An operation prompt method and system for an intelligent B-ultrasound detector

Abstract

The present invention discloses an operation prompt method and system for an intelligent B-ultrasound detector, the method comprising: obtaining a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient; analyzing the B-ultrasound image to determine whether the B-ultrasound image meets the preset image standard for diagnosing a target disease; if it meets the preset image standard, outputting a diagnosis result for the target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning; sending a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for a second or multiple detections according to the prompt message to verify the diagnosis result. By using the embodiments of the present invention, it is possible to analyze B-ultrasound images in real time, automatically determine image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasonic examinations and reducing the workload of medical staff.

Description

Technical Field

[0001] The invention belongs to the field of medical technology, and in particular to an operation prompting method and system for an intelligent B-ultrasound detector. Background Art

[0002] In modern medical diagnosis, ultrasound examination (B-ultrasound) is a non-invasive, radiation-free imaging method that is widely used for early screening and diagnosis of various diseases. In particular, in the fields of cardiovascular disease, tumors, pregnancy monitoring, and deep vein thrombosis (DVT) of the lower extremities, B-ultrasound examination is highly favored due to its accuracy and safety. However, the effectiveness of B-ultrasound examination depends largely on the experience and technical level of the operator, which may cause some beginners or inexperienced medical staff to make mistakes during the operation, resulting in deviations in the diagnostic results. Summary of the invention

[0003] The purpose of the present invention is to provide an operation prompt method and system for an intelligent B-ultrasound detector to solve the deficiencies in the prior art, which can analyze B-ultrasound images in real time, automatically judge image quality, provide operation suggestions and generate diagnosis results, improve the accuracy and efficiency of ultrasonic examination, and reduce the workload of medical staff.

[0004] An embodiment of the present application provides an operation prompt method of an intelligent B-ultrasound detector, the method comprising:

[0005] Acquire the B-ultrasound image obtained by the medical staff using the B-ultrasound detector to detect the target part of the patient;

[0006] Analyzing the B-ultrasound image to determine whether the B-ultrasound image meets the preset imaging standard for diagnosing the target disease;

[0007] If the preset imaging criteria are met, a diagnostic result for the target disease is outputted based on the B-ultrasound image using a pre-trained target disease diagnostic model based on machine learning;

[0008] A prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform secondary or multiple detections according to the prompt message to verify the diagnosis result.

[0009] Optionally, the method further includes:

[0010] If the preset image standard is not met, a prompt message indicating that the operation is not in compliance is sent to the medical staff operating the B-ultrasound detector, so that the medical staff can operate the B-ultrasound detector to re-detect the target part of the patient, and return to the step of obtaining the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient.

[0011] Optionally, the diagnosis result includes at least: whether the patient suffers from the target disease, the location of the disease and the severity of the disease.

[0012] Optionally, the method further comprises: acquiring biochemical examination data of the patient related to the target disease, and calculating the patient's disease risk index related to the target disease based on the biochemical examination data;

[0013] The method of outputting a diagnosis result for a target disease based on the B-ultrasound image and using a pre-trained target disease diagnosis model based on machine learning includes:

[0014] According to the B-ultrasound image, the biochemical examination data and the disease risk index, a pre-trained target disease diagnosis model based on machine learning is used to output a diagnosis result for the target disease.

[0015] Another embodiment of the present application provides an operation prompt system of an intelligent B-ultrasound detector, the system comprising:

[0016] An acquisition module is used to acquire a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient;

[0017] An analysis module, used to analyze the B-ultrasound image to determine whether the B-ultrasound image meets the preset image standard for diagnosing the target disease;

[0018] An output module is used to output a diagnosis result for a target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning if the preset image standard is met;

[0019] The prompt module is used to send a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

[0020] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0021] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0022] Compared with the prior art, the present invention provides an operation prompt method for an intelligent B-ultrasound detector, which obtains a B-ultrasound image obtained by a medical staff operating the B-ultrasound detector to detect a target part of a patient; analyzes the B-ultrasound image to determine whether the B-ultrasound image meets a preset image standard for diagnosing a target disease; if it meets the preset image standard, outputs a diagnosis result for the target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning; sends a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for a second or multiple detections according to the prompt message to verify the diagnosis result, thereby being able to analyze the B-ultrasound image in real time, automatically determine the image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasonic examinations and reducing the workload of medical staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A hardware structure block diagram of a computer terminal for an operation prompt method of an intelligent B-ultrasound detector provided by an embodiment of the present invention;

[0024] Figure 2 A schematic diagram of a flow chart of an operation prompt method of an intelligent B-ultrasound detector provided by an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of the structure of an operation prompt system of an intelligent B-ultrasound detector provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0027] The embodiment of the present invention firstly provides an operation prompt method of an intelligent B-ultrasound detector, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0028] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of an operation prompt method of an intelligent B-ultrasound detector provided by an embodiment of the present invention. Figure 1 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0029] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any operation prompt method of the intelligent B-ultrasound detector.

