A method and device for scatter correction, a storage medium and an electronic device

Abstract

The specification provides a method for scatter correction, which obtains a to-be-corrected image by cascading attribute information of a ray emitter of collected X-rays and a CT image obtained based on the X-rays, inputs the to-be-corrected image into a projection domain scatter correction network model to obtain a preliminary corrected image, performs three-dimensional reconstruction on the preliminary corrected image, slices the reconstructed image, determines a slice image, and then inputs the slice image into a slice domain scatter correction network model to obtain a final corrected image. As can be seen from the above method, the fusion of the attribute information of the ray emitter of the X-rays and the CT image makes the result output by the projection domain scatter correction network model more accurate, and meanwhile, the two-dimensional to-be-corrected image is subjected to scatter correction, and the slice image obtained after three-dimensional reconstruction of the corrected two-dimensional to-be-corrected image is subjected to scatter correction again, thereby further improving the effect of scatter correction.

Description

Technical Field

[0001] This application relates to the field of medical devices, and in particular to a method, apparatus, storage medium, and electronic device for scattering correction. Background Technology

[0002] With the development of medical imaging technology, it has become commonplace to use computed tomography (CT) to scan human body parts. When X-ray beams are irradiated in CT, scattering occurs, causing the X-rays to deviate from their direction, which generates noise in the imaging and seriously affects the image quality. Therefore, scattering correction is needed to improve image quality.

[0003] Traditional methods typically employ Monte Carlo simulation, inputting simulated image data into a model to train it. The trained model can mitigate X-ray beam scattering. While Monte Carlo simulation offers high accuracy, it requires numerous repetitions, resulting in low computational efficiency and a large computational load. Furthermore, relying solely on image data for scattering correction is somewhat simplistic and can negatively impact the effectiveness of the correction. Therefore, this application proposes a scattering correction method to improve both the efficiency and effectiveness of scattering correction. Summary of the Invention

[0004] This specification provides a scattering correction method, apparatus, storage medium, and electronic device to at least partially solve the above-mentioned problems.

[0005] The embodiments in this specification adopt the following technical solutions:

[0006] This specification provides a method for scattering correction, the method comprising:

[0007] Obtain the attribute information of the X-ray emitter and acquire CT images based on the X-rays;

[0008] Based on the attribute information and the CT image, determine the image to be corrected;

[0009] The image to be corrected is input into a pre-trained projection domain scattering correction network model to obtain a preliminary corrected image output by the projection domain scattering correction network model.

[0010] The preliminary corrected image is reconstructed in three dimensions to obtain a three-dimensional reconstructed corrected image, and the reconstructed corrected image is sliced ​​to determine the sliced ​​image;

[0011] The sliced ​​image is input into a pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model.

[0012] Optionally, determining the image to be corrected based on the attribute information and the CT image specifically includes:

[0013] The attribute information is converted into a matrix as an information matrix, and the CT image is converted into a matrix as an image matrix.

[0014] The information matrix and the image matrix are concatenated to obtain the matrix to be corrected;

[0015] The matrix to be corrected is converted into an image, which is then used as the image to be corrected.

[0016] Optionally, a projection domain scattering correction network model is pre-trained, specifically including:

[0017] Training samples are determined based on the attribute information of the radiation emitter and the sample CT images;

[0018] Scattering estimation is performed on the sample CT images to obtain a scattering distribution image, and the annotation of the training samples is determined based on the sample CT images and the scattering distribution image;

[0019] The training samples are input into the projection domain scattering correction network model to obtain the output results;

[0020] The projection domain scattering correction network model is trained based on the output results and the annotations.

[0021] Optionally, the annotation of the training samples is determined based on the sample CT image and the scattering distribution image, specifically including:

[0022] The sample CT image is scattered by the scattering distribution image to obtain a descattered image, which is then used as the annotation for the training sample.

[0023] Optionally, a slice-domain scattering correction network model is pre-trained, specifically including:

[0024] The output of the projection domain scattering correction network model is reconstructed in three dimensions to obtain reconstructed sample images. The reconstructed sample images are then sliced ​​to determine the sliced ​​sample images, which are used as training samples.

