Medical image reconstruction method and device, computer equipment and storage medium
By quickly obtaining the reconstruction information of the adjacent phase image using the correspondence relationship in the preset database, the problem of long motion artifact correction process in medical image reconstruction is solved, and efficient breakpoint reconstruction and artifact correction are achieved.
Patent Information
- Application Number
- CN202411052726.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-29
AI Technical Summary
The existing medical image reconstruction methods have a long reconstruction time when performing motion artifact correction, and if the process is interrupted, the entire reconstruction process will restart, resulting in inefficiency.
By determining the identification information of the adjacent phase image corresponding to the target phase image, and using the correspondence relationship in the preset database, the reconstruction information of the adjacent phase image is quickly obtained, reducing the calculation amount during the reconstruction process, and realizing breakpoint reconstruction.
It effectively reduces the reconstruction time, improves the reconstruction efficiency, avoids the phenomenon of restarting the entire reconstruction process due to process interruption, and improves the acquisition speed of artifact-corrected images.
Smart Images

Figure CN119048619A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical technology, and in particular to a medical image reconstruction method, apparatus, computer equipment and storage medium. Background Art
[0002] Common medical scan images often have artifacts. For example, if the scanned object is the heart, since the heart is beating continuously, the coronary arteries will undergo drastic changes during the heart movement, resulting in motion artifacts in the final image.
[0003] At present, in order to reduce the influence of motion artifacts, artifact correction is usually performed during the reconstruction process to obtain an artifact-corrected image. However, the process of reconstructing motion artifact correction is relatively complicated. If the reconstruction process of motion artifact correction is interrupted, the entire reconstruction process will start again.
[0004] Therefore, the current method for reconstructing an artifact-corrected image has the problem of long reconstruction time. Summary of the invention
[0005] Based on this, it is necessary to provide a medical image reconstruction method, apparatus, computer device and storage medium that can reduce the reconstruction time in order to solve the above technical problems.
[0006] In a first aspect, the present application provides a medical image reconstruction method, comprising:
[0007] Determine identification information of an adjacent time phase image corresponding to the target time phase image;
[0008] Determine first reconstruction information of adjacent time phase images according to a preset database and identification information of adjacent time phase images; the preset database includes a correspondence between identification information and reconstruction information of a plurality of time phase images;
[0009] An artifact-corrected image of the target time phase image is reconstructed based on the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0010] In one embodiment, determining first reconstruction information of adjacent phase images according to a preset database and identification information of adjacent phase images includes:
[0011] According to the identification information of the adjacent phase image, searching from a preset database whether there is corresponding reconstruction information of the adjacent phase image;
[0012] If the preset database contains reconstruction information of the adjacent phase images, the found reconstruction information is used as the first reconstruction information.
[0013] In one embodiment, the method further comprises:
[0014] If the preset database does not contain reconstruction information of the adjacent phase image, reconstructing and generating the adjacent phase image based on the scan data;
[0015] Extracting adjacent phase images to obtain first reconstruction information;
[0016] The preset database is updated according to the first reconstruction information and the identification information of the adjacent time phase images.
[0017] In one embodiment, the identification information includes an identification of scan data corresponding to adjacent phase images, a phase value of adjacent phase images, a motion cycle identification corresponding to adjacent phase images, and a storage path of reconstruction information.
[0018] In one embodiment, the reconstruction information includes position information corresponding to the coronary artery in the phase image.
[0019] In one embodiment, reconstructing an artifact-corrected image of a target phase image according to first reconstruction information of an adjacent phase image and second reconstruction information of a target phase image comprises:
[0020] Determine a motion vector field between each adjacent time phase image and the target time phase image according to first reconstruction information of the adjacent time phase image and second reconstruction information of the target time phase image;
[0021] According to the motion vector field and the corresponding segmented image corresponding to each adjacent phase image, the corrected segmented image corresponding to each segmented image is determined; each segmented image is determined according to the number of adjacent phase images and the target phase image;
[0022] An artifact-corrected image is obtained according to each segment-corrected image.
[0023] In one embodiment, the method further comprises:
[0024] Obtain the viewing angle range corresponding to the target phase image;
[0025] According to the number of adjacent phase images and the viewing angle range, the target phase image is segmented to obtain segmented images.
[0026] In a second aspect, the present application also provides a medical image reconstruction device, comprising:
[0027] A first determination module, used to determine identification information of an adjacent time phase image corresponding to a target time phase image;
[0028] A second determination module is used to determine first reconstruction information of adjacent phase images according to a preset database and identification information of adjacent phase images; the preset database includes a correspondence between identification information and reconstruction information of multiple phase images;
[0029] The reconstruction module is used to reconstruct an artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0030] 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 the processor implements the steps of any of the above methods when executing the computer program.
[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.
[0032] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.
