Image generation method and device, equipment and storage medium

Abstract

The invention relates to an image generation method and device, equipment and a storage medium. The method comprises the following steps: acquiring a tissue-to-blood concentration ratio corresponding to each scanning moment within a first scanning duration, and generating a target tissue shooting rate image of a scanned object according to the tissue-to-blood concentration ratio and a preset mapping relationship; the mapping relation represents the relation among the scanning moment, the blood activity value corresponding to the scanning moment and the accumulated blood activity value corresponding to the scanning moment, so that the accumulated blood activity value in the scanning time period corresponding to the scanning moment is obtained based on the mapping relation; therefore, the target tissue shooting rate image is obtained based on the accumulated blood activity values, the blood activity values and the plurality of tissue-to-blood concentration ratios, and the scanning object does not need to be continuously scanned for a long time.

Description

Technical Field

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

[0002] K i Parametric images are macroscopic parameter images commonly used for quantitative analysis in positron emission computed tomography (PET). They represent the uptake rate of tracers in tissues. The parametric images can provide better lesion detection capabilities and predict lesion conditions.

[0003] Currently, it is necessary to perform a long-term full-dynamic scan of the scanned object to obtain a dynamic PET image. i Parameter image. Summary of the invention

[0004] Based on this, it is necessary to provide an image generation method, device, equipment and storage medium that can reduce the scanning time in order to solve the above technical problems.

[0005] In a first aspect, the present application provides an image generation method, comprising:

[0006] Obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each of the tissue-to-blood concentration ratios is a ratio of a tissue activity value to a blood activity value of the scanned object at each of the scanning moments;

[0007] A target tissue uptake rate image of the scanned object is generated based on a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0008] In one embodiment, generating a target tissue uptake rate image of the scanned object according to a preset mapping relationship between each tissue-to-blood concentration ratio and the preset mapping relationship includes:

[0009] According to the preset feature extraction model and the ratio of each tissue to blood concentration, an initial tissue uptake rate image and an initial distribution volume image are obtained; the standard time is the ratio between the cumulative blood activity value in the scanning time period corresponding to the scanning moment within the first scanning time length and the blood activity value corresponding to the scanning moment;

[0010] Based on the mapping relationship, the standard time corresponding to each scanning moment is acquired; and the target tissue uptake rate image is generated according to the initial tissue uptake rate image, the initial distribution volume image and each standard time.

[0011] In one embodiment, generating the target tissue uptake rate image according to the initial tissue uptake rate image, the initial distribution volume image and each standard time comprises:

[0012] acquiring an intermediate distribution volume image according to the initial tissue uptake rate image, each of the tissue-to-blood concentration ratios and each of the standard times;

[0013] Correcting the initial distribution volume image according to the intermediate distribution volume image to obtain a target distribution volume image;

[0014] The target tissue uptake rate image is generated based on the initial tissue uptake rate image, the target distribution volume image and each of the standard times.

[0015] In one embodiment, generating the target tissue uptake rate image based on each of the initial tissue uptake rates, each of the target distribution volumes and each of the standard times comprises:

[0016] Based on the initial tissue uptake rate image, the target distribution volume image and the standard time, correcting each tissue-to-blood concentration ratio to obtain a corrected tissue-to-blood concentration ratio at each scanning time;

[0017] The target tissue uptake rate image is generated according to the difference value between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio.

[0018] In one embodiment, generating the target tissue uptake rate image according to the difference between each tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio comprises:

[0019] In the case where the difference value is greater than a preset difference threshold, the parameters of the feature extraction model are updated according to each of the difference values, the updated feature extraction model is used as the feature extraction model, and the step of obtaining an initial tissue uptake rate image and an initial distribution volume image according to the preset feature extraction model and each of the tissue-to-blood concentration ratios is returned to be executed until the difference value is less than or equal to the difference threshold;

[0020] When the difference value is less than or equal to the difference threshold, the corresponding initial tissue uptake rate image is used as the target tissue uptake rate image.

[0021] In one embodiment, generating a target tissue uptake rate image of the scanned object according to a preset mapping relationship between each tissue-to-blood concentration ratio and the preset mapping relationship includes:

[0022] Based on the mapping relationship, a standard time corresponding to each scanning moment is obtained; the standard time is a ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment;

[0023] The target tissue uptake rate image is generated by fitting the tissue-to-blood concentration ratio and the standard time corresponding to the scanning moment.

[0024] In one embodiment, the process of obtaining the mapping relationship includes:

[0025] Obtaining a sample standard time at each scanning moment; the sample standard time is a ratio of a cumulative blood activity value in a scanning time period corresponding to each scanning moment within a second scanning duration to a blood activity value at the corresponding scanning moment; the second scanning duration is greater than the first scanning duration;

[0026] The mapping relationship is obtained by fitting the plurality of scanning moments and the sample standard time corresponding to the scanning moments.

