Image processing methods, apparatus, systems and electronic devices

Abstract

This application relates to an image processing method, apparatus, system, and electronic device. The image processing method includes: acquiring a medical image to be processed and first configuration parameters corresponding to the medical image; matching the first configuration parameters with second configuration parameters corresponding to phantom images in a preset configuration file; wherein the configuration file includes at least one of the second configuration parameters corresponding to the phantom image, and target filter parameters for post-processing each phantom image; and, if a match is successful, performing image processing on the medical image to be processed according to the corresponding target filter parameters to generate an image processing result. This application solves the problem of low image processing efficiency and realizes a highly intelligent and multi-center PET quantitative analysis method.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to image processing methods, apparatus, systems and electronic devices. Background Technology

[0002] Standard uptake value (SUV), a semi-quantitative parameter for analyzing the level of glycolysis in tumor tissue during positron emission tomography (PET-CT), is widely used for tumor diagnosis and staging, prognosis, and treatment monitoring due to its simplicity and ease of measurement. It holds significant importance in both routine clinical practice and multicenter clinical trials. However, due to numerous factors such as differences in manufacturers, models, scanning procedures, reconstruction algorithms, and scanned subjects, SUV measurements can deviate to varying degrees. For example, using different image reconstruction parameters on raw data from a single scan of the same subject will yield different SUV values ​​for the same region of interest. In related technologies, the normalization of SUV values ​​is typically achieved by providing an input box on the workstation, allowing the operator to input the corresponding filter parameters, process the image loaded by the workstation, and then recalculate the SUV. However, there is no software support for obtaining these crucial filter parameters; currently, operators manually calculate them using tools like Excel, resulting in low efficiency in medical image processing.

[0003] Currently, no effective solution has been proposed to address the low efficiency of image processing in related technologies. Summary of the Invention

[0004] This application provides an image processing method, apparatus, system, and electronic device to at least address the problem of low efficiency in image processing in related technologies.

[0005] In a first aspect, embodiments of this application provide an image processing method, the method comprising:

[0006] The process involves acquiring a medical image to be processed and a first configuration parameter corresponding to the medical image to be processed, and matching the first configuration parameter with a second configuration parameter corresponding to a phantom image in a preset configuration file; wherein the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image;

[0007] If a match is successful, the medical image to be processed is processed according to the target filter parameters to generate an image processing result.

[0008] In some embodiments, both the first configuration parameter and the second configuration parameter include data acquisition parameters and image reconstruction parameters.

[0009] In some embodiments, prior to acquiring the medical image to be processed, the method further includes:

[0010] Obtain the preset data analysis standards and the phantom image;

[0011] The phantom image is filtered to obtain a processed phantom image. The processed phantom image is then used to calculate the image restoration coefficient. The target filter parameters are determined based on the comparison between the image restoration coefficient and the data analysis standard.

[0012] Obtain the second configuration parameters corresponding to the phantom image, and generate the configuration file based on the target filter parameters and the second configuration parameters.

[0013] In some embodiments, the step of calculating image restoration coefficients from the processed phantom image and determining the target filter parameters based on a comparison of the image restoration coefficients with the data analysis standard includes:

[0014] The image restoration coefficient is calculated on the processed phantom image, and the image restoration coefficient is compared with the standard parameter range of the data analysis standard.

[0015] In response to the comparison result indicating that the image restoration coefficients are within the range of the standard parameters, the full width at half maximum (FWHM) of the Gaussian function corresponding to the image restoration coefficients is obtained, and the target filter parameters are calculated and generated based on the FWHM.

[0016] In response to a comparison result indicating that the image restoration coefficient is outside the standard parameter range, the half-width at half-maximum (WHM) is adjusted, and a new image restoration coefficient is obtained based on the adjusted WHM until the new image restoration coefficient is detected to be within the standard parameter range. Based on the adjusted WHM, the target filter parameters are calculated and generated.

[0017] In some embodiments, after obtaining the second configuration parameters corresponding to the phantom image, the method further includes:

[0018] A visualization comparison result is generated based on the comparison result between the image restoration coefficient and the data analysis standard, and a visualization result is generated based at least on the visualization comparison result, the second configuration parameter, and the Gaussian function half-width.

[0019] The visualization results are sent to a terminal device for storage; wherein, upon receiving a query command, the terminal device displays the visualization results in response to the query command.

[0020] In some embodiments, after acquiring the medical image to be processed, the method further includes:

[0021] Obtain the region of interest adjustment information and activity ratio adjustment information of the medical image to be processed by the user, and preprocess the medical image to be processed according to the region of interest adjustment information and the activity ratio information to obtain the preprocessed medical image and the third configuration parameters corresponding to the preprocessed medical image;

[0022] The third configuration parameter is matched with the second configuration parameter. If the match is successful, the preprocessed medical image is processed according to the target filter parameter to obtain the final image processing result.

