Method and device for predicting PET (Polyethylene Terephthalate) glucose metabolism value and computer equipment

Abstract

The invention relates to a method and a device for predicting a PET (Positron Emission Tomography) sugar metabolism value and computer equipment. The method comprises the steps of collecting a sequence scanning image and a comparison image of a patient through a scanner, and generating each inversion recovery image of the patient through a sequence segmentation strategy based on the sequence scanning image; carrying out image combination processing on the inversion recovery images to obtain a target composite image of the patient, and identifying tissue abnormal information of the target composite image through an image comparison strategy based on the target composite image and the comparison image; and predicting the glucose metabolism value of the patient through a glucose metabolism value prediction strategy based on the tissue abnormal information. By adopting the method, the prediction accuracy of the PET glucose metabolism value can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, device and computer equipment for predicting PET sugar metabolism values. Background Art

[0002] PET glucose metabolism value is obtained through positron emission tomography (PET, which uses positron radionuclides to label human metabolites such as glucose as imaging agents, and reflects its metabolic changes through the uptake of imaging agents by lesions, thereby providing clinical biological metabolic information of diseases. This biological metabolic information can be used to predict diseases such as stroke lesions and cancer. Therefore, how to improve the prediction accuracy of PET glucose metabolism value is the current research focus.

[0003] The traditional method of predicting PET sugar metabolism values ​​is to have staff manually identify and analyze the PET development results, but this method is inefficient, and the efficiency of manual analysis and manual identification is low, resulting in low prediction accuracy of PET sugar metabolism values. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for predicting PET sugar metabolism values ​​in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting PET glucose metabolism value, comprising:

[0006] Using a scanner, collecting serial scanning images and contrast images of the patient, and based on the serial scanning images, generating each inversion recovery image of the patient by using a serial segmentation strategy;

[0007] Performing image merging processing on each of the inversion recovery images to obtain a target composite image of the patient, and identifying tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the comparison image;

[0008] Based on the tissue abnormality information, the glucose metabolism value of the patient is predicted using a glucose metabolism value prediction strategy.

[0009] Optionally, generating each inversion recovery image of the patient based on the sequence scanning image by a sequence segmentation strategy includes:

[0010] Based on the sequence scanned images, identifying the first image data of each target area of ​​the patient through a quantitative data generation strategy, and based on each of the first image data, identifying the first factor measurement value of each first image data through a factor value extraction operation;

[0011] Based on the first factor measurement value of each of the first image data, each inversion recovery image of the patient is generated by an inversion recovery image generation strategy.

[0012] Optionally, performing image merging processing on each of the inversion recovery images to obtain a target composite image of the patient includes:

[0013] identifying an inversion time value for each inversion recovery image;

[0014] Based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

[0015] Optionally, the identifying tissue abnormality information of the target synthetic image through an image comparison strategy based on the target synthetic image and the comparison image includes:

[0016] Performing image mapping processing on the target synthetic image and the comparison image to obtain a mapping comparison image;

[0017] By using an image comparison strategy, performing image comparison processing on the mapped comparison image, identifying each abnormal image region in the target synthetic image and abnormal information of each abnormal image region;

[0018] The abnormal information of each abnormal image region is used as the tissue abnormality information of the target synthetic image.

[0019] Optionally, predicting the patient's glucose metabolism value based on the tissue abnormality information by using a glucose metabolism value prediction strategy includes:

[0020] Based on the abnormal information of each abnormal image region, identifying the data value of each abnormal data type of each abnormal image region through an image recognition strategy;

[0021] Based on the data values ​​of each abnormal data type in each abnormal image area, a sugar metabolism value corresponding to each abnormal image area is predicted through a sugar metabolism value prediction strategy, and based on the sugar metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area, the sugar metabolism value of the patient is calculated.

[0022] Optionally, the identifying, based on the abnormal information of each abnormal image region, the data value of each abnormal data type of each abnormal image region through an image recognition strategy includes:

[0023] For each abnormal image region, identifying abnormal feature information corresponding to the abnormal information of the abnormal image region, and querying each abnormal data type corresponding to the abnormal feature information in an abnormal database;

[0024] Identify the sub-abnormal information corresponding to each abnormal data type through an image recognition network, and perform abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal index evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information;

[0025] The abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type is used as the data value of each abnormal data type.