[0025] The descattered image is reconstructed in three dimensions to obtain a reconstructed labeled image. The reconstructed labeled image is then sliced ​​to determine the slice labeled image, which is used as the label for the training sample.

[0026] The training samples are input into the slice domain scattering correction network model to obtain the output results;

[0027] The slice domain scattering correction network model is trained based on the output results and the annotations.

[0028] Optionally, the X-rays are cone-shaped X-ray beams emitted by a radiation emitter.

[0029] This specification also provides a scattering correction device, the device comprising:

[0030] The acquisition module is used to acquire the attribute information of the X-ray emitter and to acquire CT images based on the X-rays;

[0031] The determination module is used to determine the image to be corrected based on the attribute information and the CT image;

[0032] The preliminary correction module is used to input the image to be corrected into a pre-trained projection domain scattering correction network model to obtain the preliminary corrected image output by the projection domain scattering correction network model.

[0033] The reconstruction module is used to perform three-dimensional reconstruction on the preliminary corrected image to obtain a three-dimensional reconstructed corrected image, and to slice the reconstructed corrected image to determine the sliced ​​image;

[0034] The final correction module is used to input the sliced ​​image into a pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model.

[0035] Optionally, the determining module is specifically used to: convert the attribute information into a matrix as an information matrix, and convert the CT image into a matrix as an image matrix; concatenate the information matrix and the image matrix to obtain a matrix to be corrected; and convert the matrix to be corrected into an image as an image to be corrected.

[0036] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described scattering correction method.

[0037] This specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the above-described scattering correction method.

[0038] The above-described at least one technical solution used in the embodiments of this specification can achieve the following beneficial effects:

[0039] In the scattering correction method provided in this specification, the attribute information of the X-ray emitter acquired by the X-ray acquisition and the CT image obtained based on the X-ray are concatenated to obtain an image to be corrected. The image to be corrected is input into the projection domain scattering correction network model to obtain a preliminary corrected image. The preliminary corrected image is then reconstructed in three dimensions. After reconstruction, the image is sliced ​​to determine the sliced ​​image. The sliced ​​image is then input into the slice domain scattering correction network model to obtain the final corrected image.

[0040] As can be seen from the above method, by fusing the attribute information of the X-ray emitter with the CT image, the output of the projection domain scattering correction network model becomes more accurate. At the same time, by performing scattering correction on the two-dimensional image to be corrected, and then performing scattering correction again on the slice image obtained by three-dimensional reconstruction of the corrected two-dimensional image to be corrected, the effect of scattering correction is further improved. Attached Figure Description

[0041] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0042] Figure 1 This is a flowchart illustrating one of the scattering correction methods described in this specification;

[0043] Figure 2 This is a schematic diagram illustrating the process of generating the image to be corrected provided in this instruction manual;

[0044] Figure 3 This is a schematic diagram of a projection domain scattering correction network model used in this specification;

[0045] Figure 4 This is a schematic diagram of a reconstructed preliminary corrected image in this specification;

[0046] Figure 5 This is a schematic diagram of a method for determining training samples for a projection domain scattering correction network model in this specification;

[0047] Figure 6 This is a schematic diagram of training samples for a network model for determining the scattering correction of a slice domain, as described in this specification.

[0048] Figure 7 This is a schematic diagram of a scattering correction device provided in this specification;

[0049] Figure 8 The corresponding information provided in this specification Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0051] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart illustrating a scattering correction method provided in this specification, which specifically includes the following steps:

[0053] S100: Obtain the attribute information of the X-ray emitter and obtain a CT image based on the X-ray.

[0054] The scattering correction method provided in this manual can be implemented by a server, which can be used to control the X-ray emitter to emit X-rays and obtain CT images based on the X-rays. For ease of description, the scattering correction method provided in this manual will be described below using the server as the implementation subject.

