Medical diagnosis system and method based on AI application store

Abstract

The invention is suitable for the technical field of medical treatment, and provides a medical diagnosis system and method based on an AI application store. The system comprises at least one medical device and an AI application store, wherein the medical device is in communication connection with the AI application store; the medical equipment is provided with an AI application store connection port, and the AI application store connection port is used for sending an AI module downloading instruction received by the medical equipment to an AI application store; the AI application store is provided with an AI module, and the AI module comprises at least one diagnosis module and at least one algorithm module; the diagnosis module is used for automatic diagnosis of medical equipment, and the algorithm module is used for optimizing the diagnosis performance of the diagnosis module; the AI application store sends the corresponding AI module to the medical equipment based on the received AI module downloading instruction; the medical device performs automatic diagnosis based on its received AI module. By adopting the system, the AI module can be flexibly selected or replaced according to actual requirements, so that the flexibility and the accuracy of medical equipment diagnosis are improved.

Description

Technical Field

[0001] This application belongs to the field of medical technology, and in particular relates to a medical diagnosis system and method based on an AI application store. Background Art

[0002] With the continuous development of medical technology, artificial intelligence (AI) is increasingly being used in the medical field. It holds great potential, particularly in medical diagnosis, assisting doctors in diagnosing diseases and improving diagnostic accuracy and efficiency. In existing medical diagnostic technologies, AI-assisted diagnosis applications typically exist in two forms: integrating diagnostic modules directly into medical imaging systems, or connecting to independent workstations equipped with diagnostic modules to analyze patient data and output results. However, existing technologies present the following challenges: First, the deployment of existing AI applications in medical systems is limited, preventing users from flexibly selecting or switching AI applications based on their actual diagnostic needs. Second, the effectiveness of AI applications lacks timely feedback, optimization, and updates, leading to low physician adoption. Furthermore, existing automated analysis results are often generated based on general models that may not meet the personalized diagnostic needs of experienced physicians and lack the ability to customize them to specific physician habits or case types. These challenges limit the effectiveness and rapid adoption of AI technology in the medical diagnosis field. Summary of the Invention

[0003] The embodiments of the present application provide a medical diagnosis system and method based on an AI application store to solve the above technical problems.

[0004] In a first aspect, an embodiment of the present application provides a medical diagnosis system based on an AI application store, the system comprising: at least one medical device and an AI application store, the medical device being communicatively connected to the AI application store; the medical device being deployed with an AI application store connection port, the AI application store connection port being used to send an AI module download instruction received by the medical device to the AI application store; the AI application store being provided with an AI module, the AI module comprising at least one diagnostic module and at least one algorithm module; the diagnostic module being used for automatic diagnosis of the medical device, the algorithm module being used to optimize the diagnostic performance of the diagnostic module; the AI application store sending the corresponding AI module to the medical device based on the received AI module download instruction; the medical device performing automatic diagnosis based on the received AI module.

[0005] In a second aspect, an embodiment of the present application provides a medical diagnosis method based on an AI application store, which is applied to medical equipment, the method comprising: receiving a selection of an AI application store connection port on the medical equipment; based on the selection, sending a corresponding AI module download instruction to the AI application store; receiving an AI module corresponding to the AI module download instruction issued by the AI application store, wherein the AI module download instruction includes a diagnosis module download instruction and an algorithm module download instruction; the AI module includes at least one diagnosis module and at least one algorithm module, the diagnosis module is used for automatic diagnosis of the medical equipment, and the algorithm module is used to optimize the diagnostic performance of the diagnosis module; and performing automatic diagnosis based on the AI module.

[0006] In a third aspect, an embodiment of the present application provides an AI application store for medical devices, wherein the AI application store is provided with an AI module, wherein the AI module includes at least one diagnostic module and at least one algorithm module, wherein the diagnostic module is used for automatic diagnosis of the medical device, and the algorithm module is used for optimizing the diagnostic performance of the diagnostic module; the application store is communicatively connected with the medical device, and is used to receive an AI module download request instruction sent by the medical device, and to issue a corresponding AI module to the medical device.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the medical diagnostic method as described in the second aspect above is implemented.

