Medical image analysis methods, systems, equipment, media and program products

Abstract

The present application relates to a medical image analysis method, system, device, medium and program product. Applied to a first server; the method includes: obtaining an image analysis request for a target user sent by a requester based on a user terminal; generating an image analysis task corresponding to the target user according to the image analysis request; the image analysis task includes target image address information; sending the image analysis task to a target server in a second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result; the target image is stored in the image database of the first server. This method can avoid strong coupling between the first server including the image platform and the second server integrated with the AI ​​service, and prevent the target server from obtaining all the image data, thereby ensuring the data security of the target user.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a medical image analysis method, system, device, medium and program product. Background Art

[0002] Through cloud computing, big data and mobile Internet technologies, the medical imaging platform has achieved centralized storage, unified archiving and sharing of regional medical imaging data and diagnostic reports, and realized the retrieval, reading and sharing of images and reports on mobile terminals.

[0003] With the continuous development of artificial intelligence (AI), artificial intelligence (AI) image analysis services are increasingly being applied to medical imaging platforms. AI image analysis services can automatically classify, detect, identify, and segment medical imaging data. Currently, when users need to perform AI image analysis on medical imaging data from a medical imaging platform, the platform must push all received medical imaging data to the AI ​​image analysis service, allowing the AI ​​image analysis service to process the medical imaging data.

[0004] However, the way in which medical imaging platforms push all received medical imaging data to AI imaging analysis services has the problem of low data security. Summary of the Invention

[0005] Based on this, it is necessary to provide a medical image analysis method, system, equipment, medium and program product that can improve data security in response to the above technical problems.

[0006] In a first aspect, the present application provides a medical image analysis method. Applied to a first server, the method comprises:

[0007] Obtaining an image analysis request for a target user sent by a requester based on a user terminal;

[0008] Generate an image analysis task corresponding to the target user based on the image analysis request; the image analysis task includes the target image address information;

[0009] The image analysis task is sent to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result; the target image is stored in the image database of the first server.

[0010] In one embodiment, the medical image analysis method further includes:

[0011] According to the image analysis request, obtain the metadata corresponding to the image data in the image database;

[0012] Verify resource availability based on metadata;

[0013] Based on the image analysis request, an image analysis task corresponding to the target user is generated, including:

[0014] If the resource availability verification is passed, an image analysis task corresponding to the target user is generated according to the image analysis request.

[0015] In one embodiment, the metadata includes medical examination information and parameter information of medical images; verifying the resource availability of the metadata includes:

[0016] Determine whether the target user's medical images meet the algorithm analysis requirements based on the medical image parameter information and medical examination information;

[0017] If the target user's medical images meet the algorithm analysis requirements, the metadata resource availability verification is passed.

[0018] In one embodiment, generating an image analysis task corresponding to a target user according to an image analysis request includes:

[0019] Find the target algorithm from the algorithm registry according to the image analysis request;

[0020] Generate image analysis tasks based on image analysis requests and target algorithms.

[0021] In one embodiment, sending the image analysis task to a target server in the second server includes:

[0022] Check whether the remaining resources of the target algorithm corresponding to the target server meet the operating resource conditions of the image analysis task;

[0023] If the remaining resources meet the running resource conditions of the image analysis task, the image analysis task will be sent to the target server.

[0024] In one embodiment, the image analysis request includes requester authority information; the method further includes:

[0025] Obtain user permission information based on image analysis requests;

[0026] Determine whether the requester's permission information meets the preset image analysis permission requirements based on the user's permission information and the requester's permission information;

[0027] If the requester's permission information meets the preset image analysis permission requirements, the image analysis permission verification is passed;

[0028] If the resource availability verification is passed, an image analysis task corresponding to the target user is generated according to the image analysis request, including:

[0029] If the image analysis permission verification is passed and the resource availability verification is passed, an image analysis task corresponding to the target user is generated.

[0030] In one embodiment, the image analysis request includes a user identifier of a target user; and the method further includes:

[0031] According to the user ID of the target user, search the image analysis task corresponding to the target user in the task database;

[0032] If there is an image analysis task in the task database, the analysis result summary information corresponding to the image analysis task is sent to the user terminal.

[0033] In one embodiment, the medical image analysis method further includes:

[0034] receiving result summary information and / or task completion status notification sent by the second server after data analysis is completed;

[0035] Send result summary information and / or task completion status notification to the user terminal.

[0036] In a second aspect, the present application provides a medical image analysis method, which is applied to a second server and includes:

[0037] receiving an image analysis task sent by the first server; the image analysis task is to obtain an image analysis request for a target user sent by a requester based on a user terminal, verify the image analysis authority of the requester based on the image analysis request of the target user, and generate a task based on the image analysis request when the image analysis authority of the requester is verified; the image analysis task includes target image address information;

[0038] According to the target image address information, a target image is obtained from the image database; the target image is stored in the image database of the first server;

[0039] Perform data analysis on the target image to obtain image analysis results.

[0040] In one embodiment, the image analysis task includes the effective storage duration of the target image; and the method further includes:

[0041] After obtaining the image analysis results, the storage time of the target image is counted;

[0042] If the storage duration of the target image reaches the effective storage duration, the target image will be deleted.

[0043] In a third aspect, the present application further provides an imaging platform providing system, the system comprising:

[0044] A request acquisition module is used to acquire an image analysis request for a target user sent by a requester based on a user terminal;

[0045] The task generation module is used to generate an image analysis task corresponding to the target user according to the image analysis request; the image analysis task includes the target image address information;

[0046] The sending module is used to send the image analysis task to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result; the target image is stored in the image database of the first server.

[0047] In a fourth aspect, the present application further provides an image analysis service system, which includes:

[0048] a receiving module configured to receive an image analysis task sent by the first server; the image analysis task is to obtain an image analysis request for a target user sent by a requester based on a user terminal, verify the requester's image analysis authority based on the target user's image analysis request, and generate a task based on the image analysis request when the requester's image analysis authority is verified; the image analysis task includes target image address information;

[0049] An image acquisition module is used to acquire a target image in an image database according to the target image address information; the target image is stored in the image database of the first server;

[0050] The analysis module is used to perform data analysis on the target image and obtain image analysis results.

