A heart attack warning system based on image recognition

Abstract

The present invention proposes a heart attack warning system based on image recognition, including an image acquisition and processing system, a data transmission device, a central server and a user terminal; the image acquisition and processing system is used to acquire medical images, and perform image processing and initial anomaly detection on the medical images at the edge end, obtain initial anomaly detection results, and perform initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements; the data transmission device is used to establish a data connection and perform data transmission between the image acquisition and processing system and the central server, and between the central server and the user terminal; the central server is used to perform data processing and risk assessment on the initial anomaly detection results that do not meet the initial warning requirements, and obtain risk assessment results; the user terminal is used to receive the risk assessment results sent by the central server in real time, and to visually display the corresponding risk assessment results.

Description

Technical Field

[0001] The present invention proposes a heart attack warning system based on image recognition, belonging to the technical field of risk warning. Background Art

[0002] With the aging population and changing lifestyles, heart disease has become a major global threat to human health. Early warning and timely intervention for heart disease are crucial for reducing mortality and improving patients' quality of life. Traditional methods for diagnosing heart disease rely primarily on electrocardiograms (ECGs), blood tests, and clinical symptom analysis. However, these methods often have a lag and fail to provide timely warnings before an acute heart attack. In recent years, with the rapid development of computer vision and artificial intelligence technologies, image recognition technology has become increasingly widely used in the medical field, providing new insights into early warning of heart disease. Medical images, such as echocardiograms, CT (computed tomography), and MRI (magnetic resonance imaging), can intuitively display the structure and function of the heart, providing doctors with a wealth of diagnostic information. However, traditional manual interpretation of medical images is not only time-consuming and labor-intensive, but also susceptible to factors such as physician experience and fatigue, leading to the risk of misdiagnosis and missed diagnoses. Therefore, the development of a heart attack warning system based on image recognition technology is crucial. This system can automatically, quickly, and accurately analyze medical images, identify potential cardiac abnormalities, and issue warning signals when necessary, enabling patients to seek medical attention or take appropriate measures.

[0003] Currently, some image recognition-based medical diagnostic systems exist on the market, but most focus on auxiliary diagnosis rather than early warning. These systems often require high-performance computers or cloud servers, and lack support for applications requiring high real-time performance and portability. Furthermore, existing systems rely on complex algorithms and models for data processing and risk assessment, which are computationally intensive and time-consuming, making them inadequate for the urgent need for heart attack warnings.

[0004] To address these issues, this paper proposes a heart attack warning system based on image recognition. By integrating an image acquisition and processing system, data transmission equipment, a central server, and user terminals, this system automates the entire process, from medical image acquisition, initial edge processing and warning, data transmission, in-depth analysis and risk assessment on the central server, to real-time reception and visual display on the user terminal. This system not only improves the accuracy and timeliness of heart attack warnings, but also reduces the burden on the central server through edge computing technology, enhancing the system's real-time performance and portability. Summary of the Invention

[0005] The present invention provides a heart attack warning system based on image recognition to solve the technical problems in the above-mentioned prior art. The technical problems solved are as follows:

[0006] A heart attack warning system based on image recognition, comprising an image acquisition and processing system, a data transmission device, a central server, and a user terminal; wherein the image acquisition and processing system is data-connected to the central server via the data transmission device; and the central server is data-connected to the user terminal via the data transmission device.

[0007] The image acquisition and processing system is used to acquire medical images, perform image processing and initial anomaly detection on the medical images at the edge, obtain initial anomaly detection results, and issue an initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements;

[0008] The data transmission device is used to establish a data connection and perform data transmission between the image acquisition and processing system and the central server, and between the central server and the user terminal;

[0009] The central server is used to perform data processing and risk assessment on the initial anomaly detection results that do not meet the initial warning requirements and obtain risk assessment results;

[0010] The user terminal is used to receive the risk assessment results sent by the central server in real time and perform visual display corresponding to the risk assessment results.

