Image Registration Method, Device, Computer Equipment and Readable Storage Medium

Abstract

The present application relates to an image registration method, apparatus, computer device, and readable storage medium. The method includes: obtaining respiratory data and initial dynamic PET data within a first preset time period after a tracer is administered to a to-be-detected object, determining corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data, obtaining pseudo-dynamic PET images corresponding to each frame of pseudo-dynamic MR images, obtaining a registered pseudo-dynamic PET image through each frame of pseudo-dynamic PET images, and registering multiple frames of initial dynamic PET images based on the registered pseudo-dynamic PET image to obtain a registered dynamic PET image. By using this method, a registered pseudo-dynamic PET image can be obtained, and then, based on the registered pseudo-dynamic PET image, multiple frames of initial dynamic PET images are registered, so that the registered dynamic PET image can reflect structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and particularly to an image registration method, apparatus, computer device, and readable storage medium. Background Art

[0002] The kinetic parameter analysis based on dynamic positron emission computed tomography (PET) can reveal the biochemical process of the tracer and provide a basis for revealing the pathological mechanism clinically.

[0003] In order to analyze the biochemical process of the tracer, it is necessary to first inject the tracer into the detection imaging part of the object to be measured, then collect the initial PET images within a continuous period of time, and then perform kinetic parameter analysis on the initial PET images. Since it is difficult for the object to be measured to keep the body posture completely fixed for a long time, displacement will occur in the initial PET images collected at different time points. Therefore, before performing kinetic parameter analysis, it is generally necessary to first perform registration processing on the initial PET images to improve the accuracy of kinetic parameter quantification.

[0004] However, in the related art, when registering the initial PET images, there will be a problem that the registration result is not accurate enough. Summary of the Invention

[0005] Based on this, it is necessary to provide an image registration method, apparatus, computer device, and readable storage medium for the above technical problems.

[0006] In a first aspect, the present application provides an image registration method, which includes:

[0007] Obtain the respiration data and the initial dynamic PET data within a first preset time period after the object to be measured is administered with the tracer;

[0008] Determine the corresponding multi-frame quasi-dynamic MR images within the first preset time period according to the respiration data;

[0009] Obtain the quasi-dynamic PET images corresponding to each frame of the quasi-dynamic MR images, and determine the registered quasi-dynamic PET image through each frame of the quasi-dynamic PET images;

[0010] Based on the registered quasi-dynamic PET image, register the multi-frame initial dynamic PET data to obtain the registered dynamic PET image; the multi-frame initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0011] In one embodiment, based on the registered quasi-dynamic PET image, registering the multi-frame initial dynamic PET images to obtain the registered dynamic PET image includes:

[0012] Based on each frame of class dynamic PET images, perform time mapping on the initial dynamic PET data within the first preset time period to obtain the mapped initial dynamic PET data of each frame of class dynamic PET images;

[0013] Reconstruct the mapped initial dynamic PET data of each frame of class dynamic PET images to obtain the corresponding mapped initial dynamic PET images;

[0014] Through the registered class dynamic PET images, register the corresponding mapped initial dynamic PET images to obtain the registered dynamic PET images.

[0015] In one embodiment, determining the registered class dynamic PET images through each frame of class dynamic PET images includes:

[0016] Obtain the deformation fields corresponding to each frame of class dynamic MR images;

[0017] According to the deformation fields corresponding to each frame of class dynamic MR images, register the corresponding class dynamic PET images to obtain the registered class dynamic PET images.

[0018] In one embodiment, obtaining the deformation fields corresponding to each frame of class dynamic MR images includes:

[0019] Determine a reference image based on multiple frames of sample MR images;

[0020] Perform image registration on each frame of class dynamic MR images through the reference image to obtain the deformation fields corresponding to each frame of class dynamic MR images.

[0021] In one embodiment, determining the corresponding multiple frames of class dynamic MR images within the first preset time period according to the respiratory data includes:

[0022] Input the respiratory data into a prediction model to obtain the corresponding multiple frames of class dynamic MR images within the first preset time period.

[0023] In one embodiment, the above method further includes:

[0024] Obtain multiple frames of sample MR images and sample respiratory data within the second preset time period before the test object is administered with a tracer;

[0025] Train an initial prediction model through the multiple frames of sample MR images and sample respiratory data to obtain a prediction model.

[0026] In one embodiment, obtaining the class dynamic PET images corresponding to each frame of class dynamic MR images includes:

[0027] Obtain the initial PET data within the first preset time period;

[0028] Perform time mapping on each frame of dynamic MR images and the initial PET data within the first preset time period to obtain the mapped PET data of each frame of dynamic MR images;

[0029] Reconstruct the mapped PET data to obtain the class dynamic PET images corresponding to each frame of dynamic MR images.

[0030] In a second aspect, the present application provides an image registration device, which includes:

[0031] A data acquisition module, configured to acquire respiratory data and initial dynamic PET data within the first preset time period after a tracer is administered to a subject to be measured;

[0032] A first image determination module, configured to determine corresponding multiple frames of class dynamic MR images within the first preset time period according to the respiratory data;

[0033] A second image determination module, configured to acquire the class dynamic PET images corresponding to each frame of class dynamic MR images, and determine the registered class dynamic PET images through each frame of class dynamic PET images;

[0034] A registration module, configured to register multiple frames of initial dynamic PET images according to the registered class dynamic PET images to obtain registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0035] In a third aspect, the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquire respiratory data and initial dynamic PET data within the first preset time period after a tracer is administered to a subject to be measured;

[0037] Determine corresponding multiple frames of class dynamic MR images within the first preset time period according to the respiratory data;

[0038] Acquire the class dynamic PET images corresponding to each frame of class dynamic MR images, and determine the registered class dynamic PET images through each frame of class dynamic PET images;

[0039] Based on the registered class dynamic PET images, register multiple frames of initial dynamic PET images to obtain registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0040] In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0041] Obtain the respiratory data and the initial dynamic PET data within the first preset time period after a tracer is administered to the object to be measured;

[0042] Determine the corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data;