[0008] The above-mentioned medical diagnosis system and method based on the AI application store provide a variety of diagnostic modules and algorithm modules in the form of an AI application store, allowing users to flexibly select or replace AI modules for medical equipment according to actual needs, overcoming the problem of limited deployment methods of existing AI applications in medical systems, so as to improve the flexibility and accuracy of medical equipment diagnosis; at the same time, it supports self-service training and uploading of AI models, which can better meet the personalized needs of experienced doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 is a schematic diagram of a medical diagnosis system based on an AI application store in one embodiment;

[0011] Figure 2 A flowchart of how to train a preset AI model for the AI model training module;

[0012] Figure 3 1 is a flow chart of a medical diagnosis method based on an AI application store in one embodiment;

[0013] Figure 4 A schematic diagram of an AI application store applied to medical devices in one embodiment;

[0014] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0015] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0016] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0017] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0018] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0019] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0020] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0021] See also Figure 1 , Figure 1 FIG. 1 is a schematic diagram of a medical diagnosis system based on an AI application store in one embodiment. Figure 1 As shown, the present application provides a medical diagnostic system 100 based on an AI application store, including at least one medical device 110 and an AI application store 120, which are communicatively connected to each other. The medical device 110 may include, but is not limited to, ultrasound equipment, X-ray equipment, CT equipment, MRI equipment, endoscope equipment, and other medical diagnostic equipment. The AI application store 120 may be set on a server, which may be an independent server or a server cluster composed of multiple servers. The medical device 110 has hardware components such as a processor, memory, display screen, and communication module, and is capable of running various medical applications and communicating with external devices (such as cloud servers).

[0022] In this embodiment, the medical device 110 is deployed with an AI application store connection port 111, which is used to send the AI module download instruction received by the medical device 110 to the AI application store 120; the AI application store 120 is provided with an AI module, and the AI modules in the AI application store include at least one diagnostic module and at least one algorithm module, wherein the diagnostic module is used for automatic diagnosis of the medical device, and the algorithm module is used to optimize the diagnostic performance of the diagnostic module; the AI application store 120 sends the corresponding AI module to the medical device 110 based on the received AI module download instruction; the medical device 110 performs automatic diagnosis based on the received AI module.

[0023] In this embodiment, the at least one medical device 110 may include multiple different types of medical devices, such as ultrasound devices, CT devices, MR devices, endoscope devices, etc., and may also include multiple devices of the same type, such as multiple ultrasound devices.

[0024] In this embodiment, the AI application store connection port 111 deployed on the medical device can be a software interface, specifically a graphical user interface, through which users can access the AI application store 120 and download the required AI modules. The AI application store connection port 111 can be integrated into the medical device's operating system or installed as a standalone application on the medical device. Through the AI application store connection port 111, users can browse the list of AI modules in the AI application store, view detailed information about AI modules, and send AI module download instructions. In this embodiment, AI module download instructions include diagnostic module download instructions and / or algorithm module download instructions. When the medical device 110 receives the AI module download instruction from the user via the AI application store connection port 111, it sends the download instruction to the AI application store 120. Upon receiving the download instruction, the AI application store 120 identifies the AI module the user wishes to download based on the instruction content and sends the corresponding AI module to the medical device 110. Upon receiving the AI module, the medical device 110 installs it in local storage and can start it when needed. This embodiment may further include: if the medical device 110 has downloaded the diagnosis module locally in advance, only one or more algorithm modules corresponding to the diagnosis module may be downloaded and installed locally as needed.