[0011] Furthermore, the image acquisition and processing system includes multiple medical image acquisition devices, an image standard processing module, a first edge computing device and a second edge computing device; wherein, the data signal output end of the medical image acquisition device is connected to the signal input end of the image standard processing module; the signal output end of the image standard processing module is connected to the data signal input end of the first edge computing device; the signal output end of the first edge computing device is connected to the signal input end of the second edge computing device; the signal output end of the second edge computing device is the signal output end of the image acquisition and processing system.

[0012] Furthermore, the medical image acquisition device is used to acquire cardiac medical images, obtain medical images for heart attack warning, and input the medical images for heart attack warning into the image standard processing module;

[0013] The image standard processing module is configured to perform standardization processing on medical images acquired by multiple medical image acquisition devices, acquire standardized medical images, and send the standardized medical images to the first edge computing device;

[0014] The first edge computing device is configured to monitor the operating status of the second edge computing device in real time, and determine whether to send the standardized medical image to the second edge computing device based on the operating status of the second edge computing device; and, when a load on the second edge computing device exceeds a preset load requirement, activate its own initial anomaly detection function to perform initial anomaly detection on the standardized medical image for heart attack warning simultaneously with the second edge computing device;

[0015] The second edge computing device is used to perform initial anomaly detection on the standardized medical images used for heart attack warning, and to perform initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements.

[0016] Furthermore, the image standardization processing process of the image standard processing module includes:

[0017] receiving, in real time, raw medical image data acquired by the plurality of medical image acquisition devices, and performing noise reduction processing on the raw medical image data to obtain raw medical image data after noise reduction processing;

[0018] Performing data image cropping and correction processing on the original medical image after the noise reduction processing according to preset image requirement information to obtain a medical image after cropping and correction processing;

[0019] Performing initial normalization adjustment on the cropped and corrected medical image according to a preset resolution and size to obtain an initially normalized medical image;

[0020] A secondary normalization adjustment is performed on the initially normalized medical image according to preset image contrast and brightness to obtain a normalized medical image.

[0021] Furthermore, the operation process of the first edge computing device includes:

[0022] monitoring operating status parameters of the second edge computing device in real time, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length;

[0023] Obtaining a load index of the current second edge computing device according to the CPU utilization, memory utilization, and processing queue length;

[0024] When the load index of the second edge computing device does not exceed a preset load index threshold, sending the standardized medical image to the second edge computing device;

[0025] When the load index of the second edge computing device exceeds a preset load index threshold, real-time monitoring is performed on a first duration during which the load index of the second edge computing device exceeds the preset load index threshold;

[0026] When the load index of the second edge computing device exceeds a preset load index threshold for a first duration exceeding a preset time length, the first edge computing device automatically starts an initial anomaly detection function and obtains the number of image data processed by the first edge computing device based on the number of standardized medical images to be detected contained in the processing queue length of the second edge computing device and the current load index of the second edge computing device; wherein the number of image data processed is obtained by the following formula:

[0027]

[0028] in, N Indicates the number of image data processed, and N To round up; K represents the load index; K y Indicates the preset load index threshold; m The number of normalized medical images to be detected contained in the processing queue length;

[0029] The first edge computing device retrieves, from a processing queue length of the second edge computing device according to the number of processed image data, a number of standardized medical images to be detected that is equal to the number of processed image data, as target medical images, and performs initial anomaly detection on the target medical images to obtain initial anomaly detection results;

[0030] When the load index of the second edge computing device drops below a preset load index threshold, and the duration of being below the preset load index threshold exceeds a preset second duration, the first edge computing device automatically turns off the initial anomaly detection function.

