Method, device, computer equipment and storage medium for determining kinetic parameters

Abstract

This application relates to a method, apparatus, computer device, and storage medium for determining kinetic parameters. The method comprises: acquiring at least two sets of scan data from a target region, the at least two sets of scan data corresponding to different time information; inputting the at least two sets of scan data into a trained analysis model to obtain a region of interest (ROI) within the target region; determining a kinetic parameter value based on the ROI and a pharmacokinetic model, the kinetic parameter being related to determining tracer metabolic information within the target region; and reconstructing a dynamic parameter image based on the at least two scan data and the kinetic parameter values. This method can improve the efficiency of obtaining PET kinetic parameters.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular to a method, apparatus, computer equipment, and storage medium for determining dynamic parameters. Background Art

[0002] With the development of nuclear medicine imaging technology, the use of positron emission tomography (PET) parametric imaging can study the absorption, distribution, metabolism and excretion processes of drugs in the human body. The activity and concentration in a specific tissue at a specific time depend on the physiological characteristics of the local tissue (for example, blood flow, receptor density and affinity, etc.) and the input function of the local tissue (for example, tracer activity in arterial blood or plasma, etc.). The PET parametric imaging function can obtain kinetic parameters reflecting the biological characteristics of local tissues or organs through mathematical calculations based on the quantitative mathematical description of the relationship between the changes in tracer concentration in the tissue and the above-mentioned various factors. The obtained kinetic parameters are then provided to doctors as a basis for diagnosis.

[0003] Traditional technology mainly involves acquiring PET-CT images to obtain a CT image sequence, outlining the CT image to obtain the region of interest, and then mapping the outlined region of interest to the PET image. The mapped region of interest in the PET image is analyzed to obtain the dynamic parameters of the mapped region of interest and provide them to doctors as a basis for diagnosis.

[0004] However, the traditional method of obtaining PET kinetic parameters has the problem of low efficiency. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment and storage medium for determining kinetic parameters that can improve the efficiency of obtaining PET kinetic parameters in response to the above technical problems.

[0006] A method for determining kinetic parameters, comprising:

[0007] Acquire at least two sets of scanning data of the target area, where the at least two sets of scanning data correspond to different time information;

[0008] Inputting the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area;

[0009] determining a value of the kinetic parameter based on the region of interest and a pharmacokinetic model, the kinetic parameter being related to determining metabolic information of the tracer within the target region;

[0010] A dynamic parameter image is reconstructed based on the at least two sets of scanning data and the values ​​of the dynamic parameters.

[0011] In one embodiment, determining the value of the kinetic parameter based on the region of interest and the pharmacokinetic model includes:

[0012] determining a time activity curve of each voxel within the region of interest based on the region of interest of the at least two sets of scan data;

[0013] Based on the time-activity curve and the pharmacokinetic model, the value of the kinetic parameter is determined.

[0014] In one embodiment, the pharmacokinetic model comprises a compartmental model.

[0015] In one embodiment, the scanning data includes scanning data acquired by a positron emission tomography (PET) device or a single photon emission tomography (SPECT) device.

[0016] In one embodiment, the region of interest includes the aorta region.

[0017] In one embodiment, the method further comprises:

[0018] Acquire sample scan data and a gold standard image corresponding to the same target area of ​​the sample scan data; the gold standard image is marked with a region of interest of the sample scan data;

[0019] Inputting the sample scan data into an initial analysis model to determine a sample region of interest of the sample scan data;

[0020] The initial analysis model is trained according to the sample region of interest and the region of interest of the sample scanning data to obtain the trained analysis model.

[0021] In one embodiment, the initial analysis model includes a generative adversarial network model.

[0022] A device for determining kinetic parameters, comprising:

[0023] A first acquisition module is configured to acquire at least two sets of scanning data of a target area, wherein the at least two sets of scanning data correspond to different time information;

[0024] a second acquisition module, configured to input the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area;

[0025] a first determining module, configured to determine a value of a kinetic parameter based on the region of interest and a pharmacokinetic model, wherein the kinetic parameter is related to determining metabolic information of the tracer in the target region;

[0026] A reconstruction module is used to reconstruct a dynamic parameter image based on the at least two sets of scanning data and the values ​​of the dynamic parameters.