[0025] In this embodiment, the AI application store 120 can be a platform for centralized storage and distribution of medical AI modules, which can be set up on a cloud server. The AI application store 120 establishes a communication connection with the medical device 110 via a network (such as the Internet) 130, enabling the medical device 110 to access and download various medical AI modules. The AI application store 120 stores various types of medical AI modules, including at least one diagnostic module and at least one algorithm module. The diagnostic module is a medical diagnostic application developed based on artificial intelligence technology that can assist doctors in diagnosis. The diagnostic module includes at least one of an automatic scanning application, a lesion analysis application, and an automatic measurement application; the automatic scanning application can automatically configure and adjust the acquisition parameters of the medical device, and perform intelligent analysis and processing based on the collected medical data to output diagnostic results; the lesion analysis application can automatically identify lesions, analyze characteristics, and output diagnostic results; the automatic measurement application can automatically measure the anatomical structure of the data collected by the medical device. Specifically, it may include a fully automatic scanning APP, a thyroid lesion diagnosis APP, and a breast lesion diagnosis APP. The algorithm module is an auxiliary tool for optimizing the performance of the diagnostic module, including AI models. By loading the AI model into the diagnostic module, the diagnostic performance of the diagnostic module can be optimized. Specifically: users can load one or more AI models in the diagnostic module according to usage needs, for example, load more than 2 AI models to meet inspection needs. AI models include deep learning models or neural network models, specifically including: classification models, segmentation models, detection models and natural language processing (NLP) models, etc. Among them, classification network models are often used for ultrasound image section recognition, lesion trait typing, etc., and can also be used for section quality evaluation. Segmentation network models are often used for automatic measurement, lesion localization, etc., detection network models are often used for section quality evaluation, and NLP models are often used to generate reports, etc. Users can flexibly choose diagnostic modules and algorithm modules according to their needs.

[0026] In this embodiment, the AI application store supports users uploading AI modules as required and allows users to evaluate and rate downloaded and used AI modules. Before downloading an AI module through the AI application store connection port, users can browse detailed information about the AI module in the AI application store through the connection port, including evaluation, rating, user name, hospital, etc.

[0027] In this embodiment, the algorithm module may also include an AI model training module, and the AI module download instruction may also include an AI model training module download instruction. The AI model training module is a software tool specifically used to train AI models, providing functions such as data preprocessing, model building, parameter optimization, and performance evaluation. At the same time, it supports the import of existing models and the export of models after training is completed; the AI application store 120 sends the AI model training module to the medical device 110 based on the received AI model training module download instruction, and the medical device 110 performs medical examinations based on the AI model training module, stores the operation data of the medical examination, and trains a preset AI model based on the operation data, wherein the preset AI model is the AI model that the user wants to train, including a deep learning model or a neural network model, such as a classification model, a segmentation model, a detection model, and an NLP model.

[0028] The specific process of training the preset AI model is explained using ultrasound examination as an example. Figure 2 , Figure 2 A flowchart of how to train a preset AI model for the AI model training module. Figure 2As shown, the process of training the preset AI model in the AI model training module specifically includes: the user of the medical device first starts the AI model training program, and the user can configure the scanning assistant. The scanning assistant mainly reminds the user to scan according to the process so that the background can extract data for training according to a fixed format. Before starting the scanning assistant, the patient information can be created first, so that the examination data can be associated with the patient information; after starting the scanning assistant, the scanning mode (B mode) is entered, the user enters the scanning parameters, the ultrasound probe starts scanning and obtains the scanning section, the user confirms the standard section from the scanning section, the scanning assistant can further remind the user to measure and annotate the standard section, and the image is saved after the above process is completed. The process can also include: entering the next scanning mode (C mode or PW mode), the user enters the scanning parameters, the ultrasound probe starts scanning and obtains the scanning section, the user confirms the standard section from the scanning section, the scanning assistant can further remind the user to measure and annotate the standard section, and the image is saved after the above process is completed. During this process, the user's operational data is stored on the medical device. This operational data includes scanning parameters, section types, key measurement point locations, measurement contours, and annotation data. After storing the operational data, the user can select a preset AI model already in the program in the AI model training module, or load another preset AI model into the AI model training module, and then train the preset AI model based on the stored operational data. Alternatively, the user can directly input the stored operational data into the preset AI model for training without loading the preset AI model into the AI model training module. Model training can be completed when the ultrasound device is idle. The process of evaluating the scanned sections and determining the standard sections may include: counting the sections within a preset time as the current section type, such as the sections within 1 second before the image is saved or the sections within 3 seconds before the image is saved, binding each frame of data within the preset time to the section category, and determining the current section type by the user. The user can evaluate the quality of the section, and the section with the highest score is the standard section; the existing network model can also be used to assist in scoring the current image to determine the section type to which it belongs, for example, marking the standard section determined by the user with the highest score, and using the classification network model to gradually reduce the score of the section in the video sequence that is far away from the standard section.