[0031] Furthermore, the load index is obtained as follows:

[0032] Extracting operating status parameters corresponding to each unit time of the second edge computing device, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length;

[0033] Generate a parameter matrix using the CPU utilization, memory utilization and processing queue length included in the operating status parameters corresponding to each unit time A ; Wherein, the parameter matrix A The structure is as follows:

[0034]

[0035] in, A represents the parameter matrix; a 11 、 a 12 … a n3 Represents the parameter matrix A All the elements included; n Indicates the number of unit times experienced by the second edge computing device;

[0036] Extract the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d ;

[0037] Utilize the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d Obtain the current load index of the second edge computing device;

[0038] The load index is obtained by the following formula:

[0039]

[0040] in, K represents the load index; σ max Represents the parameter matrix corresponding to the current unit time A d The corresponding largest singular number; Represents the parameter matrix corresponding to the current unit time A d The corresponding norm; Represents the parameter matrix corresponding to the current unit time A d Corresponding A d T A d Determinant of a matrix; and The parameter matrix A corresponding to all unit times that the second edge computing device has experienced in history L Corresponding median and mean of the determinant of a matrix; The variance of the determinant of the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history; ε Represents the minimum constant, used to prevent the independent variable of the logarithmic function from being 0; x represents the base of the preset logarithmic function, and, x ≥2.

[0041] Furthermore, the process of the first edge computing device and the second edge computing device performing initial anomaly detection includes:

[0042] Extracting regions from different parts of the heart in the standardized medical image for heart attack warning to obtain a plurality of heart region images corresponding to the different parts of the heart;

[0043] Acquiring characteristic data corresponding to different parts of each heart from the multiple heart region images, wherein the characteristic data includes the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves;

[0044] Retrieving standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves;

[0045] comparing the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the feature data with standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape, and obtaining a similarity value between the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the feature data and the standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape;

[0046] An abnormality index parameter is obtained by using a similarity value between the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the characteristic data and the standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape, wherein the abnormality index parameter is obtained by the following formula:

[0047]

[0048] in, E represents the anomaly index parameter; r Indicates the number of feature data types contained in the feature data;S i Indicates the i The similarity value between the feature data and its corresponding standard data; S min and S max Respectively r The minimum and maximum similarity values ​​among the feature data; w min Indicates the weight value of the feature data corresponding to the minimum similarity value; w mx express r The minimum weight among the feature data; w max Indicates the weight value of the feature data corresponding to the maximum similarity value; w my express r The maximum weight among the feature data;

[0049] The abnormality index parameter is compared with the preset abnormality index threshold. When the abnormality index parameter is lower than the preset abnormality index threshold, it is determined that there is no abnormality; when the abnormality index parameter is not lower than the preset abnormality index threshold, it is determined that there is an abnormality, and an initial abnormality detection warning is performed.

[0050] Furthermore, the central server includes a data receiving module, a data processing module, a risk assessment module and an early warning module; wherein the signal input end of the data receiving module is the signal input end of the central server; the signal output end of the data receiving module is connected to the signal input end of the data processing module; the signal output end of the data processing module is connected to the signal input end of the risk assessment module; the signal output end of the risk assessment module is connected to the signal input end of the early warning module;

[0051] The data receiving module is configured to receive, in real time, the standardized medical image for heart attack warning that does not meet the initial warning requirements when the standardized medical image for heart attack warning does not meet the initial warning requirements;

[0052] The data processing module is configured to perform data preprocessing on the standardized medical image for heart attack warning that does not meet the initial warning requirements to obtain a preprocessed medical image; wherein the data preprocessing includes noise reduction and data cleaning;

[0053] The risk assessment module is used to perform a heart attack risk assessment based on the preprocessed medical image to obtain a risk assessment result;

[0054] The early warning module is used to issue a heart attack warning when the risk assessment result indicates that there is a risk of heart attack.

[0055] Furthermore, the process of the risk assessment module performing heart attack risk assessment based on the preprocessed medical image includes:

[0056] If the initial warning requirements are not met, retrieve the pre-processed medical images corresponding to the non-compliance with the initial warning requirements;

[0057] Retrieving a standardized medical image for heart attack warning from the patient's historical record corresponding to the pre-processed medical image that does not meet the initial warning requirements;

[0058] sorting the medical images according to the acquisition time of the standardized medical images for heart attack warning in the patient's historical records to generate a medical image set;

[0059] Heart attack risk assessment is performed using abnormality index parameters of every two adjacent medical images in the medical image set.

