Image registration method, device, equipment, storage medium and computer program product

Abstract

The present application relates to an image registration method, device, equipment, storage medium and computer program product, the method comprising: acquiring a first dynamic PET image of an imaging object, at least two MR images and PET images corresponding to each MR image; for each MR image, registering the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image, obtaining a first registered PET image corresponding to the corresponding MR image; registering the first dynamic PET image with the second registered PET image, obtaining a target dynamic PET image. In this way, by combining the information of the MR structural modality corresponding to multiple groups of scanning sequences with the information of PET, the effect of dynamic PET image frame registration is improved, the actual image of the to-be-detected part of the imaging object is accurately reflected, and the main displacement and deformation of the imaging object in the reconstruction of each long-time dynamic PET image is corrected based on multiple MR sequences.

Description

Technical Field

[0001] The present application relates to the field of medical image technology, and in particular to an image registration method, apparatus, device, storage medium and computer program product. Background Art

[0002] With the development of medical technology, positron emission tomography (PET) imaging is widely used in tumor staging and grading, preoperative evaluation, prognosis evaluation, etc. Dynamic PET imaging requires continuous data collection of the target object for a certain period of time, but it is difficult for patients undergoing dynamic PET imaging to keep their bodies completely fixed for a long time, which will cause displacement between data collected at different time points. Therefore, before performing dynamic parameter analysis on PET dynamic data, it is generally necessary to perform data registration processing to improve the accuracy of dynamic parameter quantification.

[0003] The related technology is to register static PET images through MR images acquired in a single sequence. However, the registration method for static PET images cannot be applied to dynamic PET image registration. Summary of the invention

[0004] Based on this, it is necessary to provide an image registration method, device, equipment, storage medium and computer program product that can be applicable to dynamic PET image registration in order to solve the above technical problems.

[0005] In a first aspect, the present application provides an image registration method. The method comprises:

[0006] Acquire a first dynamic PET image of an imaging object, at least two MR images, and PET images corresponding to each MR image;

[0007] For each MR image, registering the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image, to obtain a first registered PET image corresponding to the corresponding MR image;

[0008] The first dynamic PET image is registered with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

[0009] In one embodiment, acquiring a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each MR image includes:

[0010] acquiring an initial MR image of an imaging subject;

[0011] Positioning the imaging object according to the initial MR image to obtain a positioning result;

[0012] Based on the positioning result, a PET scan and an MR scan are performed on the imaging object to obtain a first dynamic PET image, at least two MR images, and PET images corresponding to each MR image.

[0013] In one embodiment, a PET scan and an MR scan are performed on the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images, and a PET image corresponding to each MR image, including:

[0014] Performing a PET scan and an MR scan on the imaging object based on the positioning result, acquiring PET scan data and at least two MR scan data sequences;

[0015] Reconstructing the PET scan data to obtain a first dynamic PET image;

[0016] Reconstructing each MR scan data sequence respectively to obtain at least two MR images;

[0017] According to the acquisition time of each MR scan data sequence, at least two PET scan data sequences corresponding to the at least two MR scan data sequences are determined from the PET scan data, and each PET scan data sequence is reconstructed to obtain a PET image corresponding to each MR image.

[0018] In one embodiment, the acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold.

[0019] In one embodiment, the image registration method further includes:

[0020] The first acquired MR image is used as the reference image, and the deformation field information of other MR images is obtained using a preset registration algorithm.

[0021] In one of the embodiments, the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0022] In a second aspect, the present application also provides an image registration device. The device comprises:

[0023] An acquisition module, configured to acquire a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each MR image;

[0024] A first registration module is used for registering the PET image corresponding to each MR image according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image;

[0025] The second registration module is used to register the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

[0026] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method in any one of the embodiments of the first and second aspects are implemented.

[0027] 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 the method in any one of the embodiments of the first and second aspects when executed by a processor.

[0028] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the embodiments of the first and second aspects are implemented.

[0029] The above-mentioned image registration method, device, equipment, storage medium and computer program product obtain a first dynamic PET image of the imaging object, at least two MR images and PET images corresponding to each MR image; for each MR image, the PET image corresponding to the corresponding MR image is registered according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image; the first dynamic PET image is registered with the second registered PET image to obtain a target dynamic PET image; wherein the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image. In this way, the dynamic PET image registration effect is improved by combining the information of MR structural modalities corresponding to multiple sets of scanning sequences with the information of PET. There is no need to take single-frame PET images at multiple discontinuous time points. The actual situation image of the target part to be detected of the imaging object can be more accurately reflected. The main displacement and deformation of the imaging object in the dynamic PET image reconstruction with longer time can be corrected based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, providing a precise basis for subsequent analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0031] Figure 2 A diagram of an application environment of an image registration method in an embodiment;

[0032] Figure 2-a is a schematic diagram of image registration in one embodiment;

[0033] Figure 3 is a schematic diagram of a flow chart of an image registration method in one embodiment;

[0034] Figure 4 is a schematic flow chart of an image registration method in another embodiment;

[0035] Figure 4-a A scanning schematic diagram in an embodiment;

[0036] Figure 5 is a schematic flow chart of an image registration method in another embodiment;

[0037] Figure 6 is a schematic flow chart of an image registration method in another embodiment;

[0038] Figure 7 is a structural block diagram of an image registration device in one embodiment;

[0039] Figure 8 FIG. 4 is a structural block diagram of an image registration device in one embodiment. DETAILED DESCRIPTION

[0040] 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.