[0023] In some embodiments, the step of performing image processing on the medical image to be processed according to the corresponding target filter parameters to generate an image processing result includes:

[0024] The medical image to be processed is post-processed according to the target filter parameters to obtain a normalized image;

[0025] The normalized image is calculated to obtain a normalized quantitative result, and the image processing result is generated based on the normalized quantitative result; wherein, the normalized quantitative result includes the SUV value.

[0026] Secondly, embodiments of this application provide an image processing apparatus, the apparatus comprising: an acquisition module, a matching module, and a generation module;

[0027] The acquisition module is used to acquire the medical image to be processed and the first configuration parameters corresponding to the medical image to be processed.

[0028] The matching module is used to match the first configuration parameter with the second configuration parameter corresponding to the phantom image in the preset configuration file; wherein, the configuration file includes at least one second configuration parameter corresponding to the phantom image, and target filter parameters for post-processing each phantom image;

[0029] The generation module is used to perform image processing on the medical image to be processed according to the corresponding target filter parameters when a match is successful, and generate an image processing result.

[0030] Thirdly, embodiments of this application provide an image processing system, the system comprising: a terminal device and a server device;

[0031] The terminal device is used to acquire the medical image to be processed and send the medical image to be processed to the server device;

[0032] The server device is used to perform the image processing method as described in the first aspect above on the medical image to be processed.

[0033] Fourthly, embodiments of this application provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the image processing method as described in the first aspect above.

[0034] Compared to related technologies, the image processing method, apparatus, system, and electronic device provided in this application acquire a medical image to be processed and a first configuration parameter corresponding to the medical image to be processed, and match the first configuration parameter with a second configuration parameter corresponding to a phantom image in a preset configuration file; wherein, the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image; when the matching is successful, the medical image to be processed is processed according to the corresponding target filter parameter to generate an image processing result, which solves the problem of low image processing efficiency and realizes a highly intelligent and multi-center positron emission tomography (PET) quantitative analysis method.

[0035] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 This is an application environment diagram of an image processing method according to an embodiment of this application;

[0038] Figure 2 This is a flowchart of an image processing method according to an embodiment of this application;

[0039] Figure 3 This is a schematic diagram of the interface of an image processing software according to a preferred embodiment of this application;

[0040] Figure 4This is a structural block diagram of an image processing apparatus according to an embodiment of this application;

[0041] Figure 5 This is a structural block diagram of an image processing system according to an embodiment of this application;

[0042] Figure 6 This is a structural diagram of the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application. Furthermore, it is understood that although the efforts made in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, modifications to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0044] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0045] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application means two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The terms “first,” “second,” “third,” etc., used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0046] The image processing method provided in this application can be applied to, for example... Figure 1 The application environment shown can include a terminal device 101 and a medical scanning device 102. The terminal device 101 can communicate with the medical scanning device 102 via a network. The terminal device 101 can be, but is not limited to, various personal computers, laptops, and tablets. The medical scanning device 102 can be, but is not limited to, a CT (Computed Tomography) device, a PET (Positron Emission Computed Tomography)-CT device, and an MR (Magnetic Resonance) device. Taking a CT device as an example, the CT device can be any of parallel beam, fan beam, or cone beam scanning, and the CT scanning mode includes, but is not limited to, axial scanning and spiral scanning. The application environment can also include a server device 103, and both the terminal device 101 and the medical scanning device 102 can communicate with the server device 103 via a network. The server device 103 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0047] This embodiment provides an image processing method that can be applied to intelligent image processing software tools deployed on terminal devices; Figure 2This is a flowchart of an image processing method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0048] Step S220: Obtain the medical image to be processed and the first configuration parameter corresponding to the medical image to be processed, and match the first configuration parameter with the second configuration parameter corresponding to the phantom image in the preset configuration file; wherein, the configuration file includes at least one of the second configuration parameters corresponding to the phantom image, and target filter parameters for post-processing each phantom image.

[0049] The aforementioned medical image to be processed refers to medical images such as Digital Imaging and Communications in Medicine (DICOM) images uploaded by the operator to the aforementioned terminal device after reconstruction processing. The first configuration parameter corresponding to this medical image to be processed can include data acquisition parameters, image reconstruction parameters, etc., used in the process of reconstructing and generating the medical image to be processed; that is, the corresponding medical image to be processed can be reconstructed and generated under this second configuration parameter. The aforementioned phantom image refers to an image obtained by scanning standard tooling from various manufacturers using medical scanning equipment such as computed tomography (CT) equipment.

[0050] In some embodiments, both the first configuration parameter and the second configuration parameter mentioned above include data acquisition parameters and image reconstruction parameters.

[0051] Specifically, control devices such as server equipment can analyze and calculate the phantom image using data analysis methods such as Gaussian filtering pre-set by the operator. This allows them to calculate the target filter parameters corresponding to the phantom image. The target filter parameters, along with the data acquisition parameters, image reconstruction parameters, and other configuration parameters corresponding to the phantom image under the conditions for generating the target filter parameters, are then integrated into a configuration file. This configuration file can be stored as part of the intelligent image processing software tool. During the reconstruction of the medical image uploaded by the intelligent image processing software tool, the control device can match the first configuration parameters (data acquisition parameters, image reconstruction parameters, etc.) used to generate the medical image with the second configuration parameters (data acquisition parameters, image reconstruction parameters, etc.) in the configuration file.