[0027] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] Acquire at least two sets of scanning data of the target area, where the at least two sets of scanning data correspond to different time information;

[0029] Inputting the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area;

[0030] determining a value of the kinetic parameter based on the region of interest and a pharmacokinetic model, the kinetic parameter being related to determining metabolic information of the tracer within the target region;

[0031] A dynamic parameter image is reconstructed based on the at least two sets of scanning data and the values ​​of the dynamic parameters.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0033] Acquire at least two sets of scanning data of the target area, where the at least two sets of scanning data correspond to different time information;

[0034] Inputting the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area;

[0035] determining a value of the kinetic parameter based on the region of interest and a pharmacokinetic model, the kinetic parameter being related to determining metabolic information of the tracer within the target region;

[0036] A dynamic parameter image is reconstructed based on the at least two sets of scanning data and the values ​​of the dynamic parameters.

[0037] The above-mentioned method, apparatus, computer device and storage medium for determining kinetic parameters can quickly obtain a region of interest (ROI) of the target region by acquiring at least two sets of scan data with different time information of the target region and inputting these two different sets of scan data into a trained analysis model. Thus, based on the determined region of interest and the pharmacokinetic model, the value of the kinetic parameter can be quickly determined, wherein the kinetic parameter is related to the metabolic information of the tracer in the determined target region. Furthermore, based on the acquired at least two sets of scan data of the target region and the determined value of the kinetic parameter, a dynamic parameter image can be quickly reconstructed, thereby improving the efficiency of reconstructing the dynamic parameter image. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 FIG. 1 is an application environment diagram of a method for determining kinetic parameters in one embodiment;

[0039] Figure 2 Schematic diagram of a process for determining kinetic parameters in one embodiment;

[0040] Figure 3 Schematic diagram of a process for determining kinetic parameters in another embodiment;

[0041] Figure 4 Schematic diagram of a process for determining kinetic parameters in another embodiment;

[0042] Figure 5 FIG. 4 is a structural block diagram of a device for determining kinetic parameters in one embodiment. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0044] The method for determining kinetic parameters provided in this application can be applied to Figure 1 The computer device shown. The computer device includes a processor and a memory connected via a system bus, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the following method embodiment can be executed. Optionally, the computer device may further 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, wherein 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 via 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 embodiments of the present application do not limit the specific form of the computer device.

[0045] In one embodiment, Figure 2 As shown, a method for determining kinetic parameters is provided, and this method is applied to Figure 1 The computer device in the example is used to illustrate the process, including the following steps:

[0046] S201 , obtaining at least two sets of scanning data of a target area, where the time information corresponding to the at least two sets of scanning data is different.

[0047] The target area can be a partial area of ​​the object or a whole body area of ​​the object. The object can be an animal, a human body, or a water model, and the partial area of ​​the object can be the brain, legs, chest, or abdomen of the object. Optionally, the scan data includes scan data acquired by a positron emission tomography device or a single photon emission tomography device. For example, the scan data can be a PET (Positron Emission Tomography) image. It should be noted that when the scan data is a PET image, it is possible to avoid acquiring a CT (Computed Tomography) image of the user, thereby reducing the harm of the CT scan radiation dose to the human body. Optionally, the at least two sets of scan data acquired by the computer device can be scan data of the legs acquired at different times, or scan data of the abdomen acquired at different times. Optionally, the computer device may obtain at least two sets of scan data of the target area from a PACS (Picture Archiving and Communication Systems) server, or may obtain at least two sets of scan data of the target area in real time from a scanning device. For example, the computer device may obtain at least two sets of scan data of the target area in real time from a PET device, or may obtain at least two sets of scan data of the target area in real time from a CT device. Exemplarily, the obtained at least two sets of scan data of the target area include scan data of the target area obtained at a first moment, scan data of the target area obtained at a second moment, and so on, where the second moment may be greater than or less than the first moment.