[0033] The above-mentioned medical image reconstruction method, device, computer equipment and storage medium can determine the identification information of the adjacent phase image corresponding to the target phase image. Since the preset database includes the corresponding relationship between the identification information and reconstruction information of multiple phase images, the first reconstruction information of the adjacent phase image can be quickly determined based on the preset database and the identification information of the adjacent phase image, and there is no need to re-extract the reconstruction information of the adjacent phase image every time in the process of obtaining the artifact correction image, which not only reduces the amount of calculation, but also can realize breakpoint reconstruction. Furthermore, based on the first reconstruction information of the adjacent phase image and the second reconstruction information of the target phase image, the artifact correction image of the target phase image can be efficiently reconstructed to reduce the reconstruction time. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] FIG1 is a diagram of an application environment of a medical image reconstruction method according to an embodiment of the present application;
[0036] FIG2 is a schematic diagram of a flow chart of a medical image reconstruction method in an embodiment of the present application;
[0037] Figure 3 This is a schematic diagram of a process for determining first reconstruction information in an embodiment of the present application;
[0038] Figure 4 This is a schematic diagram of another process for determining first reconstruction information in an embodiment of the present application;
[0039] Figure 5 A schematic diagram of a process for obtaining an artifact-corrected image in an embodiment of the present application;
[0040] Figure 6 This is a schematic diagram of another process for obtaining an artifact-corrected image in an embodiment of the present application;
[0041] Figure 7 A schematic diagram of a medical image reconstruction method according to an embodiment of the present application;
[0042] Figure 8 4 is a structural block diagram of a medical image reconstruction device in an embodiment of the present application. DETAILED DESCRIPTION
[0043] 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.
[0044] In the related art, motion artifacts can be processed at two nodes. In most application scenarios, image data will be corrected for artifacts during post-processing. For example, motion artifact correction can be performed on a post-processing workstation. Taking computed tomography (CT) as an example, the user sees images before artifacts in the CT system, and then archives these images to the post-processing workstation, where image domain motion artifact correction is performed. However, the above process cannot obtain artifact-corrected images in real time, and is inefficient.
[0045] In order to improve the above problems, in some application scenarios, artifact correction is performed during the reconstruction of scan data into images. For example, reconstruction can be performed directly on a reconstruction machine, so that the user directly sees the image after motion artifact correction. However, the process of motion artifact correction during reconstruction is relatively complicated. If the reconstruction process of motion artifact correction is interrupted, the entire reconstruction process will start again. Therefore, the current method of reconstructing an artifact-corrected image has the problem of long reconstruction time.
[0046] Based on this, it is necessary to provide a medical image reconstruction method, which will be introduced below.
[0047] FIG1 is an application environment diagram of the medical image reconstruction method in an embodiment of the present application. In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG1. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. 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 relevant data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a medical image reconstruction method is implemented.
[0048] Those skilled in the art will understand that the structure shown in FIG. 1 is merely a block diagram of a partial structure related to the solution of the present application, and does 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 shown in the figure, or combine certain components, or have a different arrangement of components.
[0049] This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, 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. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.
[0050] FIG2 is a flow chart of a medical image reconstruction method in an embodiment of the present application. In an exemplary embodiment, as shown in FIG2 , a medical image reconstruction method is provided, which is described by taking the method applied to the computer device in FIG1 as an example, and includes the following S201 to S203.
[0051] S201, determining identification information of an adjacent time phase image corresponding to a target time phase image.
[0052] The medical scanning device can scan the scanned object to obtain an image of the scanned object in at least one motion cycle. Taking the scanned object as the heart as an example, the motion cycle of the heart can also be called the cardiac cycle, that is, the medical scanning device can scan and obtain an image of the heart in at least one cardiac cycle. Among them, the medical scanning device can include but is not limited to a computerized tomography (Computed Tomography, CT) device, a positron emission computed tomography (Positron Emission Computed Tomography, PET) device, a magnetic resonance imaging (Magnetic Resonance Imaging, MRI) device, a PET-CT device, and a PET-MR device.
[0053] The image in each motion cycle can include multiple phase images. Continuing with the example of the scanned object including the heart, in each cardiac cycle, the heart starts to move from the initial state, goes through multiple different states and then returns to the initial state, and each state can correspond to a specific moment in the cardiac cycle. Therefore, the image of the heart in each state is the corresponding phase image. Assuming that the cardiac cycle is T, the 0.4T phase image is an image centered on 40% of the cardiac cycle. It can be understood that the phase image can include at least one scanned image.
[0054] In order to perform artifact correction, subsequent image reconstruction is performed based on the target phase image and the adjacent phase image corresponding to the target phase image to obtain an artifact-corrected image of the target phase image. Therefore, in this embodiment, the computer device can determine the identification information of the adjacent phase image corresponding to the target phase image.
[0055] The target phase image is a phase image specified in the motion cycle, which may be an image corresponding to a phase with relatively stable motion in the motion cycle. The adjacent phase image is at least one phase image adjacent to the target phase image. The phase corresponding to the adjacent phase image may differ from the phase corresponding to the target phase image by less than a preset difference, and the preset difference may be set as required. The identification information is used to locate the corresponding adjacent phase image, which may include but is not limited to the phase value of the phase image.
[0056] For example, taking the example that the adjacent phase images include 5 phase images, two adjacent phase images can be selected at a certain interval on the left and right sides with the current phase image as the center. It can be understood that the adjacent phase images can also include other numbers of phase images, for example, 3, 7, 9, etc.