[0052] Step S240: If the matching is successful, perform image processing on the medical image to be processed according to the corresponding target filter parameters to generate image processing results.

[0053] In step S240, after successfully matching the data acquisition parameters and image reconstruction parameters in the configuration file that are identical to those used to generate the medical image to be processed, the target filter parameters corresponding to the matched second configuration parameters can be added to the medical image to be processed. Since the first and second configuration parameters are matched, the medical image to be processed carries the same conditions as those used to generate the target filter parameters. This set of medical images to be processed can be directly loaded onto the workstation, and post-processing can be performed on the medical image based on the target filter parameters loaded onto it. This also achieves automatic transfer of the target filter parameters, replacing the need for operators to manually input filter parameters into input boxes provided by the workstation using small slips of paper, thus effectively improving image processing efficiency.

[0054] Through steps S220 to S240, the target filter parameters are calculated from the phantom image. The first configuration parameters corresponding to the medical image to be processed uploaded by the operator are automatically matched with the second configuration parameters in the configuration file containing the target filter parameters. Finally, the target filter parameters in the successfully matched configuration file are loaded into the medical image to be processed. There is no need to pass the manually calculated filter parameters to the workstation via a small piece of paper, which effectively improves the automation level of image processing, solves the problem of low efficiency in image processing, and realizes a highly intelligent and multi-center PET quantitative analysis method.

[0055] In some embodiments, before acquiring the medical image to be processed, the image processing method further includes the following steps:

[0056] Step S211: Obtain the preset data analysis standard and the phantom image; perform filtering processing on the phantom image to obtain the processed phantom image; calculate the image restoration coefficient on the processed phantom image; and determine the target filter parameters based on the comparison result between the image restoration coefficient and the data analysis standard.

[0057] The image restoration coefficient mentioned above refers to the image contrast restoration coefficient of the phantom image after filtering. This image restoration coefficient is a quantitative indicator used to describe the degree of intensity reduction caused by partial volume effects. The image restoration coefficient can be calculated as: Image Restoration Coefficient RC = Radioactive Concentration of Hot Spots in the Image / Actual Radioactive Concentration of Hot Spots. The data analysis standard mentioned above specifically refers to pre-set or selected methods for data analysis, such as Gaussian filtering, on the phantom image. This data analysis standard can be selected by the operator using the intelligent image processing software tool, or it can be pre-set by staff at the factory. Specifically, this data analysis standard can be different ERAL standards developed by the European Association of Nuclear Medicine (EANM), including ERAL1 and ERAL2 standards. The data analysis methods for phantom images differ between ERAL1 and ERAL2 standards. For example, the operator can choose to analyze the phantom image using ERAL1 and / or ERAL2 standards based on the actual situation using the intelligent image processing software tool. By filtering image restoration information that meets the above-mentioned ERAL standard and other data analysis standards, and performing post-processing methods such as Gaussian filtering on the above phantom image based on the image restoration coefficient that meets the filtering conditions, the target filter parameters corresponding to the phantom image can be calculated. At the same time, the deviation of SUV value caused by factors such as image reconstruction parameters can be eliminated to achieve normalization of SUV value.

[0058] In some embodiments, the above-mentioned calculation of image restoration coefficients for the processed phantom image and determination of the target filter parameters based on the comparison results of the image restoration coefficients and the data analysis standard further includes the following steps: calculating the corresponding image restoration coefficients for the processed phantom image and comparing the image restoration coefficients with the standard parameter range of the data analysis standard; in response to the comparison result indicating that the image restoration coefficients are within the standard parameter range, obtaining the half-width at half-maximum (WHM) of the Gaussian function corresponding to the image restoration coefficients, and calculating and generating the target filter parameters based on the WHM; in response to the comparison result indicating that the image restoration coefficients are outside the standard parameter range, adjusting the WHM, obtaining a new image restoration coefficient based on the adjusted WHM, until the new image restoration coefficients are detected to be within the standard parameter range, and calculating and generating the target filter parameters based on the adjusted WHM. Here, the aforementioned half-width at half-maximum (WHM) of the Gaussian function refers to a quantitative index used to describe the spatial broadening caused by partial volume effects. Specifically, multiple image restoration coefficients can be calculated using methods such as exhaustive search. For example, six cross-sections can be randomly selected from the phantom image above. At each hot spot in each layer, a circular region of interest with the same size as the actual cross-section of the hot spot can be drawn, and the corresponding image restoration coefficient can be calculated based on the radioactivity concentration value in each region of interest. Furthermore, multiple half-widths (WHMs) of Gaussian functions can be designed using methods such as exhaustive search. For example, the WHMs corresponding to the six hot spots mentioned above can be calculated. It is understood that the range of the WHMs of each Gaussian function is generally 0–10 mm, and there is generally a 0.1 mm interval between adjacent WHMs of Gaussian functions. After obtaining two standard filter lines through data analysis using the aforementioned ERAL standard and other data analysis standards, each image restoration coefficient can be compared with the standard parameter range indicated by these two standard filter lines. If an image restoration coefficient is found that matches between the two standard filter lines, or if it matches the standard filter line or has a high degree of repetition, then the phantom image can be considered to conform to the PET image standard. No post-processing adjustment is required, and a standard filter can be directly generated based on the Gaussian function half-width at half-maximum (WHM) corresponding to the image restoration coefficient. If an image restoration coefficient is detected to be outside the aforementioned standard parameter range, it indicates that the phantom image does not conform to the PET image standard. The aforementioned WHM can be readjusted, a new image restoration coefficient can be calculated and generated, and the above steps can be repeated until an image restoration coefficient within the standard parameter range is detected, and the target filter parameters are generated.