[0043] Obtain the pseudo-dynamic PET images corresponding to each frame of the pseudo-dynamic MR images, and determine the registered pseudo-dynamic PET image through each frame of the pseudo-dynamic PET images;

[0044] Based on the registered pseudo-dynamic PET image, register the multiple frames of initial dynamic PET images to obtain the registered dynamic PET image; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0045] For the above image registration method, device, computer device and readable storage medium, the computer device obtains the respiratory data and the initial dynamic PET data within the first preset time period after a tracer is administered to the object to be measured, determines the corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data, obtains the pseudo-dynamic PET images corresponding to each frame of the pseudo-dynamic MR images, and determines the registered pseudo-dynamic PET image through each frame of the pseudo-dynamic PET images. Based on the registered pseudo-dynamic PET image, register the multiple frames of initial dynamic PET images to obtain the registered dynamic PET image; the above method can directly obtain the pseudo-dynamic MR images through the respiratory data, then obtain the pseudo-dynamic PET images with the tissue / organ structure characteristics of the imaging part based on the pseudo-dynamic MR images and the initial dynamic PET data, and based on the registered pseudo-dynamic PET image, register the multiple frames of initial dynamic PET images, so that the registered dynamic PET image can reflect the structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result. Description of the Drawings

[0046] Figure 1 It is an application environment diagram of the image registration method in an embodiment;

[0047] Figure 2 It is a schematic flowchart of the image registration method in an embodiment;

[0048] Figure 3 It is a schematic flowchart of the method for registering multiple frames of initial dynamic PET images in an embodiment;

[0049] Figure 4 It is a schematic flowchart of the method for obtaining the registered pseudo-dynamic PET image through each frame of the pseudo-dynamic PET images in another embodiment;

[0050] Figure 5Schematic flow chart of a method for obtaining a deformation field corresponding to each frame of dynamic MR images in another embodiment;

[0051] Figure 6 Schematic diagram of multiple frames of different types of images in the image registration process in another embodiment;

[0052] Figure 7 Schematic flow chart of a method for obtaining corresponding dynamic PET images for each frame of dynamic MR images in another embodiment;

[0053] Figure 8 Correspondence diagram of time points, sample MR data, and respiratory data in another embodiment;

[0054] Figure 9 Structural block diagram of an image registration device in one embodiment;

[0055] Figure 10 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0056] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The image registration method provided by the present application can be applicable to Figure 1The image registration system shown can be applied to medical image registration or medical image calibration scenarios. The above image registration system includes a scanning system and a computer device. The scanning system includes a medical scanning device and a tool capable of carrying the object to be measured, and this tool can be a scanning bed, a scanning frame, a scanning plate, etc. There can be a communication connection between the computer device and the medical scanning device in the scanning system, and this communication method can be Wi-Fi, a mobile network, a Bluetooth connection, etc. The above medical scanning device can be a computed tomography (CT) system, a computed radiography (CR) system, a direct digital radiography (DR) system, a magnetic resonance (MR) scanning device, etc., and can also be a scanning system capable of collecting various types of medical data; the above computer device can be various personal computers, laptop computers, smartphones, tablet computers, and portable wearable devices, but is not limited to these. In actual applications, the object to be measured can lie on the carrying tool in different postures. The medical scanning device can scan the target imaging part of the object to be measured to obtain scanning data, and the medical scanning device sends the scanning data to the computer device. The computer device reconstructs and analyzes the scanning data, and finally realizes image registration. Optionally, after the medical scanning device finishes scanning, the magnetic resonance coil in the medical scanning device can be removed from the body of the object to be measured, and the carrying tool can be returned to its original position. Optionally, the above target imaging part can be imaging parts such as the brain, lungs, abdomen, heart, blood vessels, and joints of the object to be measured; the above object to be measured can be a human body, an animal body, etc. In medicine, in order to provide a basis for revealing the pathological mechanism clinically, it is necessary to analyze the kinetic parameters of the scanned medical images.

[0058] Among them, kinetic parameter analysis can reveal the biochemical process of the tracer. Therefore, it is necessary to administer the tracer to the object to be measured, then scan the object to be measured with the administered tracer to obtain medical images, and then perform kinetic parameter analysis on the medical images obtained at this time. Optionally, due to the limitation of the accumulation time characteristics of the tracer in the object to be measured, in this embodiment, it is necessary to continuously collect data for a certain period of time, reconstruct it to generate dynamic medical images, and then perform kinetic parameter analysis on the dynamic medical images to reveal the biochemical process of the tracer. Further, medical staff can determine the pathological results of the object to be measured according to the biochemical process of the tracer. In an actual scenario, it is difficult for the object to be measured to maintain a completely static body posture for a long time, and there will be a deviation between the obtained dynamic medical images and the actual situation. Therefore, before performing kinetic parameter analysis on the dynamic medical images, it is generally necessary to perform registration processing on the dynamic medical images first to improve the accuracy of kinetic parameter quantification. The above dynamic medical images can be dynamic positron emission tomography (PET) images, computed tomography (CT) images, MR images, etc. However, in this embodiment, the dynamic medical image is a dynamic PET image.

[0059] In one embodiment, as Figure 2 shown, a method for image registration is provided. Taking the application of this method to a computer device as an example, the method includes the following steps:

[0060] S100. Obtain the respiratory data and initial dynamic PET data of the object to be measured within a first preset time period after the administration of the tracer.

[0061] Specifically, before the medical scanning device scans any one or more imaging parts of the object to be measured, medical staff can first intravenously administer a certain amount of tracer to one or more imaging parts of the object to be measured. As the tracer accumulates in the tissue, within a specific time period, there will be a certain biochemical reaction in the tissue / organs of the imaging part administered with the tracer, and during this biochemical reaction process, there will be an obvious difference between the tissue / organs in the lesion area and the tissue / organs in the non-lesion area, which can all be reflected in the dynamic PET images.

