Medical image artifact correction method and device, equipment and medium

Abstract

The invention relates to a medical image artifact correction method and device, equipment and a medium. The method comprises the following steps: acquiring first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; acquiring a high-energy correction coefficient and a low-energy correction coefficient corresponding to each channel of the detector; based on each high-energy correction coefficient, the first projection data and the second projection data, obtaining a first error projection drawing corresponding to the initial high-energy tomography image; based on each low-energy correction coefficient, the first projection data and the second projection data, obtaining a second error projection drawing corresponding to the initial low-energy tomography image; performing artifact correction on the initial high-energy tomography image based on the first error projection drawing; and performing artifact correction on the initial low-energy tomography image based on the second error projection drawing. By adopting the method, the artifact correction accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment and medium for correcting artifacts of medical images. Background Art

[0002] The hardening effect during dual-energy computed tomography (CT) imaging will cause hardening artifacts to appear on dual-energy CT images, which will reduce the quality of CT images.

[0003] In the related art, the dual-energy CT images are mainly segmented respectively, and the segmented dual-energy CT images are forward projected to obtain material projection data for artifact correction.

[0004] However, the related art methods have the problem of low artifact correction accuracy, resulting in poor quality of CT images. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, equipment and medium for artifact correction of medical images that can improve the accuracy of artifact correction in order to solve the above technical problems.

[0006] In a first aspect, the present application provides a method for correcting artifacts of medical images, comprising:

[0007] Acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; both the initial high-energy tomography image and the initial low-energy tomography image are acquired and reconstructed by multi-channel detectors of a tomography device;

[0008] Obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel of the detector;

[0009] Based on each high-energy correction coefficient, the first projection data, and the second projection data, a first error projection map corresponding to the initial high-energy tomography image is obtained; and based on each low-energy correction coefficient, the first projection data, and the second projection data, a second error projection map corresponding to the initial low-energy tomography image is obtained;

[0010] Performing artifact correction on the initial high-energy tomography image based on the first error projection map; and performing artifact correction on the initial low-energy tomography image based on the second error projection map.

[0011] In one embodiment, based on each high energy correction coefficient, the first projection data and the second projection data, obtaining a first error projection map corresponding to the initial high energy tomography image includes:

[0012] For any channel, based on the high energy correction coefficient of the channel, the first projection data and the second projection data, determine the first sub-error projection data corresponding to the channel;

[0013] A first error projection map corresponding to the initial high-energy tomography image is determined according to the first sub-error projection data corresponding to each channel.

[0014] In one embodiment, determining a first error projection map corresponding to an initial high energy tomography image according to first sub-error projection data corresponding to each channel includes:

[0015] The sum of the first sub-error projection data corresponding to each channel is used as the first error projection data;

[0016] Image reconstruction is performed on the first error projection data to obtain a first error projection map.

[0017] In one embodiment, based on each low-energy correction coefficient, the first projection data, and the second projection data, obtaining a second error projection map corresponding to the initial low-energy tomography image includes:

[0018] For any channel, based on the low energy correction coefficient of the channel, the first projection data and the second projection data, determine the second sub-error projection data corresponding to the channel;

[0019] A second error projection map corresponding to the initial high energy tomography image is determined according to the second sub-error projection data corresponding to each channel.

[0020] In one embodiment, determining a second error projection map corresponding to the initial high energy tomography image according to the second sub-error projection data corresponding to each channel includes:

[0021] The sum of the second sub-error projection data corresponding to each channel is used as the second error projection data;

[0022] Perform image reconstruction on the second error projection data to obtain a second error projection map.

[0023] In one embodiment, obtaining a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector includes:

[0024] Determining a first energy spectrum and a second energy spectrum based on filtering information of the tomography device;

[0025] Performing water hardening correction on first projection values ​​of energy rays passing through a plurality of base materials under a first energy spectrum and second projection values ​​of energy rays passing through a plurality of base materials under a second energy spectrum respectively;

[0026] The water hardening correction results are fitted to obtain the high-energy correction coefficient and low-energy correction coefficient corresponding to each channel in the tomography device.

[0027] In a second aspect, the present application also provides a medical image artifact correction device, comprising:

[0028] A first acquisition module is used to acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by multi-channel detectors of a tomography device;

[0029] A second acquisition module is used to acquire a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector;

[0030] a third acquisition module, configured to acquire a first error projection map corresponding to the initial high-energy tomography image based on each high-energy correction coefficient, the first projection data, and the second projection data; and to acquire a second error projection map corresponding to the initial low-energy tomography image based on each low-energy correction coefficient, the first projection data, and the second projection data;

[0031] The correction module is used to perform artifact correction on the initial high-energy tomography image based on the first error projection map; and to perform artifact correction on the initial low-energy tomography image based on the second error projection map.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; both the initial high-energy tomography image and the initial low-energy tomography image are acquired and reconstructed by multi-channel detectors of a tomography device;

[0034] Obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel of the detector;

[0035] Based on the low-energy correction coefficients corresponding to each channel, the first projection data, and the second projection data, an error projection map corresponding to the initial low-energy tomography image is acquired;

[0036] The initial low-energy tomography image is subjected to artifact correction based on the error projection map corresponding to the initial low-energy tomography image to obtain a low-energy corrected image.

[0037] In one embodiment, the processor is further configured to implement:

[0038] Based on the high energy correction coefficient, the first projection data and the second projection data, acquiring an error projection map corresponding to the initial high energy tomography image;

[0039] The initial high-energy tomography image is subjected to artifact correction based on the error projection map corresponding to the initial high-energy tomography image to obtain a high-energy corrected image.

[0040] In one embodiment, the processor is further configured to implement:

[0041] Before acquiring the first projection data and the second projection data, the initial high-energy tomography image and the initial low-energy tomography image are registered.