[0059] Step S212: Obtain the second configuration parameter corresponding to the phantom image, and generate the configuration file based on the target filter parameter and the second configuration parameter.

[0060] After calculating the target filter parameters through step S211, the target filter parameters that meet the data analysis criteria, as well as the second configuration parameters such as the data acquisition parameters and image reconstruction parameters used to generate the phantom image, can be further integrated into a configuration file. In the step of matching the medical image to be processed with the configuration file, the first configuration parameters, such as the data acquisition parameters and image reconstruction parameters corresponding to the generated medical image, can be matched one by one with the second configuration parameters, such as the data acquisition parameters and image reconstruction parameters corresponding to the phantom image, in the configuration file. Finally, if the match is successful, the corresponding target filter parameters are loaded into the medical image to be processed.

[0061] Through steps S211 to S212 above, the target filter parameters are obtained by post-processing the above phantom image using preset data analysis standards, thereby realizing a one-click generation method for target filter parameters. This eliminates the need for manual calculation by the operator and helps improve the accuracy and efficiency of image processing.

[0062] In some embodiments, after obtaining the second configuration parameter corresponding to the modal data, the image processing method further includes the following steps: generating a visualization comparison result based on the comparison result between the image restoration coefficient and the data analysis standard, and generating the visualization result based at least on the visualization comparison result, the second configuration parameter, and the Gaussian function's half-width at half-maximum; sending the visualization result to a terminal device for storage; wherein, upon receiving a query command, the terminal device displays the visualization result in response to the query command. The visualization comparison result can be a table composed of various values ​​of the image restoration coefficient and various values ​​corresponding to the standard parameter range in the data analysis standard, or it can be a line graph or bar chart composed of various values ​​of the image restoration coefficient and the standard parameter range, so that the comparison result between the image restoration coefficient and the data analysis standard can be intuitively seen by the user. Specifically, to facilitate user research, the aforementioned intelligent image processing software tool can also use the acquired second configuration parameters, such as all data acquisition parameters and image reconstruction parameters corresponding to the target filter parameters, combined with the aforementioned visualization comparison results, Gaussian function half-width at half-maximum, and the measurement time of the corresponding modal image, to generate a PDF report or Excel spreadsheet, and send the generated visualization results to the terminal device so that users can access and query them at any time, thereby effectively improving the convenience of user use.

[0063] In some embodiments, after acquiring the medical image to be processed, the image processing method further includes the following steps:

[0064] Step S231: Obtain the region of interest adjustment information and activity ratio adjustment information of the medical image to be processed by the user, and preprocess the medical image to be processed according to the region of interest adjustment information and the activity ratio information to obtain the preprocessed medical image and the third configuration parameters corresponding to the preprocessed medical image.

[0065] The operator or other user can interact with the aforementioned intelligent image processing software tool to adjust parameters such as the region of interest (ROI) and activity ratio required for analyzing and processing the medical image to be processed. Specifically, during the processing of the medical image, the user can click the corresponding button on the intelligent image processing software tool to generate interactive information such as ROI adjustment information and activity ratio adjustment information, which the software tool then sends to the control device for processing. Alternatively, the user can directly input the corresponding ROI, activity ratio, and other parameter information into the intelligent image processing software tool, which then sends the interactive information generated based on the user's input to the control device. It is understood that information such as the ROI and activity ratio can also be preset by the user and stored in the intelligent image processing software tool, which will not be elaborated further here. After receiving the region of interest (ROI) adjustment information and activity ratio adjustment information, the control device can instruct the scanning device to perform a scan based on the activity ratio adjustment information. For example, the activity ratio adjustment information could be a background activity of 5.3 KBq / mL, a hot-sphere activity four times that of the background, and a background volume of 9800 mL, resulting in a medical image to be processed. Simultaneously, image segmentation processing can be performed on the medical image to be processed based on the ROI adjustment information to obtain a corresponding preprocessed medical image. For example, the tumor boundary can be delineated as the ROI in the medical image to be processed, and the preprocessed medical image can be obtained, along with corresponding third configuration parameters. These third configuration parameters may include acquisition condition parameters, image reconstruction parameters, and other configuration parameters used in reconstructing the preprocessed medical image.