[0026] In a second aspect, the present application also provides a device for predicting PET glucose metabolism value, comprising:

[0027] An acquisition module, used for acquiring a patient's sequence scan images and contrast images through a scanner, and generating each inversion recovery image of the patient through a sequence segmentation strategy based on the sequence scan images;

[0028] an identification module, configured to perform image merging processing on each of the inversion recovery images to obtain a target composite image of the patient, and identify tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the comparison image;

[0029] A prediction module is used to predict the glucose metabolism value of the patient based on the tissue abnormality information and through a glucose metabolism value prediction strategy.

[0030] Optionally, the acquisition module is specifically used to:

[0031] Based on the sequence scanned images, identifying the first image data of each target area of ​​the patient through a quantitative data generation strategy, and based on each of the first image data, identifying the first factor measurement value of each first image data through a factor value extraction operation;

[0032] Based on the first factor measurement value of each of the first image data, each inversion recovery image of the patient is generated by an inversion recovery image generation strategy.

[0033] Optionally, the identification module is specifically used to:

[0034] identifying an inversion time value for each inversion recovery image;

[0035] Based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

[0036] Optionally, the identification module is specifically used to:

[0037] Performing image mapping processing on the target synthetic image and the comparison image to obtain a mapping comparison image;

[0038] By using an image comparison strategy, performing image comparison processing on the mapped comparison image, identifying each abnormal image region in the target synthetic image and abnormal information of each abnormal image region;

[0039] The abnormal information of each abnormal image region is used as the tissue abnormality information of the target synthetic image.

[0040] Optionally, the prediction module is specifically used to:

[0041] Based on the abnormal information of each abnormal image region, identifying the data value of each abnormal data type of each abnormal image region through an image recognition strategy;

[0042] Based on the data values ​​of each abnormal data type in each abnormal image area, a sugar metabolism value corresponding to each abnormal image area is predicted through a sugar metabolism value prediction strategy, and based on the sugar metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area, the sugar metabolism value of the patient is calculated.

[0043] Optionally, the prediction module is specifically used to:

[0044] For each abnormal image region, identifying abnormal feature information corresponding to the abnormal information of the abnormal image region, and querying each abnormal data type corresponding to the abnormal feature information in an abnormal database;

[0045] Identify the sub-abnormal information corresponding to each abnormal data type through an image recognition network, and perform abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal index evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information;

[0046] The abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type is used as the data value of each abnormal data type.

[0047] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0049] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0050] The above-mentioned PET glucose metabolism value prediction method, device and computer equipment collect the patient's serial scanning images and contrast images through a scanner, and generate each inversion recovery image of the patient based on the serial scanning images through a serial segmentation strategy; perform image merging processing on each inversion recovery image to obtain the target composite image of the patient, and identify the tissue abnormality information of the target composite image based on the target composite image and the contrast image through an image comparison strategy; based on the tissue abnormality information, predict the patient's glucose metabolism value through a glucose metabolism value prediction strategy. In this scheme, after the patient's serial scanning images are collected by a scanner, in order to better visualize and delineate the lesions, this scheme uses the serial synthesis segmentation subtraction inversion recovery image to obtain the technical purpose of imaging the patient's target area, and then this scheme merges the inversion recovery (IR) images separately to create a composite image that enhances the contrast of stroke lesions while maintaining the anatomical background. Finally, tissue comparison is performed based on the merged image and the contrast image to obtain the abnormal information of the target area, so as to predict the patient's glucose metabolism value through a glucose metabolism value prediction strategy. There is no need for manual analysis and prediction. Instead, intelligent technology is used, combined with integrated sequence image synthesis and image comparison technology, to comprehensively improve the prediction accuracy of PET sugar metabolism values. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A schematic diagram of a process for predicting a PET sugar metabolism value in one embodiment;

[0053] Figure 2 A schematic diagram of a process for predicting a PET sugar metabolism value in an embodiment;