[0027] In a second aspect, the present application further provides an image generating device, comprising:

[0028] A first acquisition module is used to acquire a tissue-to-blood concentration ratio corresponding to each scanning moment within a first scanning duration; each tissue-to-blood concentration ratio is a ratio of a tissue activity value to a blood activity value of the scanned object at each scanning moment;

[0029] A generation module is used to generate a target tissue uptake rate image of the scanned object according to a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize the mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0030] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] Obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each of the tissue-to-blood concentration ratios is a ratio of a tissue activity value to a blood activity value of the scanned object at each of the scanning moments;

[0032] A target tissue uptake rate image of the scanned object is generated based on a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] Obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each of the tissue-to-blood concentration ratios is a ratio of a tissue activity value to a blood activity value of the scanned object at each of the scanning moments;

[0035] A target tissue uptake rate image of the scanned object is generated based on a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0036] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0037] Obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each of the tissue-to-blood concentration ratios is a ratio of a tissue activity value to a blood activity value of the scanned object at each of the scanning moments;

[0038] A target tissue uptake rate image of the scanned object is generated based on a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0039] The above-mentioned image generation method, device, equipment and storage medium generate a target tissue uptake rate image of the scanned object by acquiring the tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration, and according to the mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein each tissue-to-blood concentration ratio is a ratio of the tissue activity value to the blood activity value of the scanned object at each scanning moment, and the mapping relationship is used to characterize the mapping relationship between the scanning moment, the blood activity value corresponding to the scanning moment, and the cumulative blood activity value in the scanning time period corresponding to the scanning moment. Since the mapping relationship characterizes the relationship between the scanning moment, the blood activity value corresponding to the scanning moment, and the cumulative blood activity value corresponding to the scanning moment, the embodiment of the present application obtains the cumulative blood activity value in the scanning time period corresponding to the scanning moment based on the mapping relationship, thereby obtaining the target tissue uptake rate image based on each cumulative blood activity value, each blood activity value and multiple tissue-to-blood concentration ratios, without the need to perform a long-term continuous scan of the scanned object. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] FIG1 is a diagram showing an application environment of an image generation method according to an embodiment;

[0042] FIG2 is a schematic diagram of a flow chart of an image generating method in one embodiment;

[0043] FIG3 is a schematic diagram of a target tissue uptake rate image in one embodiment;

[0044] FIG4 is a schematic diagram of a target tissue uptake rate image in another embodiment;

[0045] FIG5 is a schematic diagram of a flow chart of an image generating method in one embodiment;

[0046] FIG6 is a schematic flow chart of a method for generating a target tissue uptake rate image in one embodiment;

[0047] FIG7 is a schematic flow chart of a method for generating a target tissue uptake rate image in another embodiment;

[0048] FIG8 is a schematic flow chart of a method for generating a target tissue uptake rate image in another embodiment;

[0049] FIG9 is a schematic diagram of a flow chart of a method for acquiring a mapping relationship in one embodiment;

[0050] FIG10 is a schematic diagram of a mapping relationship in one embodiment;

[0051] FIG11 is a schematic diagram of a mapping relationship in another embodiment;

[0052] FIG12 is a schematic diagram of a mapping relationship in another embodiment;

[0053] FIG13 is a schematic diagram of a mapping relationship in another embodiment;

[0054] FIG14 is a schematic flow chart of an image generating method in another embodiment;

[0055] FIG. 15 is a structural block diagram of an image generating device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] Compared with other images, the biggest advantage of PET imaging is that it can be analyzed quantitatively. However, accurate quantitative analysis requires long-term acquisition. Even healthy people find it difficult to remain still for such a long time. In addition, it increases the scanning cost and reduces the bed turnover rate in hospitals. In clinical diagnosis, because it is impossible to scan patients for a long time, conventional PET imaging widely uses the Standard Uptake Value (SUV) for semi-quantitative analysis. However, the distribution of PET tracers is a dynamic process, and many factors can interfere with SUV, thereby affecting clinical diagnosis. Compared with semi-quantitative analysis parameters such as SUV, it is a commonly used macroscopic parameter in quantitative analysis, which represents the comprehensive uptake of drugs in tissues. This parameter can provide better lesion detection capabilities.

[0058] PET scanning is a highly sensitive, non-invasive method used to study the in vivo status of human physiology, metabolism, and molecular pathways. 18 F-fluorodeoxyglucose ( 18 The uptake rate constant K obtained by PET image analysis under the presence of F-FDG tracer i The parameter image is 18 F-FDG uptake provides fine quantification. i Parametric images excel in differentiating benign from malignant lesions, improving lesion detection, and may play a key role in guiding treatment decisions and designing clinical trials.

[0059] However, using 18 F-FDG PET generates Ki Parametric images typically require scan times of more than 60 minutes, which can cause patient discomfort and increase the risk of motion-related artifacts in the image. In addition, these extended scan times can also reduce the turnover rate of the equipment, lead to increased operating expenses, and increase the financial burden on patients alone. Therefore, the present application proposes an image generation method, device, equipment, and storage medium that can reduce the scan time.

[0060] The image generation method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. The application environment includes a computer device, which can be a server, and its internal structure diagram can be shown in Figure 1. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to image generation. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an image generation method is implemented. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0061] Those skilled in the art will understand that the structure shown in FIG. 1 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0062] In an exemplary embodiment, as shown in FIG2 , an image generation method is provided, which is described by taking the method applied to the computer device in FIG1 as an example, and includes the following S201 to S202. Wherein:

[0063] S201, obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within a first scanning duration; each tissue-to-blood concentration ratio is a ratio of a tissue activity value to a blood activity value of a scanned object at each scanning moment.

[0064] The first scanning time may be 50-60 minutes, 20-30 minutes, 30-60 minutes, etc. after the tracer is injected.

