Ultrasonic remote diagnosis method and device, computer equipment and storage medium

Abstract

The invention discloses an ultrasonic remote diagnosis method. The method comprises the following steps: S1, acquiring ultrasonic image data of a patient; s2, preprocessing the ultrasonic image data, and extracting key diagnosis information; s3, executing search operation according to the key diagnosis information, and acquiring medical data related to the image; and S4, generating a personalized diagnosis report according to the acquired medical data related to the image. The invention further provides an ultrasonic remote diagnosis device, computer equipment and a storage medium. According to the invention, the ultrasonic diagnosis equipment is combined with the remote medical platform and artificial intelligence, so that the accuracy and efficiency of diagnosis are improved, timely medical services can be provided in an environment in which medical resources are deficient, and the satisfaction of patients and the treatment effect are improved.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic technology, and more specifically, to an ultrasonic remote diagnosis method, device, computer equipment and storage medium. Background Art

[0002] With the development of medical technology and the popularization of the Internet, telemedicine has gradually become an important means to solve the problem of uneven geographical distribution of medical resources. Ultrasound diagnosis, as a non-invasive, convenient and efficient medical imaging technology, is widely used in clinical medicine. However, existing ultrasound diagnosis often relies on on-site operation of equipment and professional technicians, which is a major challenge in remote areas and environments with scarce medical resources. Existing methods lack efficient remote transmission and diagnostic means, resulting in patients being unable to obtain accurate diagnosis and treatment in a timely manner. To this end, it is indeed necessary to develop an ultrasound remote diagnosis method, device, computer equipment and storage medium. Summary of the invention

[0003] The purpose of the present invention is to provide an ultrasonic remote diagnosis method to overcome the defects of the prior art.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] An ultrasonic remote diagnosis method comprises the following steps:

[0006] S1, collecting ultrasound image data of the patient;

[0007] S2, preprocessing the ultrasound image data to extract key diagnostic information;

[0008] S3, performing a search operation according to the key diagnostic information to obtain medical data related to the image;

[0009] S4. Generate a personalized diagnosis report based on the acquired medical data related to the image.

[0010] Furthermore, in step S1, an ultrasonic device is used to collect an ultrasonic image of the patient.

[0011] Furthermore, the step S2 specifically includes:

[0012] The pre-trained BERT model processes the text information in ultrasound image data to identify key pathological features or clinical indicators;

[0013] The training process of the BERT model is as follows: first, a set amount of text data related to the medical field is collected, and the text data includes medical papers and diagnostic reports; then, the text data is preprocessed including word segmentation and stop word removal; the processed text data is then input into the BERT model for training, and the performance of the model is optimized by adjusting the model parameters; finally, the trained BERT model is used to predict and analyze new ultrasound image data to extract key diagnostic information.

[0014] Furthermore, the step S3 specifically includes:

[0015] Use the pre-trained T5 model to perform relevant searches in the built-in medical knowledge base or database to find matching diagnosis cases, the latest research results, or similar disease descriptions.

[0016] The training process of the T5 model is similar to that of the BERT model. It is also trained based on a large amount of text data related to the medical field and preprocesses the text data. The performance of the model is optimized by adjusting the model parameters. The difference is that the T5 model is more effective for a variety of tasks (such as text generation, text classification, etc.).

[0017] Furthermore, the step S4 specifically includes:

[0018] The acquired medical data related to the image is refined to obtain the most helpful information for the current diagnosis, including the patient's medical history, family history, living habits, ultrasound image characteristics and abnormal manifestations, and examination results, such as blood tests, X-rays, etc. Through comprehensive analysis and judgment of this information, a personalized diagnosis report containing comprehensive diagnostic opinions, treatment recommendations and medical information can be obtained.

[0019] A personalized diagnostic report containing comprehensive diagnostic opinions, treatment recommendations and related medical information is generated by combining the information obtained from the medical knowledge base, as well as the patient's complaints and symptoms related to the patient's specific situation, the patient's physical examination results, and the patient's other relevant examination results.