[0042] In one embodiment, the processor is further configured to implement:

[0043] A virtual plain scan image is acquired based on the low-energy correction image and the high-energy correction image.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the content of any one of the embodiments of the above-mentioned medical image artifact correction method.

[0045] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the content of any one of the embodiments of the above-mentioned medical image artifact correction method.

[0046] The above-mentioned medical image artifact correction method, device, equipment and medium obtain the first projection data of the initial high-energy tomography image and the second projection data of the initial low-energy tomography image; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by the multi-channel detector of the tomography device; the high-energy correction coefficient and the low-energy correction coefficient corresponding to each channel of the detector are obtained; based on each high-energy correction coefficient, the first projection data and the second projection data, the first error projection map corresponding to the initial high-energy tomography image is obtained; and based on each low-energy correction coefficient, the first projection data and the second projection data, the second error projection map corresponding to the initial low-energy tomography image is obtained; the initial high-energy tomography image is artifact corrected based on the first error projection map; and the initial low-energy tomography image is artifact corrected based on the second error projection map. The method obtains the high-energy correction coefficient and the low-energy correction coefficient corresponding to each channel of the detector, and uses the high-energy correction coefficient and the low-energy correction coefficient to correct the projection information in the initial tomography images of different energy values, respectively, so that the content included in the calculated projection information is more comprehensive. Then, based on the calculated projection information, the error projection map corresponding to the initial tomographic image of different energy values ​​can be obtained more accurately, that is, the artifact information in the two error projection maps is more comprehensive. The artifacts in the initial tomographic image can be corrected more accurately through the two error projection maps, thereby improving the accuracy of the artifact correction process and improving the quality of the initial tomographic images of different energy values. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] FIG1 is a diagram showing an application environment of a medical image artifact correction method according to an embodiment;

[0049] FIG2 is a schematic diagram of a flow chart of a method for correcting artifacts of medical images in one embodiment;

[0050] FIG3 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0051] FIG4 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0052] FIG5 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0053] FIG6 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0054] FIG7 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0055] FIG8 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0056] FIG9 is a schematic flow chart of a method for correcting artifacts of medical images in one embodiment;

[0057] FIG10 is a schematic diagram of a flow chart of a method for correcting artifacts of medical images in one embodiment;

[0058] FIG11 is a schematic flow chart of a method for artifact correction of dual-energy CT images in one embodiment;

[0059] FIG12 is a schematic diagram of a dual-energy CT image in one embodiment;

[0060] FIG. 13 is a structural block diagram of a medical image artifact correction device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] Before introducing the technical content of this application in detail, a brief introduction to the background technology of this application is first given.

[0063] For the dual-energy CT imaging process, the hardening effect in the image domain energy spectrum imaging process will cause hardening artifacts to appear on the dual-energy CT image. The hardening artifacts will affect the quality of the dual-energy CT image and thus affect the dual-energy quantitative analysis results.

[0064] In one method of the related art, the dual-energy CT images are segmented separately, and the segmented dual-energy CT images are forward projected to obtain material projection data for artifact correction. This method cannot accurately correct the artifacts of the dual-energy CT images, so that the quality of the dual-energy CT images is still poor. In another method, projection data of different energies are used for iterative calculation to correct hardening artifacts. This method is only applicable to spectral CT systems with the same source, simultaneous and same direction, and the complexity of artifact correction is high and the robustness is poor.

[0065] In response to the above problems, the present application provides a method, device, equipment and medium for artifact correction of medical images, which comprehensively considers the projection information in the dual-energy CT image and uses the artifact determination model to calculate the projection information in the dual-energy CT image, so that the artifact image in the dual-energy CT image can be more comprehensively obtained, so that the artifact in the dual-energy CT image can be corrected more accurately to improve the quality of the dual-energy CT image. Of course, the technical solution provided in the embodiments of the present application is not limited to solving only the above problems, and there are other technical effects. For details, please refer to the following embodiment description. The technical solution of the present application is described in detail below.

[0066] The method for medical image artifact correction provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1. The computer device in the application environment can be a server, a personal computer, a laptop computer, a smart phone, a tablet computer, a smart mobile phone, etc. The computer device may include a processor, a memory and a network interface connected via a system bus or wirelessly. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the artifact correction process of medical images. The network interface of the computer device is used to communicate with an external terminal through a network connection, and the computer program is executed by the processor to implement a method for medical image artifact correction.

[0067] In an exemplary embodiment, as shown in FIG2 , a method for correcting artifacts of medical images is provided, which is described by taking the method applied to the computer device in FIG1 as an example, and includes the following steps 201 to 203. Among them:

[0068] S201, obtaining first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; both the initial high-energy tomography image and the initial low-energy tomography image are acquired and reconstructed by multi-channel detectors of a tomography device.

[0069] Among them, the initial high-energy tomography image and the initial low-energy tomography image are images obtained by scanning the same part with different energy rays through a dual-energy CT device, and the size of the energy ray can be set by the tube voltage. For example, different energy rays can be emitted by tube voltages of 80kVp and 140kVp, respectively. Then, the initial high-energy tomography image represents a high-energy CT image obtained by scanning with energy rays emitted by a tube voltage of 140kVp, and the initial low-energy tomography image represents a low-energy CT image obtained by scanning with energy rays emitted by a tube voltage of 80kVp.

[0070] It should be noted that the projection information of the high-energy CT image and the projection information of the low-energy CT image include all the hardening artifact information.

[0071] In the embodiment of the present application, the initial high-energy tomography image and the initial low-energy tomography image may be obtained by the computer device controlling the dual-energy CT device to scan the same part, or may be obtained by the computer device searching from an image database based on identification information of the scanned part. The embodiment of the present application does not limit the method of obtaining the initial high-energy tomography image and the initial low-energy tomography image.