[0062] Optionally, during the biochemical reaction process of the tissue / organ, the medical scanning device can scan the imaging site administered with the tracer to obtain dynamic PET images. Among them, as the tracer accumulates in the tissue / organ of the imaging site, the contrast of the dynamic PET images will change significantly. However, it is not the case that the longer the time, the greater the contrast of the dynamic PET images. Within a certain time period, the contrast of the dynamic PET images will reach a peak. Therefore, the above-mentioned specific time period includes the time point when the contrast of the dynamic PET images reaches the peak. Optionally, the starting time point of the specific time period can be the time point when the administration of the tracer ends, or can be a certain time point after the time point when the administration of the tracer ends. Optionally, the above-mentioned tracer can be different radionuclide drugs, which are harmless to the object to be measured.

[0063] In practical applications, the medical scanning device can scan one or more imaging sites of the object to be measured administered with the tracer to obtain the initial PET data scanned within the first preset time period, and can simultaneously collect the breathing data of the object to be measured while collecting the initial PET data. The medical scanning device can send both the initial PET data and the breathing data scanned within the first preset time period to the computer device, and the computer device can reconstruct the initial PET data within multiple sub-time periods within the first preset time period to obtain multiple frames of dynamic PET images corresponding to the first preset time period. Each sub-time period corresponds to one frame of dynamic PET image.

[0064] It should be noted that each frame of dynamic PET image can correspond to the initial PET data within a sub-time period within the first preset time period. Optionally, the first preset time period can include multiple sub-time periods, and each sub-time period has a corresponding frame of initial dynamic PET image; the duration corresponding to each sub-time period can be equal or unequal; the combined duration of multiple sub-time periods can be less than or equal to the duration corresponding to the first preset time period.

[0065] In addition, the computer device can perform static reconstruction on the initial PET data scanned by the medical scanning device to obtain static PET images. However, in this embodiment, the computer device reconstructs the initial PET data scanned by the medical scanning device into dynamic PET images, and a dynamic reconstruction algorithm can be used when reconstructing the dynamic PET images. Among them, the contrast of the dynamic PET images is greater than the contrast of the static PET images. The above-mentioned dynamic reconstruction algorithm can be the backprojection method, the iterative reconstruction algorithm, the filtered backprojection method, the Fourier transform method, etc., and this embodiment does not limit this.

[0066] S200. Determine corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the breathing data.

[0067] Specifically, the computer device can perform arithmetic operations, data conversion, analysis, data comparison, and / or reconstruction on the respiratory data within the first preset time period, etc., to obtain corresponding multiple frames of dynamic MR-like images within the first preset time period. Alternatively, the computer device can first perform preprocessing such as arithmetic operations, data conversion, analysis, data comparison, and / or reconstruction on the respiratory data within the first preset time period, and then perform specific processing on the preprocessing result using a specific algorithm to obtain corresponding multiple frames of dynamic MR-like images within the first preset time period. Optionally, the above arithmetic operations can be addition, subtraction, division, multiplication, exponential operation, and / or logarithmic operation, etc.

[0068] It should be noted that the lengths of the sub-time periods corresponding to each frame of dynamic MR-like images can be equal or unequal. Optionally, the duration of the sub-time period of each frame of dynamic MR-like images can be greater than or equal to the duration of the sub-time period of the initial dynamic PET image corresponding to the corresponding frame. Optionally, multiple frames of dynamic MR-like images can be obtained within the first preset time period; each frame of dynamic MR-like image can be a dynamic MR image generated within a certain sub-time period within the first preset time period. Among them, the sub-time period corresponding to each frame of dynamic MR-like image is different from the sub-time period corresponding to each frame of dynamic PET image.

[0069] S300. Obtain the dynamic PET-like images corresponding to each frame of dynamic MR-like images, and determine the registered dynamic PET-like images through each frame of dynamic PET-like images.

[0070] In this embodiment, the initial PET data within the first preset time period has corresponding multiple frames of dynamic PET-like images, and each frame of initial dynamic PET image has a corresponding dynamic PET-like image. In this embodiment, the initial PET data can also be referred to as dynamic PET data. Optionally, the duration of the sub-time period of each frame of initial dynamic PET image can be less than or equal to the duration of the sub-time period of the corresponding frame of dynamic PET-like image.

[0071] It can be understood that the computer device can perform mapping processing, conversion processing, and / or analysis processing, etc., on each frame of dynamic MR-like image and the corresponding frame of dynamic PET image to obtain the dynamic PET-like images corresponding to each frame of dynamic MR-like image. Optionally, the mapping processing can be understood as the process of mapping the pixel values of the corresponding pixel points at the corresponding positions in the dynamic MR-like image and the corresponding dynamic PET image with the same size, and then performing operations such as adding or subtracting the pixel values of the two pixel points at the mapped positions. Optionally, the conversion processing can be understood as the process of performing arithmetic operations on the pixel values of different positions in the dynamic MR-like image with a preset value or multiple preset values. The analysis processing can be understood as the process of analyzing the pixel resolution of each pixel point in the dynamic MR-like image.

[0072] Further, the computer device may use any frame of the pseudo-dynamic MR images as a reference image to perform image registration on each frame of the pseudo-dynamic PET images, so as to obtain the registered pseudo-dynamic PET images. Among them, the above pseudo-dynamic PET images may reflect information such as the boundaries and shapes of the tissues / organs at the imaging sites of the object to be measured. That is, the pseudo-dynamic PET images carry the structural information of the tissues / organs, and compared with other medical images, the pseudo-dynamic PET images can reflect the obvious feature points in the images.

[0073] S400. Based on the registered pseudo-dynamic PET images, perform registration on multiple frames of initial dynamic PET images to obtain the registered dynamic PET images. The multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0074] Further, the computer device may perform registration on multiple frames of initial dynamic PET images through the registered pseudo-dynamic PET images carrying the structural information of the tissues / organs, so as to improve the accuracy of the dynamic PET image registration result. Among them, the computer device may use the registered pseudo-dynamic PET images as reference images and adopt a registration algorithm to perform registration on each frame of the initial dynamic PET images to obtain the registered dynamic PET images. Optionally, the computer device may also perform arithmetic operations on the registered pseudo-dynamic PET images and each frame of the initial dynamic PET images respectively, so as to perform registration on each frame of the initial dynamic PET images to obtain the registered dynamic PET images.