[0057] Optionally, the computer device may first determine the target phase image, and determine the identification information of the adjacent phase images according to the identification information of the target phase image. Continuing with the example of five phase images, assuming that the computer device determines that the target phase image is phase image A corresponding to 0.4T in the first cardiac cycle, the adjacent phase images may include phase image B corresponding to 0.3T, phase image C corresponding to 0.35T, phase image D corresponding to 0.45T, and phase image E corresponding to 0.5T.
[0058] In an exemplary embodiment, the identification information may include an identification of scan data corresponding to adjacent phase images, a phase value of adjacent phase images, a motion cycle identification corresponding to adjacent phase images, and a storage path of reconstruction information.
[0059] Exemplarily, the identification of the scan data may be an ID (Identity document) of the scan data to indicate unique scan data. The phase value of the adjacent phase image is used to indicate the phase of the adjacent phase image in a certain motion cycle, for example, the phase value is 0.4T. The motion cycle identification corresponding to the adjacent phase image includes but is not limited to R tag information to indicate a unique motion cycle. For example, R tag If the information is R1 and R2, it means that the adjacent phase image is the phase image corresponding to the first cardiac cycle. The reconstruction information is used to reconstruct an artifact-corrected image. Taking the scan object as a heart as an example, the reconstruction information may include coronary artery information, and the coronary artery information includes the position information corresponding to the coronary artery in the phase image. The storage path of the reconstruction information is used to indicate the storage location of the reconstruction information.
[0060] Since the identification information includes the identification of the scan data corresponding to the adjacent phase images, the phase value of the adjacent phase images, the motion cycle identification corresponding to the adjacent phase images and the storage path of the reconstruction information, the reconstruction information uniquely corresponding to the identification information can be accurately determined based on the identification information.
[0061] In an exemplary embodiment, the identification information may also include at least one of the image layer thickness, image layer interval, image reconstruction position and image number of the adjacent phase image. The image layer thickness is used to indicate the thickness of the adjacent phase image, the image layer interval is used to indicate the interval between the adjacent phase image and the adjacent phase image, and the image reconstruction position is used to indicate the position where the center of the adjacent phase image is located in the entire adjacent phase image. The number of images is used to indicate the number of scanned images included in the adjacent phase image. Optionally, the number of images of each adjacent phase image is equal.
[0062] S202, determining first reconstruction information of adjacent time phase images according to a preset database and identification information of adjacent time phase images; the preset database includes a correspondence between identification information of multiple time phase images and reconstruction information.
[0063] In this embodiment, the preset database includes the correspondence between the identification information and the reconstruction information of multiple phase images. The preset database can be stored in a computer device or in other devices that can communicate with the computer device. This embodiment does not limit the implementation method of the preset database.
[0064] Continuing with the example that the scanned object is a heart and the reconstruction information includes coronary artery information, the coronary artery information can indicate the position of the coronary artery in the phase image. In an exemplary embodiment, optionally, the coronary artery information includes position information corresponding to the coronary artery in the phase image. For example, the coronary artery information of the phase image includes the three-dimensional coordinates of the coronary artery in the phase image. Further optionally, the coronary artery information can be in the form of a sparse matrix.
[0065] Since the coronary artery information includes the position information corresponding to the coronary artery in the phase image, and the data of the coronary artery in the phase image is relatively small, for example, the number of pixels of the coronary artery is between 200 and 2000, that is, the coronary artery information accounts for one millionth to one hundred thousandth of the overall image information of the phase image. Therefore, storing the coronary artery information in adjacent phase images does not increase the amount of data too much.
[0066] Then, the computer device determines the first reconstruction information of the adjacent phase image according to the preset database and the identification information of the adjacent phase image. For example, the computer device may search the preset database for the reconstruction information B corresponding to the identification information B as the first reconstruction information of the phase image B through the identification information B of the phase image B. In one embodiment, further optionally, the computer device may obtain the reconstruction information B from the storage path of the reconstruction information B according to the storage path of the reconstruction information B in the identification information B when the identification information B is searched in the preset database.
[0067] It is understandable that the computer device can calculate the first reconstruction information of each adjacent phase image. In some embodiments, the computer device can determine the first reconstruction information of each adjacent phase image according to the phase sequence of the target phase image and the adjacent phase images. Continuing with the above example, the computer device can determine reconstruction information B, reconstruction information C, reconstruction information D, and reconstruction information E in sequence.
[0068] S203, reconstructing an artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0069] In this embodiment, the computer device can obtain the second reconstruction information of the target phase image. The second reconstruction information can be reconstructed information. Exemplarily, the computer device can reconstruct the target phase image based on the scan data of the target phase image, and extract the center line of the target phase image to obtain the second reconstruction information. It can be understood that the second reconstruction information of the target phase image is also the reconstruction information corresponding to the target phase image, such as the coronary artery information of the target phase image.
[0070] Continuing with the above example, the first reconstruction information of the adjacent phase image includes reconstruction information B corresponding to phase image B, reconstruction information C corresponding to phase image C, reconstruction information D corresponding to phase image D, and reconstruction information E corresponding to phase image E. The second reconstruction information of the target phase image includes reconstruction information A corresponding to phase image A.