[0072] After acquiring the initial high-energy tomography image and the initial low-energy tomography image, the computer device can use an image projection algorithm to project the initial high-energy tomography image and the initial low-energy tomography image respectively to obtain first projection data of the initial high-energy tomography image and second projection data of the initial low-energy tomography image. For example, the image projection algorithm can be a forward projection method, an oblique projection method, etc.

[0073] S202, obtaining a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector.

[0074] Among them, the correction coefficient refers to the coefficient of each channel of the dual-energy CT device that may cause artifacts during the scanning process. The correction coefficient includes a high-energy correction coefficient and a low-energy correction coefficient.

[0075] In an embodiment of the present application, the computer device can search for high-energy correction coefficients and low-energy correction coefficients that match each channel in the tomography device from a correction coefficient database based on the identification information of the tomography device, and use the high-energy correction coefficients and low-energy correction coefficients found as the high-energy correction coefficients and low-energy correction coefficients corresponding to each channel in the tomography device. Alternatively, the computer device can also calculate the high-energy correction coefficients and low-energy correction coefficients corresponding to each channel in the tomography device according to the device parameter information of the tomography device and the calculation formula of the correction coefficients. The embodiment of the present application does not limit the method for obtaining the high-energy correction coefficients and the low-energy correction coefficients.

[0076] S203, based on each high-energy correction coefficient, the first projection data and the second projection data, obtaining a first error projection map corresponding to the initial high-energy tomography image; and based on each low-energy correction coefficient, the first projection data and the second projection data, obtaining a second error projection map corresponding to the initial low-energy tomography image.

[0077] The first error projection map represents the image of the artifact part in the initial high-energy tomography image, and the second error projection map represents the image of the artifact part in the initial low-energy tomography image. For example, the artifact is in the central area of ​​the initial tomography image, and the central area includes the artifact image and the background image. The error projection map only includes the image of the artifact part, and does not include the image of the background part.

[0078] In an embodiment of the present application, for any one channel, the computer device may multiply the high-energy correction coefficient in the channel with the first projection data and the second projection data, respectively, to obtain a multiplication result. The sum of the multiplication results of all channels is used as the first error projection data, and the first error projection data is image reconstructed to obtain a first error projection map corresponding to the initial high-energy tomography image. And, the computer device may multiply the low-energy correction coefficient in the channel with the first projection data and the second projection data, respectively, to obtain a multiplication result. The sum of the multiplication results of all channels is used as the second error projection data, and the second error projection data is image reconstructed to obtain a second error projection map corresponding to the initial low-energy tomography image.

[0079] S204, performing artifact correction on the initial high-energy tomography image based on the first error projection map; and performing artifact correction on the initial low-energy tomography image based on the second error projection map.

[0080] In the embodiment of the present application, since the first error projection map represents the image of the artifact part in the initial high-energy tomography image, the artifact correction can be achieved by filtering out the image of the artifact part in the initial high-energy tomography image. Based on this, the computer device can calculate the difference between the initial high-energy tomography image and the first error projection map, and use the obtained difference image as the initial high-energy tomography image after artifact correction.

[0081] Similarly, since the second error projection map represents the image of the artifact part in the initial low-energy tomography image, the artifact correction can be achieved by filtering out the image of the artifact part in the initial low-energy tomography image. Based on this, the computer device can calculate the difference between the initial low-energy tomography image and the second error projection map, and use the obtained difference image as the initial low-energy tomography image after artifact correction.

[0082] In the above-mentioned medical image artifact correction method, the first projection data of the initial high-energy tomography image and the second projection data of the initial low-energy tomography image are obtained; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by the multi-channel detector of the tomography device; the high-energy correction coefficient and the low-energy correction coefficient corresponding to each channel of the detector are obtained; based on each high-energy correction coefficient, the first projection data and the second projection data, the first error projection map corresponding to the initial high-energy tomography image is obtained; and based on each low-energy correction coefficient, the first projection data and the second projection data, the second error projection map corresponding to the initial low-energy tomography image is obtained; the initial high-energy tomography image is artifact corrected based on the first error projection map; and the initial low-energy tomography image is artifact corrected based on the second error projection map. The method obtains the high-energy correction coefficient and the low-energy correction coefficient corresponding to each channel of the detector, and uses the high-energy correction coefficient and the low-energy correction coefficient to correct the projection information in the initial tomography images of different energy values, respectively, so that the content included in the calculated projection information is more comprehensive. Then, based on the calculated projection information, the error projection map corresponding to the initial tomographic image of different energy values ​​can be obtained more accurately, that is, the artifact information in the two error projection maps is more comprehensive. The artifacts in the initial tomographic image can be corrected more accurately through the two error projection maps, thereby improving the accuracy of the artifact correction process and improving the quality of the initial tomographic images of different energy values.

[0083] Next, the specific contents of calculating the first error projection map and the second error projection map are introduced respectively. First, in one embodiment, as shown in FIG3 , the specific contents of obtaining the first error projection map corresponding to the initial high-energy tomography image based on each high-energy correction coefficient, the first projection data and the second projection data include:

[0084] S301, for any channel, determining first sub-error projection data corresponding to the channel based on a high-energy correction coefficient of the channel, first projection data, and second projection data;

[0085] For each channel, the method of obtaining the first sub-error projection data in the channel is exactly the same. Therefore, taking one channel as an example, since the initial high-energy image includes multiple tomographic images, the first projection data may include multiple tomographic projection data, and the second projection data may include multiple tomographic projection data. The number of high-energy correction coefficients is multiple.