[0048] S202: Input at least two sets of scanning data into a trained analysis model to obtain a region of interest of the target area.

[0049] Specifically, the computer device inputs the acquired at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area. For example, taking the target area as the brain area as an example, the obtained region of interest of the target area can be the brainstem area of ​​the brain, or other areas of the brain, etc., and this embodiment does not limit this. Optionally, in another embodiment, the determined region of interest can include the aortic area. It is understandable that the trained analysis model can be a model trained using historical scan data. Optionally, the trained analysis model can be a model that analyzes CT scan data, or a model that analyzes PET scan data. Optionally, the trained analysis model can be a long short-term memory model, or other types of neural network models, etc. Optionally, the computer device can input the acquired at least two sets of scan data into the trained analysis model in sequence, or can integrate the acquired at least two sets of scan data and input them into the trained analysis model at the same time.

[0050] S203 , determining a value of a kinetic parameter based on the region of interest and the pharmacokinetic model, where the kinetic parameter is related to determining metabolic information of the tracer in the target region.

[0051] Pharmacokinetics is the study of how drug levels in animals change over time. It can investigate the absorption, distribution, metabolism, and excretion of drugs within an organism. A pharmacokinetic model can analyze a defined region of interest (ROI) and measure a time-activity curve (TAC) representing the drug concentration in each organ over time. Specifically, in this embodiment, the pharmacokinetic model can analyze a defined region of interest (ROI) to determine kinetic parameters related to the metabolic information of the tracer within the target region. Optionally, the computer device can solve the pharmacokinetic model based on the defined ROI in the scan data to determine the values ​​of the kinetic parameters. Alternatively, the computer device can obtain relevant parameters of the kinetic model to determine the values ​​of the aforementioned kinetic parameters, such as an input function (IF) and / or a time-activity curve (TAC) of the ROI. The input function can reflect the change in tracer concentration in plasma over time. For example, the input function can be expressed as a TAC indicating the change in tracer concentration in plasma, and the TAC of the ROI can reflect the change in tracer concentration in the ROI over time. Optionally, in this embodiment, the pharmacokinetic model may include a compartment model (eg, a one-compartment model, a two-compartment model) or a retention model.

[0052] S204 , reconstructing a dynamic parameter image based on at least two sets of scanning data and values ​​of the dynamic parameters.

[0053] It will be appreciated that, since the values ​​of the kinetic parameters determined above are related to the metabolic information of the tracer within the determined target region, a dynamic parametric image can be reconstructed based on the at least two sets of scan data and the values ​​of the kinetic parameters obtained above. Optionally, the computer device can construct a reconstruction parameter curve based on the scan data and the values ​​of the kinetic parameters, and reconstruct the dynamic parametric image using the constructed reconstruction parameter curve. Optionally, the computer device can also perform rendering based on the scan data and the values ​​of the kinetic parameters to reconstruct the dynamic parametric image. Alternatively, a user (e.g., a doctor) can select an appropriate kinetic model based on the type of tracer, information about the subject (e.g., the patient's area to be scanned, the patient's body shape), information about the medical device (e.g., PET device) (e.g., the model of the medical device), scan parameters (e.g., the number of beds scanned, the scan time), the type of kinetic parameters desired to be determined, etc., perform parametric imaging, and reconstruct the dynamic parametric image. Alternatively, the computer device can directly or indirectly reconstruct the parametric image based on multiple sets of scan data, the time information corresponding to the multiple sets of scan data, and the kinetic model. The parametric image can include a K1 parameter image, a K2 parameter image, a K3 parameter image, a Ki parameter image, etc., or any combination thereof. It should be noted that each pixel (or voxel) in the reconstructed dynamic parameter image corresponds to a physical point of the object, and the pixel value (or voxel value) of each pixel (or voxel) in the parameter image represents the dynamic parameter value of the corresponding physical point of the object.