[0020] Furthermore, after step S4, the following steps are further included:

[0021] The personalized diagnostic report is reviewed and modified, and the reviewed and modified personalized diagnostic report is fed back to the patient or on-site medical staff.

[0022] In order to solve the above technical problems, the present application also provides an ultrasonic remote diagnosis device, which adopts the following technical solution:

[0023] An ultrasonic remote diagnosis method and device, comprising:

[0024] An acquisition module, used for acquiring ultrasound image data of a patient;

[0025] An artificial intelligence processing module, used to pre-process the ultrasound image data and extract key diagnostic information;

[0026] A search module, used to perform a search operation based on the key diagnostic information to obtain medical data related to the image;

[0027] A proposal generation module is used to generate a personalized diagnosis report based on the acquired medical data associated with the image.

[0028] Furthermore, it also includes:

[0029] Telemedicine platforms for receiving, storing and managing diagnostic data;

[0030] The doctor diagnosis module is used for remote doctors to view ultrasound image data and personalized diagnosis reports, and to review and modify the personalized diagnosis reports to generate final diagnosis opinions.

[0031] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0032] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the ultrasonic remote diagnosis method as described above when executing the computer-readable instructions.

[0033] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0034] A computer-readable storage medium, characterized in that computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the steps of the ultrasonic remote diagnosis method as described above are implemented.

[0035] Compared with the prior art, the advantages of the present invention are: by combining ultrasonic diagnostic equipment with a telemedicine platform and artificial intelligence, the present invention not only improves the accuracy and efficiency of diagnosis, but also can provide timely medical services in an environment with scarce medical resources, thereby improving patient satisfaction and treatment effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flow chart of the ultrasonic remote diagnosis method of the present invention.

[0038] Figure 2 It is a framework diagram of the ultrasonic remote diagnosis device of the present invention.

[0039] Figure 3 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0040] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more definite definition of the protection scope of the present invention.

[0041] See also Figure 1 As shown, this embodiment discloses an ultrasonic remote diagnosis method, comprising the following steps:

[0042] Step S1: Acquire ultrasonic image data of a patient.

[0043] In this embodiment, after receiving the ultrasound diagnosis request initiated by the user, the ultrasound device collects ultrasound images of the patient and transmits them to the remote server through the network.

[0044] Step S2: preprocess the ultrasound image data to extract key diagnostic information.

[0045] In this embodiment, the data received by the remote server is sent to the artificial intelligence module through the forwarding module to process the image and extract important information. The key artificial intelligence (AI) model is based on the BERT-T5 deep learning framework. The framework combines two powerful deep learning models: BERT (Bidirectional Encoder Representations from Transformers) and T5 (Text-to-Text Transfer Transformer). These two models are respectively excellent in text understanding and generation, and can deeply analyze the descriptive information of medical images and make diagnostic recommendations.

[0046] The BERT model is used to understand the description information of ultrasound images or the annotation information attached to the images. The BERT model is a pre-trained deep learning model that uses a large amount of text data to learn the complex relationships between words, sentences, and contexts. In the remote diagnosis system of this embodiment, the BERT model can be used to understand and parse the descriptions related to ultrasound images and capture key medical indicators and features.

[0047] The training process of the BERT model is as follows: first, a large amount of text data related to the medical field is collected, such as medical papers, diagnostic reports, etc.; then, these text data are preprocessed, including word segmentation, stop word removal, etc.; next, the processed text data is input into the BERT model for training, and the performance of the model is optimized by adjusting the model parameters; finally, the trained BERT model is used to predict and analyze new ultrasound image data to extract key diagnostic information.

[0048] The T5 model is used to generate a personalized diagnosis report based on the information extracted by the BERT model. Specifically, the T5 model unifies different natural language processing tasks into a text-to-text framework and completes the task by converting the input text into the target text. In this embodiment, the extracted information from the BERT model is integrated and used to generate a diagnosis suggestion or report to assist the doctor.

[0049] Step S3: performing a search operation according to the key diagnostic information to obtain medical data related to the image.

