Image reconstruction method and device for angiography, computer equipment and storage medium

Abstract

The invention relates to an angiography image reconstruction method and device, computer equipment and a storage medium. The quality of an angiography reconstruction image can be effectively improved. The method comprises the following steps: acquiring initial two-dimensional images of a target object with a contrast agent at each angle, and performing reconstruction based on each initial two-dimensional image to obtain an initial three-dimensional image; performing orthographic projection on the initial three-dimensional image to obtain a reference two-dimensional image of each angle; comparing the reference two-dimensional image with the initial two-dimensional image to obtain an image difference; and compensating the initial two-dimensional image according to the image difference to obtain compensation images, and performing image reconstruction based on each compensation image to obtain a target three-dimensional image.

Description

Technical Field

[0001] This application relates to the technical field of medical image processing, and particularly to an image reconstruction method, apparatus, computer device, storage medium, and computer program product for angiography. Background Art

[0002] With the development of computer technology, angiography can be performed through DSA (Digital Subtraction Angiography) technology to better observe the morphology and structure of blood vessels.

[0003] In the related art, during angiography, a contrast agent is injected into the patient's body and the blood vessels are scanned and photographed, and the final image result of the blood vessels is obtained by reconstructing the relevant scanned images.

[0004] However, the inventor has found in practice that there are artifacts in the reconstructed images obtained by the above method, which affect the image reconstruction effect of angiography. Summary of the Invention

[0005] Based on this, it is necessary to provide an image reconstruction method, apparatus, computer device, computer-readable storage medium, and computer program product for angiography that can improve the quality of the reconstructed images of blood vessel modeling for the above technical problems.

[0006] In a first aspect, this application provides an image reconstruction method for angiography, including:

[0007] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and reconstruct an initial three-dimensional image based on each of the initial two-dimensional images;

[0008] Perform forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0009] Compare the reference two-dimensional images with the initial two-dimensional images to obtain an image difference;

[0010] Compensate the initial two-dimensional images according to the image difference to obtain compensated images, and reconstruct an image based on each of the compensated images to obtain a target three-dimensional image.

[0011] In one embodiment, the comparing the reference two-dimensional images with the initial two-dimensional images to obtain an image difference includes:

[0012] Obtain a difference image between the reference two-dimensional image and the initial two-dimensional image.

[0013] In one embodiment, compensating the initial two-dimensional image according to the image difference to obtain a compensated image includes:

[0014] Determining an image compensation parameter according to the pixel value of each pixel point in the difference image;

[0015] Compensating the initial two-dimensional image based on the image compensation parameter to obtain the compensated image.

[0016] In one embodiment, compensating the initial two-dimensional image based on the image compensation parameter to obtain a compensated image includes:

[0017] For each pixel point in the initial two-dimensional image, taking the pixel value of the pixel point corresponding to this pixel point in the difference image as the image compensation parameter of this pixel point in the initial two-dimensional image;

[0018] Adjusting the pixel value of each pixel point in the initial two-dimensional image according to the image compensation parameter of each pixel point to obtain the compensated image.

[0019] In one embodiment, adjusting the pixel value of each pixel point in the initial two-dimensional image according to the image compensation parameter of each pixel point includes:

[0020] Performing weighted summation on the pixel value of each pixel point in the initial two-dimensional image and the image compensation parameter according to the respective weights of the initial two-dimensional image and the difference image;

[0021] Taking the weighted summation result of each pixel point in the initial two-dimensional image as the adjusted pixel value of each pixel point in the initial two-dimensional image.

[0022] In one embodiment, obtaining the difference image between the reference two-dimensional image and the initial two-dimensional image includes:

[0023] Obtaining the initial two-dimensional image corresponding to the reference two-dimensional image;

[0024] Determining the difference between the pixel value of each pixel point in the reference two-dimensional image and the pixel value of the corresponding pixel point in the initial two-dimensional image;

[0025] Obtaining the difference image between the reference two-dimensional image and the initial two-dimensional image according to each of the differences.