[0086] For any channel, based on multiple high-energy correction coefficients, first projection data and second projection data corresponding to each channel, the product of the projection data corresponding to each high-energy correction coefficient is calculated, and the sum of all products is used as the first sub-error projection data corresponding to the channel.

[0087] For any channel, the first sub-error projection data δp corresponding to the channel h [ichan] can be expressed as:

[0088] δp h [ichan]=C H 1×p l [ichan]+C H 2×p h [ichan]+C H 3×p l [ichan] 2 +C H 4×p h [ichan] 2 +

[0089] C H 5p h [ichan]×p l [ichan]+C H 6×p l [ichan] 3 +C H 7×p h [ichan] 3

[0090] Among them, C H 1. C H 2. C H 3. C H 4. C H 5. C H 6 and C H 7 represents seven high energy correction factors, p l [ichan] represents the second projection data of the i-th channel, ph [ichan] represents the first projection data of the i-th channel.

[0091] S302: Determine a first error projection map corresponding to the initial high energy tomography image according to the first sub-error projection data corresponding to each channel.

[0092] In the embodiment of the present application, the computer device may add the first sub-error projection data corresponding to all channels, and use the added result as the first error projection data, and then perform image reconstruction on the first error projection data to obtain a first error projection map.

[0093] Optionally, the computer device may also input the first sub-error projection data corresponding to each channel into a preset image reconstruction model, and analyze and reconstruct the first sub-error projection data corresponding to each channel through the image reconstruction model to obtain a first error projection map.

[0094] In the above-mentioned medical image artifact correction method, for any channel, based on the high-energy correction coefficient, first projection data and second projection data of the channel, the first sub-error projection data corresponding to the channel is determined; according to the first sub-error projection data corresponding to each channel, the first error projection map corresponding to the initial high-energy tomography image is determined. This method can accurately calculate the error of the first projection data through multiple high-energy correction coefficients corresponding to each channel, so that the real first sub-error projection data corresponding to each channel can be accurately determined, and then according to the first sub-error projection data corresponding to each channel, the first error projection map corresponding to each channel can be accurately obtained.

[0095] In one embodiment, as shown in FIG4 , the first error projection map corresponding to the initial high energy tomography image is determined according to the first sub-error projection data corresponding to each channel, including:

[0096] S401 , taking the sum of the first sub-error projection data corresponding to each channel as the first error projection data.

[0097] In the embodiment of the present application, each channel of the tomography device can only scan a small part of the scanning area, that is, the first sub-error projection data corresponding to each channel is only the error projection data corresponding to this small part of the area. To obtain all the error projection data, it is necessary to add the sub-error projection data of all channels to obtain the error projection data of the scanning area. Specifically, the computer device can add the first sub-error projection data corresponding to all channels, and use the result of the addition as the first error projection data.

[0098] S402, performing image reconstruction on the first error projection data to obtain a first error projection map.

[0099] In the embodiment of the present application, since the error projection data represents the data of the artifact part, after the image reconstruction is performed on the data of the artifact part, the image obtained represents the image of the artifact part. Based on this, the computer device can use the image reconstruction algorithm to reconstruct the first error projection data to obtain a first error projection map corresponding to the initial high-energy tomography image.

[0100] In the above-mentioned medical image artifact correction method, the sum of the first sub-error projection data corresponding to each channel is used as the first error projection data; the first error projection data is image reconstructed to obtain a first error projection map. This method can obtain more comprehensive first error projection data by fusing the first sub-error projection data of multiple channels, avoiding the situation where some error projection data are ignored. Based on this, the image reconstruction method is used to accurately reconstruct the first error projection map corresponding to the initial high-energy tomography image.

[0101] Next, the specific content of obtaining the second error projection map is introduced. In one embodiment, as shown in FIG. 5 , the second error projection map corresponding to the initial low-energy tomography image is obtained based on the low-energy correction coefficients, the first projection data, and the second projection data, including:

[0102] S501 , for any channel, determining second sub-error projection data corresponding to the channel based on a low-energy correction coefficient of the channel, first projection data, and second projection data.

[0103] For each channel, the method of obtaining the second sub-error projection data in the channel is exactly the same. Therefore, taking one channel as an example, since the initial low-energy image includes multiple tomographic images, the second projection data may include multiple tomographic projection data, and the second projection data may include multiple tomographic projection data. The number of low-energy correction coefficients is multiple.

[0104] For any channel, based on multiple low-energy correction coefficients, first projection data and second projection data corresponding to each channel, the product of the projection data corresponding to each low-energy correction coefficient is calculated, and the sum of all products is used as the second sub-error projection data corresponding to the channel.

[0105] For any channel, the second sub-error projection data δp1[ichan] corresponding to the channel can be expressed as:

[0106] δp1[ichan]=C L 1×p l [ichan]+C L 2×p h [ichan]+C L 3×p l [ichan]2 +C L 4×p h [ichan] 2 +

[0107] C L 5×p l [ichan]×p h [ichan]+C L 6×p l [ichan] 3 +C L 7×p h [ichan] 3

[0108] Among them, C L 1. C L 2. C L 3. C L 4. C L 5. C L 6 and C L 7 represents seven low energy correction coefficients, p l [ichan] represents the second projection data of the i-th channel, p h [ichan] represents the first projection data of the i-th channel.

[0109] S502: Determine a second error projection map corresponding to the initial high energy tomography image according to the second sub-error projection data corresponding to each channel.

[0110] In the embodiment of the present application, the computer device may add the second sub-error projection data corresponding to all channels, and use the added result as the second error projection data, and then perform image reconstruction on the second error projection data to obtain a second error projection map.

[0111] Optionally, the computer device may also input the second sub-error projection data corresponding to each channel into a preset image reconstruction model, and analyze and reconstruct the second sub-error projection data corresponding to each channel through the image reconstruction model to obtain a second error projection map.