[0041] In the past few decades, PET imaging has been widely used in tumor staging and grading, preoperative evaluation, and prognosis evaluation. In traditional technology, a single-frame static image is usually taken of the imaging object. However, a single-frame static image cannot explain the biochemical process of the tracer. Dynamic PET imaging has gradually attracted widespread attention from the clinical and scientific research communities, providing a scientific basis for clinical revelation of pathological mechanisms. In dynamic PET imaging technology, limited by the time characteristics of tracer accumulation in the imaging object, dynamic PET imaging requires continuous data collection for a certain period of time, among which the collection time of many common tracers is up to one hour. For patients undergoing dynamic PET imaging, it is difficult to keep the body completely fixed for a long time, which will cause displacement between data collected at different time points. Therefore, before performing dynamic parameter analysis on PET dynamic data, it is generally necessary to perform registration processing on the PET dynamic image to improve the accuracy of dynamic parameter quantification.

[0042] However, the current PET imaging technology is to take corresponding static PET images of the imaging object at multiple time points, and take a single sequence of MR images at the same time as each frame of the static PET image, and use the single sequence of MR images as a reference to align the corresponding static PET images. However, as the tracer accumulates, the contrast of the PET image will change significantly. At the same time, the PET image lacks structural information and obvious image feature points, so the alignment effect of the existing method is unsatisfactory.

[0043] Based on this, the present application provides an image registration method for PET dynamic image registration, which can be applied to Figure 1The computer device shown. The computer device includes a processor and a memory connected by a system bus, and a computer program is stored in the memory. When the processor executes the computer program, the steps of the following method embodiment can be executed. Optionally, the computer device may also include a network interface, a display screen and an input device. 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, and 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 network interface of the computer device is used to communicate with an external terminal through a network connection. Optionally, the computer device can be a server, a personal computer, a personal digital assistant, or other terminal devices, such as a tablet computer, a mobile phone, etc., or a cloud or remote server. The embodiment of the present application does not limit the specific form of the computer device.

[0044] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0045] It should be noted that the imaging method provided in the embodiment of the present application may be executed by a computer device having an integrated medical image hybrid imaging system. The integrated medical image hybrid imaging system may include PET-MR (Magnetic Resonance Imaging), PET (Positron Emission Computed Tomography)-CT (Computed Tomography), etc., which are not limited here. The computer device may be implemented as part or all of the computer device through software, hardware, or a combination of software and hardware. In the following method embodiments, the execution subject is a computer device as an example for explanation.

[0046] The image registration method provided in this embodiment is used for a computer device with an integrated medical image hybrid imaging system to synchronously collect scan data of two modalities for reconstruction to obtain images corresponding to each modality. For example, the hybrid imaging system synchronously performs PET scanning and at least two MR scanning sequences to obtain PET scanning data and MR scanning data sequences and reconstructs PET dynamic images, MR images, and PET images corresponding to the MR images of each sequence, respectively, and then performs image registration on the PET dynamic image based on the MR image and the corresponding PET image. The multiple modalities involved include but are not limited to MR, PET, and CT.

[0047] The following will describe and illustrate how to perform image registration by using an example of a hybrid imaging system that simultaneously performs PET scanning and at least two MR scanning sequences to reconstruct PET dynamic images, MR images, and PET images corresponding to the MR images of each sequence.

[0048] In one embodiment, Figure 2 As shown, an image registration method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0049] S202 : Acquire a first dynamic PET image of the imaging object, at least two MR images, and PET images corresponding to the MR images.

[0050] The imaging object may include a human body or an animal body, which is not limited here. The first dynamic PET image may be a dynamic PET image obtained by reconstructing the scan data obtained by performing a PET scan on the imaging object for a certain period of time and then performing dynamic image reconstruction. The MR image may be an MR scan data sequence obtained by performing MR scans on the imaging object at multiple scan sequences with a certain time interval during the PET scan period, and reconstructing MR images corresponding to the multiple scan sequences. The PET image corresponding to the MR image may be a plurality of PET images that are completely corresponding to the time and space of the multiple MR images after searching the PET scan data for the corresponding acquisition time according to the acquisition time of the MR image, and reconstructing them respectively. The multiple scan sequences may be the same scan sequence or different scan sequences, and the multiple scan sequences need to be able to display the structural features of the imaging object, including but not limited to T1WI, T2WI, etc., which are not limited here.

[0051] Specifically, after the computer device performs a PET scan for a certain period of time and an MR scan of multiple scanning sequences on the imaging object, a reconstructed first dynamic PET image, at least two MR images, and a PET image corresponding to each MR image are obtained, that is, the first dynamic PET image of the imaging object, at least two MR images, and a PET image corresponding to each MR image are acquired.