[0060] Furthermore, using the abnormality index parameters of every two adjacent medical images in the medical image set to perform heart attack risk assessment includes:

[0061] extracting abnormality index parameters of every two adjacent medical images in the medical image set;

[0062] Comparing the abnormality index parameters of each two adjacent medical images to obtain abnormality index parameter differences, and extracting, from the abnormality index parameter differences, the abnormality index parameter differences corresponding to the abnormality index parameter of the preceding medical image being lower than the abnormality index parameter of the following medical image;

[0063] Compare the abnormal index parameter difference corresponding to each abnormal index parameter of the previous medical image being lower than the abnormal index parameter of the subsequent medical image with a preset difference threshold;

[0064] When the abnormal index parameter of the earlier medical image is lower than the abnormal index parameter of the later medical image, and the abnormal index parameter difference corresponding to the abnormal index parameter exceeds a preset difference threshold, the earlier medical image and the later medical image corresponding to the abnormal index parameter difference exceeding the preset difference threshold are marked as a target abnormal image group;

[0065] Retrieving similarity values ​​of the sizes of the ventricles and atria, the shapes of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images preceding and following the target abnormal image group;

[0066] The risk determination value is obtained by using the similarity values ​​of the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images before and after the medical images included in all target abnormal image groups; wherein the risk determination value is obtained by the following formula:

[0067]

[0068] in, Y Indicates the risk assessment value; x represents the base of the preset logarithmic function, and, x ≥2; β represents a positive offset, and the positive offset has a value range of 0.28-3.63; k Indicates the number of target abnormal image groups; t j Indicates the j The time interval between the subsequent medical images in the target abnormal image group and the current moment T time difference; Q represents the similarity parameter corresponding to all target abnormal image groups, and the similarity parameter is obtained by the following formula:

[0069]

[0070] in, Q Represents the similarity parameter corresponding to all target abnormal image groups; k Indicates the number of target abnormal image groups; r j Indicates the j The number of feature data types contained in the feature data of a target abnormal image group; S hi and S xi Indicates the j The first medical image and the second medical image corresponding to the target abnormal image group i The similarity value between the feature data and its standard data; E hj and E xj Indicates the j Abnormal index parameters corresponding to the medical image before and the medical image after of the target abnormal image group;

[0071] When the risk determination value exceeds a preset risk determination threshold, it is determined that there is a risk of heart attack, and a heart attack warning is issued.

[0072] Beneficial effects of the present invention:

[0073] The present invention proposes a heart attack warning system based on image recognition. By integrating image recognition technology and risk assessment models, the system can more accurately identify the potential risk of heart attack and reduce the possibility of misdiagnosis and missed diagnosis. The preliminary processing and warning at the edge and the efficient data transmission mechanism ensure that the system can respond to the patient's medical image data in real time and issue a warning signal at the first time. The real-time reception and visual display function of the user terminal enables patients and medical staff to understand the patient's risk status anytime and anywhere, enhancing the ease of use and convenience of the system. Through the automated warning process, the system can help medical institutions allocate medical resources more effectively and provide patients with timely intervention and treatment services. The system's remote data transmission and visual display functions make telemedicine possible, providing patients with a wider range of medical service options. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a system block diagram of the system of the present invention. DETAILED DESCRIPTION

[0075] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0076] The embodiment of the present invention proposes a heart attack warning system based on image recognition, such as Figure 1 As shown, the image recognition-based heart attack warning system includes an image acquisition and processing system, a data transmission device, a central server, and a user terminal; wherein the image acquisition and processing system is data-connected to the central server via the data transmission device; and the central server is data-connected to the user terminal via the data transmission device;