[0026] In one embodiment, obtaining the initial two-dimensional image corresponding to the reference two-dimensional image includes:

[0027] For each reference two-dimensional image, among the initial two-dimensional images corresponding to each angle, the initial two-dimensional image with the same angle as the reference two-dimensional image is used as the initial two-dimensional image corresponding to the reference two-dimensional image.

[0028] In a second aspect, the present application further provides an image reconstruction device for angiography, including:

[0029] A reconstructed image acquisition module, configured to collect initial two-dimensional images of a target object at various angles after injecting a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0030] An orthographic projection module, configured to perform orthographic projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0031] A difference determination module, configured to compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0032] An image compensation module, configured to compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0034] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0035] Perform orthographic projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0036] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0037] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0040] Perform orthographic projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0041] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0042] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0043] 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 following steps:

[0044] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0045] Perform forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0046] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0047] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0048] The above-mentioned image reconstruction method, device, computer device, storage medium and computer program product for angiography collect initial two-dimensional images of a target object at various angles with a contrast agent, perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image, and perform forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles; then, the reference two-dimensional image can be compared with the initial two-dimensional image to obtain an image difference, the initial two-dimensional image can be compensated according to the image difference to obtain a compensated image, and image reconstruction is performed based on each of the compensated images to obtain a target three-dimensional image. In this embodiment, comparing the reference two-dimensional image with the initial two-dimensional image to obtain an image difference can determine the difference between the contrast agent concentration corresponding to each initial two-dimensional image and the average concentration. Therefore, compensating the initial two-dimensional image according to the image difference can reduce the contrast agent concentration difference between the obtained compensated images, effectively improve the reconstruction effect of obtaining a target three-dimensional image by performing image reconstruction based on each of the compensated images, and reduce artifacts. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0050] Figure 1 It is a schematic flowchart of a method for reconstructing angiography images in an embodiment;

[0051] Figure 2a It is an initial two-dimensional image in an embodiment;

[0052] Figure 2b It is a compensated image after compensating the initial two-dimensional image in an embodiment;

[0053] Figure 3a It is an initial three-dimensional image in an embodiment;

[0054] Figure 3b It is a target three-dimensional image in an embodiment;

[0055] Figure 4 It is a schematic flowchart of steps for obtaining a compensated image in an embodiment;

[0056] Figure 5 It is a structural block diagram of an angiography image reconstruction device in an embodiment;

[0057] Figure 6 It is an internal structure diagram of a computer device in an embodiment;

[0058] Figure 7 It is another internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0060] In one embodiment, as Figure 1 shown, a method for reconstructing angiography images is provided. In this embodiment, it is exemplified that the method is applied to a terminal. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In some optional embodiments, the terminal and / or the server can be a reconstruction machine for performing medical image reconstruction tasks. Of course, in other embodiments, the terminal can also be a personal computer or a laptop computer; the server can be implemented by an independent server or a server cluster composed of multiple servers.

[0061] In this embodiment, it includes the following steps S101 to S104.

[0062] S101. Collect the initial two-dimensional images of the target object at various angles with contrast agent, and reconstruct the initial three-dimensional image based on each initial two-dimensional image.

[0063] Among them, the target object may include blood vessels.

[0064] In specific implementation, before scanning the target object, a contrast agent will be injected into the target object first, and then the medical images of the target object with contrast agent at various angles can be collected. The medical image is a two-dimensional image. For the convenience of distinction, the medical images of the target object at each angle obtained by collection are called initial two-dimensional images. Figure 2a Shows the initial two-dimensional image of the target object at a certain angle.