[0075] In this embodiment, the object to be measured is almost in the same posture within the first preset time period. In the actual processing process, the sizes of the dynamic PET images, the pseudo-dynamic PET images, and the pseudo-dynamic MR images may be the same.

[0076] In the above image registration method, the computer device can obtain the respiration data and the initial dynamic PET data within the first preset time period after the tracer is administered to the object to be measured, determine the corresponding multi-frame pseudo-dynamic MR images within the first preset time period according to the respiration data, obtain the pseudo-dynamic PET images corresponding to each frame of pseudo-dynamic MR images, and determine the registered pseudo-dynamic PET image through each frame of pseudo-dynamic PET images. Based on the registered pseudo-dynamic PET image, register the multi-frame initial dynamic PET images to obtain the registered dynamic PET image. The above method can directly obtain the pseudo-dynamic MR images through the respiration data, and then obtain the pseudo-dynamic PET images with the tissue / organ structure characteristics of the imaging part based on the pseudo-dynamic MR images and the initial dynamic PET data. And based on the registered pseudo-dynamic PET image, register the multi-frame initial dynamic PET images, so that the registered dynamic PET image can reflect the structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result. At the same time, the above method can reduce the complexity of obtaining the pseudo-dynamic MR images, and can also enable medical staff to accurately obtain the pathological mechanism of the object to be measured from the registered dynamic PET image, further improving the accuracy of the diagnosis and treatment method, and enabling timely adoption of effective treatment methods to treat the object to be measured.

[0077] As one of the embodiments, as Figure 3 shown, the step of registering the multi-frame initial dynamic PET images based on the registered pseudo-dynamic PET image in S400 to obtain the registered dynamic PET image can be implemented through the following steps:

[0078] S410. Perform time mapping on the initial dynamic PET data within the first preset time period based on each frame of pseudo-dynamic PET images to obtain the mapped initial dynamic PET data of each frame of pseudo-dynamic PET images.

[0079] Specifically, each frame of pseudo-dynamic PET images within the first preset time period corresponds to part of the initial dynamic PET data. Therefore, the computer device can perform time mapping on each frame of pseudo-dynamic PET images and each frame of initial dynamic PET data according to the sub-time period corresponding to each frame of pseudo-dynamic PET images and the sub-time period corresponding to each frame of initial dynamic PET data to obtain the mapped initial dynamic PET data of each frame of pseudo-dynamic PET images.

[0080] S420. Reconstruct the mapped initial dynamic PET data of each frame of pseudo-dynamic PET images to obtain the corresponding mapped initial dynamic PET images.

[0081] Specifically, the computer device can use the direct backprojection method, the iterative method, or the two-dimensional Fourier transform reconstruction method to reconstruct the mapped initial dynamic PET data of each frame of the class dynamic PET image, and obtain the mapped initial dynamic PET image corresponding to each frame of the class dynamic PET image.

[0082] Exemplarily, if there are two frames of class dynamic PET images and four frames of initial dynamic PET images within the first preset time period, the two frames of class dynamic PET images are class dynamic PET image 1 and class dynamic PET image 2 respectively, and the four frames of initial dynamic PET images are initial dynamic PET image 1, initial dynamic PET image 2, initial dynamic PET image 3, and initial dynamic PET image 4 respectively. Among them, the sub-time period corresponding to class dynamic PET image 1 is [0, 2], the sub-time period corresponding to class dynamic PET image 2 is [2, 4], the sub-time period corresponding to initial dynamic PET image 1 is [0, 1], the sub-time period corresponding to initial dynamic PET image 2 is [1, 2], the sub-time period corresponding to initial dynamic PET image 3 is [2, 3], and the sub-time period corresponding to initial dynamic PET image 4 is [3, 4] (the data within the interval represents time points). Then, the computer device can map the sub-time period [0, 1] corresponding to initial dynamic PET image 1 and the sub-time period [1, 2] corresponding to initial dynamic PET image 2 into the sub-time period [0, 2] corresponding to class dynamic PET image 1, and map the sub-time period [2, 3] corresponding to initial dynamic PET image 3 and the sub-time period [3, 4] corresponding to initial dynamic PET image 4 into the sub-time period [2, 4] corresponding to class dynamic PET image 2, to obtain the mapped initial dynamic PET image 1 and mapped initial dynamic PET image 2 of class dynamic PET image 1, and the mapped initial dynamic PET image 3 and mapped initial dynamic PET image 4 of class dynamic PET image 2 respectively.

[0083] Alternatively, if the sub - time periods corresponding to the class - dynamic PET image 1 within the first preset time period are [0, 4], the sub - time periods corresponding to the class - dynamic PET image 2 are [5, 9], the sub - time periods corresponding to the initial dynamic PET image 1 are [0, 1.5], the sub - time periods corresponding to the initial dynamic PET image 2 are [2.5, 4], the sub - time periods corresponding to the initial dynamic PET image 3 are [5, 6.5], and the sub - time periods corresponding to the initial dynamic PET image 4 are [7.5, 9] (the data within the intervals represent time points), then the computer device can map the sub - time period [0, 1.5] corresponding to the initial dynamic PET image 1 and the sub - time period [2.5, 4] corresponding to the initial dynamic PET image 2 to the sub - time period [0, 4] corresponding to the class - dynamic PET image 1, and map the sub - time period [5, 6.5] corresponding to the initial dynamic PET image 3 and the sub - time period [7.5, 9] corresponding to the initial dynamic PET image 4 to the sub - time period [5, 9] corresponding to the class - dynamic PET image 2, respectively mapping the initial dynamic PET image 1 and the mapped initial dynamic PET image 2 of the class - dynamic PET image 1, and the mapped initial dynamic PET image 3 and the mapped initial dynamic PET image 4 of the class - dynamic PET image 2.