[0030] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0031] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any operation prompt method of the intelligent B-ultrasound detector.

[0032] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 1 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0033] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0034] See also Figure 2 The embodiment of the present invention provides an operation prompt method of an intelligent B-ultrasound detector, which may include the following steps:

[0035] S201, obtaining a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient;

[0036] This process usually involves medical staff using B-ultrasound detection equipment to place the ultrasound probe at the patient's specific target site, such as the lower limbs, to obtain high-quality ultrasound images for diagnosing target diseases such as deep vein thrombosis (DVT) in the lower limbs, based on the patient's specific condition and the doctor's instructions. The image is obtained through the reflection principle of ultrasound and can provide real-time visual information about the patient's internal tissues and organs. The quality and accuracy of this step directly affects the subsequent image analysis and diagnostic results. Therefore, medical staff need to adjust the probe position and angle according to different technical requirements during the operation to ensure that the image is clear, complete, and covers the target lesion area.

[0037] This acquisition step plays a vital role in the operation of the intelligent B-ultrasound detector. First, it is the starting point of the entire diagnostic chain, ensuring that the acquired B-ultrasound images can provide basic data for subsequent machine learning analysis. Secondly, accurate image acquisition not only helps to judge the patient's health status, but also provides effective information to medical staff so that they can conduct early screening and timely intervention for possible diseases. In addition, combined with intelligent algorithms and image analysis, abnormalities in images can be quickly identified, thereby improving the efficiency and accuracy of diagnosis, and ultimately improving the patient's treatment effect and medical service quality.

[0038] Taking lower extremity deep vein thrombosis (DVT) as an example, in actual operation, medical staff will first conduct necessary assessments on patients, including asking about symptoms (such as limb swelling, pain, etc.) and relevant medical history (such as recent surgery or long-term bed rest, etc.). Next, the patient needs to maintain a comfortable supine position, and medical staff apply coupling agent to their lower extremities to reduce the reflection loss of ultrasound. At the beginning of the detection, medical staff place the ultrasound probe on the inner thigh, behind the knee, and calf of the patient, carefully observe the real-time image feedback, and ensure close contact between the probe and the skin surface. During the operation, medical staff need to adjust the angle and position of the probe in time to obtain the cross-sectional and longitudinal three-dimensional images of the vein, paying special attention to possible thrombosis areas. Throughout the process, medical staff also need to pay attention to the patient's response to ensure their safety and comfort. During the detection process, the B-ultrasound image data is uploaded to the analysis system of the intelligent B-ultrasound detector in real time, and the system will automatically judge and analyze in the subsequent steps to support the final diagnosis.

[0039] S202, analyzing the B-ultrasound image to determine whether the B-ultrasound image meets a preset imaging standard for diagnosing a target disease;

[0040] In the operation prompt method of the intelligent B-ultrasound detector, judging whether the B-ultrasound image meets the preset imaging standards for diagnosing the target disease is a crucial step. This step is designed to ensure that even medical staff who are unfamiliar with B-ultrasound operations can obtain high-quality imaging data. By comparing with the preset imaging standards, the system can identify image quality problems caused by improper operation (such as incorrect detection site or blurred image). Such preset standards may include anatomical characteristics of the lower extremity veins, blood flow conditions, and image clarity to ensure that the image can reflect the presence of diseases such as deep vein thrombosis (DVT) in the lower extremities. If the image does not meet the standards, the system will issue a prompt to guide medical staff to re-detect, thereby minimizing the risk of poor image quality affecting clinical diagnosis.