[0071] Afterwards, the computer device can reconstruct the artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0072] Optionally, the computer device may obtain an artifact-corrected image based on the first reconstruction information of each adjacent phase image and the second reconstruction information of the target phase image. For example, the computer device may perform correction processing on phase image A based on reconstruction information A to reconstruction information E to obtain an artifact-corrected image of phase image A.
[0073] In one embodiment, the computer device may register the first reconstruction information corresponding to each adjacent phase image with the second reconstruction information corresponding to the target phase image to obtain a matching result. For example, the computer device may register reconstruction information A and reconstruction information B to determine a matching result 1 between phase image A and phase image B; register reconstruction information A and reconstruction information C to determine a matching result 2 between phase image A and phase image C; register reconstruction information A and reconstruction information D to determine a matching result 3 between phase image A and phase image D; and register reconstruction information A and reconstruction information E to determine a matching result 4 between phase image A and phase image E. Afterwards, the computer device determines a correction matrix according to each matching result, and then determines an artifact-corrected image according to the correction matrix and the target phase image. For example, the computer device may apply the correction matrix to the segmented image of the target phase image to obtain the corrected segmented image, and then sum the segmented images to obtain the artifact-corrected image.
[0074] In the related art, the process of reconstructing motion artifact correction is relatively complicated. If the reconstruction process of motion artifact correction is interrupted, the entire reconstruction process will start over. For example, in the process of obtaining an artifact correction image based on multiple phase images, the related art will first reconstruct each phase image, and extract each phase image in turn. After each phase image is extracted, the subsequent correction steps will be performed in turn according to the extraction results of the phase image. Assuming that a higher priority reconstruction task appears during the extraction of the last phase image, the reconstruction process of the artifact correction image will be interrupted. After the higher priority reconstruction task is completed, each phase image will be reconstructed and extracted in turn, resulting in a long reconstruction time. In the above-mentioned medical image reconstruction method, the identification information of the adjacent phase image corresponding to the target phase image can be determined. Since the preset database includes the corresponding relationship between the identification information and the reconstruction information of multiple phase images, the first reconstruction information of the adjacent phase image can be quickly determined based on the preset database and the identification information of the adjacent phase image, and it is not necessary to re-extract the reconstruction information of the adjacent phase image every time in the process of obtaining the artifact correction image, which not only reduces the amount of calculation, but also can realize breakpoint reconstruction. Furthermore, based on the first reconstruction information of the adjacent phase image and the second reconstruction information of the target phase image, the artifact correction image of the target phase image can be efficiently reconstructed to reduce the reconstruction time.
[0075] Figure 3 FIG. 1 is a flow chart of determining first reconstruction information in an embodiment of the present application. In an exemplary embodiment, as shown in FIG. Figure 3 As shown, S202 includes S301 to S302.
[0076] S301 : searching a preset database for corresponding reconstruction information of an image in an adjacent time phase according to identification information of the image in the adjacent time phase.
[0077] Continuing with the example of adjacent phase images including phase image B, after the computer device determines the identification information B, it can search from the preset database based on the identification information B whether there is corresponding reconstruction information for phase image B, that is, search whether there is reconstruction information B corresponding to the identification information B in the preset database.
[0078] S302: If reconstruction information of images of adjacent time phases exists in the preset database, the found reconstruction information is used as first reconstruction information.
[0079] If the preset database contains reconstruction information B, that is, the preset database contains reconstruction information of the phase image B, the computer device will use the found reconstruction information B as the first reconstruction information of the phase image B.
[0080] In the above embodiment, since it is possible to search from a preset database whether there is corresponding reconstruction information of an adjacent phase image based on the identification information of the adjacent phase image, and if the reconstruction information of the adjacent phase image exists in the preset database, the reconstruction information found is directly used as the first reconstruction information. Therefore, even if the process of reconstructing the artifact-corrected image is interrupted, the reconstruction information of the adjacent phase image can be quickly determined, which not only reduces the amount of calculation, but also facilitates the realization of breakpoint reconstruction of the artifact-corrected image.
[0081] Figure 4 FIG. 1 is another flow chart of determining first reconstruction information in an embodiment of the present application. In an exemplary embodiment, Figure 4 As shown, the above medical image reconstruction method also includes S401 to S402.
[0082] S401: If reconstruction information of adjacent phase images does not exist in the preset database, reconstruct adjacent phase images based on scan data.
[0083] In this embodiment, the scanning data of the adjacent phase images may be data stored in advance in the computer device, or may be data acquired by the computer device from a medical scanning device when the adjacent phase images are needed, and this embodiment is not limited thereto.
[0084] Continuing with the example that the adjacent phase images include phase image B, if the reconstruction information B does not exist in the preset database, the computer device will reconstruct and generate phase image B based on the scan data of phase image B.
[0085] That is to say, the computer device will reconstruct the adjacent phase image based on the scan data only when it fails to find the reconstruction information of the adjacent phase image in the preset data.
[0086] S402: extract adjacent time phase images to obtain first reconstruction information.