[0050] In this embodiment, based on the key information extracted by the BERT model, the T5 model performs a related search in the built-in medical knowledge base or database through a search module to find matching diagnostic cases, the latest research results or similar disease descriptions. This information will serve as the basis for building a personalized diagnostic report to obtain image-related medical information and diagnostic recommendations.

[0051] The training process of the T5 model is similar to that of the BERT model. It is also based on a large amount of medical-related text data for training and preprocessing of the text data. The performance of the model is optimized by adjusting the model parameters. The difference is that the T5 model is more effective for a variety of tasks (such as text generation, text classification, etc.).

[0052] Step S4: Generate a personalized diagnosis report based on the acquired medical data related to the image.

[0053] In this embodiment, after obtaining the relevant medical data returned by the search, the T5 model organizes and analyzes the data to extract the most helpful information for the current diagnosis, such as the patient's medical history, family history, living habits, etc. In addition, there are also characteristics and abnormal manifestations of ultrasound images, and other related examination results, such as blood tests, X-rays, etc. Through comprehensive analysis and judgment of this information, a personalized diagnosis report containing comprehensive diagnostic opinions, treatment recommendations and medical information can be obtained.

[0054] Combining information obtained from the medical knowledge base and information related to the patient's specific situation (obtained through pictures and other descriptions), such as the patient's chief complaint and symptoms, the patient's physical examination results, and the patient's other relevant examination results, the T5 model generates a personalized diagnostic report containing comprehensive diagnostic opinions, treatment recommendations, and related medical information. After the report is generated, the telemedicine platform can provide an interface for remote doctors to review and modify it. Doctors can adjust the report content based on their own experience and expertise to ensure its accuracy and applicability.

[0055] The diagnosis report reviewed and improved by the doctor is then fed back to the on-site operator through the network platform, and finally handed over to the patient or on-site medical staff for review. The personalized diagnosis report is sent to the remote doctor, who generates the final diagnosis opinion based on his or her own professional knowledge and returns it to the on-site operator through the network.

[0056] By combining ultrasonic diagnostic equipment with a telemedicine platform and artificial intelligence, the present invention not only improves the accuracy and efficiency of diagnosis, but also can provide timely medical services in an environment with scarce medical resources, thereby improving patient satisfaction and treatment effects.

[0057] See also Figure 2 As shown, in order to solve the above technical problems, the embodiment of the present application also provides an ultrasonic remote diagnosis device, which adopts the following technical solution:

[0058] An ultrasonic remote diagnosis device includes: an acquisition module for acquiring ultrasonic image data of a patient, and this embodiment adopts an ultrasonic diagnostic equipment module as the acquisition module for acquisition; an artificial intelligence processing module for preprocessing the ultrasonic image data and extracting key diagnostic information, and a network communication module is used for communication between the artificial intelligence processing module and the ultrasonic diagnostic equipment module; a search module for performing a search operation based on the key diagnostic information and acquiring medical data related to the image; and a suggestion generation module for generating a personalized diagnosis report based on the acquired medical data related to the image.

[0059] The ultrasonic remote diagnosis device also includes: a remote medical platform for receiving, storing and managing diagnostic data; a doctor diagnosis module for remote doctors to view ultrasonic image data and personalized diagnostic reports, and to review and modify the personalized diagnostic reports to generate a final diagnosis opinion.

[0060] By combining ultrasonic diagnostic equipment with a telemedicine platform and artificial intelligence, the present invention not only improves the accuracy and efficiency of diagnosis, but also can provide timely medical services in an environment with scarce medical resources, thereby improving patient satisfaction and treatment effects.

[0061] To solve the above technical problems, the present application also provides a computer device. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0062] The computer device 3 includes a memory 31, a processor 32, and a network interface 33 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 3 with components 31-33, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0063] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0064] The memory 31 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 31 can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 31 can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 7. Of course, the memory 31 can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 31 is generally used to store the operating system and various application software installed on the computer device 7, such as computer-readable instructions of the ultrasonic remote diagnosis method, etc. In addition, the memory 31 can also be used to temporarily store various types of data that have been output or are to be output.