[0041] The step of judging whether the B-ultrasound image meets the preset imaging standards is crucial to the diagnostic process, especially when medical staff are not proficient in B-ultrasound operation. This link ensures the effectiveness and reliability of the image, and can detect image quality problems in a timely manner to avoid misdiagnosis or missed diagnosis due to incorrect detection sites or blurred images. For example, in the diagnosis of lower limb DVT, if the outline of the vein in the image is unclear or not clearly displayed, the doctor may mistakenly give up further examination, resulting in delayed disease. Through automated image analysis, the system can not only quickly evaluate image quality, but also provide real-time feedback to help medical staff adjust detection strategies in a timely manner. This mechanism greatly improves the accuracy and effectiveness of diagnosis, providing patients with safer and more reliable medical services.

[0042] In specific operations, after obtaining the B-ultrasound image, the image data will be transmitted to the intelligent analysis system in real time. The system will use machine learning and image processing technology to analyze the image to determine whether it meets the preset standards. For example, the system will automatically check whether the venous anatomical features in the image are clearly visible, whether the blood flow status is normal, and the overall clarity and contrast of the image. If the image fails to fully display the main veins of the lower limbs, or the blood flow status displayed is unclear, the system will mark these problem areas and issue a prompt message to remind medical staff that they need to re-scan the detection area to ensure that the appropriate image is captured. Through this process, even less experienced medical staff can perform effective operations under the guidance of the system to ensure that the image can provide reliable data support for the diagnosis of deep vein thrombosis in the lower extremities.

[0043] S203, if the preset image standard is met, outputting a diagnosis result for the target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning;

[0044] Specifically, the diagnosis result may at least include: whether the patient suffers from the target disease, the location of the disease, and the degree of the disease.

[0045] The output of diagnostic results must include at least three key components: whether the patient has the target disease, the location of the disease, and the severity of the disease. This information is crucial for clinical decision-making. For example, when determining whether a patient has deep vein thrombosis in the lower extremities, the system must not only determine whether a thrombus is found, but also indicate the specific location of the thrombus (such as the inner side of the left calf) and its size (such as a diameter greater than 5 mm), while assessing the severity of the thrombus (such as mild, moderate or severe). With this detailed diagnostic information, doctors can more effectively formulate treatment plans and interventions to provide personalized patient care.

[0046] The detailed classification of diagnostic results helps to improve the accuracy and pertinence of clinical treatment. By providing comprehensive information about the disease status, doctors can more easily identify the development trend of the disease and formulate corresponding treatment strategies. At the same time, this can not only improve the treatment effect of patients, but also reduce unnecessary medical expenses through better risk assessment. For example, after diagnosing DVT, the doctor may quickly decide that the patient needs to receive anticoagulant therapy or further imaging examinations to avoid worsening of the disease and reduce the occurrence of complications. This clinical decision based on clear diagnostic results can help optimize the patient's treatment path and improve the overall quality of medical services.

[0047] In the operation prompt method of the intelligent B-ultrasound detector, when the B-ultrasound image obtained by the system analysis meets the preset image standards, the next step is to use the pre-trained target disease diagnosis model based on machine learning to output the diagnosis results for specific diseases (such as deep vein thrombosis, DVT in the lower extremities). The model can identify characteristic patterns related to the target disease by learning a large amount of labeled image data. For example, the model may analyze multiple factors such as the morphology of the vein, the speed and fluctuation of blood flow to determine whether there are signs of thrombosis in the image. The output diagnosis results include not only the presence or absence of the disease, but also a description of the specific lesions, such as the size and location of the thrombus. This process aims to achieve efficient and accurate diagnostic support to help medical staff make timely treatment decisions.

[0048] This step plays a very important role in the entire diagnostic process. By using machine learning models to analyze images, the accuracy and consistency of diagnosis can be greatly improved. Especially when facing complex conditions, the decision support of the model can greatly reduce the burden on medical staff. In addition, data-driven automated analysis reduces the interference of human factors and reduces diagnostic errors that may be caused by improper operation or lack of experience, further improving patient safety. For example, in the early identification of DVT, this system can quickly provide reliable diagnostic results, ensuring that patients receive treatment as soon as possible, thereby reducing the risk of thrombotic complications.