[0066] Step S232: Match the third configuration parameter with the second configuration parameter. If the match is successful, perform image processing on the preprocessed medical image according to the target filter parameter to obtain the final image processing result.

[0067] After obtaining the preprocessed medical image through step S231, similar to steps S220 to S240, the third configuration parameters corresponding to the preprocessed medical image can be matched one-to-one with the second configuration parameters in the configuration file, and the target filter parameters corresponding to the matched configuration file are filled into the preprocessed medical image. Thus, the preprocessed medical image carries the same conditions as those used to generate the target filter parameters. This set of preprocessed medical images can be directly loaded and processed on the workstation to generate the final image processing result corresponding to the preprocessed medical image.

[0068] Through steps S231 to S232, users can adjust parameters such as region of interest and activity ratio using the intelligent image processing software tool, thereby further improving the human-computer interaction between the user and the intelligent image processing software tool and effectively improving the efficiency of image processing.

[0069] In some embodiments, the above-described image processing results generation further includes the following steps:

[0070] Step S241: Post-process the medical image to be processed according to the target filter parameters to obtain a normalized image; calculate the normalized quantitative result based on the normalized image, and generate the image processing result based on the normalized quantitative result. Specifically, after loading the target filter parameters into the medical image to be processed, calculations can be performed on the medical image using post-processing methods such as Gaussian filtering based on the target filter parameters. The intelligent image processing software tool then calculates and generates the normalized image processing result with a single click, thereby eliminating deviations in image analysis parameters caused by factors such as image reconstruction parameters, thus achieving normalization of image analysis parameters, i.e., obtaining the normalized quantitative result, which is then used as the image processing result. Further, the normalized quantitative result can be an SUV value. Through the above embodiment, a multi-center PET quantitative normalization workflow based on intelligent image processing software tools is realized, improving the efficiency of image processing.

[0071] In some embodiments, after generating the image processing result, the image processing method further includes the step of sending the image processing result to a terminal device for real-time display. Further, after the image processing result is generated by the control device, it can be sent to the terminal device in real time and displayed through the intelligent image processing software tool. It is understood that during the analysis of the phantom image or the medical image to be processed, corresponding analysis progress prompts and graphs can be automatically generated and displayed to the user by the intelligent image processing software tool. These embodiments further improve the convenience for users to view results in real time.

[0072] The embodiments of this application will be described in detail below with reference to practical application scenarios. Figure 3 This is a schematic diagram of the interface of an image processing software according to a preferred embodiment of this application, such as... Figure 3 As shown, the image processing software in this embodiment is an intelligent image processing tool. The top of the software's interface displays the prompt "Quantitative Normalization," and the upper right corner has an interactive button for users to close the software. The image in the leftmost area of ​​the display interface is a phantom image, i.e., an image generated by scanning and reconstructing a standard tooling using the aforementioned medical scanning equipment. In this embodiment, the phantom image is a DICOM image. It should be noted that... Figure 3The phantom image displayed on the interface can also be highlighted with red boxes to indicate multiple small spheres of different radii that meet the above data analysis criteria; these are circular regions of interest (ROIs). These spheres are used to simulate cold and heat illness in vivo. Understandably, the radioactivity concentration around these spheres is higher than that in other areas of the phantom image. The import path for the local scan image is displayed at the top of the phantom image, and the operator can click the "Import" interactive button on the right to select the desired path. Below the phantom image are the words "Tracer: 18F-FDG" and "Image Modality: PETCT," indicating to the user the type of tracer used in this scan and the type of image modality generated. The central area of ​​the display interface shows adjustment key modules corresponding to ROI, activity ratio, and normalization standard. For ROI, the corresponding adjustment key module can be set as adjustment buttons, allowing the operator to adjust it using the four adjustment buttons "Up," "Down," "Left," and "Right" below the displayed text "ROI." For activity ratio, the corresponding adjustment key module can be set as a ratio input box, allowing the operator to input the desired ratio of hotball to background value in the ratio input box below the displayed text "Activity Ratio: Heat / Background." In this embodiment, the activity ratio is 8:1. For normalization standard, the corresponding adjustment key module can be set as a checkbox, allowing the operator to select EARL V1.0 and / or EARL V2.0 by checking the checkboxes in front of them. In this embodiment, EARL V1.0 is selected, and the intelligent image processing software tool will perform calculations based on the EARL V1.0 standard. A "Calculate" interactive button is located in the lower right corner of the central area of ​​the display interface for generating calculation results with a single click. The rightmost area of ​​the display interface shows line charts generated under the eigenvalues. In this embodiment, the eigenvalues ​​correspond to the maximum SUV value (represented as SUVmax) and the average SUV value (represented as SUVmean). Specifically, the rightmost area displays the first line chart when the SUVmax filter is 10mm (i.e., the half-width and height of the Gaussian function is 10mm) and the second line chart when the SUVmean filter is 9.6mm (i.e., the half-width and height of the Gaussian function is 9.6mm). The lower right corner of the rightmost area of ​​the display interface has a "Report" interactive button for generating a report in PDF format with one click.