[0029] The medical device 110 is also used to store the trained preset AI model; and / or, receive an AI model upload instruction and upload the trained preset AI model to the algorithm module of the AI application store. Specifically, after the training is completed, the trained AI model can be saved locally on the medical device for use in the next examination, or an AI model upload instruction can be sent to the medical device 110 to upload the trained preset AI model to the AI application store 120, specifically to the algorithm module. The AI application store 120 can test the uploaded AI model. The test process needs to determine the judgment criteria based on the model category. For example, the classification model needs to judge the classification accuracy, and the segmentation model needs to judge the intersection over union (IoU) and other evaluation indicators to ensure that the accuracy meets the requirements before uploading to the algorithm module.

[0030] Through the above system, users can selectively download diagnostic modules and AI models from the AI application store to medical devices according to actual needs to achieve automatic diagnosis functions. You can also download the AI model training module from the AI application store to perform localized training on the preset AI model to improve the performance of the AI model in specific scenarios and train an AI model that suits you. For example, breast lesion analysis relies more on the clinical guideline BI-RADS grading. Each hospital and region may have subtle differences in the use of BI-RADS grading. It is difficult to use a unified model to adapt to all situations. At this time, doctors can use the AI model training module in this application to train a model suitable for the hospital. Due to the strong autonomy of model training, it can stimulate leading hospitals and institutions to participate in the training of preset AI models. There are many high-level and experienced doctors in leading hospitals and institutions, and more high-precision AI models can be trained. After uploading to the AI application store, hospitals with poor medical standards can download the model based on the AI application store, which can guide doctors to scan. For example, a doctor at a top hospital might use a downloaded AI model training module to analyze a lesion based on the latest guidelines. This model, trained based on the operational data from the analysis, is then uploaded to the AI app store. Local hospitals can then download the model through the AI app store connection port and apply it to routine diagnosis. Using this model, they can learn from the latest guidelines to improve diagnostic accuracy. Through the training and uploading of pre-set models, a continuously evolving and improving medical AI ecosystem is formed.

[0031] In one embodiment, see Figure 3 , Figure 3 FIG. 1 is a flow chart of a medical diagnosis method based on an AI application store in one embodiment. Figure 3 As shown, a medical diagnosis method based on an AI application store, applied to a medical device, may include the following steps:

[0032] S102: Receive a selection of an AI application store connection port on a medical device.

[0033] Among them, the AI application store connection port on the medical device can provide the functions of browsing, searching, downloading and managing applications. The AI application store connection port may include a graphical user interface, and users can interact with it through input devices such as a touch screen, mouse or keyboard to perform selection operations.

[0034] Specifically, a graphical user interface (GUI) of the AI application store is displayed on the medical device. The GUI includes icons of different categories of AI modules, such as lesion diagnosis icons and automatic measurement icons. Users can click on AI module icons to select them. The GUI also displays detailed information corresponding to the AI module icons, including function descriptions, version numbers, developer information, and user reviews.

[0035] Specifically, the medical device may be an ultrasonic medical device.

[0036] S104: Based on the selection, a corresponding AI module download instruction is sent to the AI application store.

[0037] Specifically, the medical device will generate an AI module download instruction based on the user's selection and send the instruction to the AI application store via the network. The AI application store can be set up on a cloud server. The AI module download instruction may include the unique identifier of the AI module, version number, identification information of the medical device, etc.