[0055] In the embodiments of this specification, the attribute information of the X-ray emitter may be tube voltage, tube current, and the number of X-rays filtered when the X-rays irradiate the object. It may also be the grid ratio or efficiency of the filter grid. In practical applications, the type of attribute information can be determined according to the specific situation. One or more attribute information may be selected. This specification does not limit the type of attribute information.

[0056] S101: Determine the image to be corrected based on the attribute information and the CT image.

[0057] In the embodiments of this specification, scattering correction can be performed only on the CT image. However, the correction effect using only image information is not good because it does not utilize the attribute information of the X-ray emitter, which has an important influence on the estimation of scattered radiation distribution. Therefore, it is necessary to fuse the attribute information of the X-ray emitter with the CT image to improve the effect of scattering correction.

[0058] The CT image is a digital image and can be represented in matrix form. Therefore, when fusing the attribute information of the X-ray emitter and the CT image, a matrix concatenation can be performed. The specific method is as follows: The attribute information of the X-ray emitter is converted into a matrix, serving as an information matrix; the CT image is converted into a matrix, serving as an image matrix; the information matrix and the image matrix are concatenated to obtain a new matrix, serving as the calibration matrix. Each value in the calibration matrix represents the value of a pixel at a corresponding position in the image. The calibration matrix is ​​then converted into an image to be calibrated, such as... Figure 2 As shown.

[0059] The attribute information of the X-ray emitter is converted into an information matrix. Specifically, the attribute information of the X-ray emitter can be encoded, the encoded attribute information can be arranged into a matrix, and then deconvolution can be performed to obtain the information matrix. Alternatively, the specific values ​​of the attribute information of the X-ray emitter can be arranged directly, and the arranged attribute information of the X-ray emitter can be deconvolved to obtain the information matrix. No specific limitation is made on the conversion method in this specification.

[0060] S102: Input the image to be corrected into a pre-trained projection domain scattering correction network model to obtain a preliminary corrected image output by the projection domain scattering correction network model.

[0061] like Figure 3 As shown, the image to be corrected is input into the trained projection domain scattering correction network model, and a preliminary corrected image is output. The image to be corrected is an image containing scattering lines, and the preliminary corrected image is an image with some scattering lines removed.

[0062] S103: Perform three-dimensional reconstruction on the preliminary corrected image to obtain a three-dimensional reconstructed corrected image, and slice the reconstructed corrected image to determine the sliced ​​image.

[0063] like Figure 4 As shown, the preliminary corrected image is reconstructed in three dimensions. The reconstruction method is not limited to iterative reconstruction algorithms. The reconstructed corrected image is sliced ​​to determine the sliced ​​image, wherein the sliced ​​image is an image containing scattering lines.

[0064] S104: Input the sliced ​​image into the pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model.

[0065] In the embodiments of this specification, some scattered lines in the two-dimensional image to be corrected can be removed by the projection domain scattering correction network model described in step S102 to obtain a preliminary corrected image. The preliminary corrected image is then reconstructed in three dimensions to obtain a three-dimensional reconstructed corrected image. The reconstructed corrected image is then sliced ​​to determine the sliced ​​images. Then, some scattered lines in the sliced ​​images obtained by slicing the three-dimensional image are removed by the slice domain scattering correction network model described in step S104. By performing scattering correction on the two-dimensional image and the three-dimensional sliced ​​image, the effect of scattering correction is greatly improved.

[0066] In the scattering correction method provided in this specification, the image to be corrected is obtained by concatenating the attribute information of the X-ray emitter and CT images. The image to be corrected is then input into a projection domain scattering correction network model for scattering correction to obtain a preliminary corrected image. The preliminary corrected image is then reconstructed in three dimensions, sliced, and the resulting sliced ​​image is input into a slice domain scattering correction network to obtain the final corrected image. This method performs scattering correction on both two-dimensional images and sliced ​​images based on three-dimensional images, improving the descattering effect. At the same time, by concatenating the attribute information of the X-ray emitter with the CT images, the scattering correction result is more accurate, achieving the same effect as Monte Carlo simulation and improving the efficiency of scattering correction.

