Medical image data analysis method and device, storage medium, electronic equipment and product

Abstract

The embodiment of the invention discloses a medical image data analysis method and device, a storage medium, electronic equipment and a product. The method comprises the following steps: acquiring medical image data sent by a medical business system, and determining image feature description information corresponding to the medical image data; inputting the medical image data into a pre-constructed multi-level feature domain model, and obtaining multi-level image data features corresponding to the medical image data output by the multi-level feature domain model; and inputting the image feature description information and the multi-level image data features into an AI algorithm matching agent, determining a target AI algorithm according to an output result of the AI algorithm matching agent, and performing medical AI analysis on the medical image data based on the target AI algorithm. According to the scheme, the AI algorithm matched with the medical image data can be quickly and accurately determined, so that the accuracy and reliability of analyzing the medical image data based on the AI algorithm are improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, storage medium, electronic device and product for medical image data analysis. Background Technology

[0002] With the widespread application of Artificial Intelligence (AI) technology in medical image analysis, different types of medical image AI algorithms are used for scenarios such as lesion detection, segmentation, quantitative analysis, and assisted diagnosis. However, the following problems often exist in practical applications:

[0003] 1. Highly heterogeneous sources of medical imaging data: Different hospitals use imaging equipment of varying ages; different manufacturers employ different imaging protocols and proprietary Digital Imaging and Communications in Medicine (DICOM) tags; even within the same hospital, the structure of imaging data generated by different outpatient clinics, examination rooms, and equipment is inconsistent. 2. Difficulty in ensuring the integrity and standardization of imaging data: Some images lack key DICOM tags, and some tags have issues with non-standard naming or semantic inaccuracies. 3. Existing algorithm matching methods have significant shortcomings: They rely on manual configuration or fixed rules; maintenance costs are high, and scalability is poor; matching is prone to failure when data is missing or non-standardized; and it is difficult to balance speed and accuracy in large-scale imaging scenarios. Therefore, there is an urgent need for a technical solution that can quickly, accurately, and automatically determine which artificial intelligence algorithms can successfully execute medical AI tasks in a real medical environment, and complete scheduling and continuous optimization. Summary of the Invention

[0004] This application provides a medical image data analysis method, device, storage medium, electronic device, and product, which can quickly and accurately determine the target AI algorithm adapted to medical image data, thereby improving the accuracy and reliability of medical AI analysis of medical image data based on AI algorithms.

[0005] According to one aspect of this application, a method for analyzing medical image data is provided, the method comprising:

[0006] Acquire medical image data sent by the medical business system and determine the image feature description information corresponding to the medical image data;

[0007] The medical image data is input into a pre-constructed multi-level feature domain model to obtain the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model.

[0008] The image feature description information and the multi-level image data features are input into an AI algorithm matching agent. A target AI algorithm is determined based on the output of the AI ​​algorithm matching agent, and medical AI analysis is performed on the medical image data based on the target AI algorithm. According to one aspect of this application, a medical image data analysis device is provided, the device comprising:

[0009] The medical image data acquisition module is used to acquire medical image data sent by the medical business system and determine the image feature description information corresponding to the medical image data.

[0010] The multi-level image data feature acquisition module is used to input the medical image data into a pre-constructed multi-level feature domain model and acquire the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model.

[0011] The target AI algorithm determination module is used to input the image feature description information and the multi-level image data features into the AI ​​algorithm matching agent, determine the target AI algorithm based on the output result of the AI ​​algorithm matching agent, and perform medical AI analysis on the medical image data based on the target AI algorithm.

[0012] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory that is communicatively connected to at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the medical image data analysis method of any embodiment of this application.

[0016] According to another aspect of this application, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the medical image data analysis method of any embodiment of this application.

[0017] According to another aspect of this application, a computer program product is provided, which includes a computer program that, when executed by a processor, implements the medical image data analysis method of any embodiment of this application.