[0054] Figure 3is a structural block diagram of a device for predicting PET sugar metabolism value in one embodiment;

[0055] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer 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] The prediction method of PET glucose metabolism value provided in the embodiment of the present application can be applied to the application environment of PET glucose metabolism value prediction. Among them, the method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, medium-sized computers, etc. Among them, after the terminal collects the patient's serial scanning images through a scanner, in order to better visualize and delineate the lesions, this scheme uses a sequence synthesis segmentation subtraction inversion recovery image to obtain the technical purpose of imaging the patient's target area, and then this scheme merges the inversion recovery (IR) images separately to create a synthetic image that enhances the contrast of stroke lesions while maintaining the anatomical background. Finally, based on the merged image and the contrast image, tissue comparison is performed to obtain the abnormal information of the target area, so as to predict the glucose metabolism value of the patient through the glucose metabolism value prediction strategy. So that there is no need for manual analysis and prediction, but through intelligent technical means, combined with integrated sequence image synthesis and image comparison technology, the prediction accuracy of PET glucose metabolism value is comprehensively improved.

[0058] In an exemplary embodiment, Figure 1 As shown, a method for predicting PET sugar metabolism value is provided, and the method is applied to a terminal as an example for explanation, including the following steps S101 to S103. Among them:

[0059] Step S101 : using a scanner to collect serial scan images and contrast images of a patient, and based on the serial scan images, using a serial segmentation strategy, generating various inversion recovery images of the patient.

[0060] In this embodiment, the terminal uses GE Healthcare's integrated SIGNA TOF-PET / MR scanner, with a 19-channel head and neck combined coil; 18F-FDG is prepared by our hospital, with a radiochemical purity of >98%. Before the examination, the patient fasted for more than 6 hours, blood sugar ≤8.0mmol / L, and 18F-FDG imaging agent (3.7 MBq / kg body weight) was injected through the dorsal vein of the hand. The integrated PET / MR scan began 50 minutes after the injection. Then, the terminal collected the patient's serial scan images and contrast images. Among them, the PET scan parameters during the scan were: 1 bed, the scanning range included the whole brain, time-of-flight technology + point spread function, FOV 35 cm, number of iterations 8, effective subsets 32, matrix 192×192, and acquisition time 10 min. The MR scan parameters are shown in Table 1:

[0061] Table 1: MR scan parameters

[0062] sequence direction TR(ms) TE(ms) Field of view (mm) Layer thickness (mm) Ax T2-FLAIR Horizontal axis 11000 145 24×24 3 Ax DWI Horizontal axis 6200 75 24×24 3 Ax MAGiC Horizontal axis 5076 22 24×19 3

[0063] Among them, there are fluid attenuated inversion recovery (FLAIR) sequence, diffusion weighted imaging (DWI), and magnetic resonance image compilation (MAGiC).

[0064] Then, the terminal generates each inversion recovery image of the patient through a sequence segmentation strategy based on the acquired sequence scan images. The inversion recovery image is a segmented subtraction inversion recovery (dSIR) image, and the specific generation process will be described in detail later.

[0065] Step S102 , performing image merging processing on each inversion recovery image to obtain a target composite image of the patient, and identifying tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the comparison image.

[0066] In this embodiment, the terminal performs image merging processing on each inversion recovery image to obtain a target composite image of the patient, and identifies tissue abnormality information of the target composite image based on the target composite image and the contrast image through an image comparison strategy. The tissue abnormality area is an area where the patient has a lesion, for example, an area of ​​a stroke lesion. The image comparison strategy is a strategy for comparing the target composite image and the contrast image. The specific comparison process will be described in detail later.

[0067] Step S103: predicting the patient's glucose metabolism value based on the tissue abnormality information by using a glucose metabolism value prediction strategy.

[0068] Based on the tissue abnormality information, the patient's glucose metabolism value is predicted through the glucose metabolism value prediction strategy. The specific prediction process will be described in detail later, and the glucose metabolism value prediction strategy is to analyze and evaluate the abnormal information of each tissue and then calculate the metabolic value.