[0065] In some embodiments, the initial two-dimensional image may be a subtracted image of the target object. Specifically, the medical image collected before injecting the contrast agent into the target object can be obtained, and then according to the difference image between the medical image obtained after injecting the contrast agent into the target object and the medical image collected before injecting the contrast agent, that is, the difference image obtained by subtracting the medical image collected before injecting the contrast agent from the medical image obtained after injecting the contrast agent, the subtracted image of the target object can be obtained, so as to retain the image of the target object. Thus, the subtracted image (such as a blood vessel subtracted image) after subtraction can be obtained as the initial two-dimensional image through the above steps.

[0066] Of course, in some other embodiments, the initial two-dimensional image can also be obtained through other image processing methods. For example, the medical scan image of the target object with contrast agent can be collected. When the target object is scanned by the target ray (such as X-ray), since the penetration of the target ray through the liquid with contrast agent is different from that of the liquid without contrast agent, this difference can be reflected in the medical scan image. Therefore, the target object with contrast agent in the medical scan image can also be identified through relevant image processing techniques (such as a blood vessel segmentation algorithm), so as to obtain the initial two-dimensional image of the target object.

[0067] After the initial two-dimensional images at each angle are collected, the three-dimensional image of the target object can be obtained by reconstructing the images based on each initial two-dimensional image. For the convenience of distinction, the three-dimensional image reconstructed based on the initial two-dimensional image is also called the initial three-dimensional image. Figure 3a Shows an example of an initial three-dimensional image.

[0068] S102. Perform a forward projection on the initial three-dimensional image to obtain the reference two-dimensional images at various angles.

[0069] Specifically, as time goes by, the concentration of the contrast agent in the target object will also change accordingly. The concentration of the contrast agent is high at some angles and low at some angles. In other words, in addition to the difference in the scanning (or shooting) angle, there may also be a difference in the concentration of the contrast agent in each of the acquired initial two-dimensional images, which will have a certain impact on the reconstruction effect of the initial three-dimensional image, such as the appearance of artifacts.

[0070] In this regard, after obtaining the initial three-dimensional image, the initial three-dimensional image can be orthographically projected. Among them, orthographic projection is an image processing operation, which can be understood as mapping a three-dimensional structure onto a two-dimensional plane. Thus, by orthographically projecting the reconstructed three-dimensional image, two-dimensional images of the target object at various angles can be obtained again. For the convenience of distinguishing from the initial two-dimensional images obtained previously, the two-dimensional image obtained by orthographic projection is also called a reference two-dimensional image.

[0071] S103. Compare the reference two-dimensional image with the initial two-dimensional images to obtain an image difference.

[0072] In practical applications, although there are differences in the concentration of the contrast agent corresponding to the acquired initial two-dimensional images, the initial three-dimensional image reconstructed based on each initial two-dimensional image can reflect the average concentration of the contrast agent in the target object over time. In this regard, the reference two-dimensional image can be compared with the initial two-dimensional images to obtain the image difference between the initial two-dimensional images and the reference two-dimensional image. Since the reference two-dimensional image can reflect the average concentration of the target object, by comparing the initial two-dimensional image with the reference image, the difference in the concentration of the contrast agent corresponding to the initial two-dimensional image relative to the average concentration can be determined.

[0073] S104. Compensate the initial two-dimensional images according to the image difference to obtain compensated images, and perform image reconstruction based on each compensated image to obtain a target three-dimensional image.

[0074] After obtaining the image difference between the initial two-dimensional images and the reference two-dimensional image, the initial two-dimensional images can be compensated according to the image difference to obtain compensated images. By compensating the initial two-dimensional images, the concentrations of the contrast agents corresponding to the obtained compensated images can be made closer to each other, reducing the difference in the concentration of the contrast agent in the two-dimensional images of different angles of the target object. Furthermore, image reconstruction can be performed based on each compensated image to obtain a target three-dimensional image, improving the quality of the reconstructed image. Figure 3b Shows an example of a target three-dimensional image reconstructed based on compensated images. Compared with Figure 3a it can be seen that the artifacts are significantly reduced.