[0065] In the embodiment of the present application, the tissue activity value at each scanning moment can be obtained from the PET image obtained after the scanned object is PET scanned. Since the first scanning duration is scanned, multiple frames of PET images will be obtained. For each scanning moment, the tissue activity value corresponding to each pixel can be obtained based on the PET image corresponding to the scanning moment. The blood activity value can also be obtained based on the PET image analysis.

[0066] Using the blood activity value at each scanning time The tissue activity value at the corresponding scanning time is normalized to obtain the tissue-to-blood concentration ratio. Since the tissue activity value includes the tissue activity value corresponding to each pixel in the PET image , so the tissue-to-blood concentration ratio at each scanning moment includes the tissue-to-blood concentration ratio corresponding to each pixel point, that is, the tissue-to-blood concentration ratio of a pixel point can be expressed as .

[0067] S202, generating a target tissue uptake rate image of the scanned object according to a preset mapping relationship between the ratio of each tissue to blood concentration; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

[0068] Patlak graphical analysis is a kinetic model that is commonly used in medical imaging, especially in positron emission tomography, to quantify the uptake and metabolism of certain tracers by tissues. Therefore, K can be obtained based on the Patlak graphical analysis method. i Parameter image, that is, according to Get the target tissue uptake rate, K i is the tissue uptake rate parameter corresponding to a pixel, v i is the distribution volume corresponding to the pixel point, 0-t is the scanning time period, and the K corresponding to each pixel point is obtained. i After the parameters are calculated, K i Parameter image. Assume that, in the case of scanning for 60 minutes, the K obtained based on the Patlak graphical analysis method i The parameter image is shown in Figure 3.

[0069] Since the present application performs PET scanning based on the first scanning duration, which is shorter than the complete scanning duration, the short-duration scanning cannot obtain the cumulative blood activity value within the 0-t scanning time period.

[0070] The mapping relationship is used to characterize the mapping relationship between the scanning time, the blood activity value corresponding to the scanning time, and the cumulative blood activity value in the scanning time period corresponding to the scanning time. The blood activity value corresponding to the scanning time is known. Substituting the scanning time into the mapping relationship can obtain the cumulative blood activity value corresponding to the scanning time, and the above-mentioned , that is, the ratio of blood concentration integrated to the instantaneous time, or it can also be called normalized time. Therefore, the mapping relationship can be used as a representation relationship of the ratio of blood concentration integrated to the instantaneous time. For example, the first scan duration is 20-60 minutes after the injection of the tracer, and the blood activity value at the 20th minute is known. Based on the mapping relationship, the cumulative blood activity value within 0-20 minutes can be obtained.

[0071] In the embodiment of the present application, a mapping relationship is used to obtain the ratio of the cumulative blood activity value corresponding to each scanning time to the blood activity value at each scanning time, and the ratio is used as the standard time. Since the first scanning time is scanned, for each pixel point, the tissue-to-blood concentration ratio at multiple scanning times within the first scanning time is fitted with multiple tissue-to-blood concentration ratios and the standard time at the corresponding scanning time, and the target tissue uptake rate K corresponding to the pixel point can be obtained. i , thus obtaining the target tissue uptake rate K i The parameter image of the target tissue uptake rate. i The result of the parameter image is shown in Figure 4. It can be found that the K obtained by scanning for 40 minutes is different from that obtained by scanning for 60 minutes in Figure 3. i The parameter images remain basically the same and the differences are negligible.

[0072] In another possible implementation, multiple tissue-to-blood concentration ratios can be input into the feature extraction network model to obtain an initial tissue uptake rate image and an initial distribution volume image. The feature extraction network is updated based on multiple standard times, initial distribution volume images, and initial tissue uptake rate images to obtain a target tissue uptake rate image.

[0073] In the above-mentioned image generation method, by obtaining the tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration, a target tissue uptake rate image of the scanned object is generated according to the mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein each tissue-to-blood concentration ratio is a ratio of the tissue activity value to the blood activity value of the scanned object at each scanning moment, and the mapping relationship is used to characterize the mapping relationship between the scanning moment, the blood activity value corresponding to the scanning moment, and the cumulative blood activity value in the scanning time period corresponding to the scanning moment. Since the mapping relationship characterizes the relationship between the scanning moment, the blood activity value corresponding to the scanning moment, and the cumulative blood activity value corresponding to the scanning moment, the embodiment of the present application obtains the cumulative blood activity value in the scanning time period corresponding to the scanning moment based on the mapping relationship, thereby obtaining the target tissue uptake rate image based on each cumulative blood activity value, each blood activity value, and multiple tissue-to-blood concentration ratios, without the need to perform a long-term continuous scan of the scanned object.

[0074] In one embodiment, a target tissue uptake rate image of a scanned object is generated according to a preset mapping relationship between each tissue-to-blood concentration ratio and the preset mapping relationship, including: obtaining an initial tissue uptake rate image and an initial distribution volume image according to a preset feature extraction model and each tissue-to-blood concentration ratio; obtaining a standard time corresponding to each scanning moment based on the mapping relationship; generating a target tissue uptake rate image according to the initial tissue uptake rate image, the initial distribution volume image and each standard time;

[0075] The standard time is the ratio of the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration to the blood activity value corresponding to the scanning moment, that is, the blood concentration ratio integrated to the instant, or it can also be called the normalized time.

[0076] Optionally, the feature extraction model can be a recurrent neural network, a machine learning algorithm, etc.