[0051] In a fifth aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method according to any one of the embodiments of the first and second aspects are implemented.

[0052] In a sixth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of the embodiments of the first and second aspects.

[0053] In a seventh aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of the embodiments of the first and second aspects.

[0054] The above-mentioned medical image analysis method, system, device, medium and program product obtains an image analysis request for a target user sent by a requester based on a user terminal, generates an image analysis task corresponding to the target user including the target image address information according to the image analysis request, and sends the image analysis task to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result. Among them, the target image is stored in the image database of the first server. It can ensure the data security of the target user when the second server (third party) analyzes the image of the target user. Specifically, it is embodied in the following aspects: 1. Only the image analysis task is sent to the target server for intelligent analysis first, avoiding the strong coupling between the first server including the image platform and the second server integrated with the AI ​​service. 2. Only the image analysis task is sent to the target server corresponding to the second server, avoiding the target server from obtaining all the image data, thereby ensuring the data security of the target user. 3. Only the image analysis task is sent without pushing all images to the second server, avoiding redundant data transmission. 4. By integrating the intelligent gateway or multiple microservices into the imaging platform, AI applications and services can be connected to the existing imaging platform, expanding the capabilities of the imaging platform without changing the platform's existing data storage method or requiring any modifications to the AI ​​algorithm's computational logic. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A diagram showing an application environment of a medical image analysis method in one embodiment;

[0056] Figure 2 1 is a flow chart of a medical image analysis method according to an embodiment;

[0057] Figure 3 A schematic flow chart of a medical image analysis method according to another embodiment;

[0058] Figure 4 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0059] Figure 5 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0060] Figure 6 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0061] Figure 7 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0062] Figure 8 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0063] Figure 9 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0064] Figure 10 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0065] Figure 11 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0066] Figure 12 is a schematic flow chart of a medical image analysis method according to another embodiment;

[0067] Figure 13 is a schematic structural diagram of a medical image analysis system in one embodiment;

[0068] Figure 14 is a schematic structural diagram of a medical image analysis system in another embodiment;

[0069] Figure 15 A schematic diagram of the structure of an imaging platform system in one embodiment is provided;

[0070] Figure 16 is a schematic structural diagram of an image analysis service system in one embodiment;

[0071] Figure 17 FIG. 4 is a diagram showing the internal structure of a server in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0073] With the advancement of science and technology, various medical imaging platforms have been established. Leveraging cloud computing, big data, and mobile internet technologies, these platforms enable centralized storage, unified archiving, and sharing of regional medical imaging data and diagnostic reports, as well as mobile retrieval, reading, and sharing of images and reports. These platforms have brought about more convenient, flexible, and reliable remote and mobile healthcare models, promoting cross-institutional collaboration and service upgrades in imaging-related healthcare, benefiting numerous physicians and patients.

[0074] Introducing artificial intelligence (AI) image analysis services is essential to further leverage the positive impact of imaging platforms. AI technology enables automatic image classification, detection, identification, and segmentation of lesions. AI services can be integrated with manual diagnostic workflows to process images in advance or in real time, assisting doctors in completing diagnoses and potentially providing detailed analysis reports, improving efficiency and accuracy. For examinations where a diagnosis has already been obtained, AI can perform a secondary analysis of the original images and provide an independent assessment for doctors and patients to reference. This is particularly valuable for serious and difficult diseases.

[0075] In the existing technology, when the existing imaging platform is connected to a third-party AI analysis service, in order to use the third-party AI analysis service of the imaging platform, it is necessary to synchronize all relevant imaging data to the connected AI analysis service so that the third-party AI service can provide analysis results after analysis. However, there are many security and efficiency issues with the existing technology, such as: 1. How to ensure that the data passed to the AI ​​service is authorized? 2. How to ensure that the data passed can be processed by the AI ​​algorithm and that the data is non-redundant? 3. How to ensure that the AI ​​analysis results are completely saved and accurately interpreted and presented? 4. How to quickly feedback the results containing symptom prompts to the user without overwhelming the user with irrelevant details? 5. How to reduce changes to the platform when adding or updating AI algorithms and services?

[0076] Based on this, the medical image analysis method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, user terminal 102, first server 104, and second server 106 communicate via a network. A requester sends an image analysis request for a target user to first server 104 based on user terminal 102. Based on the image analysis request, first server 104 generates an image analysis task corresponding to the target user and sends the image analysis task to a target server in second server 106. Second server 106 causes the target server corresponding to the image analysis task to obtain the target image based on the target image address information, executes the image analysis task, and obtains the image analysis results. User terminal 102 may be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices may include smart watches, smart bracelets, head-mounted devices, etc. First server 104 and second server 106 may be implemented as independent servers or as a server cluster consisting of multiple servers. First server 104 may include a gateway integrated into a medical imaging platform or a server cluster consisting of multiple microservers, without limitation. The second server 106 may be a server or server cluster that integrates different AI services. The different AI services may be different AI services corresponding to different medical image acquisition devices.

[0077] In one embodiment, Figure 2 As shown, a medical image analysis method is provided, which is applied to Figure 1 Taking the first server in the example as an example, the following steps are included:

[0078] S202: Obtain an image analysis request for a target user sent by a requester based on a user terminal.

[0079] The requester is the person who initiates a request to obtain image analysis results for a target user. The target user is the user designated by the requester for whom the image analysis results are to be obtained. The image analysis request may be a request for analysis of the target user's relevant medical image data. The image analysis request may include the identifier of the target user and the identifier of the target analysis region of interest, etc., without limitation.

[0080] Specifically, the requester can select the request initiation option based on the image analysis interface of the user terminal to jump to the target user's selection interface, select the target user, that is, authorize image analysis of the target user, and initiate an image analysis request for the target user to the first server, that is, obtain the image analysis request for the target user sent by the requester based on the user terminal.