[0054] In the above-mentioned method for determining kinetic parameters, by acquiring at least two sets of scanning data with different time information of the target area and inputting these two different sets of scanning data into a trained analysis model, the region of interest of the target area can be quickly obtained, so that the value of the kinetic parameter can be quickly determined based on the determined region of interest and the pharmacokinetic model, wherein the kinetic parameter is related to the metabolic information of the tracer in the determined target area, and then the dynamic parameter image can be quickly reconstructed based on the at least two sets of scanning data of the obtained target area and the value of the determined kinetic parameter, thereby improving the efficiency of reconstructing the dynamic parameter image.

[0055] Furthermore, in one embodiment, Figure 3 As shown, the above S203 includes:

[0056] S301 , determining a time activity curve of each voxel in a region of interest based on a region of interest of at least two sets of scanning data.

[0057] The time-activity curve of each voxel within the region of interest of the scan data is used to represent the change in the drug value in each voxel within the region of interest over time. Optionally, the computer device may determine the time activity of each voxel within the region of interest based on the regions of interest of the at least two sets of scan data, and then delineate the time activity of each voxel within the region of interest to obtain the time-activity curve of each voxel within the region of interest of the scan data.

[0058] S302: Determine the value of the kinetic parameter based on the time-activity curve and the pharmacokinetic model.

[0059] Optionally, the computer device may solve a pharmacokinetic model based on the time-activity curves of each voxel within the region of interest to obtain kinetic parameters related to the metabolic information of the tracer within the determined target region. For example, the computer device may input the time-activity curves of each voxel within the region of interest into the pharmacokinetic model to obtain the values ​​of the kinetic parameters. Alternatively, the computer device may obtain the time-activity of each voxel based on the time-activity curves of each voxel within the region of interest, and then input the time-activity of each voxel into the pharmacokinetic model to determine the values ​​of the kinetic parameters.

[0060] In this embodiment, the computer device can quickly determine the time-activity curve of each voxel in the region of interest based on the region of interest of at least two scan data of the acquired target area, so that the value of the kinetic parameter can be quickly determined based on the acquired time-activity curve and the pharmacokinetic model; in addition, the value of the kinetic parameter can be accurately determined based on the time-activity curve and the pharmacokinetic model, thereby improving the accuracy of determining the value of the kinetic parameter.

[0061] In the above scenario where at least two scan data are input into the trained analysis model to obtain the regions of interest of at least two scan data, it is necessary to train the initial analysis model to obtain the trained analysis model. In one embodiment, Figure 4 As shown, the above method also includes:

[0062] S401 , obtaining sample scan data and a gold standard image corresponding to the same target area of ​​the sample scan data; the gold standard image is marked with a region of interest of the sample scan data.

[0063] The acquired sample scan data may be scan data acquired at different times. Optionally, the sample scan data may be a PET image or a CT image. Optionally, the computer device may delineate the same target area corresponding to the sample scan data to obtain a gold standard image of the same target area corresponding to the sample scan data. That is, the acquired gold standard image is marked with a region of interest of the sample scan data. Optionally, the gold standard image in this embodiment may also be an image with structural anatomical information, such as a CT image or an MR image. Optionally, the target area in this embodiment may be the head area of ​​the scanned subject or the abdominal area of ​​the scanned subject. Optionally, the region of interest of the sample scan data marked in the gold standard image of the same target area corresponding to the sample scan data may be any area of ​​the target area. For example, if the target area is the brain area, the region of interest may be the brainstem area, or other brain areas, etc.

[0064] S402: Input the sample scan data into the initial analysis model to determine the sample region of interest of the sample scan data.