[0077] In the embodiment of the present application, as shown in FIG5 , the feature extraction model may include an input layer (circle shown in FIG5 ), a bidirectional long short-term memory layer BiLSTM (square shown in FIG5 ) and a fully connected layer (octagon shown in FIG5 ), and the BiLSTM layer is configured as a LSTM unit with two dimensions in the hidden layer. The tissue-to-blood concentration ratio at each scanning moment is input into the BiLSTM layer to extract the time feature of each tissue-to-blood concentration ratio to obtain a time feature vector, and the time feature vector is input into the fully connected layer, and the time feature vector is processed by dimension conversion and the like using the fully connected layer to output the initial tissue uptake rate K corresponding to each pixel point i0 and the initial distribution volume v i0 , namely the initial tissue uptake rate image and the initial distribution volume image.

[0078] Assume that the mapping relationship is a linear mapping relationship, and the mapping relationship is expressed as , a is the slope of the mapping relationship, and b is the intercept of the mapping relationship. Based on the mapping relationship, the ratio of the cumulative blood activity value in the scanning time period corresponding to each scanning moment to the blood activity value corresponding to the scanning moment can be obtained, that is, the standard time.

[0079] Furthermore, each tissue-to-blood concentration ratio can be corrected according to the initial tissue uptake rate image, the initial distribution volume image and each standard time to obtain a corrected tissue-to-blood concentration ratio, that is, the tissue-to-blood concentration ratio of each pixel at each scanning moment is corrected using the initial tissue uptake rate parameter of each pixel in the initial tissue uptake rate image, the initial distribution volume parameter of the corresponding pixel and the standard time of each scanning moment to obtain a corrected tissue-to-blood concentration ratio of each pixel at each scanning moment. For example, the tissue-to-blood concentration ratio of the first pixel at the 20th minute can be corrected using the initial tissue uptake rate parameter of the first pixel in the initial tissue uptake rate image, the initial distribution volume parameter of the first pixel in the initial distribution volume image and the standard time of the 20th minute to obtain a corrected tissue-to-blood concentration ratio. Thus, the parameters of the feature extraction network model are iteratively updated according to each corrected tissue-to-blood concentration ratio and each tissue-to-blood concentration ratio to output the target tissue uptake rate image.

[0080] In another possible implementation, it is also possible to obtain an intermediate distribution volume image based on the initial tissue uptake rate image, the initial distribution volume image and each standard time, correct the initial distribution volume image based on the intermediate distribution volume image to obtain a target distribution volume image, and further generate a target tissue uptake rate image based on the initial tissue uptake rate image, the target distribution volume image and each standard time.

[0081] In an embodiment of the present application, an initial tissue uptake rate image and an initial distribution volume image are obtained according to a preset feature extraction model and the ratio of each tissue to blood concentration. Based on a mapping relationship, the standard time corresponding to each scanning moment is obtained. According to the initial tissue uptake rate image, the initial distribution volume image and each standard time, a target tissue uptake rate image is generated. Since PET images may contain redundant information such as noise, the present application uses a feature extraction model to obtain a target tissue uptake rate image based on the mapping relationship, which can reduce the scanning time while obtaining a high-quality target tissue uptake rate image.

[0082] FIG6 is a flow chart of a method for generating a target tissue uptake rate image in an embodiment. As shown in FIG6 , the embodiment of the present application relates to a possible implementation method of generating a target tissue uptake rate image according to an initial tissue uptake rate image, an initial distribution volume image and each standard time, including the following steps:

[0083] S601, acquiring an intermediate distribution volume image according to the initial tissue uptake rate image, the concentration ratio of each tissue to blood and each standard time.

[0084] In the embodiment of the present application, the tissue-to-blood concentration ratio corresponding to each scanning moment under each pixel is averaged to obtain the average tissue-to-blood concentration ratio. Taking the mapping relationship in the embodiment of FIG. 5 as an example, the standard time at each scanning moment can be obtained based on the mapping relationship, and the standard time at each scanning moment is averaged to obtain the average standard time. For each pixel in the initial tissue uptake rate image, the product result of the initial tissue uptake rate parameter and the average standard time of each pixel in the initial tissue uptake rate image is obtained, and the product result of the corresponding pixel is subtracted from the average tissue-to-blood concentration ratio corresponding to each pixel to obtain the intermediate distribution volume parameter of each pixel to obtain the intermediate distribution volume image. For example, the first scanning time is 50-60 minutes after the injection of the tracer. According to the mapping relationship, the standard time corresponding to each scanning moment of the 50-60 minutes can be obtained, and the average standard time is averaged to obtain the average standard time. The product result of the initial tissue uptake rate parameter and the average standard time of each pixel in the initial tissue uptake rate image is obtained. Furthermore, the average tissue-to-blood concentration ratio of each pixel at the 50th to 60th minute minus the product of the corresponding pixel is used to obtain the intermediate distribution volume parameter of each pixel, that is, the intermediate distribution volume image.

[0085] The intermediate distribution volume parameter of each pixel in the above intermediate distribution volume image is It can be expressed as ,in, is the average tissue-to-blood concentration ratio of each pixel, The average standard time.

[0086] S602, correcting the initial distribution volume image according to the intermediate distribution volume image to obtain a target distribution volume image.

[0087] In the embodiment of the present application, the corresponding pixel points in the intermediate distribution volume image and the initial distribution volume image can be averaged to obtain the target distribution volume image. That is, for each pixel point in the initial distribution volume image, the average value of the intermediate distribution volume parameter and the initial distribution volume parameter of the corresponding pixel point is obtained, and the average value is used as the target distribution volume parameter of the pixel point. , the target distribution volume image can be obtained, that is, .