[0018] The technical solution of this application embodiment involves acquiring medical image data sent by a medical business system and determining the image feature description information corresponding to the medical image data; inputting the medical image data into a pre-constructed multi-level feature domain model to obtain the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model; inputting the image feature description information and the multi-level image data features into an AI algorithm matching agent; determining a target AI algorithm based on the output result of the AI ​​algorithm matching agent; and performing medical AI analysis on the medical image data based on the target AI algorithm. Through the technical solution provided by this application embodiment, a target AI algorithm adapted to medical image data can be quickly and accurately determined, thereby improving the accuracy and reliability of medical AI analysis of medical image data based on AI algorithms.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a medical image data analysis method provided in this application embodiment;

[0022] Figure 2 A schematic diagram of the structure of a medical image data analysis device provided in this application embodiment;

[0023] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," "third," "fourth," "actual," "preset," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] Figure 1 This is a flowchart illustrating a medical image data analysis method provided in an embodiment of this application. This embodiment is applicable to situations involving the analysis of medical image data. The method can be executed by a medical image data analysis device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0027] S110. Obtain medical image data sent by the medical business system, and determine the image feature description information corresponding to the medical image data.

[0028] In this embodiment, medical image data sent by a medical business system is acquired. This medical business system may include medical equipment, a medical imaging system, a hospital information system, or other medical business systems. The medical image data can support not only standard imaging protocols but also non-standard imaging protocols; therefore, it may contain standard DICOM tags and / or proprietary tags (i.e., non-standard tags). The tags (including standard DICOM tags and / or proprietary tags) contained in the medical image data are analyzed to determine the corresponding image feature description information. For example, the tags (including standard DICOM tags and / or proprietary tags) contained in the medical image data are parsed, cleaned, normalized, and structured to generate unified image feature description data. This image feature description data may include modality, examination site, slice thickness, slice spacing, sequence description, image orientation, and location information, etc.

[0029] S120. Input the medical image data into a pre-constructed multi-level feature domain model to obtain the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model.

[0030] In this embodiment, a pre-constructed multi-level feature domain model is obtained. This multi-level feature domain model is a machine learning model capable of accurately and quickly determining the multi-level features of the input data. Medical image data is input into the multi-level feature domain model, enabling the model to analyze the medical image data and obtain the multi-level image data features corresponding to the medical image data output by the model. These multi-level image data features can include image data features under at least two feature domains, such as image data features under a global feature domain, image data features under a hospital-level feature domain, image data features under a clinic or department-level feature domain, and image data features under an examination room or equipment-level feature domain. For example, multi-level image data features may include data integrity patterns, vendor protocol features, private label distribution features, and historical algorithm matching success rates, etc.

[0031] S130. Input the image feature description information and the multi-level image data features into the AI ​​algorithm matching agent, determine the target AI algorithm based on the output result of the AI ​​algorithm matching agent, and perform medical AI analysis on the medical image data based on the target AI algorithm.

[0032] In this embodiment, image feature description information and multi-level image data features are input into an AI algorithm matching agent. The AI ​​algorithm matching agent analyzes the image feature description information and multi-level image data features, calculates the matching degree between each AI algorithm in its integrated AI algorithm set and the image feature description information and multi-level image data features, and uses the matching degree as the output result of the AI ​​algorithm matching agent. Based on the output result of the AI ​​algorithm matching agent, a target AI algorithm is determined. For example, one or more AI algorithms with the highest matching degree in the AI ​​algorithm set integrated by the AI ​​algorithm matching agent can be selected as the target AI algorithm. Medical AI analysis is then performed on the medical image data based on the target AI algorithm. Finally, the medical analysis result corresponding to the medical image data is determined based on the analysis result of the target AI algorithm, and the medical analysis result is fed back to the medical business system.

[0033] Optionally, the AI ​​algorithm matching agent includes a constraint adaptation module and a matching degree calculation module; inputting the image feature description information and the multi-level image data features into the AI ​​algorithm matching agent, and determining the target AI algorithm based on the output result of the AI ​​algorithm matching agent, includes: inputting the image feature description information and the multi-level image data features into the constraint adaptation module, and determining the constraint adaptation degree between the image feature description information and the multi-level image data features and the preset constraints corresponding to each AI algorithm in the AI ​​algorithm library integrated by the AI ​​algorithm matching agent; the matching degree calculation module determines the algorithm matching degree between the medical image data and each AI algorithm in the AI ​​algorithm library based on the constraint adaptation degree, the image feature description information, and the multi-level image data features, and uses the algorithm matching degree as the output result of the AI ​​algorithm matching agent; and selecting the AI ​​algorithm with the highest algorithm matching degree as the target AI algorithm.