[0049] The B-ultrasound images that meet the preset imaging standards are input into the pre-trained target disease diagnosis model based on machine learning. The model uses algorithms such as convolutional neural networks (CNN) to automatically extract the characteristics of veins, such as the diameter, morphology, and changes in blood flow velocity of the veins. Based on the extracted features, the model will make classification judgments and analyze whether there is deep vein thrombosis (DVT) in the lower extremities in the image. The model calculates the probability of the diagnosis result by the correlation between the learned features and the known pathology. The system will generate a detailed diagnosis result, mainly including the following information: disease status: whether the patient has DVT; lesion location: the specific anatomical location of the thrombus (such as the great saphenous vein or popliteal vein in the left leg); lesion characteristics: the size and severity of the thrombus (such as a thrombus longer than 5 mm in diameter is marked as moderate or severe). The report will be provided in the form of visual graphics and text to facilitate medical staff's understanding and analysis. The system will prompt medical staff with relevant diagnostic results through the interface so that they can obtain patient condition information in a timely manner. The training method of the target disease diagnosis model can be:

[0050] Collect historical B-ultrasound imaging data containing a variety of different conditions and normal controls to ensure that the characteristics and imaging status of different patients are covered; denoise, standardize and label the collected imaging data to ensure that each image has corresponding diagnostic information (such as the presence of DVT, thrombus size and location); when necessary, enhance the learning ability of the model through methods such as manual feature extraction, especially when the amount of data is limited; select appropriate machine learning algorithms (such as convolutional neural networks), perform iterative training, and adjust model parameters through back propagation and optimization algorithms to minimize the error between the predicted results and the actual results; use an independent test set to evaluate the performance of the model, mainly using indicators such as accuracy, sensitivity and specificity for verification; after the model is launched, continue to monitor the performance of the model on new clinical data, and retrain and update it regularly to improve its continued clinical applicability.

[0051] Through these steps, the target disease diagnosis model based on machine learning can effectively support medical staff in making rapid and accurate disease diagnosis and improve the treatment efficiency of patients.

[0052] Furthermore, biochemical examination data of the patient related to the target disease may be obtained, and based on the biochemical examination data, the patient's disease risk index related to the target disease may be calculated.

[0053] Patients may undergo biochemical tests related to the target disease, which may include but are not limited to blood tests, urine tests, etc., and test indicators such as coagulation function, liver and kidney function, and specific biomarkers (such as D-dimer, fibrinogen, etc.). These indicators can help determine whether the patient is at risk for related diseases. Doctors will select appropriate biochemical indicators based on clinical standards or guidelines, and obtain the values ​​of these indicators through laboratory equipment. The system will then input these standardized values ​​into the calculation formula of the disease risk index (DRI), integrate the patient's biochemical data and other influencing factors, and derive a comprehensive disease risk assessment, thereby providing an important basis for subsequent diagnosis.

[0054] By obtaining biochemical examination data related to the target disease and calculating the disease risk index, it is possible to provide medical personnel with a quantitative risk assessment, helping them to more accurately judge the patient's health status during the diagnosis process. Biochemical examination data provides objective and important information that can reflect the patient's physiological state, while the disease risk index integrates multi-dimensional influencing factors, allowing doctors to make more comprehensive assessments and decisions in complex situations. Combined with B-ultrasound imaging data, this multimodal evaluation method significantly improves the accuracy and reliability of diagnosis, thereby providing effective support for patients to develop personalized treatment plans.

[0055] In the specific implementation, the patient will first undergo the corresponding biochemical examination in the hospital. Assuming that the patient needs to detect the risk of deep vein thrombosis in the lower extremities, the medical staff will collect blood samples and conduct a series of analyses to obtain key biochemical indicators such as D-dimer, prothrombin time, etc. Through laboratory testing, the system will automatically receive the biochemical data and standardize it. For example, the standardized value of D-dimer may be 0.5. The system will then calculate the basic risk value C based on the patient's personal information (such as age, gender, family medical history, etc.). At the same time, the patient will fill out a questionnaire on lifestyle and mental health to obtain the lifestyle index A and the mental health index E. Finally, all indicators will be substituted into the DRI formula to calculate the patient's disease risk index. The risk assessment results will be combined with the results of B-ultrasound image analysis to form a comprehensive diagnostic report.

[0056] A disease risk index DRI can be:

[0057]

[0058] Among them, B_i is the standardized value of the i-th biochemical indicator, W_i is the weight coefficient of the i-th biochemical indicator, C is the basic risk value, which takes into account the influence of basic information such as the patient's age, gender, family medical history, etc., A is the patient's lifestyle index (such as smoking, drinking, exercise, etc.), obtained through questionnaires or behavioral monitoring, ranging from 0 to 1, E is the patient's mental health index (such as anxiety, depression, etc.), obtained through a psychological assessment scale, ranging from 0 to 1, alpha and beta are the corresponding adjustment coefficients, reflecting the degree of influence of lifestyle and mental health on the risk of disease.