[0084] In this embodiment, the durations of the sub - time periods corresponding to each frame of the initial dynamic PET image can be equal; the durations of the sub - time periods corresponding to each frame of the class - dynamic PET image are greater than the durations of the sub - time periods corresponding to the respective frames of the initial dynamic PET image.

[0085] S430. Register the corresponding mapped initial dynamic PET image with the registered class - dynamic PET image to obtain the registered dynamic PET image.

[0086] Specifically, each frame of the class - dynamic PET image has a corresponding registered class - dynamic PET image. Among them, the computer device can use each frame of the registered class - dynamic PET image as a reference image respectively, and adopt an image registration algorithm to register the mapped initial dynamic PET image corresponding to each frame of the registered class - dynamic PET image to obtain the registered dynamic PET image.

[0087] The above - mentioned image registration method can register the corresponding mapped initial dynamic PET image based on the registered class - dynamic PET image, so that the registered dynamic PET image can reflect the structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result; at the same time, through the above - mentioned method, medical staff can accurately obtain the pathological mechanism of the object to be measured from the registered dynamic PET image, further improving the accuracy of the diagnosis and treatment method, and being able to promptly adopt effective treatment methods to treat the object to be measured.

[0088] As one of the embodiments, such as Figure 4As shown, the step of determining the registered class - dynamic PET image from each frame of the class - dynamic PET image in S300 above can be implemented through the following steps:

[0089] S310. Obtain the deformation fields corresponding to each frame of the class - dynamic MR images.

[0090] Specifically, the computer device can perform arithmetic operations, conversions, analyses, and / or comparisons on each frame of the class - dynamic MR images to obtain the deformation fields corresponding to each frame of the class - dynamic MR images. In this embodiment, an image can be represented in the form of a matrix, and the size of the matrix can be the same as the size of the image. If the size of the image is 3×3, then the size of the matrix is also 3×3. The data in the first row and first column of the matrix can be the pixel value of the pixel point in the first row and first column of the image and the position (1, 1) of the pixel point in the first row and first column. The data in the first row and second column of the matrix can be the pixel value of the pixel point in the first row and second column of the image and the position (1, 2) of the pixel point in the first row and second column. There is also a corresponding relationship between the pixel values of other pixel points in the image and the data at the corresponding positions in the matrix.

[0091] It should be noted that the deformation field can be represented by a deformation - field matrix, and the size of this deformation - field matrix can be equal to the size of the pixel matrix of the class - dynamic MR image. Optionally, the values at different positions in the deformation - field matrix can represent the deformation values of the corresponding pixel points in the class - dynamic MR image.

[0092] Among them, as Figure 5 shown, the step of obtaining the deformation fields corresponding to each frame of the class - dynamic MR images in S310 above can include:

[0093] S311. Determine a reference image based on multiple frames of sample MR images.

[0094] Specifically, within a period of time before a medical staff administers a certain amount of tracer to one or more imaging parts of a subject to be measured, a medical scanning device can scan the imaging parts of the subject to be measured, obtain sample MR data, and send the sample MR data to the computer device. The computer device can reconstruct the sample MR data within this period of time to obtain multiple frames of sample MR images. Each frame of the sample MR images has a corresponding sub - period, and the combination of the sub - periods corresponding to each frame of the sample MR images has the same period as the period of the sample MR data collected by the medical scanning device.

[0095] Among them, the computer device can select any one of the multi-frame sample MR images as the reference image. However, in this embodiment, the computer device can select a frame of sample MR image corresponding to the sub-time period closest to the starting time point of the first preset time period as the reference image. Among them, the relaxation attributes of tissues / organs can be carried in the corresponding sample MR data, that is, the sample MR data can include T1WI sequence and / or T2WI sequence, etc. The T1WI sequence represents the T1 sequence of nuclear magnetic resonance, and the T2WI sequence represents the T2 sequence of nuclear magnetic resonance.

[0096] S312. Perform image registration on each frame of the class dynamic MR image respectively through the reference image to obtain the deformation field corresponding to each frame of the class dynamic MR image.

[0097] It can be understood that the computer device can adopt an image registration algorithm to perform image registration on each frame of the class dynamic MR image through the selected reference image to obtain the deformation field corresponding to each frame of the class dynamic MR image. The deformation field matrix corresponding to the deformation field can be equal to the difference between the reference image and the pixel values of each pixel point in each frame of the class dynamic MR image.

[0098] This embodiment can obtain the deformation field corresponding to each frame of the class dynamic MR image, and then through the deformation field corresponding to each frame of the class dynamic MR image, it is convenient to register each frame of the class dynamic PET image corresponding to the corresponding time period, so that the registration of the class dynamic PET image can take into account the structural density of the class dynamic MR image, thereby improving the accuracy of the image registration result.

[0099] S320. Register the corresponding class dynamic PET image according to the deformation field corresponding to each frame of the class dynamic MR image to obtain the registered class dynamic PET image.

[0100] At the same time, the computer device can adopt an image registration algorithm to register the corresponding class dynamic PET image through the deformation field corresponding to each frame of the class dynamic MR image to obtain the registered class dynamic PET image.

[0101] In this embodiment, the above image registration algorithm can be a matching algorithm based on image gray level or a matching algorithm based on image features, and can also be other image matching algorithms, which are not limited in this embodiment. Among them, the above matching algorithm based on image gray level can be the mean absolute difference algorithm, the sum of absolute errors algorithm, the sum of squared errors algorithm, the mean squared error algorithm, the normalized cross-correlation algorithm, the sequential similarity algorithm, etc.; the above matching algorithm based on image features can be feature extraction, feature matching, model parameter estimation, image transformation and gray level interpolation algorithm, etc. Figure 6Schematic diagrams of multiple frames of quasi-dynamic MR images, registered quasi-dynamic MR images, quasi-dynamic PET images, registered quasi-dynamic PET images, dynamic PET images, and registered dynamic PET images corresponding to a certain imaging part of a to-be-detected object during the image registration process.