[0073] Specifically, when a user clicks the import button on the right side of the display interface, a dropdown menu on the left displays the import path the user can select, and imports the medical image to be processed generated from the current scan. During the automatic calculation of this medical image, the operator can select the corresponding parameters by choosing the corresponding interactive buttons for ROI, activity ratio, and normalization standard deployed on the display interface, and then click the "Calculate" interactive button to allow the intelligent image processing software tool to perform the calculation with one click. The final calculated line graph is displayed in the rightmost area of ​​the display interface, and the operator can click the "Report" interactive button to allow the intelligent image processing software tool to generate a visual report with one click.

[0074] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0075] This embodiment also provides an image processing apparatus for implementing the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the terms "module," "unit," "subunit," etc., can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0076] Figure 4 This is a structural block diagram of an image processing apparatus according to an embodiment of this application, such as... Figure 4 As shown, the device includes: an acquisition module 42, a matching module 44, and a generation module 46; the acquisition module 42 is used to acquire a medical image to be processed and a first configuration parameter corresponding to the medical image to be processed; the matching module 44 is used to match the first configuration parameter with a second configuration parameter corresponding to phantom data in a preset configuration file; wherein, the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image; the generation module 46 is used to perform image processing on the medical image to be processed according to the corresponding target filter parameter when the matching is successful, and generate an image processing result.

[0077] Through the above embodiments, the matching module 44 calculates the target filter parameters by analyzing the phantom image and automatically matches the first configuration parameters corresponding to the medical image to be processed uploaded by the operator with the second configuration parameters in the configuration file containing the target filter parameters. Finally, the generation module 46 loads the target filter parameters from the successfully matched configuration file into the medical image to be processed. This eliminates the need to manually transmit the filter parameters calculated by the user to the workstation via a small note, thereby effectively improving the automation level of image processing, solving the problem of low efficiency in image processing, and realizing a highly intelligent and multi-center PET quantitative analysis device.

[0078] In some embodiments, both the first configuration parameter and the second configuration parameter mentioned above include data acquisition parameters and image reconstruction parameters.

[0079] In some embodiments, the acquisition module 42 is further configured to acquire a preset data analysis standard and the phantom image; the acquisition module 42 performs filtering processing on the phantom image to obtain a processed phantom image, calculates the image restoration coefficient on the processed phantom image, and determines the target filter parameter based on the comparison result between the image restoration coefficient and the data analysis standard; the acquisition module 42 acquires the second configuration parameter corresponding to the phantom image, and generates the configuration file based on the target filter parameter and the second configuration parameter.

[0080] In some embodiments, the acquisition module 42 is further configured to calculate the corresponding image restoration coefficient for the processed phantom image and compare the image restoration coefficient with the standard parameter range of the data analysis standard; in response to the comparison result indicating that the image restoration coefficient is within the standard parameter range, the acquisition module 42 obtains the half-width at half-maximum (WHM) of the Gaussian function corresponding to the image restoration coefficient, and calculates and generates the target filter parameters based on the WHM; in response to the comparison result indicating that the image restoration coefficient is outside the standard parameter range, the acquisition module 42 adjusts the WHM, obtains a new image restoration coefficient based on the adjusted WHM, until the new image restoration coefficient is detected to be within the standard parameter range, and calculates and generates the target filter parameters based on the adjusted WHM.

[0081] In some embodiments, the image processing apparatus further includes a storage module; the storage module is configured to generate a visualization comparison result based on the comparison result between the image restoration coefficient and the data analysis standard, and to generate a visualization result based at least on the visualization comparison result, the second configuration parameter, and the Gaussian function half-width; the storage module is also configured to send the visualization result to a terminal device for storage; wherein, upon receiving a query instruction, the terminal device displays the visualization result in response to the query instruction.

[0082] In some embodiments, the image processing apparatus further includes a preprocessing module; the preprocessing module is configured to acquire region of interest adjustment information and activity ratio adjustment information of the medical image to be processed by the user, and preprocess the medical image to be processed according to the region of interest adjustment information and the activity ratio information to obtain a preprocessed medical image and a third configuration parameter corresponding to the preprocessed medical image; the generation module is further configured to match the third configuration parameter with the second configuration parameter, and if the match is successful, perform image processing on the preprocessed medical image according to the target filter parameter to obtain a final image processing result.

[0083] In some embodiments, the image processing apparatus further includes a normalization module; the normalization module is used to post-process the medical image to be processed according to the target filter parameters to obtain a normalized image; the normalization module calculates a normalized quantitative result for the normalized image, and generates the image processing result based on the normalized quantitative result.

[0084] In some of these embodiments, the above-mentioned normalized quantitative results include SUV values.

[0085] In some embodiments, the image processing apparatus further includes a display module for sending the image processing result to a terminal device for real-time display.