[0112] In the above-mentioned medical image artifact correction method, for any channel, based on the low-energy correction coefficient of the channel, the first projection data and the second projection data, the second sub-error projection data corresponding to the channel is determined; according to the second sub-error projection data corresponding to each channel, the second error projection map corresponding to the initial high-energy tomography image is determined. This method can accurately calculate the error of the second projection data through multiple low-energy correction coefficients corresponding to each channel, so that the real second sub-error projection data corresponding to each channel can be accurately determined, and then according to the second sub-error projection data corresponding to each channel, the second error projection map corresponding to each channel can be accurately obtained.

[0113] In one embodiment, as shown in FIG6 , the second error projection map corresponding to the initial high energy tomography image is determined according to the second sub-error projection data corresponding to each channel, including:

[0114] S601: taking the sum of the second sub-error projection data corresponding to each channel as the second error projection data.

[0115] In the embodiment of the present application, the computer device may add the second sub-error projection data corresponding to all channels, and use the added result as the second error projection data.

[0116] S602: Perform image reconstruction on the second error projection data to obtain a second error projection map.

[0117] In the embodiment of the present application, since the error projection data represents the data of the artifact part, after the image reconstruction is performed on the data of the artifact part, the image obtained represents the image of the artifact part. Based on this, the computer device can use the image reconstruction algorithm to reconstruct the second error projection data to obtain a second error projection map corresponding to the initial low-energy tomography image.

[0118] In the above-mentioned medical image artifact correction method, the sum of the second sub-error projection data corresponding to each channel is used as the second error projection data; the second error projection data is image reconstructed to obtain a second error projection map. This method can obtain more comprehensive second error projection data by fusing the second sub-error projection data of multiple channels, avoiding the situation where some error projection data are ignored. Based on this, the second error projection map corresponding to the initial low-energy tomography image can be accurately reconstructed by using the image reconstruction method.

[0119] The multiple correction coefficients corresponding to each channel can be obtained by looking up a table or by calculation. Then, in one embodiment, as shown in FIG7 , the specific contents of obtaining the high energy correction coefficient and the low energy correction coefficient of each channel in the tomography device by calculation are introduced:

[0120] S701, determining a first energy spectrum and a second energy spectrum based on filtering information of a tomography device.

[0121] The first energy spectrum represents a high energy spectrum, and the second energy spectrum represents a low energy spectrum.

[0122] In an embodiment of the present application, the computer device can obtain the filtering information of the tomography device, and calculate the first energy spectrum and the second energy spectrum based on the filtering information and the calculation formula of the energy spectrum. The calculation formula of the energy spectrum can be expressed as:

[0123] S l,h [E,ichan] = S 0 l,h [E]×exp(-μ Filter (E)L(ichan))

[0124] Among them, S h [E,ichan] and S l [E,ichan] represents the first energy spectrum (high energy spectrum) and the second energy spectrum (low energy spectrum), respectively; μ Filter (E) represents the linear attenuation coefficient when the energy is E; L(ichan) represents the length that the x-ray passes through when it is incident from the tube to the i-th detector channel.

[0125] S702, performing water hardening correction on first projection values ​​of energy rays passing through a plurality of base materials under a first energy spectrum and second projection values ​​of energy rays passing through a plurality of base materials under a second energy spectrum.

[0126] The base substance may be water-iodine, water-calcium, a mixture of multiple base substances, or attenuation terms caused by the photoelectric effect and the Compton effect.

[0127] In the embodiment of the present application, the computer device can obtain the first projection value of the energy ray passing through the multiple base materials under the first energy spectrum based on the calculation formula of the projection value, and obtain the second projection value of the energy ray passing through the multiple base materials under the second energy spectrum. The calculation formula of the projection value can be expressed as:

[0128]

[0129] in, , represent the first projection value and the second projection value respectively.

[0130] Furthermore, the first projection value and the second projection value are corrected respectively by using water hardening correction. The correction process can be expressed as:

[0131]

[0132] S703, fitting the water hardening correction result to obtain a high energy correction coefficient and a low energy correction coefficient corresponding to each channel in the tomography device.

[0133] In the embodiment of the present application, the correction coefficients corresponding to different energy ray scanning processes are different, that is, for the initial high-energy tomography image, the multiple correction coefficients corresponding to each channel are different from the multiple correction coefficients corresponding to the initial low-energy tomography image. Based on this, the computer device can fit the water hardening correction result by the least square method to obtain the high-energy correction coefficient corresponding to each channel of the initial high-energy tomography image, and the low-energy correction coefficient corresponding to each channel of the initial low-energy tomography image.

[0134] Among them, the high energy correction coefficient corresponding to each channel of the initial high energy tomography image can be expressed as: C H 1. C H 2. C H 3. C H 4. C H 5. C H 6 and C H 7. The low energy correction coefficient corresponding to each channel of the initial low energy tomography image can be expressed as: C L 1. C L 2. C L 3. C L 4. C L 5. C L 6 and C L 7.

[0135] In the above-mentioned medical image artifact correction method, the first energy spectrum and the second energy spectrum are determined based on the filtering information of the tomography device; the first projection value of the energy ray passing through multiple base materials under the first energy spectrum and the second projection value of the energy ray passing through multiple base materials under the second energy spectrum are respectively subjected to water hardening correction; and the water hardening correction result is fitted to obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel in the tomography device. This method can accurately calculate the first energy spectrum and the second energy spectrum through the filtering information of the tomography device, and then use the projection and water hardening correction method to accurately obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel in the tomography device.