[0081] S204: Generate an image analysis task corresponding to the target user according to the image analysis request; the image analysis task includes target image address information.

[0082] The image analysis task may include performing intelligent analysis on a target image corresponding to a target user. The image analysis task may include an analysis algorithm, a target server identifier, target image address information, and a task delivery method, all of which are not limited herein. The target image address information refers to the storage address of the target image.

[0083] Specifically, after receiving an image analysis request, the target user's metadata and user permission information stored in the image database can be retrieved based on the target user's identification information in the image analysis request. Resource availability verification can then be performed on the metadata and / or the requested permissions can be verified based on the user permission information. If verification is successful, an intelligent analysis algorithm is matched to the target user based on the identification of the target analysis region of interest in the image analysis request. After matching to the target analysis algorithm, an image analysis task corresponding to the target user is generated. Metadata can include medical examination information, medical image parameter information, medical institution information, etc. Medical image parameter information can include image storage address, image quantity information, image quality information, image format, image acquisition method, etc., without limitation. Furthermore, image acquisition methods can include images acquired using medical imaging devices such as CT, MR, and PET. Image quality information can include image resolution, etc. Image formats can include DICOM, NII, and other formats.

[0084] S206, sending the image analysis task to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result; the target image is stored in the image database of the first server.

[0085] Specifically, after the image analysis task is generated, the image analysis task can be sent to the target server in the second server; or the image analysis task can be sent to the target server when the resources of the target server are available by detecting the resource availability of the target server; or the image analysis task can be sent to the target server when the preset sending time arrives.

[0086] When the target server receives an image analysis task, it can proactively retrieve the target image for analysis from the image database on the first server based on the target image address information included in the image analysis task. It then executes the image analysis task, performs intelligent analysis on the target image, and obtains image analysis results. These image analysis results may include analysis result summaries, analysis status information, and detailed analysis reports, without limitation.

[0087] Optionally, after sending the image analysis task to the second server, the first server may send a status query request to the target server at a preset time and receive analysis status information fed back by the target server, wherein the analysis status information is used to indicate the task progress.

[0088] Optionally, the image analysis task may include a preset target image storage time after the second server completes the analysis, so that the second server deletes the target image when the target image storage time is reached after the task is completed.

[0089] In the above-mentioned medical image analysis method, by obtaining the image analysis request for the target user sent by the requester based on the user terminal, an image analysis task corresponding to the target user including the target image address information is generated according to the image analysis request, and the image analysis task is sent to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result. Among them, the target image is stored in the image database of the first server. It can ensure the data security of the target user when the second server (third party) analyzes the image of the target user. Specifically embodied in: 1. Only the image analysis task is sent to the target server for intelligent analysis first, avoiding the strong coupling between the first server including the image platform and the second server integrated with the AI ​​service. 2. Only the image analysis task is sent to the target server corresponding to the second server, avoiding the target server from obtaining all the image data, thereby ensuring the data security of the target user. 3. Only the image analysis task is sent, without pushing all images to the second server, to avoid redundant data transmission. 4. Since the intelligent gateway or multiple microservices are integrated into the first server corresponding to the imaging platform, it is possible to expand the capabilities of the imaging platform when accessing AI applications and algorithm services on the existing imaging platform without changing the existing data storage method of the imaging platform or requiring any modifications to the calculation logic of the AI ​​algorithm.

[0090] The above embodiment describes the medical image analysis. To further ensure the security of the data, the resource availability of the data can be verified. When the verification is passed, an image analysis task is generated. Now, an embodiment is used to describe how to verify the resource availability of data. In one embodiment, Figure 3 As shown, the medical image analysis method further includes:

[0091] S302: Obtain metadata corresponding to the image data in the image database according to the image analysis request.

[0092] Specifically, the first server may include an image metadata retriever that retrieves relevant metadata other than the image from the image database based on the target user identifier carried in the image analysis request. This metadata may include medical examination information, medical image parameter information, medical institution information, and the like. Medical image parameter information may include, but is not limited to, image storage address, image quantity, image quality, image format, and image acquisition method. Medical examination information may include, but is not limited to, examination type, location, data owner, confidentiality level, patient, and medical institution information.

[0093] S304: Verify the resource availability of the metadata.

[0094] Specifically, the first server may include a data availability verifier. After obtaining the target user's metadata, the first server may compare the parameter information of the medical images in the metadata with the preset analysis requirements of the algorithm to verify the resource availability of the metadata. For example, the first server may check the quantity, quality, storage location, and acquisition method of the images to determine whether they meet the preset analysis requirements of the analysis algorithm.

[0095] Based on the image analysis request, an image analysis task corresponding to the target user is generated, including:

[0096] S306: If the resource availability verification is passed, an image analysis task corresponding to the target user is generated according to the image analysis request.

[0097] Specifically, when the resource availability verification passes, that is, the metadata meets the preset analysis requirements of the analysis algorithm, the medical examination information and medical image parameter information in the metadata can be further obtained according to the image analysis request, and the corresponding target algorithm can be found based on the pre-stored algorithm registry through the AI ​​algorithm matching filter. The AI ​​task builder then generates the image analysis task corresponding to the target user based on the metadata and target algorithm. Among them, the algorithm registry is a global directory of algorithms that records all available AI algorithm information, including the algorithm's request address, image processing capabilities, and requirements for image quality and format.

[0098] In this embodiment, metadata corresponding to the image data in the image database is obtained according to the image analysis request, and resource availability verification is performed on the metadata. If the resource availability verification passes, an image analysis task corresponding to the target user is generated according to the image analysis request, which can ensure that the transmitted image analysis task can be processed by the target algorithm and the metadata contained is non-redundant.