[0069] Based on the above scheme, after the patient's serial scanning images are collected by the scanner, this scheme uses the sequence synthesis segmentation subtraction inversion recovery image for better visualization and lesion delineation, so as to obtain the technical purpose of imaging the patient's target area, and then this scheme merges the inversion recovery (IR) images separately to create a synthetic image that enhances the contrast of stroke lesions while maintaining the anatomical background. Finally, tissue contrast is performed based on the merged image and the contrast image to obtain the abnormal information of the target area, so as to predict the patient's glucose metabolism value through the glucose metabolism value prediction strategy. This eliminates the need for manual analysis and prediction, but uses intelligent technical means, combined with integrated sequence image synthesis and image contrast technology, to comprehensively improve the prediction accuracy of PET glucose metabolism values.

[0070] Optionally, based on the serial scanning images, each inversion recovery image of the patient is generated through a serial segmentation strategy, including: based on the serial scanning images, through a quantitative data generation strategy, identifying the first image data of each target area of ​​the patient, and based on each first image data, through a factor value extraction operation, identifying the first factor measurement value of each first image data; based on the first factor measurement value of each first image data, through an inversion recovery image generation strategy, each inversion recovery image of the patient is generated.

[0071] In this embodiment, the terminal identifies the first image data of each target area of ​​the patient through a quantitative data generation strategy based on the sequence scanned images, and identifies the first factor measurement value of each first image data through a factor value extraction operation based on each first image data. Specifically, the terminal generates a quantitative T1 map (first image data) from the MAGiC sequence scanned images. Then, the terminal extracts the T1 values ​​of the stroke lesions and surrounding tissues to obtain the first factor measurement value of the first image data.

[0072] Then, the terminal generates each inversion recovery image of the patient based on the first factor measurement value of each first image data through an inversion recovery image generation strategy. The generation method of each inversion recovery image is that the terminal generates two inversion recovery (IR) images with different flip times (TI) based on the T1 measurement value.

[0073] Based on the above scheme, after identifying the factor measurement values ​​based on the sequence scanning image of the integrated sequence, each inversion recovery image of the patient is generated, which improves the visualization and delineation accuracy of the lesion.

[0074] Optionally, each inversion recovery image is subjected to image merging processing to obtain a target composite image of the patient, including: identifying the inversion time value of each inversion recovery image; based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

[0075] In this embodiment, the terminal identifies the inversion time value of each inversion recovery image, wherein the inversion time value (TI) is used to represent the inversion generation time of two inversion recovery images.

[0076] Then, based on the inversion time value of each inversion recovery image, the terminal performs image merging processing on each inversion recovery image through an inversion image merging algorithm to obtain a target merged image of the patient. The inversion image merging algorithm is dSIR=(TI1-TI2) / (TI1+TI2). TI1 is the inversion time value of the first inversion recovery image, and TI2 is the inversion time value of the second inversion recovery image.

[0077] Based on the above scheme, by generating inversion recovery images with different inversion time values, the suppression effect of interference signals is improved, so as to optimize the accuracy of predicting glucose metabolism values ​​after obtaining the synthetic image.

[0078] Optionally, based on the target composite image and the comparison image, an image comparison strategy is used to identify tissue abnormality information of the target composite image, including: performing image mapping processing on the target composite image and the comparison image to obtain a mapping comparison image; performing image comparison processing on the mapping comparison image through the image comparison strategy to identify each abnormal image region in the target composite image and abnormal information of each abnormal image region; and using the abnormal information of each abnormal image region as tissue abnormality information of the target composite image.

[0079] In this embodiment, the terminal performs image mapping processing on the target synthetic image and the comparison image to obtain a mapping comparison image. Then, the terminal performs image comparison processing on the mapping comparison image through an image comparison strategy to identify each abnormal image area in the target synthetic image and the abnormal information of each abnormal image area. Among them, each abnormal image area is an image range where there is an image difference, and the abnormal information of the abnormal image area is the difference feature information in the image range, wherein the comparison image is a T2-FLAIR image. The comparison method is tissue image comparison. The difference feature information includes difference features such as parallel difference, overlapping difference, and cross difference. Finally, the terminal uses the abnormal information of each abnormal image area as the tissue abnormality information of the target synthetic image.