[0088] In a possible implementation, the intermediate distribution volume image and the initial distribution volume image may be weighted fused to obtain a target distribution volume image.

[0089] S603, generating a target tissue uptake rate image based on the initial tissue uptake rate image, the target distribution volume image and each standard time.

[0090] In the embodiment of the present application, for each pixel point, the tissue-to-blood concentration ratio of the pixel point at each scanning moment can be corrected based on the initial tissue uptake rate parameter of the corresponding pixel point, the target distribution volume parameter and the standard time of each scanning moment to obtain a corrected tissue-to-blood concentration ratio. According to the difference between the corrected tissue-to-blood concentration ratio of each pixel point at each scanning moment and the corresponding tissue-to-blood concentration ratio, a target tissue uptake rate image is generated.

[0091] In a possible implementation, the initial tissue uptake rate image may be optimized according to the target distribution volume image and each standard time to obtain a target tissue uptake rate image.

[0092] In an embodiment of the present application, an intermediate distribution volume image is obtained based on the initial tissue uptake rate image, the ratio of each tissue to blood concentration and each standard time, the initial distribution volume image is corrected based on the intermediate distribution volume image to obtain a target distribution volume image, and a target tissue uptake rate image is generated based on the initial tissue uptake rate image, the target distribution volume image and each standard time. In an embodiment of the present application, since the feature extraction network has two convergence nodes, namely the tissue uptake rate convergence node and the distribution volume convergence node, the initial distribution volume image is corrected using the intermediate distribution volume image, and by aligning the distribution volume parameters output by the feature extraction model with the tissue uptake rate obtained from the Patlak equation, the convergence of the feature extraction network model can be mainly affected by the initial tissue uptake rate image, thereby improving the quality of the target tissue uptake rate image generation.

[0093] FIG7 is a flow chart of a method for generating a target tissue uptake rate image in another embodiment. As shown in FIG7 , the embodiment of the present application relates to a possible implementation method of generating a target tissue uptake rate image based on each initial tissue uptake rate, each target distribution volume and each standard time, including the following steps:

[0094] S701, based on the initial tissue uptake rate image, the target distribution volume image and each standard time, correct each tissue-to-blood concentration ratio to obtain a corrected tissue-to-blood concentration ratio at each scanning time.

[0095] In the embodiment of the present application, for each pixel point, the tissue-to-blood concentration ratio of the pixel point at each scanning moment can be corrected based on the initial tissue uptake rate parameter of the corresponding pixel point, the target distribution volume parameter and the standard time of each scanning moment to obtain the corrected tissue-to-blood concentration ratio Y(t). That is, it can be expressed as .

[0096] S702, generating a target tissue uptake rate image according to the difference between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio.

[0097] In the embodiment of the present application, the parameters of the feature extraction model can be optimized according to the difference between the tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio to obtain a new feature extraction model, and the target tissue uptake rate image can be obtained based on the new feature extraction model and the tissue-to-blood concentration ratio at each scanning moment. Alternatively, the initial tissue uptake rate image can be optimized according to the difference between each tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio to obtain the target tissue uptake rate image.

[0098] Specifically, a target tissue uptake rate image is generated according to the difference value between each tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio, including: when the difference value is greater than a preset difference threshold, the parameters of the feature extraction model are updated according to each difference value, the updated feature extraction model is used as the feature extraction model, and the steps of obtaining an initial tissue uptake rate image and an initial distribution volume image according to the preset feature extraction model and each tissue-to-blood concentration ratio are returned to be executed until the difference value is less than or equal to the difference threshold; when the difference value is less than or equal to the difference threshold, the corresponding initial tissue uptake rate image is used as the tissue uptake rate image.

[0099] In an embodiment of the present application, the parameters of the feature extraction model are updated according to each difference value, and the updated feature extraction model is used as the feature extraction model. The tissue-to-blood concentration ratio at each scanning moment continues to be input into the feature extraction model (i.e., the updated feature extraction model), and the above steps of using the feature extraction model and each tissue-to-blood concentration ratio to obtain the initial tissue uptake rate image and the initial distribution volume image are repeated. If the difference value is less than or equal to the preset difference threshold, the initial tissue uptake rate image output by the feature extraction model (i.e., the updated feature extraction model) is used as the target tissue uptake rate image. If the difference value is greater than the preset difference threshold, the feature extraction network model is continuously updated until the difference value is less than or equal to the preset difference threshold. Continuing with the above FIG. 3 as an example, the tracer is 18 F-FDG, using the method proposed in the embodiment of the present application, can generate K from the PET images (i.e., tissue activity values ​​and blood activity values) obtained by short-term dynamic PET scanningi Parameter images are obtained without using any extended dynamic PET images for training. Unlike the Patlak graphical analysis method that requires the blood time activity curve (TAC) obtained during the entire scanning period, that is, the blood activity value during each scanning period, the method proposed in the embodiment of the present application only requires a short-term blood TAC.

[0100] Optionally, the feature extraction model can be updated using the Mean-Square Error (MSE) loss function, which is defined as follows:

[0101] , N is the total number of tissue-to-blood concentration ratios.