[0034] In this embodiment, image feature description information and multi-level image data features are input into the constraint adaptation module of the AI ​​algorithm matching agent. The constraint adaptation module determines the constraint adaptation degree between the image feature description information and multi-level image data features and the preset constraints corresponding to the AI ​​algorithm for each AI algorithm in the AI ​​algorithm library integrated by the AI ​​algorithm matching agent. The preset constraints corresponding to the AI ​​algorithm may include mandatory conditions and optional conditions. A first number of mandatory conditions and a second number of optional conditions corresponding to the AI ​​algorithm are determined in the image feature description information and multi-level image data features. The constraint adaptation degree is calculated based on the pre-set weights of the mandatory conditions and optional conditions, as well as the first and second numbers.

[0035] The matching degree calculation module in the AI ​​algorithm matching agent determines the algorithm matching degree between medical image data and each AI algorithm in the AI ​​algorithm library based on constraint fit, image feature description information, and multi-level image data features. For example, it obtains a pre-defined first mapping relationship between image feature description information and description scores, and searches for the feature description score corresponding to the determined image feature description information within the first mapping relationship; it also obtains a pre-defined second mapping relationship between multi-level image data features and hierarchical feature scores, and searches for the hierarchical feature scores corresponding to the determined multi-level image data features within the second mapping relationship. A weighted sum is calculated among constraint fit, feature description score, and hierarchical feature score, and this weighted sum is used as the algorithm matching degree between the medical image data and the AI ​​algorithm. The algorithm matching degree corresponding to each AI algorithm in the AI ​​algorithm library is used as the output result of the AI ​​algorithm matching agent, and then the AI ​​algorithm with the highest algorithm matching degree in the AI ​​algorithm library is selected as the target AI algorithm.

[0036] Optionally, the AI ​​algorithm matching agent further includes a target sequence filtering module; before performing medical AI analysis on the medical image data based on the target AI algorithm, the method further includes: inputting the medical image data and the image feature description information into the target sequence filtering module, determining the target image sequence in the medical image data through the target sequence filtering module, and using the target image sequence as the output result of the AI ​​algorithm matching agent; performing medical AI analysis on the medical image data based on the target AI algorithm includes: performing medical AI analysis on the target image sequence based on the target AI algorithm.

[0037] In this embodiment, medical image data and image feature description information are input into the target sequence filtering module of the AI ​​algorithm matching agent. The target sequence filtering module determines the target image sequence in the medical image data based on the image feature description information. For example, the medical image data contains multiple image sequences. Each image sequence is analyzed to determine the image metadata of the image sequence. Then, the feature matching degree between the image metadata and the image feature description information is calculated. Image sequences with a feature matching degree greater than a preset feature matching degree threshold are selected from the multiple image sequences in the medical image data as the target image sequences in the medical image data.

[0038] Optionally, the medical image data and the image feature description information are input into the target sequence filtering module, and the target image sequence in the medical image data is determined by the target sequence filtering module. This includes: inputting the medical image data and the image feature description information into the target sequence filtering module; the target sequence filtering module filtering at least one candidate image sequence from the set of image sequences involved in the medical image data based on the image feature description information; and determining the target image sequence in the medical image data from at least one candidate image sequence. The advantage of this configuration is that it can further improve the accuracy and effectiveness of target image sequence determination.

[0039] For example, from multiple image sequences included in medical image data, image sequences with feature matching degrees greater than a preset feature matching degree threshold are selected as candidate image sequences. Then, each candidate image sequence is analyzed, and a target image sequence in the medical image data is selected from the candidate image sequences based on the analysis results. Optionally, determining the target image sequence in the medical image data from at least one of the candidate image sequences includes: determining whether the number of candidate image sequences is less than a preset number threshold; if so, at least one candidate image sequence is selected as the target image sequence in the medical image data; if the number of candidate image sequences is greater than the preset number threshold, for each candidate image sequence, a preset number of target keyframes are extracted from the candidate image sequence, and the target keyframes are input into a pre-trained lightweight image recognition model to obtain the sequence-level semantic recognition result output by the lightweight image recognition model; and the target image sequence in the medical image data is selected from at least one of the candidate image sequences based on the sequence-level semantic recognition result.