[0052] S204 , for each MR image, register the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image, and obtain a first registered PET image corresponding to the corresponding MR image.

[0053] The deformation field information is structural deformation information, which may be hard structural deformation information, soft structural deformation information, or light and shadow deformation information, without limitation. The light and shadow deformation information may be information on brightness and darkness.

[0054] Optionally, the deformation field information of each MR image may be the deformation field information of other MR images acquired by using a preset registration algorithm with the first acquired MR image as a reference. Alternatively, the deformation field information of the next adjacent MR image may be calculated by using the preset registration algorithm with the first acquired MR image as the first reference image, and the next adjacent MR image may be used as the new first reference image, and the step of using the preset registration algorithm to calculate the deformation field information of the next adjacent MR image may be repeated until the deformation field information of the last MR image is determined, which is not limited here.

[0055] It should be noted that the deformation field information of the MR image can accurately reflect the deformation situation, and accurate deformation information can be obtained through the MR structural information. Therefore, deformation calibration of PET images using the deformation field information of the MR image can enrich the detailed information of image deformation and improve image quality.

[0056] Specifically, after the deformation field information of each MR image is obtained, the deformation field information of each MR image is applied to the PET image corresponding to each MR image to obtain a first registered PET image.

[0057] Furthermore, the deformation field information of each MR image may be multiplied with the PET image corresponding to each MR image to obtain a first registered PET image.

[0058] S206, registering the first dynamic PET image with the second registered dynamic PET image to obtain a target dynamic PET image; the second registered dynamic PET image is the first registered PET image having the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image having the smallest tracer content difference with the first dynamic PET image.

[0059] The first dynamic PET image is an image composed of multiple PET images at a first time interval. The first time interval is much smaller than the time interval of the acquisition time of the MR image. For example, the acquisition time of the MR image is 1 minute, and the time interval is every 1 second. The first time interval is 0.1 seconds. Optionally, the first time interval can be a uniformly divided time interval, or there can be a variable time interval. For example, the acquisition time of the PET scan is 1 hour, the time interval of the first 1 minute is 0.01 seconds, and the time interval of the last 59 minutes is 0.1 seconds.

[0060] Specifically, for each PET image frame in the first dynamic PET image, find the image with the closest acquisition time to each first registered PET image as the corresponding second registered dynamic PET image, that is, the second registered dynamic PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image. Alternatively, for each PET image frame in the first dynamic PET image, find the image with the closest tracer content difference to each first registered PET image as the corresponding second registered dynamic PET image, that is, the second registered PET image is the first registered PET image with the smallest tracer content difference with the first dynamic PET image. Each PET image frame in the first dynamic PET image is registered with the corresponding second registered PET image to obtain the target dynamic PET image. For example, after obtaining each first registered PET image, for the first dynamic PET image, find the image with the closest acquisition time to each first registered PET image for each dynamic PET image frame as the second registered dynamic PET image, and register each dynamic PET image frame to obtain the final target dynamic PET image, see Figure 2-a shown.

[0061] In the above-mentioned image registration method, a first dynamic PET image of the imaging object, at least two MR images and PET images corresponding to each MR image are obtained; for each MR image, the PET image corresponding to the corresponding MR image is registered according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image; the first dynamic PET image is registered with the second registered PET image to obtain a target dynamic PET image; wherein the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image. In this way, deformation information is obtained by using the information of the MR structural modality corresponding to multiple groups of scanning sequences, and the deformation information is used to perform registration correction on the dynamic PET, thereby improving the effect of dynamic PET image frame registration. There is no need to take single-frame PET images at multiple discontinuous time points, and the actual situation image of the part to be detected of the imaging object is more accurately reflected. Based on multiple MR sequences, the main displacement and deformation of the imaging object in the dynamic PET image reconstruction with a longer time are corrected, and an image that can more accurately present the actual situation of the imaging object is obtained, providing an accurate basis for subsequent analysis. In addition, the deformation field information of the MR image can truthfully reflect the deformation situation, and accurate deformation information can be obtained through the MR structural information. Therefore, deformation calibration of PET images through the deformation field information of the MR image can enrich the detailed information of image deformation and improve image quality.

[0062] The above embodiment describes the image registration method. Before performing image registration, the target part to be detected can be determined by preprocessing and positioned. Now, an embodiment is used to describe it. In one embodiment, Figure 3 As shown, acquiring a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each MR image includes:

[0063] S302, acquiring an initial MR image of the imaging object.

[0064] Specifically, after the imaging object is positioned, an MR scan of an arbitrary scanning sequence is performed on the imaging object to obtain an initial MR image of the imaging object.

[0065] S304: Position the imaging object according to the initial MR image to obtain a positioning result.

[0066] Specifically, after the initial MR image is obtained, the scanned part in the initial MR image can be located to obtain the position of the target part to be scanned, that is, to obtain the positioning result. The initial MR image can be input into a preset neural network model to segment the initial MR image to obtain the position of the target part in the initial MR image.

[0067] S306 , performing PET scanning and MR scanning on the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images, and PET images corresponding to each MR image.