[0087] Furthermore, after obtaining the adjacent time phase image, the computer device extracts the adjacent time phase image to obtain first reconstruction information of the adjacent time phase image.
[0088] Exemplarily, the computer device extracts the center line of the phase image B to obtain the reconstruction information B of the phase image B.
[0089] S403: Update a preset database according to the first reconstruction information and identification information of the adjacent time phase images.
[0090] Furthermore, after obtaining the first reconstruction information of the adjacent phase image, the computer device may update the preset database according to the identification information and reconstruction information of the adjacent phase image. For example, the computer device may store the corresponding relationship between the identification information of the adjacent phase image and the first reconstruction information.
[0091] Continuing with the above example, when the reconstruction information B is found in the preset database, the computer device obtains the phase image B, and extracts the phase image B to obtain the reconstruction information B. Thereafter, the computer device can store the identification information B, the reconstruction information B, and the correspondence between the identification information B and the reconstruction information B in the preset database.
[0092] In the above embodiment, when there is no reconstruction information of the adjacent phase image in the preset database, the adjacent phase image is reconstructed based on the scan data, and the adjacent phase image is extracted to obtain the first reconstruction information, and the preset database is updated according to the first reconstruction information and the identification information of the adjacent phase image. Therefore, when the reconstruction of the artifact correction image is interrupted multiple times, the subsequent reconstruction process of the reconstruction of the artifact correction image can use the reconstruction information generated in the last interrupted reconstruction process, and there is no need to extract the reconstruction information again, which reduces the steps and calculation amount of the entire reconstruction and reduces the time of the entire reconstruction. In addition, the reconstruction performance is also improved by multiplexing the reconstruction information.
[0093] Figure 5 FIG. 1 is a flow chart of obtaining an artifact-corrected image in an embodiment of the present application. In an exemplary embodiment, Figure 5 As shown, S203 also includes S501 to S503.
[0094] S501 : Determine a motion vector field between each adjacent time phase image and the target time phase image according to first reconstruction information of adjacent time phase images and second reconstruction information of the target time phase image.
[0095] In this embodiment, optionally, for each adjacent phase image, the computer device may register the second reconstruction information of the target phase image with the first reconstruction information of the adjacent phase image to determine the motion vector field between each adjacent phase image and the target phase image.
[0096] Continuing with the example where the target phase image is phase image A and the adjacent phase images are adjacent phase image B, phase image C, phase image D and phase image E, the computer device will determine the motion vector field 1 between phase image A and phase image B based on the reconstruction information A and the reconstruction information B, determine the motion vector field 2 between phase image A and phase image C based on the reconstruction information A and the reconstruction information C, determine the motion vector field 3 between phase image A and phase image D based on the reconstruction information A and the reconstruction information D, and determine the motion vector field 4 between phase image A and phase image E based on the reconstruction information A and the reconstruction information E.
[0097] S502, determining a corrected segmented image corresponding to each segmented image according to the motion vector field and the corresponding segmented image corresponding to each adjacent phase image; each segmented image is determined according to the number of adjacent phase images and the target phase image.
[0098] In this embodiment, the segmented images are determined according to the number of adjacent phase images and the target phase image. Optionally, the computer device can divide the target phase image equally based on the number of adjacent phase images to obtain each segmented image. For example, continuing the above example, the adjacent phase images are phase image B, phase image C, phase image D, and phase image E, and the number of adjacent phase images is 4, then the computer device can divide the target phase image, that is, phase image A, equally to obtain 4 segmented images.
[0099] Then, the computer device can determine the corrected segmented image corresponding to each segmented image according to the motion vector field and segmented image corresponding to each adjacent phase image. Optionally, the computer device can apply the motion vector field corresponding to the adjacent phase image to the segmented image corresponding to the adjacent phase image to obtain the corrected segmented image corresponding to the segmented image.
[0100] Exemplarily, assuming that the segmented images include segmented image 1 to segmented image 4, segmented image 1 corresponds to phase image B, segmented image 2 corresponds to phase image C, segmented image 3 corresponds to phase image D, and segmented image 4 corresponds to phase image E, the computer device can apply motion vector field 1 to segmented image 1 to obtain corrected segmented image 1 corresponding to segmented image 1, and apply motion vector field 2 to segmented image 2 to obtain corrected segmented image 2 corresponding to segmented image 2, and so on, to obtain corrected segmented image 1 to corrected segmented image 4.
[0101] S503: Obtain an artifact-corrected image according to each segment-corrected image.
[0102] In this embodiment, the computer device may optionally combine the segmented corrected images to obtain an artifact corrected image. For example, the computer device may combine corrected segmented images 1 to 4 to obtain an artifact corrected image corresponding to phase image A.
[0103] In the above embodiment, since the motion vector field between each adjacent phase image and the target phase image can be determined based on the first reconstruction information of the adjacent phase image and the second reconstruction information of the target phase image, and the corrected segmented image corresponding to each segmented image can be determined based on the motion vector field and the segmented image corresponding to each adjacent phase image, and each segmented image is determined based on the number of adjacent phase images and the target phase image, an artifact corrected image can be efficiently obtained based on each segmented corrected image.