[0099] The above embodiment has described the data availability analysis, and now an embodiment is used to further describe how to verify resource availability. In one embodiment, Figure 4 As shown, metadata includes medical examination information and parameter information of medical images; verification of metadata resource availability includes:

[0100] S402: Determine whether the medical image of the target user meets the algorithm analysis requirements based on the parameter information of the medical image and the medical examination information.

[0101] S404: If the medical images of the target user meet the algorithm analysis requirements, the metadata resource availability verification is passed.

[0102] Specifically, the parameter information of the medical image and the medical examination information are compared with the algorithm analysis requirements. If the medical image of the target user meets the algorithm analysis requirements, the metadata resource availability verification is passed. For example, the algorithm analysis requirements are to detect the heart of the target user, and the target image format is required to be DICOM format, and all images from April 2022 are required. Then, the medical examination information can be compared to see whether it records the specified time period (April 2022), the detection site is the heart, and the image format in the parameter information of the medical image is DICOM. If any of the items do not match, the verification fails, otherwise the verification passes.

[0103] In this embodiment, whether the target user's medical image meets the algorithm analysis requirements is determined based on the parameter information and medical examination information of the medical image. If the target user's medical image meets the algorithm analysis requirements, the metadata resource availability verification is passed, which can ensure that the transmitted metadata is data that can be processed by the AI ​​algorithm.

[0104] The above embodiment has described the resource availability verification of data. Now, an embodiment is used to further describe how to generate an image analysis task. In one embodiment, Figure 5 As shown in the figure, based on the image analysis request, the image analysis task corresponding to the target user is generated, including:

[0105] S502: Find a target algorithm from an algorithm registry according to the image analysis request.

[0106] Specifically, first, the metadata corresponding to the target user can be determined through the image analysis request, and then the medical examination information and medical image parameter information carried in the metadata can be matched with the descriptions of each algorithm in the algorithm registry through the algorithm filter to find the most matching target algorithm, that is, the target algorithm that can obtain metadata.

[0107] S504: Generate an image analysis task according to the image analysis request and the target algorithm.

[0108] Specifically, after the target algorithm is determined, the target algorithm and the address information of the target image included in the metadata can be used to construct a task through a task constructor to generate an image analysis task.

[0109] Optionally, after the image analysis task is generated, the image analysis task is stored in a task database and then placed in a task queue to be assigned. The task database is implemented using a general relational database, and the queue is implemented using a general message queue or database table.

[0110] In this embodiment, the target algorithm is found from the algorithm registry according to the image analysis request, and an image analysis task is generated according to the image analysis request and the target algorithm. This is faster and more accurate than matching images and corresponding algorithms through methods such as deep learning in the existing technology.

[0111] The above embodiment describes how to generate an image analysis task. Now, an embodiment is used to describe how to send an image analysis task. In one embodiment, Figure 6 As shown, sending the image analysis task to the target server in the second server includes:

[0112] S602: Detect whether the remaining resources of the target algorithm corresponding to the target server meet the running resource conditions of the image analysis task.

[0113] It should be noted that the target server can execute multiple image analysis tasks simultaneously or one by one, without any limitation. If the target server executes multiple image analysis tasks simultaneously, it is necessary to determine whether the target server has sufficient operating resources to execute the current image analysis task.

[0114] Specifically, a processing status reader can be used to detect the operating status and remaining resource information of the target algorithm corresponding to the target server corresponding to the image analysis task. A status data parser can then be used to parse the read target algorithm operating status and remaining resource information to obtain information that can identify the target algorithm operating status and remaining resource information. Optionally, the operating status and resource utilization of the target algorithm on the target server can be queried through a preset query interface.

[0115] Optionally, the queried running status of the target algorithm and the remaining resource information of the target algorithm are saved in the task database.

[0116] S604: If the remaining resources meet the running resource conditions of the image analysis task, the image analysis task is sent to the target server.

[0117] Specifically, when the running state of the target algorithm is that the remaining resources of the target algorithm are available, the image analysis task can be dispatched to the designated target server through the task dispatcher to execute the image analysis task.

[0118] In this embodiment, by detecting whether the remaining resources of the target algorithm corresponding to the target server meet the running resource conditions of the image analysis task, if the remaining resources meet the running resource conditions of the image analysis task, the image analysis task is sent to the target server, which can ensure that the image analysis task is processed when the target algorithm of the target server is available.

[0119] The above embodiment explains how to send an image analysis task. If you want to further enhance the security of the data, you can also verify the privacy rights of the requester to ensure that the requester can obtain the target user's information before analyzing the image data. Now, an embodiment is used to explain how to verify the rights. In one embodiment, Figure 7 As shown, the image analysis request includes the requester's authority information; the medical image analysis method also includes:

[0120] S702, obtaining user authority information according to the image analysis request;

[0121] The user authority information may include user privacy level, user access authority conditions, etc., which are not limited here.

[0122] Specifically, the image analysis request carries identification information of the target user, and the user authority information in the user information database can be searched through the identification information.

[0123] S704: Determine, based on the user authority information and the requester authority information, whether the requester authority information meets the preset image analysis authority requirements.

[0124] The preset image analysis requirement is a correspondence between preset user authority information and requester authority information, that is, under the specified correspondence, the requester's authority information meets the image analysis authority requirement.

[0125] Specifically, the requester's permission information in the image analysis request can be compared with the user's permission information through privacy and authorization filters to determine whether the preset impact analysis permission requirements are met. For example, the requester's permission information can be compared with the user's permission information, including information such as the data owner, confidentiality level, patient, and medical institution.

[0126] Optionally, the user authority information includes the user's privacy level; the requester authority information includes the requester's privacy level; the user's privacy level is compared with the requester's privacy level, and if the requester's privacy is equal to or greater than the user's privacy level, the preset image analysis authority requirement is met.

[0127] S706: If the requester's permission information meets the preset image analysis permission requirements, the image analysis permission verification is passed.

[0128] Specifically, if the requester's permission information meets the preset image analysis permission requirements, the image analysis permission verification is passed.