[0102] In an embodiment of the present application, based on the initial tissue uptake rate image, the target distribution volume image and each standard time, each tissue-to-blood concentration ratio is corrected to obtain the corrected tissue-to-blood concentration ratio at each scanning moment, and the target tissue uptake rate image is generated according to the difference between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio. In the actual application process, the present application uses the difference between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio for self-supervised training to obtain the target tissue uptake rate image, and does not need to use any dynamic PET data that extends the scanning time to pre-train the feature extraction model, nor does it need to obtain a large amount of training data. At the same time, it avoids the situation where the pre-trained model cannot be applied to any scanned object, and improves the flexibility of generating the target tissue uptake rate image.

[0103] FIG8 is a flow chart of a method for generating a target tissue uptake rate image in another embodiment. As shown in FIG8 , the embodiment of the present application relates to another possible implementation method of generating a target tissue uptake rate image of a scanned object according to a mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship, including the following steps:

[0104] S801, based on the mapping relationship, obtain the standard time corresponding to each scanning moment; the standard time is the ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment.

[0105] In the embodiment of the present application, since the mapping relationship is used to characterize the relationship between the scanning time, the blood activity value corresponding to the scanning time, and the cumulative blood activity value within the scanning time period corresponding to the scanning time, the scanning time is combined with the mapping relationship to obtain the cumulative blood activity value within the scanning time period corresponding to the scanning time, thereby obtaining the standard time based on the cumulative blood activity value and the blood activity value corresponding to the scanning time.

[0106] S802, fitting the concentration ratio of each tissue to blood and the standard time corresponding to the scanning moment to generate a target tissue uptake rate image.

[0107] In an embodiment of the present application, for each pixel point, the tissue-to-blood concentration ratio at each scanning moment and the standard time at the corresponding scanning moment are fitted to obtain the target tissue uptake rate parameter of the pixel point, thereby obtaining a target tissue uptake rate image.

[0108] In the embodiment of the present application, based on the mapping relationship, the standard time corresponding to each scanning moment is obtained, which can reduce the scanning time, and the ratio of the cumulative blood activity value corresponding to each scanning moment and the blood activity value at each scanning moment can be obtained without long scanning. Furthermore, the blood concentration ratio of each tissue and the standard time corresponding to the scanning moment are fitted to generate the target tissue uptake rate image, making the generation of the target tissue uptake rate image simpler and improving the efficiency of the generation of the target tissue uptake rate image.

[0109] FIG9 is a flow chart of a method for obtaining a mapping relationship in an embodiment, and as shown in FIG9 , the method includes the following steps:

[0110] S901, obtaining the sample standard time of each scanning moment; the sample standard time is the ratio of the cumulative blood activity value in the scanning time period corresponding to each scanning moment in the second scanning duration to the blood activity value at the corresponding scanning moment; the second scanning duration is greater than the first scanning duration.

[0111] S902, fitting multiple scanning moments and sample standard times corresponding to the scanning moments to obtain a mapping relationship.

[0112] The second scan duration is the time required to perform a complete scan on the patient. When the tracer is different, the second scan duration is also different. For example, when the tracer is 18 In the case of F-FDG, the second scan duration is generally 60 to 180 minutes.

[0113] In the embodiment of the present application, fitting is performed between multiple scanning moments and the sample standard time corresponding to the scanning moments, which may be exponential fitting, polynomial fitting, logarithmic fitting, and the polynomial fitting may be linear fitting, etc.

[0114] As shown in Figure 10, the tracer is 18F-FDG, by fitting multiple scanning moments within the second scanning duration with the sample standard time of the corresponding scanning moment, it can be found that within 20 minutes to 60 minutes after the injection of the tracer, the sample standard time is linearly related to time. Based on this finding, the sample standard time in all data can be statistically analyzed and linearly fitted to obtain a mapping relationship based on multiple reference objects, that is, the mapping relationship is the expression of population-based normalization time (PBNT) obtained by statistically analyzing the sample normalization time in all data and performing linear fitting.

[0115] If the first scan duration is 20 minutes after the tracer injection, the linear fitting mapping relationship can be used to obtain the standard time of each scan moment; if the first scan duration is 20 minutes after the tracer injection, the linear fitting mapping relationship can be used to obtain the standard time of each scan moment.

[0116] The scanning duration before 20 minutes after the scan needs to be determined based on the mapping relationship fitted 20 minutes ago to obtain the standard time of each scanning moment.

[0117] Figure 10 shows the fitting of the sample standard time and scanning time of 25 reference objects. The dotted line represents the fitting result of each reference object, and 25 fitting lines are obtained. For each fitting line, the determination coefficient (R²) of each fitting line is 0.99 ± 0.01, indicating that the linearity of the fitting result of each reference object is very high. And the coefficient of variation (CV) between the sample standard time of each reference object and the fitting line is 1.01%, which proves that the distribution range of each sample standard time of each reference object is very small. After averaging these fitting lines, the sample standard time can be modeled as a function of time through linear fitting, and the mapping relationship can be expressed as The slope a ranges from 1.67 ± 0.13 (CV = 7.78%), and the intercept b ranges from -5.84 ± 3.07 (CV = 52.57%). The mapping relationship obtained is the solid line shown in FIG10. Preferably, the mapping relationship obtained based on the linear simulation can be expressed as: .

[0118] Furthermore, Figures 11-13 respectively show the PBNTs constructed under three different tracers, namely FDG tracer, PSMA tracer and Methionine tracer. It can be found that when the state of the tracer is irreversible, the PBNT formula obtained in Figure 10 is valid.