[0077] The image acquisition and processing system is used to acquire medical images, perform image processing and initial anomaly detection on the medical images at the edge, obtain initial anomaly detection results, and issue an initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements;

[0078] The data transmission device is used to establish a data connection and perform data transmission between the image acquisition and processing system and the central server, and between the central server and the user terminal;

[0079] The central server is used to perform data processing and risk assessment on the initial anomaly detection results that do not meet the initial warning requirements and obtain risk assessment results;

[0080] The user terminal is used to receive the risk assessment results sent by the central server in real time and perform visual display corresponding to the risk assessment results.

[0081] The working principle of the above technical solution is: the above-mentioned image recognition-based heart attack warning system in this embodiment, through a highly integrated process, realizes a fully automated warning process from real-time acquisition of patient medical images, preliminary processing and warning at the edge, rapid data transmission, in-depth analysis and risk assessment by the central server, to real-time reception and visual display at the user terminal.

[0082] First, the image acquisition and processing system captures the patient's medical images in real time. These images undergo preliminary image processing and feature extraction at the edge, along with initial anomaly detection. If the detected anomaly meets the preset initial warning requirements, the system immediately triggers an initial warning signal, alerting the patient or medical staff.

[0083] These images and their preliminary processing results are then rapidly transmitted to a central server via efficient data transmission equipment. Upon receiving the data, the central server utilizes advanced image recognition technology and risk assessment models to conduct in-depth processing and risk assessment for abnormal results that do not meet initial warning requirements but require further analysis. This process comprehensively considers a patient's diverse medical information and historical data to produce a more comprehensive and accurate risk assessment.

[0084] Finally, the central server sends the risk assessment results in real time to the user terminal, which displays these results through an intuitive graphical interface, allowing patients and medical staff to quickly understand the patient's heart attack risk and take necessary intervention and treatment measures.

[0085] The effect of the above technical solution is: by integrating image recognition technology and risk assessment models, the system can more accurately identify the potential risk of heart attack, reducing the possibility of misdiagnosis and missed diagnosis. The preliminary processing and early warning at the edge and the efficient data transmission mechanism ensure that the system can respond to the patient's medical image data in real time and issue early warning signals at the first time. The real-time reception and visual display functions of the user terminal enable patients and medical staff to understand the patient's risk status anytime and anywhere, enhancing the ease of use and convenience of the system. Through automated early warning processes, the system can help medical institutions allocate medical resources more effectively and provide patients with timely intervention and treatment services. The system's remote data transmission and visual display functions make telemedicine possible, providing patients with a wider range of medical service options.

[0086] In summary, this heart attack warning system based on image recognition provides strong support for early warning and timely intervention of heart disease through its unique working principle and technical advantages.

[0087] In one embodiment of the present invention, the image acquisition and processing system includes multiple medical image acquisition devices, an image standard processing module, a first edge computing device and a second edge computing device; wherein, the data signal output end of the medical image acquisition device is connected to the signal input end of the image standard processing module; the signal output end of the image standard processing module is connected to the data signal input end of the first edge computing device; the signal output end of the first edge computing device is connected to the signal input end of the second edge computing device; the signal output end of the second edge computing device is the signal output end of the image acquisition and processing system.

[0088] The medical image acquisition device is used to acquire cardiac medical images, obtain medical images for heart attack warning, and input the medical images for heart attack warning into the image standard processing module;

[0089] The image standard processing module is configured to perform standardization processing on medical images acquired by multiple medical image acquisition devices, acquire standardized medical images, and send the standardized medical images to the first edge computing device;

[0090] The first edge computing device is configured to monitor the operating status of the second edge computing device in real time, and determine whether to send the standardized medical image to the second edge computing device based on the operating status of the second edge computing device; and, when a load on the second edge computing device exceeds a preset load requirement, activate its own initial anomaly detection function to perform initial anomaly detection on the standardized medical image for heart attack warning simultaneously with the second edge computing device;

[0091] The second edge computing device is used to perform initial anomaly detection on the standardized medical images used for heart attack warning, and to perform initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements.