[0104] Figure 6 FIG. 1 is another flow chart of obtaining an artifact-corrected image in an embodiment of the present application. In an exemplary embodiment, Figure 6 As shown, the above medical image reconstruction method also includes S601 to S602.
[0105] S601, obtaining a viewing angle range corresponding to a target time phase image.
[0106] In this embodiment, the viewing angle range is also the viewing angle range of the medical scanning device for scanning, which is generally within 0° to 360°. For example, the viewing angle range corresponding to the phase image A is 360°.
[0107] S602, segmenting the target time phase image according to the number of adjacent time phase images and the viewing angle range to obtain segmented images.
[0108] In this embodiment, optionally, the computer device can determine the sub-viewing angle range corresponding to each segmented image based on the number and viewing angle range of adjacent phase images, and segment the target phase image according to the sub-viewing angle range corresponding to each segmented image to obtain each segmented image.
[0109] Continuing with the above example, if the number of adjacent phase images is 4, the computer device may use the image with a viewing angle range of 0°~90° in phase image A as segmented image 1, the image with a viewing angle range of 90°~180° in phase image A as segmented image 2, the image with a viewing angle range of 180°~270° in phase image A as segmented image 3, and the image with a viewing angle range of 270°~360° in phase image A as segmented image 4.
[0110] In the above embodiment, since the viewing angle range corresponding to the target phase image can be obtained, according to the number and viewing angle range of adjacent phase images, each segmented image can be obtained after segmenting the target phase image.
[0111] Figure 7 FIG. 1 is a schematic diagram of a medical image reconstruction method according to an embodiment of the present application. Figure 7 As shown, the computer device can execute the medical image reconstruction method according to the following process.
[0112] S701, determining identification information of an adjacent time phase image corresponding to a target time phase image.
[0113] S702: According to the identification information of the adjacent time phase image, searching from a preset database whether there is corresponding reconstruction information of the adjacent time phase image.
[0114] S703: If reconstruction information of images of adjacent time phases exists in the preset database, the found reconstruction information is used as first reconstruction information.
[0115] S704: If the reconstruction information of the adjacent phase image does not exist in the preset database, the adjacent phase image is reconstructed and generated based on the scan data, and the adjacent phase image is extracted to obtain first reconstruction information.
[0116] S705: Update a preset database according to the first reconstruction information and identification information of adjacent time phase images.
[0117] S706 , determining a motion vector field between each adjacent time phase image and the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0118] S707, obtaining a viewing angle range corresponding to the target time phase image.
[0119] S708, segmenting the target time phase image according to the number of adjacent time phase images and the viewing angle range to obtain segmented images.
[0120] S709 , determining a corrected segmented image corresponding to each segmented image according to the motion vector field and the corresponding segmented image corresponding to each adjacent time phase image.
[0121] S710, obtaining an artifact-corrected image according to each segment-corrected image.
[0122] The steps of S701~S710 can refer to the above-mentioned embodiment and will not be described again here. It can be seen that in view of the problem that the reconstruction of motion artifact correction in the related art is interrupted, resulting in a long reconstruction time. Since the operation time of each step in obtaining the artifact correction image is analyzed, it is determined that the main time consumption is in the extraction of the coronary centerline and the subsequent steps. Therefore, this embodiment will obtain the artifact correction image by storing and reusing the reconstruction information obtained by the previous reconstruction. In this way, not only can the reconstruction time be reduced when the same reconstruction is interrupted, but also the overall calculation amount can be reduced by reusing different reconstruction parameters, thereby reducing the overall reconstruction time and improving the reconstruction performance.
[0123] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.
[0124] Based on the same inventive concept, the embodiment of the present application also provides a medical image reconstruction device for implementing the medical image reconstruction method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more medical image reconstruction device embodiments provided below can refer to the limitations on the medical image reconstruction method above, and will not be repeated here.
[0125] Figure 8 is a structural block diagram of a medical image reconstruction device in an embodiment of the present application. In an exemplary embodiment, Figure 8 As shown, a medical image reconstruction device 800 is provided, comprising: a first determination module 801, a second determination module 802 and a reconstruction module 803, wherein:
[0126] The first determining module 801 is used to determine identification information of an adjacent time phase image corresponding to a target time phase image.
[0127] The second determination module 802 is used to determine first reconstruction information of adjacent phase images according to the preset database 804 and identification information of adjacent phase images; the preset database 804 includes the correspondence between identification information and reconstruction information of multiple phase images.
[0128] The reconstruction module 803 is used to reconstruct an artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0129] In the related art, the process of reconstructing motion artifact correction is relatively complicated. If the reconstruction process of motion artifact correction is interrupted, the entire reconstruction process will start over. For example, in the process of obtaining an artifact correction image based on multiple phase images, the related art will first reconstruct each phase image, and extract each phase image in turn. After each phase image is extracted, the subsequent correction steps will be performed in turn according to the extraction results of the phase image. Assuming that a higher priority reconstruction task appears during the extraction of the last phase image, the reconstruction process of the artifact correction image will be interrupted. After the higher priority reconstruction task is completed, each phase image will be reconstructed and extracted in turn, resulting in a long reconstruction time. In the above-mentioned medical image reconstruction device, the identification information of the adjacent phase image corresponding to the target phase image can be determined. Since the preset database includes the corresponding relationship between the identification information and the reconstruction information of multiple phase images, the first reconstruction information of the adjacent phase image can be quickly determined based on the preset database and the identification information of the adjacent phase image, and it is not necessary to re-extract the reconstruction information of the adjacent phase image every time in the process of obtaining the artifact correction image, which not only reduces the amount of calculation, but also can realize breakpoint reconstruction. Furthermore, based on the first reconstruction information of the adjacent phase image and the second reconstruction information of the target phase image, the artifact correction image of the target phase image can be efficiently reconstructed to reduce the reconstruction time.