[0038] Furthermore, upon receiving the download instruction, the AI App Store verifies the identity and permissions of the medical device to confirm whether the device is authorized to download the requested AI module. Once verified, the AI App Store packages the corresponding AI module and sends it to the medical device. The transmission of the AI module can utilize an encrypted communication protocol to ensure data security and integrity.

[0039] S106, receiving an AI module corresponding to an AI module download instruction issued by an AI application store, wherein the AI module download instruction includes a diagnosis module download instruction and an algorithm module download instruction, and the AI module includes at least one diagnosis module and at least one algorithm module. The diagnosis module is used for automatic diagnosis of medical equipment, and the algorithm module is used for optimizing the diagnostic performance of the diagnosis module.

[0040] Specifically, the diagnosis module includes at least one of an automatic scanning application, a lesion analysis application, and an automatic measurement application; the algorithm module includes an AI model.

[0041] S108, performing automatic diagnosis based on the AI module.

[0042] Specifically, the AI module controls medical equipment to collect data or processes already collected data. For example, a fully automated scanning program controls medical equipment to scan according to preset parameters and paths, collecting a series of medical images. However, the lesion localization performance is poor. When paired with a better-performing segmentation network model, the diagnostic results are improved. A lesion diagnosis program processes ultrasound, CT, or MRI images to identify and label suspicious lesions, but the lesion trait classification is poor. When paired with a better-performing classification network model, the diagnostic results are improved.

[0043] The above-mentioned medical diagnostic method can flexibly select or replace AI modules according to actual needs, overcoming the problem of limited deployment methods of existing AI applications in medical systems.

[0044] Based on and before step S108, this embodiment further includes:

[0045] S107, starting a diagnosis module on the medical device and loading an algorithm module into the diagnosis module, wherein the algorithm module includes an AI model.

[0046] Specifically, after receiving the AI module, the medical device automatically installs it. The user can click to launch the diagnostic module. After the diagnostic module launches, an interface will be displayed. The user can load at least one algorithm module into the diagnostic module as needed. The algorithm module includes an AI model. If the downloaded AI model is ineffective when applied, a new AI model can be downloaded and reloaded. Alternatively, based on the diagnostic mode selected on the diagnostic module display interface, the diagnostic module automatically checks available algorithm modules and prompts the user to select the AI model to load. It may also recommend an AI model based on the usage habits of most users. After the user selects an appropriate AI model, the diagnostic module loads the model into memory and initializes the model parameters. After loading is complete, the diagnostic module enters a ready state, waiting for the user to begin diagnostic operations. The AI model is the core component of the diagnostic module and determines the diagnostic capabilities and performance of the application. Different AI models are suitable for different diagnostic tasks and medical scenarios. For example, some AI models are specifically designed for tumor detection in breast ultrasound images, some for nodule identification in lung CT images, and some for functional analysis of cardiac ultrasound images. This method provides users with more options and greater flexibility.

[0047] This embodiment also includes: the results obtained by automatic diagnosis based on the AI module are presented in a visual manner on the display screen of the medical device, including marking abnormal areas in the image, displaying quantitative indicators, generating a diagnostic report, etc.

[0048] The AI module download instruction in this embodiment also includes an AI model training module download instruction. The AI module includes an AI model training module. The method also includes receiving the AI model training module issued by the AI application store, training the preset AI model based on the AI model training module, and saving the trained preset AI model or sending the trained preset AI model to the AI application store.

[0049] The AI model training module enables medical professionals to train or fine-tune AI models using local data without having to delve into the technical details of machine learning. Users can use the program to specify training data samples, select a preset AI model, and set training parameters.

[0050] The data samples used to train the pre-set AI model can come from historical operational data from medical examinations performed by medical devices using the AI model training module. These data samples typically include scan parameters, section types, key measurement point locations, and annotation data. The AI model training module preprocesses the data samples, including image normalization, data augmentation, and feature extraction, to improve training effectiveness.

[0051] During training, the AI model training module displays metrics such as training progress, loss function curves, and accuracy, allowing users to monitor training results in real time. After training is complete, the program evaluates model performance and generates a performance report, including metrics such as accuracy, sensitivity, and specificity.

