes the steps of:
[0050] S300: Substituting the reconstructed image value into a preset diffusion model for solving, to obtain an updated reconstructed image value.
[0051] Furthermore, the updated reconstructed image value is also the grayscale value of the pixel of the image.
[0052] Furthermore, the preset diffusion model is equation 1:
[0053]
[0054] Wherein, t represents time; x represents the horizontal direction of space; function φ represents the reconstructed image value after the reconstruction; function φ xx represents the second-order partial derivative of the function φ in the horizontal direction of the space; Ω represents the position set of all points on the image, represents the position set of edge points on the image, Ω′ is the position set of non-edge points on the reconstructed image, wherein all points include the edge points and the non-edge points; function u represents the updated reconstructed image value; function u t represents the partial derivative of function u with respect to the time; function u xx represents the second-order partial derivative of the function u in the horizontal direction of the space; μ represents a constant coefficient.
[0055] This diffusion model only considers the transmission along the long side of the plate, that is, the propagation in the horizontal direction, so only the second-order partial derivative is calculated for x. The construction of this diffusion model is achieved by making full use of the characteristics that the gradient value and grayscale value at the visible boundary in the finite angle CT reconstructed image are approximately accurate. The equation of this diffusion model is a heat conduction equation with a stable heat source obtained by combining time stepping technology and edge information. Therefore, solving this diffusion model can realize edge protection and numerical diffusion of the finite angle CT image of the plate, that is, to achieve the rapid removal of finite angle artifacts in the CT image of the plate.
[0056] Furthermore, the solution method is a finite element method or a finite difference method, but is not limited thereto, and may be other solution methods.
[0057] like Figure 1 As shown, the method also includes the steps of:
[0058] S400: Based on the reconstruction method, perform the image reconstruction process using the updated reconstructed image value and the projection data to obtain a final reconstructed image.
[0059] Furthermore, the updated reconstructed image initial value is updated using the updated reconstructed image value, and the steps of performing image reconstruction processing based on a preset reconstruction method using the preset reconstructed image initial value and the projection data to obtain a reconstructed image value after reconstruction are repeated, and the step of substituting the reconstructed image value after reconstruction into a preset diffusion model for solving to obtain an updated reconstructed image value is repeated, until the number of repetitions reaches a preset number of iterations or the updated reconstructed image value converges, thereby obtaining the final reconstructed image.
[0060] The steps S100, S200, and S300 of the method are, as a whole, an iterative method proposed by the present invention.
[0061] After obtaining the projection data q of the plate-like object, in this iterative method:
[0062] First, the initial value of the reconstructed image is preset to be u j＝0 =0 and the preset number of iterations is j=0, 1, 2, ..., n.
[0063] Then the , ...
[0064] S1. Image reconstruction using projection data: j+1 / 2 =RECON(u j ,q); where u j＝0 Represents the initial value of the reconstructed image, u j+1 / 2 Represents the reconstructed image value after reconstruction, and RECON indicates image reconstruction.
[0065] S2, reconstructed image update: u j+1 =SOLVE(equation 1); where u j+1 represents the updated reconstructed image value, SOLVE represents the updated reconstructed image value, and SOLVE represents the updated reconstructed image value. j+1 / 2 Substitute into the diffusion model and solve it.
[0066] S3. Accumulate the number of iterations: j=j+1.
[0067] Finally, when the updated reconstructed image converges or the number of iterations reaches n, the iteration is stopped to obtain the final reconstructed image.
[0068] The criterion for stopping the iteration depends on the quality of the reconstructed image in each iteration. The reconstructed image is displayed after each iteration. If the limited angle artifacts in the reconstructed image have been significantly removed and no more iterations have any significant effect on the reconstructed image, the iteration stops.
[0069] Aiming at the problem of limited angle CT reconstruction of plate-like objects, this method combines the constructed optimized diffusion model with iterative update, and realizes edge protection and numerical diffusion of limited angle CT images of plate-like objects by solving the model, that is, the removal of limited angle artifacts in CT images of plate-like objects. Moreover, this method only needs a small number of iterations to obtain high-quality CT reconstruction images of plate-like objects.