[0129] If the resource availability verification is passed, an image analysis task corresponding to the target user is generated based on the image analysis request, including:

[0130] S708: If the image analysis authority verification is passed and the resource availability verification is passed, an image analysis task corresponding to the target user is generated.

[0131] Specifically, if the image analysis authority verification is passed and the resource availability verification is passed, the target algorithm and the address information of the target image included in the metadata can be used to construct a task through the task constructor to generate an image analysis task.

[0132] Optionally, metadata can be validated against custom rules using custom rule filters. Rules beyond the aforementioned privacy and authorization filters and data availability filters can be read to determine whether to proceed with image analysis task generation or directly assign a target algorithm. Custom rules can be implemented using a general rule engine; adding or modifying rules is done by modifying the corresponding configuration file without changing the data processing flow within the gateway.

[0133] In this embodiment, user authority information is obtained based on the image analysis request, and whether the requester's authority information meets the preset image analysis authority requirements is determined based on the user authority information and the requester's authority information. If the requester's authority information meets the preset image analysis authority requirements, the image analysis authority verification is passed. If the image analysis authority verification is passed and the resource availability verification is passed, an image analysis task corresponding to the target user is generated, which can ensure that the data passed to the second server for intelligent analysis are all authorized data, further ensuring the security of the data.

[0134] The above embodiment explains how to perform permission verification. Before generating an image analysis task, it is possible that a related image analysis task has already been executed. In this case, there is no need to generate an image analysis task again. Now, an embodiment is used to explain how to determine whether to generate an image analysis task. In one embodiment, Figure 8 As shown, the image analysis request includes a user identifier of a target user; the medical image analysis method further includes:

[0135] S802: Search the task database for the image analysis task corresponding to the target user according to the user ID of the target user.

[0136] Specifically, the request result retriever can be used to search the task database for an image analysis task corresponding to the target user according to the target user's identifier.

[0137] S804: If the image analysis task exists in the task database, analysis result summary information corresponding to the image analysis task is sent to the user terminal.

[0138] Specifically, if an image analysis task exists in the task database, the analysis result summary information corresponding to the image analysis task is sent to the user terminal. The analysis result summary information may include the positive or negative information of the disease, the summary information of the lesion prompt, and the method for obtaining a detailed report.

[0139] In this embodiment, the image analysis task corresponding to the target user is searched for in the task database based on the user identifier of the target user. If the image analysis task exists in the task database, the analysis result summary information corresponding to the image analysis task is sent to the user terminal. In the case where the image analysis task already exists (that is, the image analysis task has been completed), the results including symptom prompts can be quickly fed back to the requester, and the requester will not be overwhelmed by irrelevant details.

[0140] The above embodiment describes how to determine whether to generate an image analysis task. When the result summary information and / or task completion status notification is obtained, it needs to be fed back to the user terminal. Now, an embodiment is used for description. In one embodiment, Figure 9 As shown, the medical image analysis method further includes:

[0141] S902: Receive result summary information and / or task completion status notification sent by the second server after data analysis is completed.

[0142] S904: Send result summary information and / or task completion status notification to the user terminal.

[0143] Specifically, after the first server receives the result summary information and / or task completion status notification sent by the second server after data analysis is complete, it stores the information locally, sends the result summary information and / or task completion status notification to the user terminal, and updates the user terminal display. Furthermore, after receiving the analysis completion status notification and result summary information, the requester can request a detailed analysis report as needed.

[0144] Furthermore, the user terminal can directly initiate a request to obtain a detailed analysis report of the target from the second server. The detailed report can then be retrieved from the second server according to the detailed analysis report acquisition method and displayed. The display can be performed via an online web application, typically displaying the analysis evidence and conclusions in the form of lists, images, symbols, etc., and is implemented by the second server provider.

[0145] In this embodiment, by receiving the result summary information and / or task completion status notification sent by the second server after the data analysis is completed, the result summary information and / or task completion status notification is sent to the user terminal, the results including symptom prompts can be quickly fed back to the user terminal, and the requester will not be overwhelmed by irrelevant details.

[0146] The above embodiment describes the medical image analysis method applied to the first server. Now, an embodiment is used to describe the medical image analysis method applied to the second server. In one embodiment, Figure 10 As shown, medical image analysis methods include:

[0147] S102, receiving an image analysis task sent by the first server; the image analysis task is a task generated according to an image analysis request for a target user sent by a requester based on a user terminal; the image analysis task includes target image address information.

[0148] The requester is the initiator of a request to obtain the image analysis results for the target user. The target user is the user designated by the requester for whom the image analysis results are to be obtained. The image analysis request may be a request for analysis of the target user's relevant medical image data. The image analysis request may include the identifier of the target user, the identifier of the target analysis region of interest, etc., without limitation herein. The image analysis task may include how to perform intelligent analysis on the target image corresponding to the target user. The image analysis task may include an analysis algorithm, a target server identifier, target image address information, a task delivery method, etc., without limitation herein. The target image address information is the storage address of the target image.

[0149] Specifically, the requester can select the request initiation option based on the image analysis interface of the user terminal to jump to the target user's selection interface, select the target user, that is, authorize image analysis of the target user, and initiate an image analysis request for the target user to the first server, that is, obtain the image analysis request for the target user sent by the requester based on the user terminal.

[0150] After receiving an image analysis request, the target user's metadata and user permission information stored in the image database can be retrieved based on the target user's identification information in the image analysis request. Resource availability verification can be performed on the metadata and / or the requested permissions can be verified based on the user permission information. If verification is successful, an intelligent analysis algorithm is matched to the target user based on the identification of the target analysis region of interest in the image analysis request. After matching the target analysis algorithm, an image analysis task corresponding to the target user is generated and sent to the second server, thereby receiving the image analysis task sent by the first server. The metadata may include medical examination information, medical image parameter information, medical institution information, etc. Medical image parameter information may include image storage address, image quantity information, image quality information, image format, image acquisition method, etc., without limitation. Furthermore, image acquisition methods may include images acquired using medical imaging devices such as CT, MR, and PET. Image quality information may include image resolution, etc. Image formats may include DICOM, NII, and other formats.