[0102] In the above image registration method, the computer device can obtain the respiratory data and multiple frames of initial dynamic PET images within the first preset time period after the to-be-detected object is administered with a tracer, determine multiple frames of corresponding quasi-dynamic MR images within the first preset time period according to the respiratory data, obtain the corresponding quasi-dynamic PET images for each frame of the quasi-dynamic MR images, and obtain the registered quasi-dynamic PET images through each frame of the quasi-dynamic PET images. Based on the registered quasi-dynamic PET images, the multiple frames of initial dynamic PET images are registered to obtain the registered dynamic PET images. The above method can directly obtain quasi-dynamic MR images through respiratory data, then obtain quasi-dynamic PET images with the tissue / organ structure characteristics of the imaging part based on the quasi-dynamic MR images and the initial dynamic PET data, and register the multiple frames of initial dynamic PET images based on the registered quasi-dynamic PET images, so that the registered dynamic PET images can reflect the structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result. At the same time, the above method can also enable medical staff to accurately obtain the pathological mechanism of the to-be-detected object from the registered dynamic PET images, further improving the accuracy of the diagnosis and treatment method, and being able to promptly adopt effective treatment methods to treat the to-be-detected object.

[0103] As one of the embodiments, the step of determining multiple frames of corresponding quasi-dynamic MR images within the first preset time period according to the respiratory data in S200 above may include: inputting the respiratory data into a prediction model to obtain multiple frames of corresponding quasi-dynamic MR images within the first preset time period.

[0104] Specifically, the computer device can input the respiratory data of the first preset time period into the prediction model, and the prediction model outputs multiple frames of corresponding quasi-dynamic MR images within the first preset time period. Among them, the prediction model can be a pre-trained network model, and the prediction model has been trained before the steps in S200 above are executed. The above prediction model can be composed of at least one of a convolutional neural network model, a recurrent neural network model, and an adversarial neural network model.

[0105] Among them, before performing the step of inputting the respiratory data into the prediction model to obtain multiple frames of corresponding quasi-dynamic MR images within the first preset time period, the above image registration method may further include: obtaining multiple frames of sample MR images and sample respiratory data within the second preset time period before the to-be-detected object is administered with a tracer; training an initial prediction model through the multiple frames of sample MR images and sample respiratory data to obtain a prediction model.

[0106] It should be noted that the computer device can train the initial prediction model through multiple frames of sample MR images and sample respiratory data within the second preset time period before administering the tracer to obtain a pre-trained prediction model. That is, input the multiple frames of sample MR images and sample respiratory data within the second preset time period into the initial prediction model for iterative training to obtain the optimal prediction model. Optionally, the duration of the second preset time period can be greater than, less than, or equal to the duration of the first preset time period.

[0107] It can be understood that the computer device can input the multiple frames of sample MR images and sample respiratory data within the second preset time period into the initial prediction model to obtain a class dynamic MR prediction result, calculate the prediction error value between the class dynamic MR prediction result and the standard class dynamic MR image through a loss function, and update the initial network parameters in the initial prediction model according to the prediction error value, continuously iterating the above training steps until the prediction error value meets the preset error threshold or the number of iterations reaches the preset iteration number threshold to obtain a pre-trained prediction model. Within the second time period before administering the tracer to the imaging part of the object to be measured, the medical scanning device can scan the imaging part of the object to be measured to obtain sample MR data. The computer device can segment the second time period to obtain multiple sub-time periods, and then reconstruct the sample MR data within each time period to obtain multiple frames of sample MR images corresponding to the multiple sub-time periods. The durations of the sub-time periods corresponding to each frame of sample MR image can be equal or unequal. The time period corresponding to the combination of the sub-time periods corresponding to each frame of sample MR image can be equal to the second preset time period. Optionally, the above standard class dynamic MR image can be an idealized class dynamic MR image.

[0108] The above image registration method can use the respiratory data synchronously collected with the dynamic PET data to obtain a class dynamic MR image with structural information, thereby reducing the data acquisition duration. At the same time, the class dynamic MR image can be directly obtained through the respiratory data, without the need to first collect dynamic MR data, reconstruct the dynamic MR data into a dynamic MR image, and then indirectly process the dynamic MR image to obtain the class dynamic MR image, thus reducing the entire data processing process of image registration and shortening the image registration duration.

[0109] As one of the embodiments, as Figure 7 shown, the step of obtaining the class dynamic PET image corresponding to each frame of class dynamic MR image in S300 above may include:

[0110] S330. Obtain the initial PET data within the first preset time period.

[0111] Specifically, after a tracer is administered to the imaging part of the object to be measured, a medical scanning device can scan the imaging part administered with the tracer in real time for a period of time to collect initial PET data within a first preset time period, and send the collected initial PET data to a computer device. Alternatively, the computer device can also obtain the initial PET data collected within a historical time period, that is, the initial PET data within the first preset time period, from the cloud or local data. In this embodiment, the method for obtaining the initial PET data within the first preset time period may not be limited. Figure 8 Fig. shows a corresponding relationship diagram of the first preset time period, the second preset time period, the time point of administering the tracer, and the corresponding initial PET data, sample MR data, and respiratory data on the same time axis. Figure 8 In it, the training sequence can be the sample MR data of multiple sub-time periods collected when training the prediction model; Sequence 1, Sequence 2, and Sequence 3 can be the sample MR data of 3 sub-time periods corresponding after administering the tracer. However, the sample MR data of 3 sub-time periods corresponding after administering the tracer may not be used in the image registration process.

[0112] S340. Perform time mapping on each frame of class dynamic MR image and the initial PET data within the first preset time period to obtain the mapped PET data of each frame of class dynamic MR image.

[0113] Specifically, performing time mapping on each frame of class dynamic MR image and the initial PET data within the first preset time period can be understood as mapping the sub-time periods of each frame of class dynamic MR image to the corresponding sub-time periods within the first preset time period to obtain the mapped PET data of each frame of class dynamic MR image.

[0114] S350. Reconstruct the mapped PET data to obtain the class dynamic PET images corresponding to each frame of class dynamic MR image.