[0040] For example, it is determined whether the number of candidate image sequences is less than a preset threshold. If so, all candidate image sequences are directly used as target image sequences in the medical image data. If not, it indicates that there are too many candidate image sequences selected based on image feature description information, meaning that it is impossible to effectively filter image sequences in the medical image data based on image feature description information. Therefore, all candidate image sequences are further filtered to select the target image sequences in the medical image data. Specifically, for each candidate image sequence, a preset number of target keyframes are randomly extracted from the candidate image sequence or according to a preset extraction strategy. Then, the extracted target keyframes are input into a pre-trained lightweight image recognition model, enabling the lightweight image recognition model to perform semantic recognition on the target keyframes and obtain the sequence-level semantic recognition result output by the lightweight image recognition model. It can be understood that the sequence-level semantic recognition result corresponding to each candidate image sequence can be determined in the above manner. Then, the target image sequence in the medical image data is selected from all candidate image sequences based on the sequence-level semantic recognition result corresponding to each candidate image sequence. For example, the semantic similarity between the sequence-level semantic recognition results corresponding to all candidate image sequences is calculated, and the candidate image sequences with semantic similarity greater than a preset similarity threshold are used as the target image sequences in the medical image data. Another example is to cluster the sequence-level semantic recognition results corresponding to all candidate image sequences to generate clusters, and use the candidate image sequences corresponding to each sequence-level semantic recognition result contained in the clusters as the target image sequences in the medical image data.

[0041] In this embodiment, the target image sequence is used as the output of the AI ​​algorithm matching agent. Then, when performing medical AI analysis on medical image data based on the target AI algorithm, the target image sequence corresponding to the medical image data can be directly input into the target AI algorithm, allowing the target AI algorithm to analyze the target image sequence and determine the medical AI analysis result corresponding to the medical image data. This setup effectively reduces the computational resources required by the target AI algorithm.

[0042] The technical solution of this application embodiment involves acquiring medical image data sent by a medical business system and determining the image feature description information corresponding to the medical image data; inputting the medical image data into a pre-constructed multi-level feature domain model to obtain the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model; inputting the image feature description information and the multi-level image data features into an AI algorithm matching agent; determining a target AI algorithm based on the output result of the AI ​​algorithm matching agent; and performing medical AI analysis on the medical image data based on the target AI algorithm. Through the technical solution provided by this application embodiment, a target AI algorithm adapted to medical image data can be quickly and accurately determined, thereby improving the accuracy and reliability of medical AI analysis of medical image data based on AI algorithms.

[0043] In some embodiments, after performing medical AI analysis on the medical image data based on the target AI algorithm, the method further includes: obtaining the analysis results of the target AI algorithm on the medical image data; and updating the multi-level feature domain model and / or the AI ​​algorithm matching agent based on the analysis results. For example, the analysis status of the medical image data by the target AI algorithm is determined, where the analysis status includes successful or failed analysis. When the analysis status is successful, the analysis results of the medical image data by the target AI algorithm are further obtained, and a quality evaluation result for the analysis results is determined. Then, the multi-level feature domain model and / or the AI ​​algorithm matching agent is updated based on the analysis status, analysis results, and quality evaluation result. The advantage of this setup is that it can effectively form a closed-loop self-learning mechanism, further improving the reliability of the multi-level feature domain model and the AI ​​algorithm matching agent, thereby improving the accuracy of the multi-level feature domain model and the AI ​​algorithm matching agent in analyzing relevant data.

[0044] Figure 2 This is a schematic diagram of a medical image data analysis device provided in an embodiment of this application. This device can execute the medical image data analysis method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Figure 2 As shown, the device includes:

[0045] The medical image data acquisition module 210 is used to acquire medical image data sent by the medical business system and determine the image feature description information corresponding to the medical image data.

[0046] The multi-level image data feature acquisition module 220 is used to input the medical image data into a pre-constructed multi-level feature domain model and acquire the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model.

[0047] The target AI algorithm determination module 230 is used to input the image feature description information and the multi-level image data features into the AI ​​algorithm matching agent, determine the target AI algorithm based on the output result of the AI ​​algorithm matching agent, and perform medical AI analysis on the medical image data based on the target AI algorithm.