[0075] The above image reconstruction method for angiography involves collecting initial two-dimensional images of a target object at various angles with a contrast agent, reconstructing an initial three-dimensional image based on the initial two-dimensional images, performing a forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles; then, the reference two-dimensional images can be compared with the initial two-dimensional images to obtain an image difference, the initial two-dimensional images can be compensated according to the image difference to obtain compensated images, and an image reconstruction is performed based on the compensated images to obtain a target three-dimensional image. In this embodiment, comparing the reference two-dimensional images with the initial two-dimensional images to obtain an image difference can determine the difference in the contrast agent concentration corresponding to each initial two-dimensional image relative to the average concentration. Thus, compensating the initial two-dimensional images according to the image difference can reduce the difference in the contrast agent concentration among the obtained compensated images, effectively improving the reconstruction effect of the target three-dimensional image obtained by performing an image reconstruction based on the compensated images and reducing artifacts.

[0076] In one embodiment, in step S103, comparing the reference two-dimensional images with the initial two-dimensional images to obtain an image difference may include the following steps:

[0077] Obtain a difference image between the reference two-dimensional image and the initial two-dimensional image.

[0078] In practical applications, after obtaining the reference two-dimensional image, the pixel values of the pixel points in the reference two-dimensional image can be compared with the pixel values of the pixel points in the initial two-dimensional image to obtain a difference image between the reference two-dimensional image and the initial two-dimensional image. By obtaining the difference image, it is possible to quickly and accurately determine the difference in the contrast agent concentration corresponding to each initial two-dimensional image relative to the average contrast agent concentration according to the difference in the pixel values between the reference two-dimensional image and the initial two-dimensional image.

[0079] In one embodiment, as Figure 4 shown, in step S104, compensating the initial two-dimensional images according to the image difference to obtain compensated images may include the following steps:

[0080] S401, determine an image compensation parameter according to the pixel values of the pixel points in the difference image.

[0081] Specifically, the pixel values of the pixel points in the difference image can reflect the pixel value difference between the pixel values of the pixel points in the initial two-dimensional image and the pixel values of the pixel points in the reference two-dimensional image, and this pixel value difference can be understood to be caused by the difference in the contrast agent concentration. In this regard, an image compensation parameter can be determined according to the pixel values of the pixel points in the difference image.

[0082] S402, compensate the initial two-dimensional image based on the image compensation parameter to obtain a compensated image.

[0083] After obtaining the image compensation parameters, the initial two-dimensional image can be compensated according to the image compensation parameters, and thus a compensated image can be obtained. This compensation process can be to adjust the pixel values of the pixel points in the initial two-dimensional image according to the image compensation parameters, so as to simulate a two-dimensional image obtained by photographing a target object under relatively stable contrast agent concentration. Figure 2b shows the compensated image obtained after compensating the initial two-dimensional image of the target object at a certain angle. Comparing with Figure 2a the initial two-dimensional image, it can be seen that the compensated image can more clearly reflect some detailed information of the target object.

[0084] In this embodiment, by determining the image compensation parameters according to the pixel values of each pixel point in the difference image and compensating the initial two-dimensional image accordingly, a two-dimensional image obtained by photographing a target object under relatively stable contrast agent concentration can be accurately simulated, and the difference in contrast agent concentration of the two-dimensional images obtained for different target objects at different times can be reduced.

[0085] In one embodiment, in step S402, compensating the initial two-dimensional image based on the image compensation parameters to obtain a compensated image may include the following steps:

[0086] For each pixel point in the initial two-dimensional image, the pixel value of the pixel point corresponding to this pixel point in the difference image is used as the image compensation parameter of this pixel point in the initial two-dimensional image; according to the image compensation parameter of each pixel point, the pixel value of each pixel point in the initial two-dimensional image is adjusted to obtain a compensated image.