[0068] Specifically, after the positioning result is obtained, the scanning field of view can be adjusted to the target part, and the imaging object can be given a tracer, and a PET scan of a preset duration and at least two scanning sequences of MR scans can be started at the same time or in advance. A first dynamic PET image is obtained by dynamically reconstructing the PET scan data obtained by the PET scan; a plurality of MR scan data sequences obtained by the MR scan are reconstructed to obtain corresponding MR images; and a PET image corresponding to each MR image is reconstructed from the PET scan data of the corresponding time extracted from the PET scan data according to the scan time corresponding to the MR scan sequence. Among them, the target part can include the lungs, liver, pancreas, stomach, etc., which are not limited here.

[0069] Optionally, the imaging object can be pre-scanned by a CT imaging device to obtain a positioning result of the target part of the imaging object, and a PET scan and an MR scan can be performed on the target part of the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images and PET images corresponding to each MR image.

[0070] Optionally, the imaging object can be scanned by a PET imaging device to obtain a single-frame PET image, the imaging object can be positioned based on the single-frame PET image, the positioning result of the target part can be determined, and the target part of the imaging object can be scanned by PET and MR based on the positioning result to obtain a first dynamic PET image, at least two MR images and PET images corresponding to each MR image.

[0071] In this embodiment, an initial MR image of the imaging object is acquired, the imaging object is positioned according to the initial MR image to obtain a positioning result, and a PET scan and an MR scan are performed on the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images, and a PET image corresponding to each MR image. The imaging object can be pre-scanned to determine the position of the target part to be scanned and obtain a positioning result. Based on the positioning result, the scanning field of view is positioned to the target part, and subsequent PET scans and MR scans are performed to more accurately analyze the target part and obtain an analysis result of the target part.

[0072] The above embodiment describes how to determine the location of the target part of the imaging object. Now, an embodiment is used to describe how to obtain a dynamic PET image, each MR image, and a PET image corresponding to each MR image. In one embodiment, Figure 4 As shown, based on the positioning result, a PET scan and an MR scan are performed on the imaging object to obtain a first dynamic PET image, at least two MR images, and PET images corresponding to each MR image, including:

[0073] S402: Perform PET scanning and MR scanning on the imaging object based on the positioning result to obtain PET scanning data and at least two MR scanning data sequences.

[0074] Specifically, after the positioning result is determined, the field of view position is adjusted according to the positioning result, and a PET scan of a preset duration and an MR scan of at least two scanning sequences are performed on the target part of the imaging object to obtain PET scan data and at least two MR scan data sequences. Among them, the preset duration can be set according to the effective duration of the tracer. It should be noted that since the imaging object cannot be scanned continuously for a long time during the MR scanning process, it will cause certain damage to the imaging object. Therefore, multiple scanning sequences with a certain time interval are set to perform MR scanning on the imaging object.

[0075] For example, after the positioning result is determined, the field of view position is adjusted according to the positioning result, and the scanning requirements corresponding to each MR scanning time interval are determined. A PET scan of a preset duration is performed on the target part of the imaging object to obtain a PET scan number. The scanning requirements corresponding to each scanning data sequence are determined, and the scanning conditions corresponding to each scanning requirement are determined. MR scanning is performed according to the scanning conditions corresponding to each scanning data sequence to obtain MR scanning data sequences corresponding to each scanning condition. There are at least two MR scanning time intervals.

[0076] Each scanning data sequence is obtained according to the scanning requirements. The scanning requirements may be different or the same. For example, if the scanning requirement is to obtain an image of characteristic parameters of target tissue in a prominent target part, the scanning condition may be to obtain an image of T1 relaxation difference of the prominent tissue in the first time period of the MR acquisition time period, and perform MR scanning according to the scanning condition to obtain a T1W1 sequence (i.e., T1 weighted imaging). For another example, if the scanning requirement is to obtain an image of characteristic parameters of target tissue in a prominent target part, the scanning condition may be to obtain an image of T2 relaxation difference of the prominent tissue in the second time period of the MR acquisition time period, and perform MR scanning according to the scanning condition to obtain a T2W1 sequence (i.e., T2 weighted imaging).

[0077] It should be noted that if the scanning requirements during the entire MR acquisition time are the same, the multiple MR scanning data sequences obtained by performing MR scanning on the imaging object are all the same sequence. If the scanning requirements during the entire MR acquisition time are different, the multiple MR scanning data sequences obtained by performing MR scanning on the imaging object are multiple sequences.

[0078] Optionally, the acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold, Figure 4-a shown.

[0079] Specifically, the acquisition time of each MR image must be earlier than the end time of the PET scan. Preferably, the acquisition end time of the last MR image among the multiple MR images is as close as possible to the end time of the PET scan. For example, if the end time of the PET scan is 12:50, the acquisition end time of the last MR image can be 12:49.

[0080] S404, reconstructing the PET scan data to obtain a first dynamic PET image.

[0081] Specifically, after the PET scan data is obtained by performing a PET scan for the entire preset time, dynamic reconstruction can be performed to obtain a first dynamic PET image. For example, a set of first dynamic PET images that meet the requirements of dynamic parameter analysis can be reconstructed through the dynamic reconstruction function of integrated PET / MR imaging.