[0136] The projection data may be obtained by forward projection processing. In one embodiment, the specific contents of obtaining the first projection data of the initial high-energy tomography image and the second projection data of the initial low-energy tomography image are introduced, and the specific contents include:

[0137] The initial high-energy tomography image and the initial low-energy tomography image are respectively forward projected to obtain first projection data of the initial high-energy tomography image and second projection data of the initial low-energy tomography image.

[0138] In the embodiment of the present application, the computer device may project the initial high-energy tomography image through a forward projection algorithm to obtain first projection data of the initial high-energy tomography image, and may project the initial low-energy tomography image through a forward projection algorithm to obtain second projection data of the initial low-energy tomography image.

[0139] The second projection data can be expressed as p l [chanNum, ViewNum, ImageNum], the first projection data can be expressed as ph[chanNum, ViewNum, ImageNum], wherein chanNum represents the number of channels of the tomography device, ViewNum represents the number of the front projection angle, and ImageNum represents the number of slices in the initial tomography image.

[0140] In the above-mentioned medical image artifact correction method, the initial high-energy tomography image and the initial low-energy tomography image are respectively subjected to forward projection processing to obtain first projection data of the initial high-energy tomography image and second projection data of the initial low-energy tomography image. The method projects the initial high-energy tomography image and the initial low-energy tomography image respectively by forward projection processing, and can accurately obtain the first projection data and the second projection data.

[0141] Next, the contents of the artifact correction process of the initial high-energy tomography image are introduced through an embodiment. As shown in FIG8 , the specific contents of the artifact correction of the initial high-energy tomography image based on the first error projection map include:

[0142] S801, calculating the difference between the initial high energy tomography image and the first error projection image.

[0143] In an embodiment of the present application, after obtaining the first error projection map, the pixel value of each pixel point in the initial high-energy tomography image and the first error projection map is subtracted, and the image composed of the pixel values ​​obtained by the subtraction is used as the difference between the initial high-energy tomography image and the first error projection map.

[0144] S802, and taking the difference as the initial high-energy tomography image after artifact correction.

[0145] In the embodiment of the present application, since the first error projection image is only an image of the artifact part, the initial high-energy tomography image is an image of the artifact part and the background part. Therefore, the difference between the two represents the image of the background part after the artifact is removed. Based on this, the computer device can use the difference between the initial high-energy tomography image and the first error projection image as the initial high-energy tomography image after artifact correction.

[0146] Among them, the initial high-energy tomography image can be expressed as:

[0147] I C h =I O h -α h δI h

[0148] Among them, I C h I represents the initial high-energy tomography image after artifact correction; O h represents the initial high-energy tomography image; δI h represents the first error projection map; α h Represents a constant used for dimensional conversion.

[0149] In the above-mentioned medical image artifact correction method, the difference between the initial high-energy tomography image and the first error projection map is calculated; and the difference is used as the initial high-energy tomography image after artifact correction. This method removes the artifact part in the initial high-energy tomography image by making a difference, avoids the influence of the artifact on the quality of the initial high-energy tomography image, and improves the quality of the initial high-energy tomography image.

[0150] Next, another embodiment is used to introduce the content of the artifact correction process of the initial low-energy tomography image. As shown in FIG9 , the specific content of the artifact correction of the initial low-energy tomography image based on the second error projection map includes:

[0151] S901, calculating the difference between the initial low-energy tomography image and the second error projection image.

[0152] In an embodiment of the present application, after obtaining the second error projection map, the pixel value of each pixel point in the initial low-energy tomography image and the second error projection map are subtracted, and the image composed of the pixel values ​​obtained by the subtraction is used as the difference between the initial low-energy tomography image and the second error projection map.

[0153] S902, and taking the difference as the initial low-energy tomography image after artifact correction.

[0154] In the embodiment of the present application, since the second error projection image is only an image of the artifact part, the initial low-energy tomography image is an image of the artifact part and the background part. Therefore, the difference between the two represents the image of the background part after the artifact is removed. Based on this, the computer device can use the difference between the initial low-energy tomography image and the second error projection image as the initial low-energy tomography image after artifact correction.

[0155] Among them, the initial low-energy tomography image can be expressed as:

[0156] I C l =I C l -α l δI l

[0157] Among them, I C l I represents the initial low-energy tomography image after artifact correction; O l represents the initial low-energy tomography image; δI l represents the second error projection map; α l Represents a constant used for dimensional conversion.

[0158] In the above-mentioned medical image artifact correction method, the difference between the initial low-energy tomography image and the second error projection map is calculated; and the difference is used as the initial low-energy tomography image after artifact correction. This method removes the artifact part in the initial low-energy tomography image by making a difference, avoids the influence of the artifact on the quality of the initial low-energy tomography image, and improves the quality of the initial low-energy tomography image.

[0159] As a specific embodiment of the present application, the artifact correction process of medical images is specifically introduced below. In one embodiment, as shown in FIG10 , the artifact correction method of medical images includes:

[0160] S1001, performing forward projection processing on an initial high-energy tomography image and an initial low-energy tomography image respectively to obtain first projection data of the initial high-energy tomography image and second projection data of the initial low-energy tomography image;

[0161] S1002, obtaining a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector;

[0162] S1003, for any channel, determining first sub-error projection data corresponding to the channel based on the high-energy correction coefficient of the channel, the first projection data, and the second projection data;

[0163] S1004, taking the sum of the first sub-error projection data corresponding to each channel as the first error projection data;

[0164] S1005, performing image reconstruction on the first error projection data to obtain a first error projection map;

[0165] S1006, for any channel, based on the low energy correction coefficient of the channel, the first projection data, and the second projection data, determining second sub-error projection data corresponding to the channel;

[0166] S1007, taking the sum of the second sub-error projection data corresponding to each channel as the second error projection data;

[0167] S1008, performing image reconstruction on the second error projection data to obtain a second error projection map;

[0168] S1009, calculating the difference between the initial high-energy tomography image and the first error projection image, and using the difference as the initial high-energy tomography image after artifact correction; and calculating the difference between the initial low-energy tomography image and the second error projection image, and using the difference as the initial low-energy tomography image after artifact correction.