[0048] Optionally, the AI ​​algorithm matching agent includes a constraint condition adaptation module and a matching degree calculation module;

[0049] The target AI algorithm determination module includes:

[0050] The constraint condition fit degree determination unit is used to input the image feature description information and the multi-level image data features into the constraint condition fit module, and to determine the constraint condition fit degree between the image feature description information and the multi-level image data features and the preset constraint conditions corresponding to each AI algorithm in the AI ​​algorithm library integrated by the AI ​​algorithm matching agent.

[0051] The algorithm matching degree determination unit is used by the matching degree calculation module to determine the algorithm matching degree between the medical image data and each AI algorithm in the AI ​​algorithm library based on the constraint condition fit degree, the image feature description information and the multi-level image data features, and to use the algorithm matching degree as the output result of the AI ​​algorithm matching agent;

[0052] The target AI algorithm determination unit is used to select the AI ​​algorithm with the highest matching degree as the target AI algorithm.

[0053] Optionally, the AI ​​algorithm matching agent further includes a target sequence filtering module;

[0054] Also includes:

[0055] The target image sequence filtering module is used to input the medical image data and the image feature description information into the target sequence filtering module before performing medical AI analysis on the medical image data based on the target AI algorithm. The target image sequence filtering module determines the target image sequence in the medical image data and uses the target image sequence as the output result of the AI ​​algorithm matching agent.

[0056] The target AI algorithm determination module is used for:

[0057] Medical AI analysis is performed on the target image sequence based on the target AI algorithm.

[0058] Optional, the target image sequence filtering module includes:

[0059] A candidate image sequence filtering unit is used to input the medical image data and the image feature description information into the target sequence filtering module. The target sequence filtering module filters at least one candidate image sequence from the set of image sequences involved in the medical image data based on the image feature description information.

[0060] A target image sequence filtering unit is used to determine a target image sequence from at least one of the candidate image sequences in the medical image data.

[0061] Optionally, a target image sequence filtering unit is used for:

[0062] Determine whether the number of candidate image sequences is less than a preset number threshold. If so, then at least one of the candidate image sequences is used as the target image sequence in the medical image data.

[0063] If the number of candidate image sequences is greater than the preset number threshold, then for each candidate image sequence, a preset number of target keyframes are extracted from the candidate image sequence, and the target keyframes are input into a pre-trained lightweight image recognition model to obtain the sequence-level semantic recognition result output by the lightweight image recognition model.

[0064] Based on the sequence-level semantic recognition results, target image sequences in the medical image data are selected from at least one of the candidate image sequences.

[0065] Optional, also includes:

[0066] The analysis result acquisition module is used to acquire the analysis results of the target AI algorithm on the medical image data after performing medical AI analysis on the medical image data based on the target AI algorithm;

[0067] The model update module is used to update the multi-level feature domain model and / or the AI ​​algorithm matching agent based on the analysis results.

[0068] The medical image data analysis device provided in this application embodiment can execute a medical image data analysis method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of executing the method.

[0069] Figure 3 A schematic diagram of an electronic device 10, which can be used to implement embodiments of this application, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0070] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0071] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of monitors, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0072] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as medical image data analysis methods.

[0073] In some embodiments, the medical image data analysis method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the medical image data analysis method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the medical image data analysis method by any other suitable means (e.g., by means of firmware).

[0074] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable medical image data analysis device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0076] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0077] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0078] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0079] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0080] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the medical image data analysis method provided in any embodiment of this application.

[0081] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired information of the technical solution of this application can be achieved, and this is not limited herein.

[0083] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for analyzing medical image data, characterized in that, The method includes: Acquire medical image data sent by the medical business system and determine the image feature description information corresponding to the medical image data; The medical image data is input into a pre-constructed multi-level feature domain model to obtain the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model. The image feature description information and the multi-level image data features are input into the AI ​​algorithm matching agent. The target AI algorithm is determined based on the output of the AI ​​algorithm matching agent, and medical AI analysis is performed on the medical image data based on the target AI algorithm. The AI ​​algorithm matching agent includes a constraint condition adaptation module and a matching degree calculation module; The image feature description information and the multi-level image data features are input into the AI ​​algorithm matching agent, and the target AI algorithm is determined based on the output of the AI ​​algorithm matching agent, including: The image feature description information and the multi-level image data features are input to the constraint condition adaptation module. The constraint condition adaptation module determines the constraint condition adaptation degree between the image feature description information and the multi-level image data features and the preset constraint conditions corresponding to each AI algorithm in the AI ​​algorithm library integrated by the AI ​​algorithm matching agent. The matching degree calculation module determines the algorithm matching degree between the medical image data and each AI algorithm in the AI ​​algorithm library based on the constraint condition fit degree, the image feature description information and the multi-level image data features, and uses the algorithm matching degree as the output result of the AI ​​algorithm matching agent; The AI ​​algorithm with the highest matching degree is selected as the target AI algorithm.