[0092] The working principle of the above technical solution is: multiple medical image acquisition devices (such as echocardiographs, MRI scanners, etc.) are used to acquire cardiac medical images. The original medical images acquired by the above devices are input into the image standard processing module.

[0093] The image standardization module performs unified standardization on medical images acquired by multiple medical image acquisition devices to improve image consistency and comparability. The standardized medical images are sent to the first edge computing device for further processing.

[0094] The first edge computing device monitors the operating status of the second edge computing device in real time, including its load. If the second edge computing device's load exceeds a preset load requirement, the first edge computing device activates its own initial anomaly detection function, processing the standardized medical images in parallel with the second edge computing device. This mechanism ensures that the system can continue to effectively perform initial anomaly detection even under high load conditions.

[0095] The second edge computing device (or the first edge computing device activated simultaneously) performs initial anomaly detection on the standardized medical images. If the detection results meet the preset initial warning requirements (for example, detecting abnormal image features that may be associated with a heart attack), the system will issue an initial anomaly detection warning to alert medical staff or patients.

[0096] The above technical solution achieves the following: Medical images are uniformly processed through standardized processing modules, reducing the complexity and error rate of subsequent processing. Real-time monitoring and load management mechanisms of edge computing devices ensure stable system operation even under high loads. The initial anomaly detection function enables rapid real-time analysis of medical images, identifying abnormal features that may be associated with a heart attack. Parallel processing across multiple edge computing devices improves detection accuracy and reliability.

[0097] The real-time monitoring function of the first edge computing device can promptly detect anomalies in the second edge computing device and take appropriate measures to ensure continuous system operation. The system's modular design allows each component to operate independently, improving the overall system's fault tolerance. Through automated initial anomaly detection and early warning, the system can promptly identify potential heart attack risks, providing strong support for the rational allocation of medical resources. The application of edge computing reduces data transmission latency and bandwidth costs, while improving the system's real-time performance and responsiveness. The timely initial anomaly detection and early warning allows patients to seek medical treatment promptly, avoiding the higher medical costs associated with worsening conditions.

[0098] In one embodiment of the present invention, the image standardization processing process of the image standardization processing module includes:

[0099] A1. receiving original medical image data acquired by the plurality of medical image acquisition devices in real time, and performing noise reduction processing on the original medical image data to obtain original medical image data after noise reduction processing;

[0100] A2. performing data image cropping and correction processing on the original medical image after noise reduction processing according to preset image requirement information to obtain a cropped and corrected medical image;

[0101] A3. performing initial normalization adjustment on the cropped and corrected medical image according to a preset resolution and size to obtain an initially normalized medical image;

[0102] A4. Perform secondary normalization adjustment on the initially normalized medical image according to preset image contrast and brightness to obtain a normalized medical image.

[0103] The working principle of the above technical solution is to receive raw medical image data from multiple medical image acquisition devices in real time. Denoising is then performed on this raw medical image data to remove any noise and interference signals that may be present in the image. This denoising process improves image clarity and signal-to-noise ratio, providing better image quality for subsequent processing.

[0104] Based on pre-defined image requirements (such as regions of interest and image orientation), the original medical image after noise reduction is cropped and corrected. Cropping removes irrelevant parts of the image while retaining key information. Correction adjusts the image's geometry and position to ensure image accuracy and consistency.

[0105] After cropping and correction, the medical images are initially normalized to a preset resolution and size. This step aims to unify the image size and resolution, providing standardized input data for subsequent processing. This initial normalization ensures that medical images from different sources and types are comparable in subsequent processing.

[0106] After initial normalization, medical images undergo secondary normalization based on preset image contrast and brightness settings. This step further adjusts the image contrast and brightness to improve visual quality and readability. This secondary normalization ensures that images maintain optimal display quality across a variety of display devices and environmental conditions.