[0070] In addition, this method combines the constructed optimized diffusion model with iterative updating. Compared with the isotropic TV-based regularized reconstruction method (TV-L1) and the L0-based regularized reconstruction method (TV-L0), the directionality of finite-angle artifacts is taken into account, and the artifact removal effect is better; compared with the gradient-based anisotropic regularized reconstruction method (ATV, RwATV, etc.), the tightly fitted detailed structure inside the measured plate-like object is taken into account, so the edge information will not be submerged, and the artifact removal effect is better; compared with the reconstruction method based on the differential properties of Fourier transform, there is no need to perform approximation when processing the zero frequency, so no jagged artifacts will be introduced, and the artifact removal effect is better.
[0071] Figure 4 (a) is the traditional SART method for Figure 2 The first reconstructed image is obtained by directly reconstructing the projection data of the simulated circuit board containing noise, Figure 4 (b) is the Figure 2 The second reconstructed image is obtained by reconstructing the projection data of the simulated circuit board with noise. It can be seen from the figure that in the first reconstructed image, the limited angle artifact is very obvious, the circuit board image details are blurred, and the image quality is low; in the second reconstructed image, most of the limited angle artifacts have been removed, and the circuit board image details are clear, and the image quality is high, which is consistent with the Figure 2 The gap between the original circuit boards is smaller.
[0072] In summary, the present invention discloses a plate-like object CT image reconstruction method based on a diffusion model, comprising the steps of: scanning a plate-like object using a CT system to obtain projection data of the plate-like object; performing image reconstruction processing using a preset initial value of a reconstructed image and the projection data based on a preset reconstruction method to obtain a reconstructed image value after reconstruction; substituting the reconstructed image value after reconstruction into a preset diffusion model for solution to obtain an updated reconstructed image value; and performing image reconstruction processing using the updated reconstructed image value and the projection data based on the reconstruction method to obtain a final reconstructed image. The plate-like object CT image reconstruction method based on a diffusion model proposed by the present invention obtains an updated reconstructed image value by solving a diffusion model, and obtains a final reconstructed image by performing image reconstruction processing using the updated reconstructed image value and the projection data of the plate-like object, so that the method can realize edge protection and numerical diffusion of the final reconstructed image, that is, effectively remove the finite angle artifacts in the final reconstructed image. Therefore, compared with the prior art, the present method solves the technical problem that the current method for detecting plate-like objects is difficult to eliminate the finite angle artifacts in the projection data.
[0073] Based on the above embodiments, the present invention also provides a plate-like object CT image reconstruction device based on a diffusion model, such as Figure 5 As shown, the device comprises:
[0074] A projection data acquisition unit 11 is used to scan the plate-like object using a CT system to obtain projection data of the plate-like object;
[0075] A reconstructed image value acquisition unit 12 is used to perform image reconstruction processing based on a preset reconstruction method, using a preset reconstructed image initial value and the projection data to obtain a reconstructed image value after reconstruction;
[0076] The updated reconstructed image value acquisition unit 13 is used to substitute the reconstructed image value into the preset diffusion model for solution to obtain the updated reconstructed image value; the final reconstructed image acquisition unit 14 is used to perform the image reconstruction processing based on the reconstruction method using the updated reconstructed image value and the projection data to obtain the final reconstructed image.
[0077] The working principle of each unit in the plate-like object CT image reconstruction device based on the diffusion model of this embodiment is the same as the principle of each step in the plate-like object CT image reconstruction method based on the diffusion model in the above embodiment, and will not be repeated here.
[0078] Based on the above embodiments, the present invention further provides a computer device, the principle block diagram of the computer device can be as follows: Figure 6 The computer device may include: one or more processors 100 ( Figure 6 The processors 100 include a processor 101 (only one of which is shown in the figure), a memory 101, and a computer program 102 (for example, a program for plate-like object CT image reconstruction based on a diffusion model) stored in the memory 101 and executable on one or more processors 100. When one or more processors 100 execute the computer program 102, the various steps of the plate-like object CT image reconstruction method based on a diffusion model in the above-mentioned embodiment can be implemented. Alternatively, when one or more processors 100 execute the computer program 102, the functions of various units of the plate-like object CT image reconstruction device based on a diffusion model in the above-mentioned embodiment can be implemented, which is not limited here.