[0080] Based on the above scheme, by performing difference comparison, the abnormal information of each abnormal image area is identified, thereby improving the accuracy of image analysis of abnormal images.

[0081] Optionally, based on tissue abnormality information, a glucose metabolism value prediction strategy is used to predict the patient's glucose metabolism value, including: based on the abnormal information of each abnormal image area, using an image recognition strategy to identify the data value of each abnormal data type of each abnormal image area; based on the data value of each abnormal data type of each abnormal image area, using a glucose metabolism value prediction strategy to predict the corresponding glucose metabolism value of each abnormal image area; and based on the glucose metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area, the patient's glucose metabolism value is calculated.

[0082] In this embodiment, the terminal identifies the data value of each abnormal data type of each abnormal image region based on the abnormal information of each abnormal image region through an image recognition strategy. The specific identification process of the data value will be described in detail later.

[0083] Then, based on the data values ​​of each abnormal data type of each abnormal image area, the terminal predicts the corresponding glucose metabolism value of each abnormal image area through the glucose metabolism value prediction strategy, and calculates the patient's glucose metabolism value based on the glucose metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area. The calculation method is to calculate the PET metabolism value based on the glucose metabolism value corresponding to each abnormal image area obtained above, by using the SUV count value measured by PET.

[0084] Based on the above scheme, after obtaining the data values ​​of each abnormal data type of each abnormal image area, the glucose metabolism value corresponding to each abnormal image area is calculated, thereby calculating the glucose metabolism value of the patient, thereby improving the accuracy of the calculation.

[0085] Optionally, based on the abnormal information of each abnormal image area, an image recognition strategy is used to identify data values ​​of each abnormal data type of each abnormal image area, including: for each abnormal image area, identifying abnormal feature information corresponding to the abnormal information of the abnormal image area, and querying each abnormal data type corresponding to the abnormal feature information in an abnormal database; identifying sub-abnormal information corresponding to each abnormal data type through an image recognition network, and performing abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal indicator evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information; and using the abnormal evaluation value corresponding to the sub-abnormal information of each abnormal data type as the data value of each abnormal data type.

[0086] In this embodiment, the terminal identifies the abnormal feature information corresponding to the abnormal information of each abnormal image area, and searches the abnormal database for each abnormal data type corresponding to the abnormal feature information. The corresponding relationship between each abnormal data type and the abnormal feature information is stored in the abnormal database.

[0087] Then, the terminal identifies the sub-abnormal information corresponding to each abnormal data type through the image recognition network, and performs abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through the abnormal index evaluation strategy to obtain the abnormal evaluation value corresponding to each sub-abnormal information. Among them, the abnormal index evaluation strategy includes the abnormal evaluation value corresponding to each sub-abnormal information range of each abnormal data type. The terminal identifies the sub-abnormal information range to which the sub-abnormal information of each abnormal data type belongs, thereby determining the abnormal evaluation value corresponding to each abnormal data type.

[0088] Finally, the terminal uses the abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type as the data value of each abnormal data type.

[0089] Based on the above scheme, by evaluating the sub-abnormal information corresponding to each abnormal data type in each abnormal image area, the abnormal evaluation value corresponding to the abnormal data type is obtained, thereby improving the efficiency and accuracy of generating the abnormal evaluation value.

[0090] This application also provides a prediction example of PET glucose metabolism value, such as Figure 2 As shown, the specific processing process includes the following steps:

[0091] Step S201, collecting serial scan images and contrast images of the patient through a scanner.

[0092] Step S202, based on the serial scan images, the first image data of each target area of ​​the patient is identified through a quantitative data generation strategy, and based on each first image data, the first factor measurement value of each first image data is identified through a factor value extraction operation.

[0093] Step S203 : generating each inversion recovery image of the patient based on the first factor measurement value of each first image data by using an inversion recovery image generation strategy.

[0094] Step S204: identifying the inversion time value of each inversion recovery image.