2. The method according to claim 1, characterized in that, The AI ​​algorithm matching agent also includes a target sequence filtering module; Before performing medical AI analysis on the medical image data based on the target AI algorithm, the following steps are also included: The medical image data and the image feature description information are input into the target sequence filtering module. The target image sequence in the medical image data is determined by the target sequence filtering module, and the target image sequence is used as the output result of the AI ​​algorithm matching agent. Medical AI analysis of the medical image data based on the target AI algorithm includes: Medical AI analysis is performed on the target image sequence based on the target AI algorithm.

3. The method according to claim 2, characterized in that, The medical image data and the image feature description information are input into the target sequence filtering module, and the target image sequence in the medical image data is determined by the target sequence filtering module, including: The medical image data and the image feature description information are input into the target sequence filtering module, and the target sequence filtering module filters at least one candidate image sequence from the set of image sequences involved in the medical image data based on the image feature description information. The target image sequence in the medical image data is determined from at least one of the candidate image sequences.

4. The method according to claim 3, characterized in that, Determining a target image sequence from the medical image data from at least one of the candidate image sequences includes: Determine whether the number of candidate image sequences is less than a preset number threshold. If so, then at least one of the candidate image sequences is used as the target image sequence in the medical image data. If the number of candidate image sequences is greater than the preset number threshold, then for each candidate image sequence, a preset number of target keyframes are extracted from the candidate image sequence, and the target keyframes are input into a pre-trained lightweight image recognition model to obtain the sequence-level semantic recognition result output by the lightweight image recognition model. Based on the sequence-level semantic recognition results, target image sequences in the medical image data are selected from at least one of the candidate image sequences.

5. The method according to claim 1, characterized in that, After performing medical AI analysis on the medical image data based on the target AI algorithm, the process also includes: Obtain the analysis results of the target AI algorithm on the medical image data; The multi-level feature domain model and / or the AI ​​algorithm matching agent are updated based on the analysis results.

6. A medical image data analysis device, characterized in that, include: The medical image data acquisition module is used to acquire medical image data sent by the medical business system and determine the image feature description information corresponding to the medical image data. The multi-level image data feature acquisition module is used to input the medical image data into a pre-constructed multi-level feature domain model and acquire the multi-level image data features corresponding to the medical image data output by the multi-level feature domain model. The target AI algorithm determination module is used to input the image feature description information and the multi-level image data features into the AI ​​algorithm matching agent, determine the target AI algorithm based on the output result of the AI ​​algorithm matching agent, and perform medical AI analysis on the medical image data based on the target AI algorithm. The AI ​​algorithm matching agent includes a constraint condition adaptation module and a matching degree calculation module; The target AI algorithm determination module includes: The constraint condition fit degree determination unit is used to input the image feature description information and the multi-level image data features into the constraint condition fit module, and to determine the constraint condition fit degree between the image feature description information and the multi-level image data features and the preset constraint conditions corresponding to each AI algorithm in the AI ​​algorithm library integrated by the AI ​​algorithm matching agent. The algorithm matching degree determination unit is used by the matching degree calculation module to determine the algorithm matching degree between the medical image data and each AI algorithm in the AI ​​algorithm library based on the constraint condition fit degree, the image feature description information and the multi-level image data features, and to use the algorithm matching degree as the output result of the AI ​​algorithm matching agent; The target AI algorithm determination unit is used to select the AI ​​algorithm with the highest matching degree as the target AI algorithm.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the medical image data analysis method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the medical image data analysis method according to any one of claims 1-5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the medical image data analysis method according to any one of claims 1-5.

Images