[0115] Furthermore, the computer device can reconstruct the mapped PET data within each sub-time period to obtain the class dynamic PET images corresponding to each frame of class dynamic MR image.

[0116] The above image registration method can obtain class dynamic PET images, further register the class dynamic PET images, and then based on the registered class dynamic PET images, register multiple frames of initial dynamic PET images, so that the registered dynamic PET images can reflect structural information and obvious image features, thereby improving the accuracy of the dynamic PET image registration result.

[0117] For the convenience of understanding by those skilled in the art, the image registration method provided by this application is introduced by taking the execution subject as a computer device. Specifically, the method includes:

[0118] (1) Obtain the respiratory data and initial dynamic PET data within the first preset time period after the object to be measured is administered with a tracer.

[0119] (2) Obtain multiple frames of sample MR images and sample respiratory data within the second preset time period before the object to be measured is administered with a tracer.

[0120] (3) Train the initial prediction model with the multiple frames of sample MR images and sample respiratory data to obtain a prediction model.

[0121] (4) Input the respiratory data into the prediction model to obtain multiple frames of corresponding pseudo-dynamic MR images within the first preset time period.

[0122] (5) Perform time mapping on each frame of pseudo-dynamic MR image and the initial PET data within the first preset time period to obtain the mapped PET data of each frame of pseudo-dynamic MR image.

[0123] (6) Reconstruct the mapped PET data to obtain the pseudo-dynamic PET images corresponding to each frame of pseudo-dynamic MR image.

[0124] (7) Determine a reference image based on the multiple frames of sample MR images.

[0125] (8) Perform image registration on each frame of pseudo-dynamic MR image with the reference image respectively to obtain the deformation field corresponding to each frame of pseudo-dynamic MR image.

[0126] (9) According to the deformation field corresponding to each frame of pseudo-dynamic MR image, perform registration on the corresponding pseudo-dynamic PET image to obtain the registered pseudo-dynamic PET image.

[0127] (10) Based on each frame of pseudo-dynamic PET image, perform time mapping on each frame of initial dynamic PET data within the first preset time period to obtain the mapped initial dynamic PET data of each frame of pseudo-dynamic PET image.

[0128] (11) Reconstruct the mapped initial dynamic PET data of each frame of pseudo-dynamic PET image to obtain the corresponding mapped initial dynamic PET image.

[0129] (12) Perform registration on the corresponding mapped initial dynamic PET image with the registered pseudo-dynamic PET image to obtain the registered dynamic PET image.

[0130] The implementation processes of the above (1) to (12) can specifically refer to the descriptions of the above embodiments. Their implementation principles and technical effects are similar, and will not be elaborated here.

[0131] It should be understood that although Figure 2-5The steps in the flowcharts of FIGS. 0 and 7 are sequentially shown according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-5 At least some of the steps in FIGS. 0 and 7 may include multiple steps or multiple stages. 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 sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0132] In one embodiment, as Figure 9 shown, an image registration device is provided, including: a data acquisition module 11, a first image determination module 12, a second image determination module 13, and a registration module 14, where:

[0133] The data acquisition module 11 is configured to obtain respiratory data and initial dynamic PET data within a first preset time period after a tracer is administered to an object to be measured;

[0134] The first image determination module 12 is configured to determine corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data;

[0135] The second image determination module 13 is configured to obtain pseudo-dynamic PET images corresponding to each frame of pseudo-dynamic MR images, and determine the registered pseudo-dynamic PET images through each frame of pseudo-dynamic PET images;

[0136] The registration module 14 is configured to register multiple frames of initial dynamic PET images according to the registered pseudo-dynamic PET images to obtain registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0137] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0138] In one of the embodiments, the registration module 14 includes: a first time mapping unit, a reconstruction unit, and a first registration unit, where:

[0139] The first time mapping unit is configured to perform time mapping on the initial dynamic PET data within the first preset time period according to each frame of pseudo-dynamic PET images to obtain the mapped initial dynamic PET data of each frame of pseudo-dynamic PET images;

[0140] A reconstruction unit for reconstructing the mapped initial dynamic PET data of each frame of dynamic PET images to obtain the corresponding mapped initial dynamic PET images;

[0141] A first registration unit for registering the corresponding mapped initial dynamic PET images through the registered dynamic PET-like images to obtain the registered dynamic PET images.

[0142] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0143] In one embodiment, the second image determination module 13 includes: a deformation field acquisition unit and a second registration unit, where:

[0144] The deformation field acquisition unit is used to acquire the deformation fields corresponding to each frame of dynamic MR-like images;

[0145] The second registration unit is used to register the corresponding dynamic PET-like images according to the deformation fields corresponding to each frame of dynamic MR-like images to obtain the registered dynamic PET-like images.

[0146] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0147] In one embodiment, the deformation field acquisition unit includes: a reference image determination subunit and an image registration subunit, where:

[0148] The reference image determination subunit is used to determine a reference image according to multiple frames of sample MR images;

[0149] The image registration subunit is used to perform image registration on each frame of dynamic MR-like images through the reference image to obtain the deformation fields corresponding to each frame of dynamic MR-like images.

[0150] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0151] In one embodiment, the first image determination module 12 is specifically configured to input respiratory data into a prediction model to obtain multiple frames of dynamic MR-like images corresponding to a first preset time period.

[0152] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0153] In one embodiment, the above image registration device further includes: a data acquisition module and a training module, where:

[0154] A data acquisition module, configured to acquire multiple frames of sample MR images and sample respiratory data within a second preset time period before a tracer is administered to an object to be measured;

[0155] A training module, configured to train an initial prediction model with the multiple frames of sample MR images and sample respiratory data to obtain a prediction model.

[0156] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0157] In one embodiment, the second image determination module 13 includes: a data acquisition unit, a second time mapping unit, and a data reconstruction unit, where:

[0158] The data acquisition unit is configured to acquire initial PET data within a first preset time period;

[0159] The second time mapping unit is configured to perform time mapping on each frame of class dynamic MR image and the initial PET data within the first preset time period to obtain the mapped PET data of each frame of class dynamic MR image;

[0160] The data reconstruction unit is configured to reconstruct the mapped PET data to obtain class dynamic PET images corresponding to each frame of class dynamic MR image.