[0082] S406, reconstructing each MR scan data sequence respectively to obtain at least two MR images.

[0083] Specifically, after obtaining each MR scan data sequence, image reconstruction is performed to obtain corresponding MR images. For example, the MR images corresponding to each MR scan sequence can be reconstructed through the image reconstruction function of integrated PET / MR imaging.

[0084] S408, determining at least two PET scan data sequences corresponding to the at least two MR scan data sequences from the PET scan data according to the acquisition time of each MR scan data sequence, reconstructing each PET scan data sequence to obtain a PET image corresponding to each MR image.

[0085] Specifically, after the PET scan data is obtained, the PET scan data sequences with the same acquisition time as the respective MR scan data sequences can be extracted from the PET scan data according to the acquisition time of the respective MR scan data sequences, i.e., the scanning time of the respective MR scan sequences. Image reconstruction is performed on the respective PET scan data sequences to obtain a set of PET images that completely correspond to the time and space of the respective MR images.

[0086] Optionally, the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0087] In this embodiment, PET scanning and MR scanning are performed on the imaging object based on the positioning result to obtain PET scanning data and at least two MR scanning data sequences, the PET scanning data are reconstructed to obtain a first dynamic PET image, each MR scanning data sequence is reconstructed to obtain at least two MR images, and according to the acquisition time of each MR scanning data sequence, a PET scanning data sequence corresponding to the at least two MR scanning data sequences is determined from the PET scanning data, each PET scanning data sequence is reconstructed to obtain a PET image corresponding to each MR image, so that it is possible to use multiple MR images to match PET images corresponding to the same time and space, and use this as a reference for subsequent registration of dynamic PET images, thereby realizing registration of dynamic PET images.

[0088] The above embodiment describes how to obtain a dynamic PET image, each MR image, and each MR image corresponding to a PET image. In the image registration method, it is necessary to calculate the deformation field information between each MR image. Here, how to determine the deformation field information is described. In one embodiment, the image registration method further includes:

[0089] The first acquired MR image is used as the reference image, and the deformation field information of other MR images is obtained using a preset registration algorithm.

[0090] Specifically, after obtaining multiple MR images, the MR image with the earliest acquisition time among the MR images, that is, the first MR image, is determined as the reference image based on the acquisition time. Using the preset registration algorithm, the deformation field information between all MR images except the first MR image and the reference image can be calculated. Among them, the preset registration algorithm may include: a registration algorithm based on image grayscale, a registration algorithm based on image features, and a registration algorithm based on understanding and interpretation of the image, which is not limited here.

[0091] It should be noted that the deformation field information is structural deformation information, which can be hard structural deformation information, soft structural deformation information, or light and shadow deformation information, without specific limitation. The light and shadow deformation information can be information about the degree of brightness. The deformation field information of the MR image can reflect the deformation situation truthfully, and accurate deformation information can be obtained through the MR structural information. Therefore, deformation calibration of the PET image through the deformation field information of the MR image can enrich the detailed information of the image deformation and improve the image quality.

[0092] In this embodiment, by taking the first MR image acquired as the reference image and utilizing a preset registration algorithm to obtain the deformation field information of other MR images, the first MR image can be used as the reference image to determine the deformation field information between other MR images and the reference image over time, thereby performing registration on the PET images that completely correspond to them in time and space, thereby achieving registration of dynamic PET images.

[0093] To facilitate understanding by those skilled in the art, an image registration method is further described with reference to an embodiment. In one embodiment, the image registration method includes:

[0094] S100, acquiring an initial MR image of an imaging object;

[0095] S200, positioning the imaging object according to the initial MR image to obtain a positioning result;

[0096] S300, performing PET scanning and MR scanning on the imaging object based on the positioning result, and acquiring PET scanning data and at least two MR scanning data sequences;

[0097] S400, reconstructing the PET scan data to obtain a first dynamic PET image;

[0098] S500, reconstructing each MR scan data sequence respectively to obtain at least two MR images;

[0099] S600, according to the acquisition time of each MR scan data sequence, at least two PET scan data sequences corresponding to the at least two MR scan data sequences are determined from the PET scan data, and each PET scan data sequence is reconstructed to obtain a PET image corresponding to each MR image. The acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold. The acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0100] S700, acquiring a first dynamic PET image of an imaging object, at least two dynamic MR images, and a second dynamic PET image corresponding to each dynamic MR image sequence;

[0101] S800: Taking the first acquired MR image as a reference image, using a preset registration algorithm, the deformation field information of other MR images is acquired.