[0087] Specifically, after obtaining the difference image, for each pixel point in the initial two-dimensional image, a pixel point at the same position as this pixel point in the initial two-dimensional image can be determined in the difference image as the pixel point corresponding to this pixel point in the difference image, and then the pixel value of the pixel point corresponding to this pixel point in the difference image is used as the image compensation parameter of this pixel point in the initial two-dimensional image.

[0088] For each pixel point in the initial two-dimensional image, the pixel value of this pixel point can be adjusted with the image compensation parameter of this pixel point, and then, according to each pixel point with the adjusted pixel value, a compensated image can be obtained.

[0089] In this embodiment, by using the pixel value of the pixel point corresponding to this pixel point in the difference image as the image compensation parameter of this pixel point in the initial two-dimensional image, detailed and accurate image compensation can be performed on different regions in the initial two-dimensional image, so that in the compensated image obtained after compensation, the contrast agent concentrations of the target objects at different positions can be as consistent as possible, reducing the contrast agent concentration difference.

[0090] In one embodiment, adjusting the pixel value of each pixel in the initial two-dimensional image according to the image compensation parameter of each pixel may include the following steps:

[0091] Perform a weighted sum of the pixel value and the image compensation parameter of each pixel in the initial two-dimensional image according to the respective weights of the initial two-dimensional image and the difference image; use the weighted sum result of each pixel in the initial two-dimensional image as the adjusted pixel value of each pixel in the initial two-dimensional image.

[0092] In a specific implementation, respective weights may be set for the initial two-dimensional image and the difference image, and the weights may be determined according to past image reconstruction experience information (such as the image reconstruction effect of the target three-dimensional image obtained by multiple past reconstructions based on the compensated image).

[0093] Then, for each pixel in the initial two-dimensional image, a weighted sum of the pixel value and the image compensation parameter of the pixel may be performed according to their respective weights, and the weighted sum result may be used as the adjusted pixel value of the pixel, thereby obtaining the adjusted pixel values of each pixel. By performing a weighted sum of the pixel value and the image compensation parameter of each pixel in the initial two-dimensional image according to the respective weights of the initial two-dimensional image and the difference image, the flexibility of compensation can be improved and the image effect of the compensated image can be optimized.

[0094] In one embodiment, obtaining the difference image between the reference two-dimensional image and the initial two-dimensional image may include the following steps:

[0095] S1. Obtain the initial two-dimensional image corresponding to the reference two-dimensional image.

[0096] In a specific implementation, after obtaining the reference two-dimensional image, the initial two-dimensional image corresponding to the reference two-dimensional image may be determined from the initial two-dimensional images of each angle of the target object, and the image content in the corresponding initial two-dimensional image corresponds to the image content of the reference two-dimensional image.

[0097] S2. Determine the difference between the pixel value of each pixel in the reference two-dimensional image and the pixel value of the corresponding pixel in the initial two-dimensional image.

[0098] S3. Obtain the difference image between the reference two-dimensional image and the initial two-dimensional image according to the respective differences.

[0099] In practical applications, for each pixel point in the reference two-dimensional image, the difference between the pixel value of this pixel point and the pixel value corresponding to the pixel point at the same position in the initial two-dimensional image can be determined. Then, based on the differences of each pixel point in the reference two-dimensional image and the positions of the pixel points, a difference image can be obtained. Thus, the pixel values of each pixel point in the difference image can accurately reflect the difference in the contrast agent concentration of the target object at different positions in the initial two-dimensional image relative to the average concentration.

[0100] In one embodiment, in step S1, obtaining the initial two-dimensional image corresponding to the reference two-dimensional image may include the following steps:

[0101] For each reference two-dimensional image, in the initial two-dimensional images corresponding to each angle, the initial two-dimensional image with the same angle as the reference two-dimensional image is used as the initial two-dimensional image corresponding to the reference two-dimensional image.