[0107] The above technical solution achieves the following results: through noise reduction, cropping, correction, and normalization, it effectively removes noise and interfering signals from images, improving image clarity and signal-to-noise ratio. Furthermore, by adjusting image contrast and brightness, it improves image visual quality and readability, providing a better image quality foundation for subsequent processing and analysis. Through a unified cropping, correction, and normalization process, medical images from different sources and types are comparable in subsequent processing. This reduces processing errors and deviations caused by image differences, improving the accuracy and reliability of overall processing results. The standardized process automates the processing and analysis of medical images, reducing the need for human intervention and manual adjustments. It improves processing efficiency and speed, reducing processing costs and time. Standardized medical images exhibit greater consistency and comparability, providing a more reliable data foundation for subsequent processing and analysis. This enables more accurate disease diagnosis, condition assessment, and treatment efficacy evaluation, among other clinical applications.

[0108] In one embodiment of the present invention, the operation process of the first edge computing device includes:

[0109] B1. Monitoring operating status parameters of the second edge computing device in real time, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length;

[0110] B2. Obtaining a load index of the current second edge computing device based on the CPU utilization, memory utilization, and processing queue length;

[0111] B3. When the load index of the second edge computing device does not exceed a preset load index threshold, sending the standardized medical image to the second edge computing device;

[0112] B4. When the load index of the second edge computing device exceeds a preset load index threshold, real-time monitoring is performed on a first duration during which the load index of the second edge computing device exceeds the preset load index threshold;

[0113] B5. When the load index of the second edge computing device exceeds a preset load index threshold for a first duration exceeding a preset time length, the first edge computing device automatically starts an initial anomaly detection function and obtains the number of image data processed by the first edge computing device based on the number of standardized medical images to be detected contained in the processing queue length of the second edge computing device and the current load index of the second edge computing device; wherein the number of image data processed is obtained by the following formula:

[0114]

[0115] in,N Indicates the number of image data processed, and N To round up; K represents the load index; K y Indicates the preset load index threshold; m The number of normalized medical images to be detected contained in the processing queue length;

[0116] B6. The first edge computing device retrieves, from the processing queue length of the second edge computing device, a number of standardized medical images to be detected equal to the number of image data to be processed, as target medical images, and performs initial anomaly detection on the target medical images to obtain initial anomaly detection results.

[0117] B7. When the load index of the second edge computing device drops below the preset load index threshold, and the duration of being below the preset load index threshold exceeds the preset second duration, the first edge computing device automatically turns off the initial anomaly detection function.

[0118] The working principle of the above technical solution is as follows: The first edge computing device monitors the operating status parameters of the second edge computing device in real time, including CPU utilization, memory utilization, and processing queue length. Based on these parameters, the second edge computing device calculates its current load index to assess whether its processing capacity is saturated. If the load index of the second edge computing device does not exceed a preset load index threshold, the normalized medical images are directly sent to the second edge computing device for further processing. If the load index exceeds the threshold and persists for a preset period of time, the first edge computing device activates the initial anomaly detection function and processes some medical images independently to reduce the burden on the second edge computing device. Based on parameters such as the load index and processing queue length, the first edge computing device calculates and determines the number of medical images it needs to process (i.e., the number of image data to be processed). It then retrieves the corresponding number of medical images from the processing queue of the second edge computing device for initial anomaly detection to quickly identify possible anomalies. When the load on the second edge computing device drops below the preset threshold and persists for a second preset period of time, the first edge computing device disables the initial anomaly detection function and resumes normal operation.