[0102] S900, for each MR image, registering the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image, to obtain a first registered PET image corresponding to the corresponding MR image;

[0103] S1000, register the first dynamic PET image with the second registered dynamic PET image to obtain a target dynamic PET image; the second registered dynamic PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

[0104] In this embodiment, a first dynamic PET image of the imaging object, at least two MR images and PET images corresponding to each MR image are obtained; for each MR image, the PET image corresponding to the corresponding MR image is registered according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image; the first dynamic PET image is registered with the second registered PET image to obtain a target dynamic PET image; wherein the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image. In this way, the effect of dynamic PET image frame registration is improved by combining the information of MR structural modalities corresponding to multiple groups of scanning sequences with the information of PET, and there is no need to shoot a single frame PET image only at multiple discontinuous time points, which accurately reflects the actual situation image of the to-be-detected part of the imaging object, and corrects the main displacement and deformation of the imaging object in the reconstruction of each long dynamic PET image based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, providing an accurate basis for subsequent analysis.

[0105] The above embodiments illustrate the image registration method. Based on the same inventive concept, an image registration method corresponding to a complete workflow of PET scanning, MR scanning, image reconstruction, and image registration is provided. The implementation solution provided by the image registration method to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more of the image registration method embodiments provided below can refer to the limitations on the image registration method above, and will not be repeated here. In one embodiment, Figure 5 As shown, the image registration method includes:

[0106] S502, performing a PET scan and at least two MR scan sequences on the imaging object to obtain PET scan data and at least two MR scan data sequences; the acquisition end time of each MR scan data sequence is before the PET scan end time;

[0107] S504, performing image reconstruction according to each MR scan data sequence to obtain a plurality of MR images, and performing image reconstruction according to the PET scan data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image;

[0108] S506, performing image reconstruction according to the PET scanning data to obtain a first dynamic PET image;

[0109] The PET images corresponding to the MR images are registered according to the deformation field information of each MR image to obtain a first registered PET image; the deformation field information is information determined by a plurality of MR images using a preset registration algorithm;

[0110] S508, register the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest tracer content difference with the first dynamic PET image.

[0111] Optionally, the acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold.

[0112] Optionally, the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0113] In this embodiment, PET scanning and MR scanning of at least two scanning sequences are performed on the imaging object to obtain PET scanning data and each MR scanning data sequence, image reconstruction is performed according to each MR scanning data sequence to obtain multiple MR images, and image reconstruction is performed according to the PET scanning data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image, image reconstruction is performed according to the PET scanning data to obtain a first dynamic PET image, and the PET images corresponding to each MR image are registered according to the deformation field information of each MR image to obtain a first registered PET image; the deformation field information is obtained by using a preset registration of multiple MR images. The information determined by the algorithm is used to align the first dynamic PET image with the second registration PET image to obtain the target dynamic PET image. The information of the MR structural modality corresponding to the multiple sets of scanning sequences and the PET information are combined to improve the effect of dynamic PET image frame registration. There is no need to take single-frame PET images at multiple discontinuous time points. The actual situation image of the part to be detected of the imaging object is accurately reflected, and the main displacement and deformation of the imaging object in the reconstruction of dynamic PET images with longer time are corrected based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, which provides a precise basis for subsequent analysis.

[0114] In one embodiment, Figure 6 As shown, the image registration method further includes:

[0115] S602, performing an initial MR scan on the imaging object to obtain an initial MR image;

[0116] S604, positioning the imaging object according to the initial MR image to obtain a positioning result;

[0117] S606, based on the positioning result, performing a step of performing a PET scan and at least two scanning sequences of MR scans on the imaging object to obtain PET scan data and each MR scan data sequence.

[0118] In this embodiment, an initial MR image of the imaging object is acquired, the imaging object is positioned according to the initial MR image to obtain a positioning result, and a PET scan and an MR scan are performed on the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images, and a PET image corresponding to each MR image. By pre-scanning the prime minister object, the position of the target part to be scanned can be determined to obtain a positioning result. According to the positioning result, the scanning field of view is positioned to the target part, and subsequent PET scans and MR scans are performed to more accurately analyze the target part and obtain an analysis result of the target part.

[0119] In one embodiment, the deformation field information is information determined by using a preset registration algorithm for a plurality of MR images, including:

[0120] The first acquired MR image is used as the reference image, and the deformation field information of other MR images is obtained using a preset registration algorithm.

[0121] In this embodiment, by taking the first MR image acquired as the reference image and utilizing a preset registration algorithm to obtain the deformation field information of other MR images, the first MR image can be used as the reference image to determine the deformation field information between other MR images and the reference image over time, thereby performing registration on the PET images that completely correspond to them in time and space, thereby achieving registration of dynamic PET images.

[0122] For the convenience of understanding by those skilled in the art, an embodiment is now used to further illustrate the image registration method. In one embodiment, the image registration method includes:

[0123] S10, performing an initial MR scan on the imaging object to obtain an initial MR image;

[0124] S20, positioning the imaging object according to the initial MR image to obtain a positioning result;

[0125] S30, based on the positioning result, performing a PET scan and at least two MR scan sequences on the imaging object to obtain PET scan data and each MR scan data sequence; the acquisition end time of each MR scan data sequence is before the PET scan end time; the acquisition time of the MR image is earlier than the PET scan end time, and the time difference between the acquisition end time of the MR image and the PET scan end time is less than a preset threshold;

[0126] S40, performing image reconstruction according to each MR scan data sequence to obtain a plurality of MR images, and performing image reconstruction according to the PET scan data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image; the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image;

[0127] S50, performing image reconstruction according to the PET scanning data to obtain a first dynamic PET image;

[0128] S60, registering the PET images corresponding to the MR images according to the deformation field information of the MR images to obtain a first registered PET image; the deformation field information is obtained by taking the first acquired MR image as a reference image and using a preset registration algorithm to obtain the deformation field information of other MR images.