[0169] FIG11 is a flow chart of an artifact correction method for a dual-energy CT image, which includes: S1101, acquiring an initial high-energy CT image and an initial low-energy CT image; S1102, registering the initial high-energy CT image and the initial low-energy CT image; S1103, respectively performing orthographic projection on the registered initial high-energy CT image and the registered initial low-energy CT image to obtain high-energy orthographic projection data and low-energy orthographic projection data; S1104, searching for a correction coefficient from a correction coefficient table; S1105, registering the correction coefficient. The positive coefficients, high-energy forward projection data and low-energy forward projection data are substituted into the polynomial to calculate the high-energy error projection data and the low-energy error projection data; S1106, reconstructing the high-energy error projection data and the low-energy error projection data respectively to obtain a high-energy artifact image and a low-energy artifact image; S1107, taking the difference between the initial high-energy CT image after registration and the high-energy artifact image as the initial high-energy CT image after artifact correction; and, taking the difference between the initial low-energy CT image after registration and the low-energy artifact image as the initial low-energy CT image after artifact correction.

[0170] FIG12 is a schematic diagram of a dual-energy CT image, wherein the upper left figure and the upper right figure respectively represent an initial high-energy CT image and an initial low-energy CT image, and the lower left figure and the lower right figure respectively represent an initial high-energy CT image after artifact correction and an initial low-energy CT image after artifact correction. By comparison, artifacts in both high-energy CT images and low-energy CT images have been removed, thereby improving the quality of high-energy CT images and low-energy CT images.

[0171] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0172] Based on the same inventive concept, the embodiment of the present application also provides an artifact correction device for implementing the above-mentioned artifact correction method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more artifact correction device embodiments provided below can refer to the limitations of the artifact correction method above, and will not be repeated here.

[0173] In an exemplary embodiment, as shown in FIG13 , a medical image artifact correction device is provided, comprising: a first acquisition module 11, a second acquisition module 12, a third acquisition module 13 and a correction module 14, wherein:

[0174] A first acquisition module 11 is used to acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; both the initial high-energy tomography image and the initial low-energy tomography image are acquired and reconstructed by multi-channel detectors of a tomography device;

[0175] A second acquisition module 12 is used to acquire a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector;

[0176] A third acquisition module 13 is used to acquire a first error projection map corresponding to the initial high-energy tomography image based on each high-energy correction coefficient, the first projection data, and the second projection data; and to acquire a second error projection map corresponding to the initial low-energy tomography image based on each low-energy correction coefficient, the first projection data, and the second projection data;

[0177] The correction module 14 is used to perform artifact correction on the initial high-energy tomography image based on the first error projection map; and to perform artifact correction on the initial low-energy tomography image based on the second error projection map.

[0178] In an exemplary embodiment, the third acquisition module includes: a first determination unit and a second determination unit, wherein:

[0179] A first determining unit, configured to determine, for any one channel, first sub-error projection data corresponding to the channel based on a high-energy correction coefficient of the channel, the first projection data, and the second projection data;

[0180] The second determining unit is used to determine a first error projection map corresponding to the initial high energy tomography image according to the first sub-error projection data corresponding to each channel.

[0181] In an exemplary embodiment, the second determining unit is further configured to take the sum of the first sub-error projection data corresponding to each channel as the first error projection data; and perform image reconstruction on the first error projection data to obtain a first error projection map.

[0182] In an exemplary embodiment, the third acquisition module further includes: a third determination unit and a fourth determination unit, wherein:

[0183] A third determining unit, configured to determine, for any one channel, second sub-error projection data corresponding to the channel based on the low-energy correction coefficient of the channel, the first projection data, and the second projection data;

[0184] The fourth determining unit is used to determine a second error projection map corresponding to the initial high energy tomography image according to the second sub-error projection data corresponding to each channel.

[0185] In an exemplary embodiment, the fourth determining unit is further configured to take the sum of the second sub-error projection data corresponding to each channel as the second error projection data; and perform image reconstruction on the second error projection data to obtain a second error projection map.

[0186] In an exemplary embodiment, the second acquisition module further includes: an energy spectrum determination unit, a correction unit and a fitting unit, wherein:

[0187] An energy spectrum determination unit, configured to determine a first energy spectrum and a second energy spectrum based on filtering information of the tomography device;

[0188] A correction unit, for performing water hardening correction on first projection values ​​of energy rays passing through a plurality of base materials under a first energy spectrum and second projection values ​​of energy rays passing through a plurality of base materials under a second energy spectrum;

[0189] The fitting unit is used to fit the water hardening correction result to obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel in the tomography device.

[0190] Each module in the above-mentioned artifact correction device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0191] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0192] Acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; both the initial high-energy tomography image and the initial low-energy tomography image are acquired and reconstructed by multi-channel detectors of a tomography device;

[0193] Obtain the high energy correction coefficient and the low energy correction coefficient corresponding to each channel of the detector;

[0194] Based on the low-energy correction coefficients corresponding to each channel, the first projection data, and the second projection data, an error projection map corresponding to the initial low-energy tomography image is acquired;

[0195] The initial low-energy tomography image is subjected to artifact correction based on the error projection map corresponding to the initial low-energy tomography image to obtain a low-energy corrected image.

[0196] In one embodiment, the processor is further used to obtain an error projection map corresponding to the initial high energy tomography image based on the high energy correction coefficient, the first projection data, and the second projection data;

[0197] The initial high-energy tomography image is subjected to artifact correction based on the error projection map corresponding to the initial high-energy tomography image to obtain a high-energy corrected image.