[0052] If the user is satisfied with the training results, they can choose to upload the trained AI model to the app store. Before uploading, the AI model training module will package and encrypt the model to ensure its security and integrity. During the upload process, the user needs to provide a description of the model, including applicable scenarios, performance indicators, and training data characteristics, so that other users can understand and select it.

[0053] After receiving the uploaded AI model, the App Store will review and verify it to ensure that the model meets quality and safety standards. Once the review is passed, the model will be added to the App Store's algorithm module for download and use by other medical devices.

[0054] Through this approach, medical devices can easily access and use various diagnostic and algorithm modules to achieve automated diagnosis. Furthermore, medical professionals can use the AI model training module to locally train AI models and share the optimized models with other users, promoting the development and application of medical AI technology.

[0055] It should be understood that although Figure 3The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 3 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0056] In one embodiment, see Figure 4 , Figure 4 FIG. 1 is a schematic diagram of an AI application store for medical devices in one embodiment. Figure 4 As shown, the AI application store includes a diagnosis module and an algorithm module. The diagnosis module is used for automatic diagnosis of medical equipment, and the algorithm module is used to optimize the diagnostic performance of the diagnosis module. The AI application store is connected to the medical equipment for communication, and is used to receive the AI module download request instruction sent by the medical equipment and send the corresponding AI module to the medical equipment.

[0057] Among them, the diagnosis module includes at least one of an automatic scanning application, a lesion analysis application, and an automatic measurement application; the algorithm module includes an algorithm module, and the AI model in the algorithm module can be loaded into the diagnosis module to optimize the automatic diagnosis of the diagnosis module.

[0058] Furthermore, the algorithm module also includes an AI model training module, which is used by medical equipment to perform medical examinations and train a preset AI model based on the operational data of the medical examinations; the medical equipment can upload the trained preset AI model to the application store, and the application store can receive the upload of the preset AI model.

[0059] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory (such as an internal memory), a communication interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies; when the computer program is executed by the processor, a medical diagnosis method based on an AI application store is implemented. The display screen of the computer device can be a liquid crystal display or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0060] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0061] Receive a selection of an AI application store connection port on a medical device;

[0062] Based on the selection, send the corresponding AI module download instruction to the AI application store;

[0063] Receiving an AI module corresponding to an AI module download instruction issued by an AI application store, wherein the AI module download instruction includes a diagnostic module download instruction and an algorithm module download instruction, and the AI module includes at least one diagnostic module and at least one algorithm module, the diagnostic module is used for automatic diagnosis of medical equipment, and the algorithm module is used for optimizing diagnostic performance of the diagnostic module;

[0064] Automatic diagnosis based on AI module.

[0065] The implementation principles and technical effects of each step implemented by the processor in this embodiment are the same as those of the above-mentioned medical diagnosis method based on the AI application store, and will not be repeated here.

[0066] Those skilled in the art will understand that Figure 5 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.

[0067] 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 following steps are implemented:

[0068] Receive a selection of an AI application store connection port on a medical device;

[0069] Based on the selection, send the corresponding AI module download instruction to the AI application store;

[0070] Receiving an AI module corresponding to an AI module download instruction issued by an AI application store, wherein the AI module download instruction includes a diagnostic module download instruction and an algorithm module download instruction, and the AI module includes at least one diagnostic module and at least one algorithm module, the diagnostic module is used for automatic diagnosis of medical equipment, and the algorithm module is used for optimizing diagnostic performance of the diagnostic module;

[0071] Starting a diagnostic module on the medical device and loading an algorithm module into the diagnostic module, wherein the algorithm module includes an AI model;

[0072] Automatic diagnosis based on AI module.

[0073] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0074] The algorithm module download instruction includes the AI model training module download instruction. The algorithm module includes the AI model training module. The medical device trains the preset AI model based on the received AI model training module, and saves the trained preset AI model or sends the trained preset AI model to the AI application store.