[0067] exist Figure 1 In step S102, scattering correction of the image to be corrected is performed using a projection domain scattering correction network model. Therefore, the model needs to be trained in advance. The specific training method can be as follows: Based on the attribute information of the ray emitter and the sample CT images, training samples are determined, such as... Figure 5 As shown, scattering estimation is performed on the sample CT image to obtain a scattering distribution image. The scattering estimation method is not limited to Monte Carlo simulation or scattering kernel stacking. Based on the sample CT image and the scattering distribution image, the annotation of the training sample is determined. The training sample is input into a projection domain scattering correction network model to obtain the output result. The difference between the output result and the annotation is determined, and the loss is then determined. The projection domain scattering correction network model is trained with the goal of minimizing the loss. The scattering distribution image can be used to compensate for the scattering of the sample CT image to obtain a descattered image, which is then used as the annotation of the training sample.

[0068] exist Figure 1In step S104, scattering correction of the sliced ​​image is performed using a sliced ​​domain scattering correction network model. Therefore, the model needs to be trained in advance. The specific training method can be as follows: The output of the projection domain scattering correction network model is used for three-dimensional reconstruction to obtain reconstructed sample images. These reconstructed sample images are then sliced ​​to determine the sliced ​​sample images, which are used as training samples. Figure 6 As shown, the reconstruction method is not limited to iterative reconstruction algorithms, etc. The descattered image is reconstructed in three dimensions to obtain a reconstructed labeled image. The reconstructed labeled image is then sliced ​​to determine the slice labeled image, which is used as the label of the training sample. The training sample is input into the slice domain scattering correction network model to obtain the output result. The difference between the output result and the label is determined, and then the loss is determined. The slice domain scattering correction network model is trained with the goal of minimizing the loss.

[0069] In the embodiments described in this specification, the X-rays are cone-shaped X-ray beams emitted by the X-ray emitter.

[0070] The above are one or more embodiments of the scattering correction method provided in this specification. Based on the same idea, this specification also provides a corresponding scattering correction device, such as... Figure 7 As shown.

[0071] Figure 7 A schematic diagram of a scattering correction device provided in this specification specifically includes:

[0072] The acquisition module 701 is used to acquire the attribute information of the X-ray emitter and to acquire the CT image based on the X-ray.

[0073] The determining module 702 is used to determine the image to be corrected based on the attribute information and the CT image;

[0074] The preliminary correction module 703 is used to input the image to be corrected into a pre-trained projection domain scattering correction network model to obtain the preliminary corrected image output by the projection domain scattering correction network model.

[0075] The reconstruction module 704 is used to perform three-dimensional reconstruction on the preliminary corrected image to obtain a three-dimensional reconstructed corrected image, and to slice the reconstructed corrected image to determine the sliced ​​image;

[0076] The final correction module 705 is used to input the sliced ​​image into a pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model.

[0077] Optionally, the determining module 702 is used to convert the attribute information into a matrix as an information matrix and the CT image into a matrix as an image matrix; concatenate the information matrix and the image matrix to obtain a matrix to be corrected; and convert the matrix to be corrected into an image as an image to be corrected.

[0078] Optionally, the preliminary correction module 703 is further configured to determine training samples based on the attribute information of the ray emitter and the sample CT image; perform scattering estimation on the sample CT image to obtain a scattering distribution image, and determine the label of the training sample based on the sample CT image and the scattering distribution image; input the training sample into the projection domain scattering correction network model to obtain the output result; and train the projection domain scattering correction network model based on the output result and the label.

[0079] Optionally, the preliminary correction module 703 is used to perform scatter compensation on the sample CT image through the scattering distribution image to obtain a descattered image, and use the descattered image as the annotation of the training sample.

[0080] Optionally, the final correction module 705 is further configured to perform three-dimensional reconstruction on the output result of the projection domain scattering correction network model to obtain a reconstructed sample image, and slice the reconstructed sample image to determine the sliced ​​sample image as a training sample; perform three-dimensional reconstruction on the descattered image to obtain a reconstructed labeled image, and slice the reconstructed labeled image to determine the sliced ​​labeled image as a label for the training sample; input the training sample into the sliced ​​domain scattering correction network model to obtain an output result; and train the sliced ​​domain scattering correction network model based on the output result and the label.