[0095] Step S205 , based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

[0096] Step S206, performing image mapping processing on the target synthetic image and the comparison image to obtain a mapped comparison image.

[0097] Step S207 , performing image comparison processing on the mapped comparison image through an image comparison strategy, and identifying each abnormal image region in the target synthetic image and abnormal information of each abnormal image region.

[0098] Step S208: Using the abnormal information of each abnormal image region as the tissue abnormality information of the target synthetic image.

[0099] Step S209: for each abnormal image region, identifying abnormal feature information corresponding to the abnormal information of the abnormal image region, and searching the abnormal database for each abnormal data type corresponding to the abnormal feature information.

[0100] Step S210, identifying the sub-abnormal information corresponding to each abnormal data type through an image recognition network, and performing abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal index evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information.

[0101] Step S211: taking the abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type as the data value of each abnormal data type.

[0102] Step S212, based on the data values ​​of each abnormal data type of each abnormal image area, predict the corresponding glucose metabolism value of each abnormal image area through a glucose metabolism value prediction strategy, and calculate the patient's glucose metabolism value based on the glucose metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area.

[0103] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0104] Based on the same inventive concept, the embodiment of the present application also provides a PET glucose metabolism value prediction device for implementing the above-mentioned PET glucose metabolism value prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the one or more PET glucose metabolism value prediction device embodiments provided below can refer to the limitations of the PET glucose metabolism value prediction method above, and will not be repeated here.

[0105] In an exemplary embodiment, Figure 3As shown, a prediction device for PET glucose metabolism value is provided, comprising: a collection module 310, an identification module 320 and a prediction module 330, wherein:

[0106] The acquisition module 310 is used to acquire the patient's sequence scan images and contrast images through a scanner, and generate each inversion recovery image of the patient based on the sequence scan images through a sequence segmentation strategy;

[0107] The identification module 320 is used to perform image merging processing on each of the inversion recovery images to obtain a target composite image of the patient, and identify tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the contrast image;

[0108] The prediction module 330 is used to predict the glucose metabolism value of the patient based on the tissue abnormality information and through a glucose metabolism value prediction strategy.

[0109] Optionally, the acquisition module 310 is specifically used for:

[0110] Based on the sequence scanned images, identifying the first image data of each target area of ​​the patient through a quantitative data generation strategy, and based on each of the first image data, identifying the first factor measurement value of each first image data through a factor value extraction operation;

[0111] Based on the first factor measurement value of each of the first image data, each inversion recovery image of the patient is generated by an inversion recovery image generation strategy.

[0112] Optionally, the identification module 320 is specifically configured to:

[0113] identifying an inversion time value for each inversion recovery image;

[0114] Based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

[0115] Optionally, the identification module 320 is specifically configured to:

[0116] Performing image mapping processing on the target synthetic image and the comparison image to obtain a mapping comparison image;

[0117] By using an image comparison strategy, performing image comparison processing on the mapped comparison image, identifying each abnormal image region in the target synthetic image and abnormal information of each abnormal image region;

[0118] The abnormal information of each abnormal image region is used as the tissue abnormality information of the target synthetic image.

[0119] Optionally, the prediction module 330 is specifically configured to:

[0120] Based on the abnormal information of each abnormal image region, identifying the data value of each abnormal data type of each abnormal image region through an image recognition strategy;

[0121] Based on the data values ​​of each abnormal data type in each abnormal image area, a sugar metabolism value corresponding to each abnormal image area is predicted through a sugar metabolism value prediction strategy, and based on the sugar metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area, the sugar metabolism value of the patient is calculated.

[0122] Optionally, the prediction module 330 is specifically configured to:

[0123] For each abnormal image region, identifying abnormal feature information corresponding to the abnormal information of the abnormal image region, and querying each abnormal data type corresponding to the abnormal feature information in an abnormal database;

[0124] Identify the sub-abnormal information corresponding to each abnormal data type through an image recognition network, and perform abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal index evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information;

[0125] The abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type is used as the data value of each abnormal data type.