[0129] S70, registering the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image having the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image having the smallest tracer content difference with the first dynamic PET image.

[0130] In this embodiment, a PET scan and an MR scan of at least two scan sequences are performed on the imaging object to obtain PET scan data and each MR scan data sequence, image reconstruction is performed according to each MR scan data sequence to obtain multiple MR images, and image reconstruction is performed respectively according to the PET scan data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image, image reconstruction is performed according to the PET scan data to obtain a first dynamic PET image, and for each MR image, the PET images corresponding to each corresponding MR image are registered according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image; the deformation field information is obtained by the multiple MR scan data sequences. The R image uses the information determined by the preset registration algorithm to register the first dynamic PET image with the second registered PET image to obtain the target dynamic PET image. It can combine the information of the MR structural modality corresponding to multiple groups of scanning sequences with the information of PET to improve the effect of dynamic PET image frame registration. There is no need to take single-frame PET images at multiple discontinuous time points. It can accurately reflect the actual situation image of the part to be detected of the imaging object, and correct the main displacement and deformation of the imaging object in the reconstruction of dynamic PET images with longer time based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, providing a precise basis for subsequent analysis.

[0131] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0132] Based on the same inventive concept, the embodiment of the present application also provides an image registration device for implementing the above-mentioned image registration method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more image registration device embodiments provided below can refer to the limitations of the image registration method above, and will not be repeated here.

[0133] In one embodiment, Figure 7 As shown, an image registration device is provided, comprising:

[0134] An acquisition module 701 is used to acquire a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each MR image;

[0135] A first registration module 702 is used to register the PET image corresponding to each MR image according to the deformation field information of the MR image, so as to obtain a first registered PET image corresponding to the corresponding MR image;

[0136] The second registration module 703 is used to register the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

[0137] Optionally, the acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold.

[0138] Optionally, the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0139] In this embodiment, the acquisition module acquires a first dynamic PET image, at least two MR images, and PET images corresponding to each MR image of the imaging object. The first registration module registers the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image for each MR image to obtain a first registered PET image corresponding to the corresponding MR image. The second registration module registers the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image. The information of the MR structural modality corresponding to multiple groups of scanning sequences and the PET information are combined to improve the effect of dynamic PET image frame registration, without the need to shoot a single frame PET image only at multiple discontinuous time points, accurately reflecting the actual situation image of the to-be-detected part of the imaging object, and correcting the main displacement and deformation of the imaging object in the reconstruction of each long dynamic PET image based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, providing a precise basis for subsequent analysis.

[0140] In one embodiment, the acquisition module 701 includes:

[0141] an acquisition unit, configured to acquire an initial MR image of an imaging object;

[0142] A positioning unit, used for positioning the imaging object according to the initial MR image to obtain a positioning result;

[0143] The scanning unit is used to perform PET scanning and MR scanning on the imaging object based on the positioning result to obtain a first dynamic PET image, at least two MR images and PET images corresponding to each MR image.

[0144] In one embodiment, the scanning unit is specifically configured to perform a PET scan and an MR scan on the imaging object based on the positioning result, and acquire PET scan data and at least two MR scan data sequences;

[0145] The PET scan data are reconstructed to obtain a first dynamic PET image; each MR scan data sequence is reconstructed to obtain at least two MR images; at least two PET scan data sequences corresponding to the at least two MR scan data sequences are determined from the PET scan data according to the acquisition time of each MR scan data sequence, and each PET scan data sequence is reconstructed to obtain a PET image corresponding to each MR image.

[0146] In one embodiment, the image registration device further comprises:

[0147] The deformation field information determination module is used to obtain the deformation field information of other MR images by using the first acquired MR image as a reference image and utilizing a preset registration algorithm.

[0148] The above embodiment describes the image registration device. Based on the same inventive concept, the embodiment of the present application also provides an image registration device for implementing the image registration method corresponding to the complete workflow of PET scanning, MR scanning, image reconstruction, and image registration. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method. Therefore, the specific limitations in the one or more image registration device embodiments provided below can refer to the limitations on the image registration method above, and will not be repeated here.

[0149] In one embodiment, Figure 8 As shown, the image registration device comprises:

[0150] The scanning module 801 is used to perform a PET scan and at least two MR scan sequences on the imaging object to obtain PET scan data and each MR scan data sequence; the acquisition end time of each MR scan data sequence is before the PET scan end time;

[0151] A first reconstruction module 802 is used to perform image reconstruction according to each MR scan data sequence to obtain a plurality of MR images, and to perform image reconstruction according to the PET scan data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image;

[0152] A second reconstruction module 803 is used to perform image reconstruction according to the PET scanning data to obtain a first dynamic PET image;

[0153] The third registration module 804 is used to register the PET image corresponding to each MR image according to the deformation field information of the MR image, so as to obtain a first registered PET image corresponding to the corresponding MR image; the deformation field information is information determined by a plurality of MR images using a preset registration algorithm;

[0154] The fourth registration module 805 is used to register the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

[0155] Optionally, the acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the MR image acquisition and the end time of the PET scan is less than a preset threshold.