[0075] The implementation principles and technical effects of the steps implemented when the computer program in this embodiment is executed by the processor are the same as those of the above-mentioned medical diagnosis method based on the AI application store, and will not be repeated here.

[0076] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods 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, storage, 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 or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0077] 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.

[0078] The above-described embodiments merely represent 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 could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A medical diagnosis system based on AI application store, characterized in that: The system includes: at least one medical device and an AI application store, wherein the medical device is communicatively connected to the AI application store; The medical device is deployed with an AI application store connection port, and the AI application store connection port is used to send the AI module download instruction received by the medical device to the AI application store; The AI application store is provided with an AI module, which includes at least one diagnostic module and at least one algorithm module. The diagnostic module is used for the medical device to perform automatic diagnosis, and the algorithm module is used to optimize the diagnostic performance of the diagnostic module. The AI application store sends the corresponding AI module to the medical device based on the received AI module download instruction. The medical device performs automatic diagnosis based on the received AI module.

2. The system according to claim 1, wherein At least one of the diagnostic modules includes at least one of an automatic scanning application, a lesion analysis application, and an automatic measurement application; at least one of the algorithm modules includes at least one AI model, and the AI model includes a deep learning model or a neural network model.

3. The system according to claim 1, wherein: The AI module also includes an AI model training module, and the AI module download instruction includes an AI model training module download instruction; the AI application store sends the AI model training module to the medical device based on the received AI model training module download instruction; the medical device performs a medical examination based on the AI model training module, stores the operation data of the medical examination, and trains a preset AI model based on the operation data.

4. The system according to claim 3, wherein: The medical device is also used to store the trained preset AI model; and / or receive an AI model upload instruction to upload the trained preset AI model to the algorithm module of the AI application store.

5. The system according to claim 1, wherein: The AI module download instruction includes a diagnosis module download instruction and / or an algorithm module download instruction.

6. The system according to any one of claims 1 to 5, characterized in that The AI application store is set on the cloud server.

7. A medical diagnosis method based on an AI application store, applied to medical equipment, characterized in that: include: receiving a selection of an AI application store connection port on the medical device; Based on the selection, a corresponding AI module download instruction is sent to the AI application store; receiving an AI module corresponding to the AI module download instruction issued by the AI application store, wherein the AI module download instruction includes a diagnostic module download instruction and an algorithm module download instruction; the AI module includes at least one diagnostic module and at least one algorithm module, the diagnostic module is used to automatically diagnose the medical device, and the algorithm module is used to optimize the diagnostic performance of the diagnostic module; Automatic diagnosis is performed based on the AI module.

8. The method according to claim 7, wherein Before performing automatic diagnosis based on the AI module, the method further includes: starting the diagnosis module on the medical device and loading the algorithm module into the diagnosis module.

9. The method according to claim 7, wherein: The AI module download instruction further includes an AI model training module download instruction, the AI module further includes an AI model training module, and the method further includes: Receive the AI model training module issued by the AI application store, train the preset AI model based on the AI model training module, and save the trained preset AI model or send the trained preset AI model to the AI application store.

10. The method according to claim 7, wherein The medical device is an ultrasonic medical device.

11. An AI application store for medical devices, characterized in that: The AI application store is provided with an AI module, which includes at least one diagnostic module and at least one algorithm module, wherein the diagnostic module is used for automatically diagnosing the medical device, and the algorithm module is used for optimizing the diagnostic performance of the diagnostic module; The application store is in communication with the medical device, and is configured to receive an AI module download request instruction sent by the medical device, and to send the corresponding AI module to the medical device.

12. The application store according to claim 11, wherein: At least one of the diagnostic modules includes at least one of an automatic scanning application, a lesion analysis application, and an automatic measurement application; and at least one of the algorithm modules includes at least one AI model.

13. The application store according to claim 11, wherein: The AI module further includes an AI model training module, which is used by the medical device to perform medical examinations and train a preset AI model based on the operation data of the medical examinations; The application store may receive an upload of the preset AI model.

14. A computer-readable storage medium storing 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 7 to 10 are implemented.

Images