[0151] S104, acquiring a target image from an image database according to the target image address information; the target image is stored in the image database of the first server.

[0152] Specifically, after the image analysis task is obtained, the target image can be acquired from the image database in the first server according to the target image address information carried in the image analysis task.

[0153] S106: Perform data analysis on the target image to obtain image analysis results.

[0154] Specifically, once the target image is obtained, a target algorithm can be used to perform data analysis on the target image to obtain image analysis results. The image analysis results may include analysis result summaries, analysis status information, and detailed analysis reports, without limitation. The target algorithm can be an AI image analysis service, typically an AI-based image preprocessing, analysis, and inference algorithm service.

[0155] In this embodiment, an image analysis task is received from a first server, and based on the target image address information, a target image in an image database is retrieved, and data analysis is performed on the target image to obtain an image analysis result. The target image is stored in the image database of the first server. The image analysis task is generated based on an image analysis request for a target user sent by a requester based on a user terminal. The image analysis task includes the target image address information. Based on the image analysis task, only the target image used for analysis can be proactively retrieved from the first server, avoiding the information redundancy caused by pushing all images from the first server to the second server in the prior art. By only retrieving relevant image information, the security of other data is further improved, while also enhancing the overall efficiency of image analysis.

[0156] The above embodiment describes the medical image analysis method. To further ensure the security of the target image and avoid the problem of information leakage due to permanent storage on the second server, i.e., the third-party platform, the target image can also be deleted when the effective time after the data analysis is completed. Figure 11 As shown, the image analysis task includes the effective storage time of the target image; the medical image analysis method also includes:

[0157] S112: After obtaining the image analysis result, the storage time of the target image is counted.

[0158] S114: If the storage duration of the target image reaches the effective storage duration, the target image is deleted.

[0159] Specifically, after obtaining the image analysis result, the storage time of the target image is counted, and when the storage time of the target image reaches the effective storage time carried in the image analysis task, the target image is deleted.

[0160] Optionally, the target image can be deleted at the end of the image analysis task.

[0161] In this embodiment, after obtaining the image analysis results, the storage time of the target image is counted. If the storage time of the target image reaches the effective storage time, the target image is deleted. This can further ensure the security of the target image and avoid the problem of information leakage due to permanent storage by the second server, that is, the third-party platform.

[0162] In order to facilitate the understanding of those skilled in the art, the medical image analysis method is further described with a complete embodiment. In one embodiment, Figure 12 As shown, medical image analysis methods include:

[0163] S10: The requester sends an image analysis request for a target user to the first server based on the user terminal.

[0164] S20, the first server obtains metadata corresponding to the image data in the image database according to the image analysis request; the metadata includes medical examination information and parameter information of the medical image.

[0165] S30: The first server determines whether the medical image of the target user meets the algorithm analysis requirements based on the parameter information of the medical image and the medical examination information.

[0166] S40: If the medical images of the target user meet the algorithm analysis requirements, the resource availability verification of the metadata is passed.

[0167] S50: The first server obtains user authority information according to the image analysis request.

[0168] S60: The first server determines whether the permission information of the requester meets the preset image analysis permission requirement based on the user permission information and the permission information of the requester.

[0169] S70: If the requester's permission information meets the preset image analysis permission requirements, the image analysis permission verification is passed.

[0170] S80: If the image analysis authority verification is passed and the resource availability verification is passed, the image analysis task corresponding to the target user is searched in the task database according to the user ID of the target user.

[0171] S90: If the image analysis task exists in the task database, analysis result summary information corresponding to the image analysis task is sent to the user terminal.

[0172] S100: If the image analysis task does not exist in the task database, a target algorithm is searched from an algorithm registration table according to the image analysis request.

[0173] S110, generating an image analysis task according to the image analysis request and the target algorithm; the image analysis task includes target image address information.

[0174] S120: Detect whether the remaining resources of the target algorithm corresponding to the target server meet the running resource conditions of the image analysis task.

[0175] S130: If the remaining resources meet the running resource conditions of the image analysis task, the image analysis task is sent to the target server in the second server.

[0176] S140: The second server obtains the target image from the image database according to the target image address information; the target image is stored in the image database of the first server.

[0177] S150 , the second server performs data analysis on the target image, obtains image analysis results, result summary information, and task completion status notification, and sends the result summary information and / or task completion status notification to the first server.

[0178] S160: The first server sends result summary information and / or task completion status notification to the user terminal.

[0179] S170: After obtaining the image analysis result, the second server collects statistics on the storage time of the target image.

[0180] S180: If the storage duration of the target image reaches the effective storage duration, the second server deletes the target image.

[0181] S190: After receiving the result summary information and / or the task completion status notification, the user terminal sends a request for obtaining a target detailed analysis report to the second server.

[0182] S200: The second server receives a request for obtaining a detailed analysis report, and sends a target detailed analysis report to a user terminal for display.

[0183] The medical image analysis method provided in this embodiment can execute the above method embodiments, and its implementation principle will not be repeated here.

[0184] In this embodiment, by obtaining the image analysis request for the target user sent by the requester based on the user terminal, an image analysis task including the target image address information corresponding to the target user is generated according to the image analysis request, and the image analysis task is sent to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result. Among them, the target image is stored in the image database of the first server. It can ensure the data security of the target user when the second server (third party) analyzes the image of the target user. Specifically embodied in: 1. Only send the image analysis task to the target server for intelligent analysis first, avoiding the strong coupling between the first server including the image platform and the second server integrated with the AI ​​service. 2. Only send the image analysis task to the target server corresponding to the second server, avoiding the target server to obtain all the image data, thereby ensuring the data security of the target user. 3. Only send the image analysis task, without pushing all images to the second server, to avoid redundant data transmission. 4. By integrating the intelligent gateway or multiple microservices into the imaging platform, AI applications and services can be connected to the existing imaging platform, expanding the capabilities of the imaging platform without changing the platform's existing data storage method or requiring any modifications to the AI ​​algorithm's computational logic.