[0081] Optionally, the X-rays are cone-shaped X-ray beams emitted by the X-ray emitter.

[0082] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The provided method for scattering correction.

[0083] The embodiments in this specification also propose Figure 8 The diagram shows a schematic structural representation of the electronic device. Figure 8 At the hardware level, this electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above. Figure 1The scattering correction method described above. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0084] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0085] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0086] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0087] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0088] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0093] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0094] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0095] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0096] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0098] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0099] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for scattering correction, characterized in that, The method includes: Obtain the attribute information of the X-ray emitter and acquire CT images based on the X-rays; Based on the attribute information and the CT image, the image to be corrected is determined, specifically including: The attribute information is converted into a matrix as an information matrix, and the CT image is converted into a matrix as an image matrix; the information matrix and the image matrix are concatenated to obtain the matrix to be corrected; the matrix to be corrected is converted into an image as the image to be corrected. The image to be corrected is input into a pre-trained projection domain scattering correction network model to obtain a preliminary corrected image output by the projection domain scattering correction network model. The preliminary corrected image is reconstructed in three dimensions to obtain a three-dimensional reconstructed corrected image, and the reconstructed corrected image is sliced ​​to determine the sliced ​​image; The sliced ​​image is input into a pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model.

2. The method as described in claim 1, characterized in that, Pre-training the projection domain scattering correction network model, specifically including: Training samples are determined based on the attribute information of the radiation emitter and the sample CT images; Scattering estimation is performed on the sample CT images to obtain a scattering distribution image, and the annotation of the training samples is determined based on the sample CT images and the scattering distribution image; The training samples are input into the projection domain scattering correction network model to obtain the output results; The projection domain scattering correction network model is trained based on the output results and the annotations.

3. The method as described in claim 2, characterized in that, The annotation of the training samples is determined based on the sample CT images and the scattering distribution images, specifically including: The sample CT image is scattered by the scattering distribution image to obtain a descattered image, which is then used as the annotation for the training sample.

4. The method as described in claim 3, characterized in that, Pre-training a slice-domain scattering correction network model, specifically including: The output of the projection domain scattering correction network model is reconstructed in three dimensions to obtain reconstructed sample images. The reconstructed sample images are then sliced ​​to determine the sliced ​​sample images, which are used as training samples. The descattered image is reconstructed in three dimensions to obtain a reconstructed labeled image. The reconstructed labeled image is then sliced ​​to determine the slice labeled image, which is used as the label for the training sample. The training samples are input into the slice domain scattering correction network model to obtain the output results; The slice domain scattering correction network model is trained based on the output results and the annotations.

5. The method according to any one of claims 1 to 4, characterized in that, The X-rays are cone-shaped X-ray beams emitted by the X-ray emitter.

6. A scattering correction device, characterized in that, The device includes: The acquisition module is used to acquire the attribute information of the X-ray emitter and to acquire CT images based on the X-rays; The determination module is used to determine the image to be corrected based on the attribute information and the CT image; The preliminary correction module is used to input the image to be corrected into a pre-trained projection domain scattering correction network model to obtain the preliminary corrected image output by the projection domain scattering correction network model. The reconstruction module is used to perform three-dimensional reconstruction on the preliminary corrected image to obtain a three-dimensional reconstructed corrected image, and to slice the reconstructed corrected image to determine the sliced ​​image; The final correction module is used to input the sliced ​​image into a pre-trained slice domain scattering correction network model to obtain the final corrected image output by the slice domain scattering correction network model; wherein, the determination module is specifically used to convert the attribute information into a matrix as an information matrix, and convert the CT image into a matrix as an image matrix; concatenate the information matrix and the image matrix to obtain the matrix to be corrected; and convert the matrix to be corrected into an image as the image to be corrected.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 5.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 5.

Images