[0065] The processor 32 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 32 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 32 is used to run computer-readable instructions stored in the memory 31 or process data, such as computer-readable instructions for running the ultrasonic remote diagnosis method.

[0066] The network interface 33 may include a wireless network interface or a wired network interface. The network interface 33 is generally used to establish a communication connection between the computer device 3 and other electronic devices.

[0067] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the ultrasonic remote diagnosis method as described above.

[0068] By combining ultrasonic diagnostic equipment with a telemedicine platform and artificial intelligence, the present invention not only improves the accuracy and efficiency of diagnosis, but also can provide timely medical services in an environment with scarce medical resources, thereby improving patient satisfaction and treatment effects.

[0069] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, the patent owner may make various variations or modifications within the scope of the appended claims. As long as they do not exceed the protection scope described in the claims of the present invention, they should be within the protection scope of the present invention.

Claims

1. An ultrasonic remote diagnosis method, characterized in that: The following steps are involved: S1. Collecting ultrasound image data of the patient; S2, preprocessing the ultrasound image data to extract key diagnostic information; S3, performing a search operation according to the key diagnostic information to obtain medical data related to the image; S4. Generate a personalized diagnosis report based on the acquired medical data related to the image.

2. The ultrasonic remote diagnosis method according to claim 1, characterized in that: In step S1, an ultrasonic device is used to collect an ultrasonic image of the patient.

3. The ultrasonic remote diagnosis method according to claim 1, characterized in that: The step S2 specifically includes: The pre-trained BERT model is used to process text information in ultrasound image data to identify key pathological features or clinical indicators. The training process of the BERT model is as follows: first, a set amount of text data related to the medical field is collected, and the text data includes medical papers and diagnostic reports; then, the text data is preprocessed including word segmentation and stop word removal; the processed text data is then input into the BERT model for training, and the performance of the model is optimized by adjusting the model parameters; finally, the trained BERT model is used to predict and analyze new ultrasound image data to extract key diagnostic information.

4. The ultrasonic remote diagnosis method according to claim 1, characterized in that: The step S3 specifically includes: Use the pre-trained T5 model to perform relevant searches in the built-in medical knowledge base or database to find matching diagnosis cases, the latest research results, or similar disease descriptions.

5. The ultrasonic remote diagnosis method according to claim 1, characterized in that: The step S4 specifically includes:. Extract the acquired medical data related to the image to obtain the most helpful information for the current diagnosis, including the patient's medical history, family history, lifestyle, characteristics and abnormal manifestations of ultrasound images, and examination results; A personalized diagnostic report containing comprehensive diagnostic opinions, treatment recommendations and related medical information is generated by combining the information obtained from the medical knowledge base, as well as the patient's complaints and symptoms related to the patient's specific situation, the patient's physical examination results, and the patient's other relevant examination results.

6. The ultrasonic remote diagnosis method according to claim 1, characterized in that: After step S4, the following steps are also included: The personalized diagnostic report is reviewed and modified, and the reviewed and modified personalized diagnostic report is fed back to the patient or on-site medical staff.

7. A device for implementing the ultrasonic remote diagnosis method according to any one of claims 1 to 6, characterized in that: include: An acquisition module, used for acquiring ultrasound image data of a patient; An artificial intelligence processing module, used to pre-process the ultrasound image data and extract key diagnostic information; A search module, used to perform a search operation based on the key diagnostic information to obtain medical data related to the image; A proposal generation module is used to generate a personalized diagnosis report based on the acquired medical data associated with the image.

8. The device according to claim 7, characterized in that Also includes: Telemedicine platforms for receiving, storing and managing diagnostic data; The doctor diagnosis module is used for remote doctors to view ultrasound image data and personalized diagnosis reports, and to review and modify the personalized diagnosis reports to generate final diagnosis opinions.

9. A computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the ultrasonic remote diagnosis method according to any one of claims 1 to 6 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the ultrasonic remote diagnosis method according to any one of claims 1 to 6 are implemented.

Images