[0065] In this embodiment, the computer device inputs the acquired sample scan data into an initial analysis model, and through the initial analysis model, determines the sample region of interest in the sample scan data. For example, the computer device inputs the scanned subject's head scan data into the initial analysis model to determine the sample region of interest in the head scan data. Alternatively, the computer device may input the scanned subject's abdomen scan data into the initial analysis model to determine the sample region of interest in the abdomen scan data. Optionally, the initial analysis model may include machine learning, such as a deep learning network model, which can automatically learn a large number of parameters acquired from the sample scan data and the gold standard image corresponding to the sample scan data. These parameters can be used to identify and quantify the sample scan data corresponding to the region of interest of the gold standard image, which can greatly speed up the acquisition of the region of interest. Furthermore, the deep learning network model may include a generative adversarial network model. In this embodiment, the sample images are trained by the generative adversarial network model to increase the number of samples, which can solve the problem of a small amount of sample image data. The generative adversarial network model consists of a generative network model and a discriminative network model. Sample scan data is input into the generative network model, and its output needs to mimic the region of interest in the gold standard image corresponding to the sample scan data as much as possible. The discriminative (network) model is fed the output of the generative (network) model, with the goal of distinguishing the output of the generative model from the sample scan data as much as possible. The generative model, on the other hand, needs to generate regions of interest in the sample scan data that the discriminative model cannot distinguish as true or false. The two models compete with each other and continuously adjust parameters, with the ultimate goal of making it impossible for the discriminative network model to determine whether the output of the generative network model is true. In other words, based on the generative adversarial network model, regions of interest in sample scan data that are similar to those in the gold standard image and that are judged as true by the discriminative network can be generated, effectively improving the accuracy of extracting regions of interest from sample scan data.

[0066] In this embodiment, when the sample scan data includes positron emission tomography (PET) data or single photon emission tomography (SPECT) data, compared to images with structural information such as computed tomography (CT), the scanned image can be subjected to image enhancement processing, for example, before being input into the initial analysis model, to make the outline of the region of interest (ROI) in the scanned image (e.g., the boundaries of tumor tissue, adjacent blood vessels, or blood-feeding tissue) clearer. In this embodiment, the scanned image can be segmented before being input into the initial analysis model, for example, by removing background image areas that are not ROI, while retaining the ROI. Preprocessing the scanned image can improve the accuracy of ROI extraction from the scanned image using the initial analysis model. Furthermore, to improve the accuracy of ROI extraction from the scanned image, during the training of the initial analysis model, conventional CT delineation can be mapped to a PET image. The conventional CT delineation and the image mapped to the PET image are used as label data. The sample scan data is then input into the initial analysis model to learn the ROI of the sample scan data, and the initial analysis model is trained using the label data and the obtained ROI of the sample scan data. In addition, the limitations of hardware performance on the training process of the initial analysis model are taken into consideration. For example, considering that the size of the graphics processing unit (GPU) of the device for training the initial analysis model is limited, the sample scanning data can be processed in blocks, and the block data can be input into the initial analysis model, thereby improving the training efficiency of the initial analysis model and accelerating the training speed of the initial analysis model.

[0067] In this embodiment, sample scan data is input into an initial analysis model to determine a sample region of interest (ROI) for the sample scan data. This includes a registration function obtained by the initial analysis model between the sample scan data and a gold standard image corresponding to the sample scan data, specifically, a motion field between the sample scan data and the gold standard image corresponding to the sample scan data. Generally speaking, when scanning a patient, for example, movement of organs such as the heart and lungs caused by medication, respiratory movement, or cardiac motion, can cause the regions of interest corresponding to the sample scan data to differ at different times. Furthermore, differences in the scanning times of the sample scan data and the gold standard image can also result in differences between the sample scan data and the gold standard image. In this embodiment, image registration can be performed between the sample scan data and the gold standard image corresponding to the sample scan data based on the registration function obtained by the initial analysis model, thereby optimizing the training of the initial analysis model and improving the accuracy of the region of interest obtained for the sample scan data.

[0068] S403 : Training the initial analysis model according to the sample scan data and the region of interest of the sample scan data to obtain a trained analysis model.

[0069] Optionally, the computer device may compare the sample region of interest with the region of interest of the sample scan data to obtain a loss function for the initial analysis model, and train the initial analysis model using the loss function of the initial analysis model to obtain the trained analysis model. Optionally, the computer device may use the value of the loss function of the initial analysis model to adjust the parameters of the initial analysis model, and use the adjusted parameters of the initial analysis model to obtain an adjusted analysis model, thereby further obtaining a trained analysis model based on the adjusted analysis model.