[0059] B_i: The standardized value of each biochemical index represents the degree of influence of different biochemical indexes on the risk of disease. Through standardization, the influence of different detection index dimensions can be eliminated, so that they can be compared with each other on the same basis, reflecting the physiological state of the patient.

[0060] W_i: The weight coefficient of each biochemical indicator, reflecting the relative importance of the biochemical indicator to the target disease. By assigning different weights, the contribution of different biochemical data to the overall risk can be more accurately reflected, helping doctors prioritize the most critical factors among multiple indicators.

[0061] C: Basic risk value, which takes into account the impact of basic patient information (age, gender, family medical history, etc.). The disease risks of different patient groups vary significantly, and the introduction of basic risk values ​​can better personalize the assessment and reduce the errors caused by population differences.

[0062] A: Lifestyle index, obtained through questionnaires or behavioral monitoring, ranges from 0 to 1, indicating the impact of the patient's lifestyle on health. For example, behaviors such as smoking, drinking and exercise, a good lifestyle usually reduces the risk of disease.

[0063] E: Mental health index, obtained through a psychological assessment scale, ranging from 0 to 1, reflects the impact of the patient's mental state on health. Mental health is closely related to physical health, and improving mental state can help reduce the risk of disease.

[0064] Alpha and beta: adjustment coefficients, used to reflect the impact of lifestyle and mental health on disease risk. These coefficients can be derived through historical data analysis to make the model more accurate.

[0065] In another implementation, the diagnostic result for the target disease can be outputted based on the B-ultrasound image, the biochemical examination data and the disease risk index using a pre-trained target disease diagnostic model based on machine learning.

[0066] Based on the combination of B-ultrasound images, biochemical examination data and the calculated disease risk index, the target disease diagnosis model based on machine learning will analyze and judge this information. The system will receive pathological features from B-ultrasound images, related biochemical indicators and calculated DRI values, and use pre-trained machine learning models to evaluate the relevance and potential risks of these data. By analyzing these multi-dimensional data, the model will give a clear judgment on whether the patient has the target disease, and provide detailed diagnostic results, including the location and severity of the disease. Such a comprehensive analysis ensures the accuracy of the final results, allowing doctors to make more scientific decisions when facing complex cases. It should be noted that at this time, the training set of the machine learning model needs to be adaptively modified to historical B-ultrasound images, historical biochemical examination data and historical DRI values.

[0067] This diagnostic method based on the fusion of multiple data not only improves the accuracy of disease identification, but also provides a more comprehensive basis for clinical decision-making. By combining imaging data with biochemical indicators and risk assessment, doctors can understand the patient's health status in a broader context, develop personalized treatment plans, and improve the patient's treatment effect and safety. Especially in the case of complex diseases, this multimodal analysis method can greatly reduce the risk of misdiagnosis and missed diagnosis, thereby better serving the patient's health management.

[0068] Suppose a patient is examined for deep vein thrombosis in the lower extremities in the hospital. First, the medical staff performed a B-ultrasound test according to the patient's condition and obtained relevant imaging data. Then, the patient underwent a series of biochemical tests, and the laboratory test showed that the patient's D-dimer value was 0.8 (standardized value). At the same time, the medical staff obtained the patient's lifestyle index (A=0.6) and mental health index (E=0.4) through a questionnaire. According to clinical data, the basic risk value C is determined to be 0.3. Substituting these data into the DRI calculation formula, assuming the weight coefficient (such as W_1=0.7), combined with the historical data feedback adjustment coefficient (such as alpha=1.5, beta=1.2), the patient's DRI value can be calculated to determine his risk of disease. Finally, the DRI value is combined with the B-ultrasound image and biochemical examination values, and the machine learning model will output the patient's diagnosis results, guiding medical staff to formulate subsequent treatment plans. Through this comprehensive diagnostic process, doctors can quickly obtain comprehensive patient health information to take timely and effective treatment measures.

[0069] S204, sending a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

[0070] After completing the analysis of the B-ultrasound image and obtaining the diagnosis result, the system will automatically generate a prompt message containing the diagnosis information, such as "the patient is at risk of deep vein thrombosis in the lower extremities" and the corresponding detailed description (such as the location of the disease, severity, etc.). These prompt messages will be sent to the medical staff operating the B-ultrasound detector through the user interface or real-time communication. Based on these prompts, medical staff can obtain the latest medical information in the first time, so as to decide whether to conduct a second or multiple detections to confirm or exclude the accuracy and reliability of the initial diagnosis results.