[0086] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0087] This embodiment also provides an image processing system. Figure 5 This is a structural block diagram of an image processing system according to an embodiment of this application, such as... Figure 5As shown, the system includes a terminal device 101 and a server device 103. The terminal device 101 is used to acquire a medical image to be processed and a first configuration parameter corresponding to the medical image to be processed, and to send the medical image to be processed and the first configuration parameter to the server device 103. The server device 103 is used to acquire the medical image to be processed and the first configuration parameter sent by the terminal device 101, and to match the first configuration parameter with a second configuration parameter corresponding to a phantom image in a preset configuration file. The configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image. If the match is successful, the server device 103 performs image processing on the medical image to be processed according to the corresponding target filter parameter to generate an image processing result.

[0088] Through the above embodiments, the server device 103 calculates the target filter parameters from the phantom image and automatically matches the first configuration parameters corresponding to the medical image to be processed uploaded by the operator with the second configuration parameters in the configuration file containing the target filter parameters. Finally, the target filter parameters in the successfully matched configuration file are loaded into the medical image to be processed. There is no need to pass the filter parameters manually calculated by the user to the workstation via a small piece of paper, thereby effectively improving the automation level of image processing, solving the problem of low efficiency in image processing, and realizing a highly intelligent and multi-center PET quantitative analysis device.

[0089] In some embodiments, both the first configuration parameter and the second configuration parameter mentioned above include data acquisition parameters and image reconstruction parameters.

[0090] In some embodiments, the server device 103 is further configured to acquire a preset data analysis standard and the phantom image; the server device 103 performs filtering processing on the phantom image to obtain a processed phantom image, calculates the image restoration coefficient on the processed phantom image, and determines the target filter parameter based on the comparison result between the image restoration coefficient and the data analysis standard; the server device 103 acquires the second configuration parameter corresponding to the phantom image, and generates the configuration file based on the target filter parameter and the second configuration parameter.

[0091] In some embodiments, the server device 103 is further configured to calculate the corresponding image restoration coefficient on the processed phantom image and compare the image restoration coefficient with the standard parameter range of the data analysis standard; if the comparison result indicates that the image restoration coefficient is within the standard parameter range, the server device 103 obtains the half-width at half-maximum (WHM) of the Gaussian function corresponding to the image restoration coefficient, and calculates and generates the target filter parameters based on the WHM; if the comparison result indicates that the image restoration coefficient is outside the standard parameter range, the server device 103 adjusts the WHM, obtains a new image restoration coefficient based on the adjusted WHM, until the new image restoration coefficient is detected to be within the standard parameter range, and calculates and generates the target filter parameters based on the adjusted WHM.

[0092] In some embodiments, the server device 103 is further configured to generate a visualization comparison result based on the comparison result between the image restoration coefficient and the data analysis standard, and generate a visualization result based at least on the visualization comparison result, the second configuration parameter, and the Gaussian function half-width; the server device 103 sends the visualization result to the terminal device 101 for storage; wherein, upon receiving a query instruction, the terminal device 101 displays the visualization result in response to the query instruction.

[0093] In some embodiments, the server device 103 is further configured to acquire region of interest adjustment information and activity ratio adjustment information of the medical image to be processed by the user, and preprocess the medical image to be processed according to the region of interest adjustment information and the activity ratio information to obtain a preprocessed medical image and a third configuration parameter corresponding to the preprocessed medical image; the server device 103 matches the third configuration parameter with the second configuration parameter, and if the matching is successful, performs image processing on the preprocessed medical image according to the target filter parameter to obtain the image processing result.

[0094] In some embodiments, the server device 103 is further configured to perform post-processing on the medical image to be processed according to the target filter parameters to obtain a normalized image; the server device 103 calculates a normalized quantitative result for the normalized image, and generates the image processing result based on the normalized quantitative result.

[0095] In some of these embodiments, the above-mentioned normalized quantitative results include SUV values.

[0096] In some embodiments, the server device 103 is also used to send the image processing result to the terminal device 101 for real-time display.

[0097] This embodiment also provides a computer device, which may be a server. Figure 6 This is a structural diagram of the internal structure of a computer device according to an embodiment of this application, such as... Figure 6 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and the database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores image processing results. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an image processing method.

[0098] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0099] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0100] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0101] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0102] S1, acquire the medical image to be processed and the first configuration parameter corresponding to the medical image to be processed, and match the first configuration parameter with the second configuration parameter corresponding to the phantom image in the preset configuration file; wherein, the configuration file includes at least one second configuration parameter corresponding to the phantom image, and target filter parameters for post-processing each phantom image.

[0103] S2, if a match is successful, performs image processing on the medical image to be processed according to the corresponding target filter parameters to generate the image processing result.

[0104] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0105] Furthermore, in conjunction with the image processing methods described in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium stores a computer program; when executed by a processor, the computer program implements any of the image processing methods described in the above embodiments.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been 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.