[0156] Optionally, the acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

[0157] In this embodiment, the scanning module performs a PET scan and an MR scan of at least two scanning sequences on the imaging object to obtain PET scan data and each MR scan data sequence, the first reconstruction module performs image reconstruction according to each MR scan data sequence to obtain a plurality of MR images, and performs image reconstruction respectively according to the PET scan data corresponding to the acquisition time of each MR image to obtain a PET image corresponding to each MR image, the second reconstruction module performs image reconstruction according to the PET scan data to obtain a first dynamic PET image, and the third registration module performs registration on the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image for each MR image to obtain a PET image corresponding to the corresponding MR image. The fourth registration module registers the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image, which can improve the effect of dynamic PET image registration by combining the information of MR structural modalities corresponding to multiple groups of scanning sequences with the information of PET, and does not need to take single-frame PET images at multiple discontinuous time points, which accurately reflects the actual situation image of the part to be detected of the imaging object, and corrects the main displacement and deformation of the imaging object in the reconstruction of dynamic PET images with longer time based on multiple MR sequences, so as to obtain an image that can more accurately present the actual situation of the imaging object, and provides a precise basis for subsequent analysis.

[0158] In one embodiment, the image registration device further comprises:

[0159] An initial scanning module, used for performing an initial MR scan on an imaging object to obtain an initial MR image;

[0160] A positioning module, used for positioning the imaging object according to the initial MR image to obtain a positioning result;

[0161] The execution module is used to perform a step of performing a PET scan and at least two scanning sequences of MR scans on the imaging object based on the positioning result to obtain PET scan data and each MR scan data sequence.

[0162] In one embodiment, the third registration module is specifically configured to use the first acquired MR image as a reference image and utilize a preset registration algorithm to acquire deformation field information of other MR images.

[0163] Each module in the above-mentioned image registration device can be implemented in whole or in part by software, hardware or a combination thereof. Each module 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 operations corresponding to each module above.

[0164] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 1 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. 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 scanned image data. The network 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, an image registration method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0165] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0166] 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 steps of the image registration method in any of the above embodiments are implemented.

[0167] 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 steps of the image registration method in any of the above embodiments are implemented.

[0168] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the image registration method in any one of the above embodiments.

[0169] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0170] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile 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.

[0171] 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.

[0172] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image registration method, characterized in that: The method comprises: Acquire a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each of the MR images; For each MR image, registering the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image to obtain a first registered PET image corresponding to the corresponding MR image; The first dynamic PET image is registered with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET image.

2. The method according to claim 1, characterized in that The step of acquiring a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each of the MR images includes: acquiring an initial MR image of the imaging object; Positioning the imaging object according to the initial MR image to obtain a positioning result; Based on the positioning result, a PET scan and an MR scan are performed on the imaging object to obtain the first dynamic PET image, the at least two MR images, and PET images corresponding to each of the MR images.

3. The method according to claim 2, characterized in that The step of performing a PET scan and an MR scan on the imaging object based on the positioning result to obtain the first dynamic PET image, the at least two MR images, and a PET image corresponding to each of the MR images includes: Performing a PET scan and an MR scan on the imaging object based on the positioning result to acquire PET scan data and at least two MR scan data sequences; Reconstructing the PET scan data to obtain the first dynamic PET image; Reconstructing each of the MR scan data sequences respectively to obtain at least two of the MR images; According to the acquisition time of each of the MR scan data sequences, at least two PET scan data sequences corresponding to at least two of the MR scan data sequences are determined from the PET scan data, and each of the PET scan data sequences is reconstructed to obtain a PET image corresponding to each of the MR images.

4. The method according to any one of claims 1 to 3, characterized in that: The acquisition time of the MR image is earlier than the end time of the PET scan, and the time difference between the end time of the acquisition of the MR image and the end time of the PET scan is less than a preset threshold.

5. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: The first acquired MR image is used as a reference image, and a preset registration algorithm is used to obtain deformation field information of other MR images.

6. The method according to any one of claims 1 to 3, characterized in that: The acquisition time of the MR image matches the acquisition time of the PET image corresponding to the MR image.

7. An image registration device, characterized in that: The device comprises: An acquisition module, configured to acquire a first dynamic PET image of an imaging object, at least two MR images, and a PET image corresponding to each of the MR images; A first registration module is used for registering, for each MR image, the PET image corresponding to the corresponding MR image according to the deformation field information of the MR image, to obtain a first registered PET image corresponding to the corresponding MR image; The second registration module is used to register the first dynamic PET image with the second registered PET image to obtain a target dynamic PET image; the second registered PET image is the first registered PET image with the smallest acquisition time difference with the first dynamic PET image, or the second registered PET image is the first registered PET image with the smallest difference in tracer content with the first dynamic PET 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.

Images