[0071] Sending prompt information of diagnostic results to medical staff can significantly improve the efficiency and safety of clinical decision-making. By providing accurate diagnostic information in a timely manner, medical staff can quickly assess the patient's health status and take further examination measures when necessary. This information sharing can promote medical staff's comprehensive understanding of the patient's condition and help them make wise treatment decisions in complex situations. In addition, the suggestion of secondary detection not only helps to confirm the initial diagnosis, but also uncovers potential abnormalities, thereby promoting early intervention and treatment of patients, and ultimately improving the quality and safety of patients' medical care.

[0072] Furthermore, if the preset imaging standards are not met, a prompt message indicating that the operation is not in compliance is sent to the medical staff operating the B-ultrasound detector, so that the medical staff can operate the B-ultrasound detector to re-detect the target part of the patient, and return to the step of obtaining the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient.

[0073] When analyzing B-ultrasound images, if the system determines that the acquired images do not meet the preset imaging standards for diagnosing the target disease, such as blurred images, excessive signal noise, or lack of necessary views, the system will automatically generate and send a prompt message of non-compliant operation. This prompt message will inform medical staff in a clear and concise manner, prompting them to re-operate the B-ultrasound detector to re-detect the patient's target area. At the same time, the system will guide medical staff back to the step of acquiring the image to ensure that the image quality meets the diagnostic requirements.

[0074] The purpose of sending prompt messages for inconsistent operations is to provide immediate feedback to medical staff to ensure the accuracy and effectiveness of the diagnosis process. By promptly notifying image quality issues, unnecessary misdiagnosis or missed diagnosis can be avoided, and the patient's life safety and interests can be protected. Re-detection can not only correct possible errors in a timely manner, but also ensure that the image information obtained is complete and effective, thus providing a solid foundation for subsequent diagnosis. This dynamic adjustment mechanism enhances the intelligence and flexibility of the system, demonstrates good adaptability and rigor in complex clinical environments, and improves the overall quality of medical services.

[0075] It can be seen that the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient is obtained; the B-ultrasound image is analyzed to determine whether the B-ultrasound image meets the preset image standards for diagnosing the target disease; if it meets the preset image standards, according to the B-ultrasound image, a pre-trained target disease diagnosis model based on machine learning is used to output the diagnosis result for the target disease; a prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for secondary or multiple detections according to the prompt message to verify the diagnosis result, thereby being able to analyze the B-ultrasound image in real time, automatically determine the image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasound examinations and reducing the workload of medical staff.

[0076] Another embodiment of the present invention provides an operation prompt system for an intelligent B-ultrasound detector, see Figure 3 , the system may include:

[0077] The acquisition module 301 is used to acquire the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient;

[0078] An analysis module 302 is used to analyze the B-ultrasound image to determine whether the B-ultrasound image meets a preset imaging standard for diagnosing a target disease;

[0079] Output module 303, used to output the diagnosis result for the target disease based on the B-ultrasound image by using the pre-trained target disease diagnosis model based on machine learning if the preset image standard is met;

[0080] The prompt module 304 is used to send a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff can operate the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

[0081] It can be seen that the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient is obtained; the B-ultrasound image is analyzed to determine whether the B-ultrasound image meets the preset image standards for diagnosing the target disease; if it meets the preset image standards, according to the B-ultrasound image, a pre-trained target disease diagnosis model based on machine learning is used to output the diagnosis result for the target disease; a prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for secondary or multiple detections according to the prompt message to verify the diagnosis result, thereby being able to analyze the B-ultrasound image in real time, automatically determine the image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasound examinations and reducing the workload of medical staff.

[0082] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0083] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0084] S201, obtaining a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient;

[0085] S202, analyzing the B-ultrasound image to determine whether the B-ultrasound image meets a preset imaging standard for diagnosing a target disease;

[0086] S203, if the preset image standard is met, outputting a diagnosis result for the target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning;

[0087] S204, sending a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

[0088] It can be seen that the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient is obtained; the B-ultrasound image is analyzed to determine whether the B-ultrasound image meets the preset image standards for diagnosing the target disease; if it meets the preset image standards, according to the B-ultrasound image, a pre-trained target disease diagnosis model based on machine learning is used to output the diagnosis result for the target disease; a prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for secondary or multiple detections according to the prompt message to verify the diagnosis result, thereby being able to analyze the B-ultrasound image in real time, automatically determine the image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasound examinations and reducing the workload of medical staff.