[0108] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for processing positron emission tomography (PET) images, characterized in that, The method is applied to intelligent image processing software tools deployed on terminal devices; the method includes: The process involves acquiring a medical image to be processed and a first configuration parameter corresponding to the medical image to be processed, and matching the first configuration parameter with a second configuration parameter corresponding to a phantom image in a preset configuration file; wherein the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image; both the first configuration parameter and the second configuration parameter include data acquisition parameters and image reconstruction parameters. If a match is successful, the medical image to be processed is processed according to the corresponding target filter parameters to generate an image processing result. The medical image to be processed is subjected to image processing according to the corresponding target filter parameters, and the image processing result includes: The medical image to be processed is post-processed according to the target filter parameters to obtain a normalized image; The normalized image is calculated to obtain a normalized quantitative result, and the image processing result is generated based on the normalized quantitative result; wherein, the normalized quantitative result includes a standard uptake value.

2. The positron emission tomography (PET) image processing method according to claim 1, characterized in that, Before acquiring the medical image to be processed, the method further includes: Obtain the preset data analysis standards and the phantom image; The phantom image is filtered to obtain a processed phantom image. The processed phantom image is then used to calculate the image restoration coefficient. The target filter parameters are determined based on the comparison between the image restoration coefficient and the data analysis standard. Obtain the second configuration parameters corresponding to the phantom image, and generate the configuration file based on the target filter parameters and the second configuration parameters.

3. The positron emission tomography (PET) image processing method according to claim 2, characterized in that, The step of calculating the image restoration coefficients from the processed phantom image and determining the target filter parameters based on the comparison results of the image restoration coefficients and the data analysis standard includes: The image restoration coefficient is calculated on the processed phantom image, and the image restoration coefficient is compared with the standard parameter range of the data analysis standard. In response to the comparison result indicating that the image restoration coefficients are within the range of the standard parameters, the full width at half maximum (FWHM) of the Gaussian function corresponding to the image restoration coefficients is obtained, and the target filter parameters are calculated and generated based on the FWHM. In response to a comparison result indicating that the image restoration coefficient is outside the standard parameter range, the half-width at half-maximum (WHM) is adjusted, and a new image restoration coefficient is obtained based on the adjusted WHM until the new image restoration coefficient is detected to be within the standard parameter range. Based on the adjusted WHM, the target filter parameters are calculated and generated.

4. The positron emission tomography (PET) image processing method according to claim 3, characterized in that, After obtaining the second configuration parameter corresponding to the phantom image, the method further includes: A visualization comparison result is generated based on the comparison result between the image restoration coefficient and the data analysis standard, and a visualization result is generated based at least on the visualization comparison result, the second configuration parameter, and the Gaussian function half-width. The visualization results are sent to a terminal device for storage; wherein, upon receiving a query command, the terminal device displays the visualization results in response to the query command.

5. A method for processing positron emission tomography (PET) images, characterized in that, The method is applied to intelligent image processing software tools deployed on terminal devices; the method includes: Acquire medical images to be processed; Obtain the region of interest adjustment information and activity ratio adjustment information of the medical image to be processed by the user, and preprocess the medical image to be processed according to the region of interest adjustment information and the activity ratio adjustment information to obtain the preprocessed medical image and the third configuration parameters corresponding to the preprocessed medical image; The third configuration parameter is matched with the second configuration parameter corresponding to the phantom image in the preset configuration file, wherein the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image; the second configuration parameter includes data acquisition parameters and image reconstruction parameters; the third configuration parameter includes acquisition condition parameters and image reconstruction parameters. If a match is successful, the preprocessed medical image is processed according to the target filter parameters to obtain the final image processing result. The preprocessed medical image is processed according to the target filter parameters to obtain the final image processing result, including: The preprocessed medical image is post-processed according to the target filter parameters to obtain a normalized image; The normalized image is calculated to obtain a normalized quantitative result, and the image processing result is generated based on the normalized quantitative result; wherein, the normalized quantitative result includes a standard uptake value.

6. A positron emission tomography (PET) image processing device, characterized in that, The device includes: an acquisition module, a matching module, and a generation module; The acquisition module is used to acquire the medical image to be processed and the first configuration parameters corresponding to the medical image to be processed. The matching module is used to match the first configuration parameter with the second configuration parameter corresponding to the phantom image in the preset configuration file; wherein, the configuration file includes at least one second configuration parameter corresponding to the phantom image, and a target filter parameter for post-processing each phantom image; both the first configuration parameter and the second configuration parameter include data acquisition parameters and image reconstruction parameters; The generation module is used to perform image processing on the medical image to be processed according to the corresponding target filter parameters when the matching is successful, and generate an image processing result. The medical image to be processed is subjected to image processing according to the corresponding target filter parameters, and the image processing result includes: The medical image to be processed is post-processed according to the target filter parameters to obtain a normalized image. A normalized quantitative result is calculated on the normalized image, and the image processing result is generated based on the normalized quantitative result, wherein the normalized quantitative result includes a standard uptake value.

7. A positron emission tomography (PET) image processing system, characterized in that, The system includes: terminal equipment and server equipment; The terminal device is used to acquire the medical image to be processed and send the medical image to be processed to the server device; The server device is used to perform the positron emission tomography (PET) image processing method as described in any one of claims 1 to 5 on the medical image to be processed.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the positron emission tomography image processing method according to any one of claims 1 to 5.

Images