[0070] In this embodiment, the computer device obtains sample scanning data and a gold standard image of the same target area corresponding to the sample scanning data, and inputs the sample scanning data into the initial analysis model, so as to quickly determine the sample region of interest of the sample scanning data. Then, the initial analysis model can be quickly trained based on the sample region of interest and the region of interest of the sample scanning data to obtain a trained analysis model, thereby improving the efficiency of obtaining the trained analysis model.

[0071] It should be understood that although Figure 2-4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2-4 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0072] In one embodiment, Figure 5 As shown, a device for determining dynamic parameters is provided, comprising: a first acquisition module, a second acquisition module, a first determination module and a reconstruction module, wherein:

[0073] The first acquisition module is configured to acquire at least two sets of scanning data of the target area, where the time information corresponding to the at least two sets of scanning data is different.

[0074] The second acquisition module is used to input at least two sets of scanning data into the trained analysis model to obtain a region of interest in the target area.

[0075] The first determination module is used to determine a value of a kinetic parameter based on the region of interest and the pharmacokinetic model, where the kinetic parameter is related to metabolic information of the tracer in the target region.

[0076] The reconstruction module is used to reconstruct a dynamic parameter image based on at least two sets of scanning data and values ​​of dynamic parameters.

[0077] Optionally, the pharmacokinetic model includes a compartmental model.

[0078] Optionally, the scanning data includes scanning data acquired by a positron emission tomography device or a single photon emission tomography device.

[0079] Optionally, the region of interest includes the aorta region.

[0080] The device for determining kinetic parameters provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be described in detail here.

[0081] Based on the above embodiment, optionally, the first determining module includes: a first determining unit and a second determining unit; wherein:

[0082] The first determining unit is configured to determine a time activity curve of each voxel in the region of interest based on the region of interest of at least two sets of scanning data.

[0083] The second determining unit is used to determine the value of the kinetic parameter based on the time activity curve and the pharmacokinetic model.

[0084] The device for determining kinetic parameters provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be described in detail here.

[0085] Based on the above embodiment, optionally, the above apparatus further includes: a third acquisition module, a second determination module, and a training module, wherein:

[0086] The third acquisition module is used to acquire the sample scanning data and a gold standard image corresponding to the same target area of ​​the sample scanning data; the gold standard image is marked with a region of interest of the sample scanning data.

[0087] The second determination module is configured to input the sample scanning data into the initial analysis model and determine the sample region of interest of the sample scanning data.

[0088] The training module is used to train the initial analysis model according to the sample region of interest and the region of interest of the sample scanning data to obtain a trained analysis model.

[0089] Optionally, the initial analysis model includes a generative adversarial network model.

[0090] The device for determining kinetic parameters provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effects are similar, which will not be described in detail here.

[0091] The specific definition of the kinetic parameter determination device can be found in the definition of the kinetic parameter determination method above and will not be repeated here. The various modules in the above-mentioned kinetic parameter determination device can be implemented in whole or in part by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be 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.

[0092] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0093] Acquire at least two sets of scanning data of the target area, where the time information corresponding to the at least two sets of scanning data is different;

[0094] Inputting at least two sets of scan data into the trained analysis model to obtain a region of interest in the target area;

[0095] Based on the region of interest and the pharmacokinetic model, the values ​​of the kinetic parameters are determined, and the kinetic parameters are related to determining the metabolic information of the tracer in the target region;

[0096] A dynamic parameter image is reconstructed based on the at least two sets of scan data and the values ​​of the dynamic parameters.

[0097] The implementation principle and technical effects of the computer device provided in the above embodiment are similar to those of the above method embodiment and will not be repeated here.

[0098] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0099] Acquire at least two sets of scanning data of the target area, where the time information corresponding to the at least two sets of scanning data is different;

[0100] Inputting at least two sets of scan data into the trained analysis model to obtain a region of interest in the target area;

[0101] Based on the region of interest and the pharmacokinetic model, the values ​​of the kinetic parameters are determined, and the kinetic parameters are related to determining the metabolic information of the tracer in the target region;

[0102] A dynamic parameter image is reconstructed based on the at least two sets of scan data and the values ​​of the dynamic parameters.