[0119] Therefore, the method of constructing the mapping relationship can also be integrated into the workstation of the PET equipment to replace the traditional idea of ​​obtaining the cumulative blood activity value: even for short-term scanning PET data, quantitative analysis of tissue uptake rate images can be performed; or for traditional short-axis PET data, using PBNT, there is no need to scan the heart to obtain blood activity values, and quantitative analysis of tissue uptake rate images can be performed.

[0120] In an embodiment of the present application, the sample standard time of each scanning moment is obtained, and multiple scanning moments are fitted with the sample standard time of the corresponding scanning moment to obtain a mapping relationship, thereby laying a foundation for subsequently obtaining a target tissue uptake rate image based on the mapping relationship.

[0121] FIG. 14 is a flow chart of an image generating method in another embodiment, as shown in FIG. 14 , comprising the following steps:

[0122] S1401, obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within a first scanning duration; each tissue-to-blood concentration ratio is a ratio of a tissue activity value to a blood activity value of the scanned object at each scanning moment;

[0123] S1402, acquiring an initial tissue uptake rate image and an initial distribution volume image according to a preset feature extraction model and a concentration ratio of each tissue to blood;

[0124] S1403, based on the mapping relationship, obtaining the standard time corresponding to each scanning moment; the standard time is the ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment;

[0125] S1404, acquiring an intermediate distribution volume image according to the initial tissue uptake rate image, the concentration ratio of each tissue to blood, and each standard time;

[0126] S1405, correcting the initial distribution volume image according to the intermediate distribution volume image to obtain a target distribution volume image;

[0127] S1406, based on the initial tissue uptake rate image, the target distribution volume image and each standard time, correcting each tissue-to-blood concentration ratio to obtain a corrected tissue-to-blood concentration ratio at each scanning time;

[0128] S1407, when the difference between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio is greater than a preset difference threshold, updating the parameters of the feature extraction model according to each difference value, and using the updated feature extraction model as the feature extraction model;

[0129] S1408, when the difference value is less than or equal to the difference threshold, taking the corresponding initial tissue uptake rate image as the target tissue uptake rate image;

[0130] S1409, based on the mapping relationship, obtaining the standard time corresponding to each scanning moment; the standard time is the ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment;

[0131] S1410, fitting the concentration ratio of each tissue to blood and the standard time corresponding to the scanning moment to generate a target tissue uptake rate image.

[0132] Since the mapping relationship represents the relationship between the scanning time, the blood activity value corresponding to the scanning time, and the cumulative blood activity value corresponding to the scanning time, the embodiment of the present application obtains the cumulative blood activity value within the scanning time period corresponding to the scanning time based on the mapping relationship, and thus obtains the target tissue uptake rate image based on each cumulative blood activity value, each blood activity value and multiple tissue-to-blood concentration ratios, without the need for long-term continuous scanning of the scanned object.

[0133] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0134] Based on the same inventive concept, the embodiment of the present application also provides an image generation device for implementing the above-mentioned image generation method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more image generation device embodiments provided below can refer to the limitations on the image generation method above, and will not be repeated here.

[0135] In an exemplary embodiment, as shown in FIG15 , an image generating device is provided, comprising: a first acquiring module 11 and a generating module 12, wherein:

[0136] The first acquisition module 11 is used to acquire the tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each tissue-to-blood concentration ratio is the ratio of the tissue activity value to the blood activity value of the scanned object at each scanning moment;

[0137] The generation module 12 is used to generate a target tissue uptake rate image of the scanned object according to a preset mapping relationship between the ratio of each tissue to blood concentration; wherein the mapping relationship is used to characterize the mapping relationship between the scanning time, the blood activity value corresponding to the scanning time, and the cumulative blood activity value within the scanning time period corresponding to the scanning time.

[0138] In one embodiment, the generation module 12 is specifically used to obtain an initial tissue uptake rate image and an initial distribution volume image according to a preset feature extraction model and the ratio of each tissue to blood concentration; based on a mapping relationship, obtain the standard time corresponding to each scanning moment; generate a target tissue uptake rate image according to the initial tissue uptake rate image, the initial distribution volume image and each standard time; the standard time is the ratio between the cumulative blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment.

[0139] In one embodiment, the generating module 12 is specifically used to obtain an intermediate distribution volume image based on the initial tissue uptake rate image, each tissue to blood concentration ratio and each standard time;

[0140] Correcting the initial distribution volume image according to the intermediate distribution volume image to obtain a target distribution volume image;

[0141] A target tissue uptake rate image is generated based on the initial tissue uptake rate image, the target distribution volume image and each standard time.

[0142] In one embodiment, the generating module 12 is specifically used to correct each tissue-to-blood concentration ratio based on the initial tissue uptake rate image, the target distribution volume image and each standard time to obtain a corrected tissue-to-blood concentration ratio at each scanning time;

[0143] A target tissue uptake rate image is generated based on the difference between each tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio.

[0144] In one embodiment, the generating module 12 is specifically configured to use the initial tissue uptake rate image as the tissue uptake rate image when the difference value is less than or equal to a preset difference threshold;

[0145] When the difference value is greater than a preset difference threshold, the parameters of the feature extraction model are updated according to each difference value, the updated feature extraction model is used as the feature extraction model, and the step of obtaining the initial tissue uptake rate image and the initial distribution volume image according to the preset feature extraction model and each tissue-to-blood concentration ratio is returned to be executed until the difference value is less than or equal to the difference threshold.