[0185] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0186] The above embodiment describes the medical image analysis method applied to the second server. The medical image analysis method is applied to the medical image analysis system, such as Figure 13 As shown; the medical image analysis system includes a first server 131 and a second server 132;

[0187] The first server 131 is configured to execute the steps of the medical image analysis method applied to the first server 131;

[0188] The second server 132 is configured to execute the steps of the medical image analysis method applied in the second server 132 .

[0189] The medical image analysis system provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described in detail here. Figure 14 shown.

[0190] Based on the same inventive concept, embodiments of the present application also provide an image platform provision system for implementing the aforementioned medical image analysis method applied to the first server. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more of the following image platform provision system embodiments can be found in the aforementioned limitations on the medical image analysis method and will not be further elaborated here.

[0191] In one embodiment, Figure 15 As shown, an image platform providing system is provided, including:

[0192] The request acquisition module 151 is used to acquire an image analysis request for a target user sent by a requester based on a user terminal;

[0193] The task generation module 152 is used to generate an image analysis task corresponding to the target user according to the image analysis request; the image analysis task includes the target image address information;

[0194] The sending module 153 is used to send the image analysis task to the target server in the second server, so that the target server obtains the target image according to the target image address information, executes the image analysis task, and obtains the image analysis result; the target image is stored in the image database of the first server.

[0195] The imaging platform providing system provided in this embodiment can execute the above method embodiments, and its implementation principles and technical effects are similar, which will not be repeated here.

[0196] In one embodiment, the imaging platform provides a system further comprising:

[0197] The metadata acquisition module is used to obtain metadata corresponding to image data in the image database according to the image analysis request;

[0198] Resource verification module, used to verify the resource availability of metadata;

[0199] The task generation module includes:

[0200] The first task generating unit is configured to generate an image analysis task corresponding to a target user according to an image analysis request if the resource availability verification is passed.

[0201] In one embodiment, the metadata includes medical examination information and parameter information of the medical image; the resource verification module is specifically used to determine whether the medical image of the target user meets the algorithm analysis requirements based on the parameter information of the medical image and the medical examination information; if the medical image of the target user meets the algorithm analysis requirements, the resource availability verification of the metadata is passed.

[0202] In one embodiment, the task generation module includes:

[0203] A search unit, used for searching a target algorithm from an algorithm registry according to an image analysis request;

[0204] The second generating unit is used to generate an image analysis task according to the image analysis request and the target algorithm.

[0205] In one embodiment, the sending module includes:

[0206] A detection unit, used to detect whether the remaining resources of the target algorithm corresponding to the target server meet the operating resource conditions of the image analysis task;

[0207] The sending unit is used to send the image analysis task to the target server if the remaining resources meet the running resource conditions of the image analysis task.

[0208] In one embodiment, the image analysis request includes requester authority information; the medical image analysis system further includes:

[0209] The permission acquisition module is used to obtain user permission information based on image analysis requests;

[0210] The authority determination module is used to determine whether the authority information of the requester meets the preset image analysis authority requirements based on the user authority information and the requester authority information;

[0211] The privacy verification module is used to verify that the image analysis permission is passed if the requester's permission information meets the preset image analysis permission requirements;

[0212] The resource verification module includes:

[0213] The authority verification unit is used to generate an image analysis task corresponding to the target user if the image analysis authority verification and the resource availability verification are passed.

[0214] In one embodiment, the image analysis request includes a user identifier of a target user; and the medical image analysis system further includes:

[0215] A task search module is used to search for the image analysis task corresponding to the target user in the task database according to the user ID of the target user;

[0216] The second sending module is configured to send analysis result summary information corresponding to the image analysis task to the user terminal if the image analysis task exists in the task database.

[0217] In one embodiment, the medical image analysis system further includes:

[0218] a notification receiving module, configured to receive result summary information and / or task completion status notification sent by the second server after data analysis is completed;

[0219] The notification sending module is used to send result summary information and / or task completion status notification to the user terminal.

[0220] The imaging platform providing system provided in this embodiment can execute the above method embodiments, and its implementation principles and technical effects are similar, which will not be repeated here.

[0221] Based on the same inventive concept, embodiments of the present application also provide an image analysis service system for implementing the aforementioned medical image analysis method applied to the second server. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more of the following image analysis service system embodiments can be found in the aforementioned limitations on the medical image analysis method and will not be further elaborated here.

[0222] In one embodiment, Figure 16 As shown, the image analysis service system includes:

[0223] The receiving module 161 is configured to receive an image analysis task sent by the first server. The image analysis task is a task generated based on an image analysis request for a target user sent by a requester based on a user terminal. The image analysis task includes target image address information.

[0224] An image acquisition module 162 is configured to acquire a target image from an image database according to the target image address information; the target image is stored in the image database of the first server;

[0225] The analysis module 163 is used to perform data analysis on the target image to obtain image analysis results.

[0226] The image analysis service system provided in this embodiment can execute the above method embodiment. Its implementation principles and technical effects are similar and will not be repeated here.

[0227] In one embodiment, the image analysis task includes the effective storage duration of the target image; the image analysis service system further includes:

[0228] The duration statistics module is used to count the storage duration of the target image after obtaining the image analysis results;

[0229] The deletion module is used to delete the target image if the storage time of the target image reaches the storage effective time.

[0230] The image analysis service system provided in this embodiment can execute the above method embodiment. Its implementation principles and technical effects are similar and will not be repeated here.

[0231] Each module in the aforementioned imaging platform provision system and image analysis service system may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device's memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0232] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 17 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store medical image data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a medical image analysis method is implemented.

[0233] Those skilled in the art will understand that Figure 17 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0234] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the medical image analysis method in any of the above embodiments are implemented.