[0103] The computer-readable storage medium provided in the above embodiment has similar implementation principles and technical effects to those of the above method embodiment, and will not be described in detail here.

[0104] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. 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).

[0105] The technical features of the above embodiments can 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.

[0106] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining kinetic parameters, characterized in that: The method comprises: Acquire at least two sets of scanning data of the target area, where the at least two sets of scanning data correspond to different time information; Inputting the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area; determining a value of a kinetic parameter based on the region of interest and a pharmacokinetic model, the kinetic parameter being related to determining metabolic information of the tracer within the target region; the pharmacokinetic model being selected based on a type of tracer, information about a subject corresponding to the target region, information about a medical device that acquired the at least two sets of scan data, scan parameters, and a type of kinetic parameter desired to be determined; reconstructing a dynamic parameter image based on the at least two sets of scan data and the values ​​of the dynamic parameters; Acquire sample scan data and a gold standard image corresponding to the same target area of ​​the sample scan data; the gold standard image is marked with a region of interest of the sample scan data; wherein the sample scan data includes a CT image and a PET image, and the outline of the CT image is mapped to the PET image, and the pair of images of the outline of the CT image and the image mapped to the PET image are used as label data; Inputting the sample scan data into an initial analysis model to determine a sample region of interest of the sample scan data; Inputting the sample scan data into the initial analysis model to determine the sample region of interest of the sample scan data includes: obtaining a registration function through the initial analysis model, and performing image registration on the sample scan data and a gold standard image corresponding to the sample scan data according to the registration function; The initial analysis model is trained according to the sample region of interest and the region of interest of the sample scanning data to obtain the trained analysis model.

2. The method according to claim 1, characterized in that Determining the value of the kinetic parameter based on the region of interest and the pharmacokinetic model includes: determining a time activity curve of each voxel within the region of interest based on the region of interest of the at least two sets of scan data; Based on the time-activity curve and the pharmacokinetic model, the value of the kinetic parameter is determined.

3. The method according to claim 1, characterized in that The pharmacokinetic model includes a compartmental model.

4. The method according to claim 1, wherein The scanning data includes scanning data acquired by a positron emission tomography device or a single photon emission tomography device.

5. The method according to claim 1, wherein The region of interest includes the aorta region.

6. The method according to claim 1, wherein The initial analysis model includes a generative adversarial network model.

7. The method according to claim 1, characterized in that Before inputting the sample scan data into the initial analysis model, the method further includes: The sample scan data is processed into blocks.

8. A device for determining kinetic parameters, characterized in that: The device comprises: A first acquisition module is configured to acquire at least two sets of scanning data of a target area, wherein the at least two sets of scanning data correspond to different time information; a second acquisition module, configured to input the at least two sets of scan data into a trained analysis model to obtain a region of interest of the target area; a first determination module, configured to determine a value of a kinetic parameter based on the region of interest and a pharmacokinetic model, wherein the kinetic parameter is related to determining metabolic information of the tracer within the target region; the pharmacokinetic model is selected based on a type of tracer, information about a subject corresponding to the target region, information about a medical device that acquires the at least two sets of scan data, scan parameters, and a type of kinetic parameter desired to be determined; a reconstruction module, configured to reconstruct a dynamic parameter image based on the at least two sets of scanning data and the values ​​of the dynamic parameters; a third acquisition module, configured to acquire sample scan data and a gold standard image corresponding to the same target area of ​​the sample scan data; the gold standard image being marked with a region of interest of the sample scan data; wherein the sample scan data includes a CT image and a PET image, mapping a contour of the CT image to the PET image, and using the contour of the CT image and the pair of images mapped to the PET image as label data; a second determining module, configured to input the sample scan data into an initial analysis model to determine a sample region of interest of the sample scan data; The second determining module is further configured to obtain a registration function using the initial analysis model, and perform image registration on the sample scan data and a gold standard image corresponding to the sample scan data according to the registration function; A training module is used to train the initial analysis model according to the sample region of interest and the region of interest of the sample scanning data to obtain the trained analysis model.

9. 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 7 are implemented.

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

Images