[0198] In one embodiment, the processor is further configured to implement registration processing on the initial high-energy tomography image and the initial low-energy tomography image before acquiring the first projection data and the second projection data.

[0199] In one embodiment, the processor is further configured to acquire a virtual plain scan image based on the low-energy correction image and the high-energy correction image.

[0200] After reconstructing the high-energy and low-energy images, the dual-energy data is processed to create various dual-energy CT applications. By mixing the high-energy and low-energy images (mixed images), weighted average images at different tube voltages can be obtained. Iodine maps can be created by extracting iodine (material decomposition); by subtracting the iodine map from the weighted average image, a virtual plain scan image is obtained.

[0201] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the content of any one embodiment of the above-mentioned artifact correction method is implemented.

[0202] In one embodiment, a computer program product is provided, comprising a computer program, which implements the content of any one of the embodiments of the above-mentioned artifact correction method when executed by a processor.

[0203] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0204] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0205] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0206] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for correcting artifacts in medical images, characterized in that: The method comprises: Acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by multi-channel detectors of a tomography device; Obtaining a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector; Based on each of the high-energy correction coefficients, the first projection data, and the second projection data, a first error projection map corresponding to the initial high-energy tomography image is acquired; and based on each of the low-energy correction coefficients, the first projection data, and the second projection data, a second error projection map corresponding to the initial low-energy tomography image is acquired; Performing artifact correction on the initial high-energy tomography image based on the first error projection map; and performing artifact correction on the initial low-energy tomography image based on the second error projection map.

2. The method according to claim 1, characterized in that: The step of acquiring a first error projection map corresponding to the initial high energy tomography image based on each of the high energy correction coefficients, the first projection data, and the second projection data comprises: For any one channel, based on the high energy correction coefficient of the channel, the first projection data and the second projection data, determine first sub-error projection data corresponding to the channel; A first error projection map corresponding to the initial high-energy tomography image is determined according to the first sub-error projection data corresponding to each of the channels.

3. The method according to claim 2, characterized in that Determining the first error projection map corresponding to the initial high energy tomography image according to the first sub-error projection data corresponding to each of the channels includes: taking the sum of the first sub-error projection data corresponding to each of the channels as the first error projection data; Perform image reconstruction on the first error projection data to obtain the first error projection map.

4. The method according to claim 1, characterized in that: The step of acquiring a second error projection map corresponding to the initial low-energy tomography image based on the low-energy correction coefficients, the first projection data, and the second projection data comprises: For any one channel, based on the low energy correction coefficient of the channel, the first projection data and the second projection data, determine the second sub-error projection data corresponding to the channel; A second error projection map corresponding to the initial high-energy tomography image is determined according to the second sub-error projection data corresponding to each of the channels.

5. The method according to claim 4, characterized in that Determining the second error projection map corresponding to the initial high energy tomography image according to the second sub-error projection data corresponding to each of the channels includes: taking the sum of the second sub-error projection data corresponding to each of the channels as the second error projection data; Perform image reconstruction on the second error projection data to obtain the second error projection map.

6. The method according to any one of claims 1 to 5, characterized in that: The obtaining of the high energy correction coefficient and the low energy correction coefficient corresponding to each channel of the detector comprises: Determining a first energy spectrum and a second energy spectrum based on filtering information of the tomography device; Performing water hardening correction on first projection values ​​of energy rays passing through a plurality of base materials under the first energy spectrum and second projection values ​​of energy rays passing through a plurality of base materials under the second energy spectrum respectively; The water hardening correction result is fitted to obtain a high-energy correction coefficient and a low-energy correction coefficient corresponding to each channel in the tomography device.

7. A medical image artifact correction device, characterized in that: The device comprises: A first acquisition module is used to acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by multi-channel detectors of a tomography device; A second acquisition module is used to acquire a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector; A third acquisition module is used to acquire a first error projection map corresponding to the initial high-energy tomography image based on each of the high-energy correction coefficients, the first projection data, and the second projection data; and to acquire a second error projection map corresponding to the initial low-energy tomography image based on each of the low-energy correction coefficients, the first projection data, and the second projection data; A correction module is used to perform artifact correction on the initial high-energy tomography image based on the first error projection map; and to perform artifact correction on the initial low-energy tomography image based on the second error projection map.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the following steps are implemented: Acquire first projection data of an initial high-energy tomography image and second projection data of an initial low-energy tomography image; the initial high-energy tomography image and the initial low-energy tomography image are both acquired and reconstructed by multi-channel detectors of a tomography device; Obtaining a high energy correction coefficient and a low energy correction coefficient corresponding to each channel of the detector; Based on the low-energy correction coefficients corresponding to the channels, the first projection data, and the second projection data, acquiring an error projection map corresponding to the initial low-energy tomography image; Perform artifact correction on the initial low-energy tomography image based on the error projection map corresponding to the initial low-energy tomography image to obtain a low-energy corrected image.

9. The computer device according to claim 8, characterized in that The processor is also used to implement: Based on the high energy correction coefficient, the first projection data and the second projection data, acquiring an error projection map corresponding to the initial high energy tomography image; Perform artifact correction on the initial high-energy tomography image based on the error projection map corresponding to the initial high-energy tomography image to obtain a high-energy corrected image.

10. The computer device according to claim 8, characterized in that The processor is also used to implement: Before acquiring the first projection data and the second projection data, the initial high-energy tomography image and the initial low-energy tomography image are registered.

11. The computer device according to claim 9, characterized in that The processor is also used to implement: A virtual plain scan image is acquired based on the low-energy corrected image and the high-energy corrected image.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images