[0235] 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 medical image analysis method in any of the above embodiments are implemented.

[0236] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the medical image analysis method in any of the above embodiments.

[0237] 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.

[0238] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0239] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0240] The above embodiments merely illustrate several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A medical image analysis method, characterized in that: Applied to the first server, the method includes: Obtaining an image analysis request for a target user sent by a requester based on a user terminal; According to the image analysis request and the image metadata retriever in the first server, obtaining metadata other than the image from the image database; Comparing the medical examination information and medical image parameter information in the metadata with the preset analysis requirements of the algorithm to determine whether the resource availability verification of the metadata has passed; If approved, an image analysis task corresponding to the target user is generated; the image analysis task includes target image address information, storage validity period, and a target algorithm adapted to the medical examination information and medical image parameter information carried in the metadata corresponding to the image analysis request; The image analysis task is sent to the target server in the second server, so that the target server retrieves the target image from the image database of the first server according to the target image address information, performs the image analysis task on the target image using the target algorithm, obtains the image analysis result, and performs statistics on the storage time of the target image. If the storage time of the target image reaches the effective storage time, the target image is deleted; the image analysis task includes the effective storage time of the target image.

2. The method according to claim 1, characterized in that The parameter information of the medical image at least includes image storage address, image quantity information, image quality information, image format and image acquisition method.

3. The method according to claim 1, characterized in that The target image address information is the storage address of the target image.

4. The method according to claim 1, wherein Generating an image analysis task corresponding to the target user according to the image analysis request includes: Finding a target algorithm from an algorithm registry according to the image analysis request; The image analysis task is generated according to the image analysis request and the target algorithm.

5. The method according to claim 4, characterized in that The sending of the image analysis task to a target server in the second server includes: Detecting whether the remaining resources of the target algorithm corresponding to the target server meet the running resource conditions of the image analysis task; If the remaining resources meet the running resource conditions of the image analysis task, the image analysis task is sent to the target server.

6. The method according to any one of claims 1 to 5, characterized in that The image analysis request includes the requester's authority information; the method further includes: Obtaining user authority information according to the image analysis request; Determining, based on the user authority information and the requester authority information, whether the requester authority information meets the preset image analysis authority requirements; If the requester's permission information meets the preset image analysis permission requirements, the image analysis permission verification is passed; If the resource availability verification passes, then generating an image analysis task corresponding to the target user according to the image analysis request includes: If the image analysis authority verification passes and the resource availability verification passes, an image analysis task corresponding to the target user is generated.

7. The method according to claim 1, characterized in that The image analysis request includes a user identifier of the target user; the method further includes: According to the user identifier of the target user, searching the task database for the image analysis task corresponding to the target user; If the image analysis task exists in the task database, analysis result summary information corresponding to the image analysis task is sent to the user terminal.

8. The method according to any one of claims 1 to 5, characterized in that The method further comprises: receiving result summary information and / or task completion status notification sent by the second server after data analysis is completed; The result summary information and / or the task completion status notification are sent to the user terminal.

9. A medical image analysis method, characterized in that: Applied to the second server, the method includes: An image analysis task is received from a first server; the image analysis task is generated when metadata resource availability verification is passed; the metadata resource availability verification is obtained based on a comparison of medical examination information and medical image parameter information in the metadata with preset analysis requirements of the algorithm; the metadata is obtained from an image database based on an image analysis request and an image metadata retriever in the first server; the image analysis request is a request sent by a requester to a target user based on a user terminal; the image analysis task includes target image address information, storage validity period, and a target algorithm adapted to the medical examination information and medical image parameter information carried in the metadata corresponding to the image analysis request; Retrieving a target image from an image database of the first server according to the target image address information; the target image is stored in the image database of the first server; Performing the image analysis task on the target image using the target algorithm to obtain an image analysis result; the image analysis task includes a storage effective time of the target image; Collecting statistics on the storage time of the target image; If the storage time of the target image reaches the storage effective time, the target image is deleted.

10. An image platform providing system, characterized in that: The system comprises: A request acquisition module is used to acquire an image analysis request for a target user sent by a requester based on a user terminal; A verification module is configured to obtain metadata other than images from an image database based on an image analysis request from the target user and an image metadata retriever in the first server; compare the medical examination information and medical image parameter information in the metadata with preset analysis requirements of the algorithm to determine whether the metadata resource availability verification has passed; if so, generate an image analysis task corresponding to the target user; the image analysis task includes target image address information, storage validity period, and a target algorithm adapted to the medical examination information and medical image parameter information carried in the metadata corresponding to the image analysis request; A sending module is used to send the image analysis task to the target server in the second server, so that the target server retrieves the target image from the image database of the first server according to the target image address information, performs the image analysis task on the target image using the target algorithm, obtains the image analysis result, and counts the storage time of the target image. If the storage time of the target image reaches the effective storage time, the target image is deleted; the image analysis task includes the effective storage time of the target image.

11. An image analysis service system, characterized in that: The system comprises: A receiving module is configured to receive an image analysis task sent by a first server; the image analysis task is generated when metadata resource availability verification is passed; the metadata resource availability verification is based on a comparison of medical examination information and medical image parameter information in the metadata with preset analysis requirements of the algorithm; the metadata is obtained from an image database based on an image analysis request and an image metadata retriever in the first server; the image analysis request is a request sent by a requester to a target user via a user terminal; the image analysis task includes target image address information, storage validity period, and a target algorithm adapted to the medical examination information and medical image parameter information carried in the metadata corresponding to the image analysis request; An image acquisition module, configured to retrieve a target image from an image database of the first server according to the target image address information; An analysis module, configured to perform the image analysis task on the target image using the target algorithm to obtain an image analysis result; the image analysis task includes a storage effective time of the target image; A duration statistics module, used to count the storage duration of the target image; The deleting module is configured to delete the target image when the storage time of the target image reaches the storage effective time.

12. 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 9 are implemented.

13. 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 9 are implemented.

14. 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 9 are implemented.

Images