[0089] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0090] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0091] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0092] S201, obtaining a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient;

[0093] S202, analyzing the B-ultrasound image to determine whether the B-ultrasound image meets a preset imaging standard for diagnosing a target disease;

[0094] S203, if the preset image standard is met, outputting a diagnosis result for the target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning;

[0095] S204, sending a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

[0096] It can be seen that the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient is obtained; the B-ultrasound image is analyzed to determine whether the B-ultrasound image meets the preset image standards for diagnosing the target disease; if it meets the preset image standards, according to the B-ultrasound image, a pre-trained target disease diagnosis model based on machine learning is used to output the diagnosis result for the target disease; a prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector for secondary or multiple detections according to the prompt message to verify the diagnosis result, thereby being able to analyze the B-ultrasound image in real time, automatically determine the image quality, provide operation suggestions, and generate diagnosis results, thereby improving the accuracy and efficiency of ultrasound examinations and reducing the workload of medical staff.

[0097] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. An operation prompt method for an intelligent B-ultrasound detector, characterized in that: The method comprises: Acquire the B-ultrasound image obtained by the medical staff using the B-ultrasound detector to detect the target part of the patient; Analyzing the B-ultrasound image to determine whether the B-ultrasound image meets the preset imaging standard for diagnosing the target disease; If the preset imaging criteria are met, a diagnostic result for the target disease is outputted based on the B-ultrasound image using a pre-trained target disease diagnostic model based on machine learning; A prompt message containing the diagnosis result is sent to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform secondary or multiple detections according to the prompt message to verify the diagnosis result.

2. The method according to claim 1, characterized in that The method further comprises: If the preset image standard is not met, a prompt message indicating that the operation is not in compliance is sent to the medical staff operating the B-ultrasound detector, so that the medical staff can operate the B-ultrasound detector to re-detect the target part of the patient, and return to the step of obtaining the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient.

3. The method according to claim 2, characterized in that The diagnosis result includes at least: whether the patient suffers from the target disease, the location of the disease and the degree of the disease.

4. The method according to claim 3, characterized in that The method further includes: acquiring biochemical examination data of the patient related to the target disease, and calculating the patient's disease risk index related to the target disease based on the biochemical examination data; The method of outputting a diagnosis result for a target disease based on the B-ultrasound image and using a pre-trained target disease diagnosis model based on machine learning includes: According to the B-ultrasound image, the biochemical examination data and the disease risk index, a pre-trained target disease diagnosis model based on machine learning is used to output a diagnosis result for the target disease.

5. An operation prompt system for an intelligent B-ultrasound detector, characterized in that: The system comprises: An acquisition module is used to acquire a B-ultrasound image obtained by a medical staff operating a B-ultrasound detector to detect a target part of a patient; An analysis module, used to analyze the B-ultrasound image to determine whether the B-ultrasound image meets the preset image standard for diagnosing the target disease; An output module is used to output a diagnosis result for a target disease based on the B-ultrasound image using a pre-trained target disease diagnosis model based on machine learning if the preset image standard is met; The prompt module is used to send a prompt message containing the diagnosis result to the medical staff operating the B-ultrasound detector, so that the medical staff operates the B-ultrasound detector to perform a second or multiple detections according to the prompt message to verify the diagnosis result.

6. The system according to claim 5, characterized in that The system further comprises: The sending module is used to send a prompt message of non-compliance of the operation to the medical staff operating the B-ultrasound detector if the preset image standard is not met, so that the medical staff can operate the B-ultrasound detector to re-detect the target part of the patient, and return to the step of obtaining the B-ultrasound image obtained by the medical staff operating the B-ultrasound detector to detect the target part of the patient.

7. The system according to claim 6, characterized in that The diagnosis result includes at least: whether the patient suffers from the target disease, the location of the disease and the degree of the disease.

8. The system according to claim 7, characterized in that The system further comprises: a calculation module, which is used to obtain biochemical examination data of the patient related to the target disease, and calculate the patient's disease risk index related to the target disease based on the biochemical examination data; The output module is specifically used for: According to the B-ultrasound image, the biochemical examination data and the disease risk index, a pre-trained target disease diagnosis model based on machine learning is used to output a diagnosis result for the target disease.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images