[0102] Specifically, by performing a forward projection on the initial three-dimensional image, the reference two-dimensional images of the target object at different angles can be obtained. For each reference two-dimensional image, in the initial two-dimensional images corresponding to each angle, the initial two-dimensional image with the same angle as the reference two-dimensional image can be determined. Since the angles are the same, it can effectively ensure that the reference two-dimensional image and the initial two-dimensional image are images of the same shooting content, improving the correspondence between the reference two-dimensional image and the initial two-dimensional image and the accuracy of the subsequent obtained difference image.

[0103] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential either, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0104] Based on the same inventive concept, the embodiments of the present application also provide an image reconstruction device for angiography for implementing the image reconstruction method for angiography described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the image reconstruction device for angiography provided below can refer to the limitations on the image reconstruction method for angiography in the above text, and will not be elaborated here.

[0105] In an exemplary embodiment, as Figure 5 shown, an image reconstruction device for angiography is provided, including:

[0106] A reconstructed image acquisition module 501, configured to collect initial two-dimensional images of a target object at various angles after injecting a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0107] A forward projection module 502, configured to perform forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0108] A difference determination module 503, configured to compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0109] An image compensation module 504, configured to compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0110] In one embodiment, the difference determination module 503 is configured to:

[0111] Obtain a difference image between the reference two-dimensional image and the initial two-dimensional image.

[0112] In one embodiment, the image compensation module 504 is configured to:

[0113] Determine an image compensation parameter according to the pixel value of each pixel point in the difference image;

[0114] Compensate the initial two-dimensional image based on the image compensation parameter to obtain the compensated image.

[0115] In one embodiment, the image compensation module 504 is configured to:

[0116] For each pixel point in the initial two-dimensional image, use the pixel value of the pixel point corresponding to the pixel point in the difference image as the image compensation parameter for the pixel point in the initial two-dimensional image;

[0117] Adjust the pixel value of each pixel point in the initial two-dimensional image according to the image compensation parameter of each pixel point to obtain a compensated image.

[0118] In one embodiment, the image compensation module 504 is configured to:

[0119] Perform weighted summation on the pixel value of each pixel point in the initial two-dimensional image and the image compensation parameter according to the respective weights of the initial two-dimensional image and the difference image;

[0120] Use the weighted sum result of each pixel point in the initial two-dimensional image as the adjusted pixel value of each pixel point in the initial two-dimensional image.

[0121] In one embodiment, the difference determination module 503 is configured to:

[0122] Obtain the initial two-dimensional image corresponding to the reference two-dimensional image;

[0123] Determine the difference between the pixel value of each pixel point in the reference two-dimensional image and the pixel value of the corresponding pixel point in the initial two-dimensional image;

[0124] Obtain a difference image between the reference two-dimensional image and the initial two-dimensional image according to the differences.

[0125] In one embodiment, the difference determination module 503 is configured to:

[0126] For each reference two-dimensional image, among the initial two-dimensional images corresponding to each angle, use the initial two-dimensional image with the same angle as the reference two-dimensional image as the initial two-dimensional image corresponding to the reference two-dimensional image.

[0127] Each module in the above image reconstruction device for angiography can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0128] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes 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 medical image data of a target object. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an image reconstruction method for angiography.

[0129] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structural diagram may be as shown in Figure 7 . The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for reconstructing angiography images. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0130] Those skilled in the art can understand that Figure 6 and Figure 7 the structures shown in are only block diagrams of some structures related to the solution of the present application, and do not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0131] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0132] Collect initial two-dimensional images of the target object at various angles with contrast agent, and reconstruct the initial three-dimensional image based on each of the initial two-dimensional images;

[0133] Perform forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0134] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0135] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0136] In one embodiment, when the processor executes the computer program, it also implements the steps in the above-mentioned other embodiments.

[0137] 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 following steps are implemented:

[0138] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0139] Perform a forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0140] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0141] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0142] In one embodiment, when the computer program is executed by a processor, it also implements the steps in the above-mentioned other embodiments.