[0130] Optionally, the second determining module 802 includes:
[0131] The searching unit is used to search the preset database 804 for corresponding reconstruction information of the adjacent time phase images according to the identification information of the adjacent time phase images.
[0132] The first determining unit is configured to use the found reconstruction information as the first reconstruction information if reconstruction information of an image in an adjacent time phase exists in the preset database 804 .
[0133] Optionally, the medical image reconstruction device 800 further includes:
[0134] The generating module is configured to reconstruct and generate the adjacent phase image based on the scan data if the reconstruction information of the adjacent phase image does not exist in the preset database 804 .
[0135] The extraction module is used to extract the adjacent phase images to obtain the first reconstruction information.
[0136] An updating module is used to update the preset database 804 according to the first reconstruction information and the identification information of the adjacent phase image.
[0137] Optionally, the identification information includes an identification of scan data corresponding to adjacent phase images, a phase value of adjacent phase images, a motion cycle identification corresponding to adjacent phase images, and a storage path of the reconstruction information.
[0138] Optionally, the reconstruction information includes position information corresponding to the coronary artery in the phase image.
[0139] Optionally, the reconstruction module 803 includes:
[0140] The second determining unit is used to determine the motion vector field between each adjacent time phase image and the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0141] The third determination unit is used to determine the corrected segmented image corresponding to each segmented image according to the motion vector field and the segmented image corresponding to each adjacent phase image; each segmented image is determined according to the number of adjacent phase images and the target phase image.
[0142] The fourth determining unit is used to obtain an artifact-corrected image according to each segment-corrected image.
[0143] Optionally, the medical image reconstruction device 800 further includes:
[0144] An acquisition module, used to acquire the viewing angle range corresponding to the target phase image;
[0145] The processing module is used to perform segmentation processing on the target time phase image according to the number of the adjacent time phase images and the viewing angle range to obtain each of the segmented images.
[0146] It should be noted that the above example uses the preset database 804 being located outside the medical image reconstruction device 800 , and the preset database 804 may also be located inside the medical image reconstruction device 800 , and the present embodiment is not limited thereto.
[0147] Each module in the above-mentioned medical image reconstruction device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0148] In one 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:
[0149] Determine identification information of an adjacent time phase image corresponding to the target time phase image;
[0150] Determine first reconstruction information of adjacent time phase images according to a preset database and identification information of adjacent time phase images; the preset database includes a correspondence between identification information and reconstruction information of a plurality of time phase images;
[0151] An artifact-corrected image of the target time phase image is reconstructed based on the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0152] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0153] According to the identification information of the adjacent phase image, the preset database is searched to see whether there is corresponding reconstruction information of the adjacent phase image; if the preset database contains reconstruction information of the adjacent phase image, the found reconstruction information is used as the first reconstruction information.
[0154] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0155] If the preset database does not contain reconstruction information of the adjacent phase image, the adjacent phase image is reconstructed based on the scan data; the adjacent phase image is extracted to obtain first reconstruction information; and the preset database is updated according to the first reconstruction information and identification information of the adjacent phase image.
[0156] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0157] According to the first reconstruction information of the adjacent phase images and the second reconstruction information of the target phase image, the motion vector field between each adjacent phase image and the target phase image is determined; according to the motion vector field and the segmented image corresponding to each adjacent phase image, the corrected segmented image corresponding to each segmented image is determined; each segmented image is determined according to the number of adjacent phase images and the target phase image; and the artifact corrected image is obtained according to each segmented corrected image.
[0158] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:
[0159] The viewing angle range corresponding to the target phase image is obtained; and the target phase image is segmented according to the number and viewing angle range of adjacent phase images to obtain segmented images.
[0160] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
[0161] Determine identification information of an adjacent time phase image corresponding to the target time phase image;
[0162] Determine first reconstruction information of adjacent time phase images according to a preset database and identification information of adjacent time phase images; the preset database includes a correspondence between identification information and reconstruction information of a plurality of time phase images;
[0163] An artifact-corrected image of the target time phase image is reconstructed based on the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0164] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0165] According to the identification information of the adjacent phase image, the preset database is searched to see whether there is corresponding reconstruction information of the adjacent phase image; if the preset database contains reconstruction information of the adjacent phase image, the found reconstruction information is used as the first reconstruction information.
[0166] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0167] If the preset database does not contain reconstruction information of the adjacent phase image, the adjacent phase image is reconstructed based on the scan data; the adjacent phase image is extracted to obtain first reconstruction information; and the preset database is updated according to the first reconstruction information and identification information of the adjacent phase image.