[0146] In one embodiment, the generating module 12 is specifically used to obtain the standard time corresponding to each scanning moment based on the mapping relationship; the standard time is the ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning time length and the blood activity value corresponding to the scanning moment;

[0147] The concentration ratio of each tissue to blood is fitted with the standard time corresponding to the scanning moment to generate the target tissue uptake rate image.

[0148] In one embodiment, the image generating device further comprises:

[0149] A second acquisition module is used to acquire a sample standard time at each scanning moment; the sample standard time is a ratio of a cumulative blood activity value in a scanning time period corresponding to each scanning moment within a second scanning duration to a blood activity value at the corresponding scanning moment; the second scanning duration is longer than the first scanning duration;

[0150] The fitting module is used to fit multiple scanning moments and the sample standard time corresponding to the scanning moments to obtain a mapping relationship.

[0151] Each module in the above-mentioned image generation device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0152] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any of the above method embodiments when executing the computer program.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0154] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of any of the above method embodiments when executed by a processor.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0156] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0158] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An image generation method, characterized in that: The method comprises: Obtaining a tissue-to-blood concentration ratio corresponding to each scanning moment within the first scanning duration; each of the tissue-to-blood concentration ratios is a ratio of a tissue activity value to a blood activity value of the scanned object at each of the scanning moments; A target tissue uptake rate image of the scanned object is generated based on a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize a mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

2. The method according to claim 1, characterized in that The step of generating a target tissue uptake rate image of the scanned object according to the mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship includes: Acquiring an initial tissue uptake rate image and an initial distribution volume image according to a preset feature extraction model and each of the tissue-to-blood concentration ratios; Based on the mapping relationship, a standard time corresponding to each scanning moment is obtained; the standard time is a ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment; The target tissue uptake rate image is generated according to the initial tissue uptake rate image, the initial distribution volume image and each of the standard times.

3. The method according to claim 2, characterized in that The step of generating the target tissue uptake rate image according to the initial tissue uptake rate image, the initial distribution volume image and each standard time comprises: acquiring an intermediate distribution volume image according to the initial tissue uptake rate image, each of the tissue-to-blood concentration ratios and each of the standard times; Correcting the initial distribution volume image according to the intermediate distribution volume image to obtain a target distribution volume image; The target tissue uptake rate image is generated based on the initial tissue uptake rate image, the target distribution volume image and each of the standard times.

4. The method according to claim 3, characterized in that The step of generating the target tissue uptake rate image based on each of the initial tissue uptake rates, each of the target distribution volumes and each of the standard times comprises: Based on the initial tissue uptake rate image, the target distribution volume image and the standard time, correcting each tissue-to-blood concentration ratio to obtain a corrected tissue-to-blood concentration ratio at each scanning time; The target tissue uptake rate image is generated according to the difference value between each tissue-to-blood concentration ratio and the corresponding corrected tissue-to-blood concentration ratio.

5. The method according to claim 4, characterized in that The step of generating the target tissue uptake rate image according to the difference between each tissue-to-blood concentration ratio and the corrected tissue-to-blood concentration ratio comprises: In the case where the difference value is greater than a preset difference threshold, the parameters of the feature extraction model are updated according to each of the difference values, the updated feature extraction model is used as the feature extraction model, and the step of obtaining an initial tissue uptake rate image and an initial distribution volume image according to the preset feature extraction model and each of the tissue-to-blood concentration ratios is returned to be executed until the difference value is less than or equal to the difference threshold; When the difference value is less than or equal to a preset difference threshold, the corresponding initial tissue uptake rate image is used as the target tissue uptake rate image.

6. The method according to claim 1, characterized in that The step of generating a target tissue uptake rate image of the scanned object according to the mapping relationship between the tissue-to-blood concentration ratio and a preset mapping relationship includes: Based on the mapping relationship, a standard time corresponding to each scanning moment is obtained; the standard time is a ratio between the accumulated blood activity value in the scanning time period corresponding to the scanning moment within the first scanning duration and the blood activity value corresponding to the scanning moment; The target tissue uptake rate image is generated by fitting the tissue-to-blood concentration ratio and the standard time corresponding to the scanning moment.

7. The method according to any one of claims 1 to 6, characterized in that: The process of obtaining the mapping relationship includes: Obtaining a sample standard time at each scanning moment; the sample standard time is a ratio of a cumulative blood activity value in a scanning time period corresponding to each scanning moment within a second scanning duration to a blood activity value at the corresponding scanning moment; the second scanning duration is greater than the first scanning duration; The mapping relationship is obtained by fitting the plurality of scanning moments and the sample standard time corresponding to the scanning moments.

8. An image generating device, characterized in that: The device comprises: A first acquisition module is used to acquire a tissue-to-blood concentration ratio corresponding to each scanning moment within a first scanning duration; each tissue-to-blood concentration ratio is a ratio of a tissue activity value to a blood activity value of the scanned object at each scanning moment; A generation module is used to generate a target tissue uptake rate image of the scanned object according to a preset mapping relationship between each tissue-to-blood concentration ratio and a preset mapping relationship; wherein the mapping relationship is used to characterize the mapping relationship between a scanning moment, a blood activity value corresponding to the scanning moment, and a cumulative blood activity value within a scanning time period corresponding to the scanning moment.

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