[0143] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0144] Collect initial two-dimensional images of a target object at various angles with a contrast agent, and perform reconstruction based on each of the initial two-dimensional images to obtain an initial three-dimensional image;

[0145] Perform a forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles;

[0146] Compare the reference two-dimensional image with the initial two-dimensional image to obtain an image difference;

[0147] Compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

[0148] In one embodiment, when the computer program is executed by a processor, it also implements the steps in the above-mentioned other embodiments.

[0149] 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 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 need to comply with relevant regulations.

[0150] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. 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), magnetoresistive 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. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0151] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope recorded in this specification.

[0152] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An image reconstruction method for angiography, characterized in that, The method includes: Collecting initial two-dimensional images of a target object at various angles with a contrast agent, and reconstructing an initial three-dimensional image based on each of the initial two-dimensional images; Performing a forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles; Comparing the reference two-dimensional images with the initial two-dimensional images to obtain an image difference; Compensating the initial two-dimensional images according to the image difference to obtain compensated images, and reconstructing an image based on each of the compensated images to obtain a target three-dimensional image.

2. The method according to claim 1, wherein The comparing the reference two-dimensional images with the initial two-dimensional images to obtain an image difference includes: Obtaining a difference image between the reference two-dimensional image and the initial two-dimensional image.

3. The method according to claim 2, characterized in that, The compensating the initial two-dimensional images according to the image difference to obtain compensated images includes: Determining an image compensation parameter according to the pixel value of each pixel point in the difference image; Compensating the initial two-dimensional images based on the image compensation parameter to obtain the compensated images.

4. The method according to claim 3, characterized in that, The compensating the initial two-dimensional images based on the image compensation parameter to obtain compensated images includes: For each pixel point in the initial two-dimensional image, taking the pixel value of the pixel point corresponding to the pixel point in the difference image as the image compensation parameter of the pixel point in the initial two-dimensional image; Adjusting the pixel value of each pixel point in the initial two-dimensional image according to the image compensation parameter of each pixel point to obtain a compensated image.

5. The method according to claim 4, characterized in that The adjusting the pixel value of each pixel point in the initial two-dimensional image according to the image compensation parameter of each pixel point includes: Performing a weighted sum on the pixel value of each pixel point in the initial two-dimensional image and the image compensation parameter according to the respective weights of the initial two-dimensional image and the difference image; Taking the weighted sum result of each pixel point in the initial two-dimensional image as the adjusted pixel value of each pixel point in the initial two-dimensional image.

6. The method according to claim 2, characterized in that The obtaining a difference image between the reference two-dimensional image and the initial two-dimensional image includes: Obtaining the initial two-dimensional image corresponding to the reference two-dimensional image; Determining the difference between the pixel value of each pixel point in the reference two-dimensional image and the pixel value of the corresponding pixel point in the initial two-dimensional image; Obtaining a difference image between the reference two-dimensional image and the initial two-dimensional image according to each of the differences.

7. The method according to claim 6, wherein The obtaining the initial two-dimensional image corresponding to the reference two-dimensional image includes: For each reference two-dimensional image, in the initial two-dimensional images corresponding to various angles, taking the initial two-dimensional image with the same angle as the reference two-dimensional image as the initial two-dimensional image corresponding to the reference two-dimensional image.

8. An image reconstruction device for angiography, characterized in that, The device includes: A reconstructed image acquisition module, configured to collect initial two-dimensional images of a target object at various angles after injecting a contrast agent, and reconstruct an initial three-dimensional image based on each of the initial two-dimensional images; A forward projection module, configured to perform a forward projection on the initial three-dimensional image to obtain reference two-dimensional images at various angles; A difference determination module, configured to compare the reference two-dimensional images with the initial two-dimensional images to obtain an image difference; An image compensation module, configured to compensate the initial two-dimensional image according to the image difference to obtain a compensated image, and perform image reconstruction based on each of the compensated images to obtain a target three-dimensional image.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images