[0126] Each module in the above-mentioned PET glucose metabolism value prediction device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0127] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system 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 input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting PET sugar metabolism values ​​is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0128] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0129] 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 a method for predicting PET glucose metabolism values ​​when executing the computer program.

[0130] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for predicting PET glucose metabolism value are implemented.

[0131] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the method for predicting PET glucose metabolism value when executed by a processor.

[0132] 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.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0134] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] 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 construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting PET sugar metabolism value, characterized in that: The method comprises: Acquire serial scanning images and contrast images of the patient through a scanner, and generate inversion recovery images of the patient through a serial segmentation strategy based on the serial scanning images; Performing image merging processing on each of the inversion recovery images to obtain a target composite image of the patient, and identifying tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the comparison image; Based on the tissue abnormality information, the glucose metabolism value of the patient is predicted using a glucose metabolism value prediction strategy.

2. The method according to claim 1, characterized in that The step of generating each inversion recovery image of the patient based on the sequence scanning image by a sequence segmentation strategy includes: Based on the sequence scanned images, identifying the first image data of each target area of ​​the patient through a quantitative data generation strategy, and based on each of the first image data, identifying the first factor measurement value of each first image data through a factor value extraction operation; Based on the first factor measurement value of each of the first image data, each inversion recovery image of the patient is generated by an inversion recovery image generation strategy.

3. The method according to claim 1, characterized in that The step of performing image merging processing on each of the inversion recovery images to obtain a target composite image of the patient includes: identifying an inversion time value for each inversion recovery image; Based on the inversion time value of each inversion recovery image, each inversion recovery image is subjected to image merging processing by an inversion image merging algorithm to obtain a target merged image of the patient.

4. The method according to claim 3, characterized in that The identifying tissue abnormality information of the target synthetic image through an image comparison strategy based on the target synthetic image and the comparison image includes: Performing image mapping processing on the target synthetic image and the comparison image to obtain a mapping comparison image; By using an image comparison strategy, performing image comparison processing on the mapped comparison image, identifying each abnormal image region in the target synthetic image and abnormal information of each abnormal image region; The abnormal information of each abnormal image region is used as the tissue abnormality information of the target synthetic image.

5. The method according to claim 4, characterized in that The step of predicting the patient's glucose metabolism value based on the tissue abnormality information by using a glucose metabolism value prediction strategy includes: Based on the abnormal information of each abnormal image region, identifying the data value of each abnormal data type of each abnormal image region through an image recognition strategy; Based on the data values ​​of each abnormal data type in each abnormal image area, a sugar metabolism value corresponding to each abnormal image area is predicted through a sugar metabolism value prediction strategy, and based on the sugar metabolism value corresponding to each abnormal image area and the abnormal data information of each abnormal image area, the sugar metabolism value of the patient is calculated.

6. The method according to claim 4, characterized in that The step of identifying the data value of each abnormal data type of each abnormal image region based on the abnormal information of each abnormal image region through an image recognition strategy includes: For each abnormal image region, identifying abnormal feature information corresponding to the abnormal information of the abnormal image region, and querying each abnormal data type corresponding to the abnormal feature information in an abnormal database; Identify the sub-abnormal information corresponding to each abnormal data type through an image recognition network, and perform abnormal evaluation processing on the sub-abnormal information corresponding to each abnormal data type through an abnormal index evaluation strategy to obtain an abnormal evaluation value corresponding to each sub-abnormal information; The abnormality evaluation value corresponding to the sub-abnormality information of each abnormal data type is used as the data value of each abnormal data type.

7. A device for predicting PET sugar metabolism value, characterized in that: The device comprises: An acquisition module, used for acquiring a patient's sequence scan images and contrast images through a scanner, and generating each inversion recovery image of the patient through a sequence segmentation strategy based on the sequence scan images; an identification module, configured to perform image merging processing on each of the inversion recovery images to obtain a target composite image of the patient, and identify tissue abnormality information of the target composite image through an image comparison strategy based on the target composite image and the comparison image; A prediction module is used to predict the glucose metabolism value of the patient based on the tissue abnormality information and through a glucose metabolism value prediction strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images