[0161] The image registration device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0162] For the specific limitations on the image registration device, reference can be made to the limitations on the image registration method in the above text, which will not be elaborated here. Each module in the above image registration device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0163] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 10As shown. The computer device includes a processor, a memory, and a network interface connected via 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 and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store respiratory data and dynamic PET images. The network interface of the computer device is used to communicate with an external endpoint via a network connection. When the computer program is executed by the processor, it implements a method for analyzing the degree of enhancement.

[0164] Those skilled in the art can understand that Figure 10 the structure shown in is only a block diagram of some structures 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 different component arrangements.

[0165] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0166] Obtain respiratory data and initial dynamic PET data within a first preset time period after the test object is administered with a tracer;

[0167] Determine corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data;

[0168] Obtain the pseudo-dynamic PET images corresponding to each frame of pseudo-dynamic MR images, and determine the registered pseudo-dynamic PET images through each frame of pseudo-dynamic PET images;

[0169] Based on the registered pseudo-dynamic PET images, register multiple frames of initial dynamic PET images to obtain registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0170] In one embodiment, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented:

[0171] Obtain respiratory data and initial dynamic PET data within a first preset time period after the test object is administered with a tracer;

[0172] Determine corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data;

[0173] Obtain the class dynamic PET images corresponding to each frame of the class dynamic MR images, and determine the registered class dynamic PET images through each frame of the class dynamic PET images;

[0174] Based on the registered class dynamic PET images, register multiple frames of initial dynamic PET images to obtain the registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0175] In one embodiment, a computer program product is provided, including a computer program, which when executed by a processor implements the following steps:

[0176] Obtain the respiratory data and the initial dynamic PET data within the first preset time period after a tracer is administered to the object to be measured;

[0177] Determine the corresponding multiple frames of class dynamic MR images within the first preset time period according to the respiratory data;

[0178] Obtain the class dynamic PET images corresponding to each frame of the class dynamic MR images, and determine the registered class dynamic PET images through each frame of the class dynamic PET images;

[0179] Based on the registered class dynamic PET images, register multiple frames of initial dynamic PET images to obtain the registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

[0180] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the method embodiments as described above. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0181] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0182] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. An image registration method, characterized in that, The method includes: Obtaining respiratory data and initial dynamic PET data within a first preset time period after a tracer is administered to an object to be measured; Determining corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data; Obtaining pseudo-dynamic PET images corresponding to each frame of the pseudo-dynamic MR images, and determining a registered pseudo-dynamic PET image through each frame of the pseudo-dynamic PET images; Registering multiple frames of initial dynamic PET images based on the registered pseudo-dynamic PET image to obtain a registered dynamic PET image; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

2. The image registration method according to claim 1, wherein, The registering multiple frames of initial dynamic PET images based on the registered pseudo-dynamic PET image to obtain the registered dynamic PET image includes: Performing time mapping on the initial dynamic PET data within the first preset time period based on each frame of the pseudo-dynamic PET images to obtain mapped initial dynamic PET data of each frame of the pseudo-dynamic PET images; Reconstructing the mapped initial dynamic PET data of each frame of the pseudo-dynamic PET images to obtain corresponding mapped initial dynamic PET images; Registering the corresponding mapped initial dynamic PET images through the registered pseudo-dynamic PET image to obtain the registered dynamic PET image.

3. The image registration method according to claim 1 or 2, characterized in that The determining the registered pseudo-dynamic PET image through each frame of the pseudo-dynamic PET images includes: Obtaining a deformation field corresponding to each frame of the pseudo-dynamic MR images; Registering the corresponding pseudo-dynamic PET image according to the deformation field corresponding to each frame of the pseudo-dynamic MR images to obtain the registered pseudo-dynamic PET image.

4. The image registration method according to claim 3, wherein The obtaining the deformation field corresponding to each frame of the pseudo-dynamic MR images includes: Determining a reference image based on multiple frames of sample MR images; Performing image registration on each frame of the pseudo-dynamic MR images through the reference image to obtain a deformation field corresponding to each frame of the pseudo-dynamic MR images.

5. The image registration method according to claim 1 or 2, characterized in that, The determining the corresponding multiple frames of pseudo-dynamic MR images within the first preset time period according to the respiratory data includes: Inputting the respiratory data into a prediction model to obtain corresponding multiple frames of pseudo-dynamic MR images within the first preset time period.

6. The image registration method according to claim 5, characterized in that, The method further includes: Obtaining multiple frames of sample MR images and sample respiratory data within a second preset time period before the tracer is administered to the object to be measured; Training an initial prediction model through the multiple frames of sample MR images and the sample respiratory data to obtain the prediction model.

7. The image registration method according to claim 1 or 2, characterized in that, The obtaining the pseudo-dynamic PET images corresponding to each frame of the pseudo-dynamic MR images includes: Obtaining initial PET data within the first preset time period; Performing time mapping on each frame of the pseudo-dynamic MR images and the initial PET data within the first preset time period to obtain mapped PET data of each frame of the pseudo-dynamic MR images; Reconstructing the mapped PET data to obtain pseudo-dynamic PET images corresponding to each frame of the pseudo-dynamic MR images.

8. An image registration device, characterized in that, The device includes: A data acquisition module for acquiring respiratory data and initial dynamic PET data within a first preset time period after a tracer is administered to an object to be measured; A first image determination module for determining corresponding multiple frames of quasi-dynamic MR images within the first preset time period according to the respiratory data; A second image determination module for obtaining quasi-dynamic PET images corresponding to each frame of quasi-dynamic MR images and determining registered quasi-dynamic PET images through the quasi-dynamic PET images of each frame; A registration module for registering multiple frames of initial dynamic PET images according to the registered quasi-dynamic PET images to obtain registered dynamic PET images; the multiple frames of initial dynamic PET images are images reconstructed from the initial dynamic PET data.

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

10. A 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 1-7 are implemented.

Images