[0079] Based on the above embodiments, the present invention further provides a computer-readable storage medium on which a computer program (e.g., a program for plate-like object CT image reconstruction based on a diffusion model) is stored. When the computer program is executed by a processor, the various steps of the plate-like object CT image reconstruction method based on a diffusion model in the above embodiments can be implemented. Alternatively, when the computer program is executed by a processor, the functions of the various units of the plate-like object CT image reconstruction device based on a diffusion model in the above embodiments can be implemented, which is not limited here.
[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A plate-like object CT image reconstruction method based on a diffusion model, characterized in that: Includes steps: Scanning the plate-shaped object using a CT system to obtain projection data of the plate-shaped object; Based on a preset reconstruction method, image reconstruction processing is performed using a preset initial value of the reconstructed image and the projection data to obtain a reconstructed image value after reconstruction; Substituting the reconstructed image value after reconstructing into a preset diffusion model for solving, to obtain an updated reconstructed image value; based on the reconstruction method, performing the image reconstruction process using the updated reconstructed image value and the projection data, to obtain a final reconstructed image.
2. The plate-like object CT image reconstruction method based on diffusion model according to claim 1, characterized in that: Based on the reconstruction method, the step of performing the image reconstruction process using the updated reconstructed image value and the projection data to obtain a final reconstructed image includes: The step of updating the initial reconstructed image value by using the updated reconstructed image value, repeating the steps of performing image reconstruction processing based on a preset reconstruction method by using the preset initial reconstructed image value and the projection data to obtain a reconstructed image value after reconstruction, and repeating the step of substituting the reconstructed image value after reconstruction into a preset diffusion model for solving to obtain an updated reconstructed image value, until the number of repetitions reaches a preset number of iterations or the updated reconstructed image value converges, thereby obtaining the final reconstructed image.
3. The plate-like object CT image reconstruction method based on diffusion model according to claim 2, characterized in that: The diffusion model is: Wherein, t represents time; x represents the horizontal direction of space; function φ represents the reconstructed image value after the reconstruction; function φ xx represents the second-order partial derivative of the function φ in the horizontal direction of the space; Ω represents the position set of all points on the image, represents the location set of edge points on the image, Ω ′ is a position set of non-edge points on the reconstructed image, wherein all points include the edge points and the non-edge points; function u represents the updated reconstructed image value; function u t represents the partial derivative of function u with respect to the time; function u xx represents the second-order partial derivative of the function u in the horizontal direction of the space; μ represents a constant coefficient.
4. The plate-like object CT image reconstruction method based on diffusion model according to claim 3, characterized in that: The solution method is the finite element method or the finite difference method.
5. The plate-like object CT image reconstruction method based on diffusion model according to claim 2, characterized in that: The step of scanning a plate-like object by using a CT system to obtain projection data of the plate-like object comprises the steps of: The CT system is used to perform limited-angle CT scanning on the plate-like object to obtain the projection data of the plate-like object corresponding to a preset limited angle α.
6. The plate-like object CT image reconstruction method based on diffusion model according to claim 5, characterized in that:
7. The plate-like object CT image reconstruction method based on diffusion model according to any one of claims 1 to 6, characterized in that: The reconstruction method is an ART method or a SART method, the initial reconstructed image value, the reconstructed image value after reconstruction, and the updated reconstructed image value are all grayscale values of pixels of the image, and the initial reconstructed image value is 0.
8. A plate-like object CT image reconstruction device based on a diffusion model, characterized in that: include: A projection data acquisition unit, used for scanning the plate-like object using a CT system to obtain projection data of the plate-like object; A reconstructed image value acquisition unit is used to perform image reconstruction processing based on a preset reconstruction method, using a preset reconstructed image initial value and the projection data to obtain a reconstructed image value after reconstruction; An updated reconstructed image value acquisition unit, used for substituting the reconstructed image value into a preset diffusion model for solving, so as to obtain an updated reconstructed image value; The final reconstructed image acquisition unit is used to perform the image reconstruction process based on the reconstruction method using the updated reconstructed image value and the projection data to obtain a final reconstructed image.
9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the plate-like object CT image reconstruction method based on the diffusion model are implemented as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the plate-like object CT image reconstruction method based on a diffusion model are implemented as described in any one of claims 1 to 7.