[0168] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0169] According to the first reconstruction information of the adjacent phase images and the second reconstruction information of the target phase image, the motion vector field between each adjacent phase image and the target phase image is determined; according to the motion vector field and the segmented image corresponding to each adjacent phase image, the corrected segmented image corresponding to each segmented image is determined; each segmented image is determined according to the number of adjacent phase images and the target phase image; and the artifact corrected image is obtained according to each segmented corrected image.
[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0171] The viewing angle range corresponding to the target phase image is obtained; and the target phase image is segmented according to the number and viewing angle range of adjacent phase images to obtain segmented images.
[0172] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:
[0173] Determine identification information of an adjacent time phase image corresponding to the target time phase image;
[0174] Determine first reconstruction information of adjacent time phase images according to a preset database and identification information of adjacent time phase images; the preset database includes a correspondence between identification information and reconstruction information of a plurality of time phase images;
[0175] An artifact-corrected image of the target time phase image is reconstructed based on the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
[0176] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0177] According to the identification information of the adjacent phase image, the preset database is searched to see whether there is corresponding reconstruction information of the adjacent phase image; if the preset database contains reconstruction information of the adjacent phase image, the found reconstruction information is used as the first reconstruction information.
[0178] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0179] If the preset database does not contain reconstruction information of the adjacent phase image, the adjacent phase image is reconstructed based on the scan data; the adjacent phase image is extracted to obtain first reconstruction information; and the preset database is updated according to the first reconstruction information and identification information of the adjacent phase image.
[0180] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0181] According to the first reconstruction information of the adjacent phase images and the second reconstruction information of the target phase image, the motion vector field between each adjacent phase image and the target phase image is determined; according to the motion vector field and the segmented image corresponding to each adjacent phase image, the corrected segmented image corresponding to each segmented image is determined; each segmented image is determined according to the number of adjacent phase images and the target phase image; and the artifact corrected image is obtained according to each segmented corrected image.
[0182] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:
[0183] The viewing angle range corresponding to the target phase image is obtained; and the target phase image is segmented according to the number and viewing angle range of adjacent phase images to obtain segmented images.
[0184] 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 this application can include at least one of non-volatile 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), 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. 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, etc., but are not limited to this.
[0185] 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 specification.
[0186] The above-described 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 medical image reconstruction method, characterized in that: The method comprises: Determine identification information of an adjacent time phase image corresponding to the target time phase image; Determine first reconstruction information of the adjacent time phase image according to a preset database and identification information of the adjacent time phase image; the preset database includes a correspondence between identification information and reconstruction information of a plurality of time phase images; An artifact-corrected image of the target time phase image is reconstructed based on the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
2. The method according to claim 1, characterized in that The determining, according to the identification information of the adjacent time phase images and a preset database, first reconstruction information of the adjacent time phase images comprises: According to the identification information of the adjacent time phase image, searching the preset database for corresponding reconstruction information of the adjacent time phase image; If the preset database contains reconstruction information of the adjacent phase images, the found reconstruction information is used as the first reconstruction information.
3. The method according to claim 2, characterized in that The method further comprises: If the preset database does not contain reconstruction information of the adjacent phase image, reconstructing and generating the adjacent phase image based on the scan data; Extracting the adjacent phase images to obtain the first reconstruction information; The preset database is updated according to the first reconstruction information and the identification information of the adjacent phase images.
4. The method according to any one of claims 1 to 3, characterized in that: The identification information includes an identification of the scan data corresponding to the adjacent phase image, a phase value of the adjacent phase image, a motion cycle identification corresponding to the adjacent phase image, and a storage path of the reconstruction information.
5. The method according to any one of claims 1 to 3, characterized in that: The step of reconstructing an artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image comprises: Determine a motion vector field between each of the adjacent time phase images and the target time phase image according to the first reconstruction information of the adjacent time phase images and the second reconstruction information of the target time phase image; Determine the corrected segmented image corresponding to each of the segmented images according to the motion vector field and the corresponding segmented image corresponding to each of the adjacent phase images; each of the segmented images is determined according to the number of the adjacent phase images and the target phase image; The artifact-corrected image is obtained according to each of the segmented corrected images.
6. The method according to claim 5, characterized in that The method further comprises: Acquire the viewing angle range corresponding to the target phase image; According to the number of the adjacent time phase images and the viewing angle range, the target time phase image is segmented to obtain the segmented images.
7. A medical image reconstruction device, characterized in that: The device comprises: A first determination module, used to determine identification information of an adjacent time phase image corresponding to a target time phase image; A second determination module is used to determine the first reconstruction information of the adjacent time phase image according to a preset database and the identification information of the adjacent time phase image; the preset database includes the correspondence between the identification information and the reconstruction information of a plurality of time phase images; A reconstruction module is used to reconstruct an artifact-corrected image of the target time phase image according to the first reconstruction information of the adjacent time phase image and the second reconstruction information of the target time phase image.
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 steps of the method according to any one of claims 1 to 6 are implemented.
9. 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.
10. A computer program product, comprising a computer program, 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.