[0119] The above technical solution ensures stable system operation even under high load conditions through real-time monitoring and load assessment, preventing system crashes or data loss caused by overloading a single device. The initial anomaly detection function promptly identifies and addresses potential issues, reducing the likelihood of system failures. When the second edge computing device is overloaded, the first edge computing device automatically assumes some processing work, enabling dynamic resource allocation and optimized utilization. By calculating the number of image data to be processed, the first edge computing device is ensured to handle additional tasks without significantly impacting its own performance. The initial anomaly detection function quickly identifies and processes critical medical images, improving the system's overall processing efficiency and responsiveness. Once the load on the second edge computing device decreases, the first edge computing device quickly disables the anomaly detection function and resumes normal operations, reducing unnecessary resource consumption. The above technical solution can be flexibly configured and expanded according to actual needs, adapting to application scenarios of varying scale and complexity. By adjusting preset parameters such as load index thresholds and time durations, system performance can be finely controlled and optimized.

[0120] By monitoring the operating parameters of the second edge computing device (CPU utilization, memory utilization, and processing queue length) in real time, the first edge computing device can dynamically assess its load. When the load index does not exceed a preset threshold, tasks (i.e., normalized medical images) are assigned to the second edge computing device for processing. When the load index exceeds the threshold, further measures are taken, such as enabling initial anomaly detection, to reduce the burden on the second edge computing device. If the load on the second edge computing device is excessive and persists for longer than a preset value, the first edge computing device automatically activates initial anomaly detection and calculates the number of images to be processed based on the second edge computing device's processing queue length and the current load index. This approach not only avoids resource waste but also ensures timely processing of critical tasks (such as anomaly detection). Based on the calculated number of image data to be processed, the first edge computing device retrieves the corresponding number of images to be detected from the second edge computing device's processing queue for initial anomaly detection. This flexible task allocation optimizes the overall processing flow and improves processing efficiency.

[0121] When the load index of the second edge computing device drops below a preset threshold and lasts for more than a preset second duration, the first edge computing device can automatically turn off the initial anomaly detection function. The above-mentioned automatic recovery mechanism can quickly restore the system to a normal state and avoid unnecessary resource consumption. Through the above-mentioned dynamic adjustment mechanism, the above-mentioned technical solution can ensure that the system can still operate stably under high load conditions, avoiding system crashes or performance degradation caused by excessive load. At the same time, through the initial anomaly detection function, potential abnormal problems can also be discovered and handled in a timely manner, thereby improving the reliability of the system. For users using the system, dynamic load balancing and efficient resource utilization mean faster processing speeds and more stable system performance. It can further enhance user satisfaction and trust in the system.

[0122] In summary, the above technical solution effectively improves system stability, reliability, processing efficiency, and responsiveness through real-time monitoring, load assessment, offload processing, and anomaly detection, while also enhancing system scalability and flexibility. Furthermore, by dynamically monitoring and adjusting the load of edge computing devices, this solution achieves efficient resource utilization and flexible task allocation. This not only improves system stability and reliability but also optimizes the user experience. This technical solution has significant practical value for scenarios requiring complex tasks such as processing large volumes of medical images.

[0123] In one embodiment of the present invention, the process of obtaining the load index is as follows:

[0124] Extracting operating status parameters corresponding to each unit time of the second edge computing device, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length;

[0125] Generate a parameter matrix using the CPU utilization, memory utilization and processing queue length included in the operating status parameters corresponding to each unit time A ; Wherein, the parameter matrix A The structure is as follows:

[0126]

[0127] in, A represents the parameter matrix; a 11 、 a 12 … a n3 Represents the parameter matrix A All the elements included; n Indicates the number of unit times experienced by the second edge computing device;

[0128] Extract the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d ;

[0129] Utilize the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d Obtain the current load index of the second edge computing device;

[0130] The load index is obtained by the following formula:

[0131]

[0132] in, K represents the load index; σ max Represents the parameter matrix corresponding to the current unit time A d The corresponding largest singular number; Represents the parameter matrix corresponding to the current unit time A d The corresponding norm; Represents the parameter matrix corresponding to the current unit time A d Corresponding A d T A d Determinant of a matrix; and The parameter matrix A corresponding to all unit times that the second edge computing device has experienced in history L Corresponding median and mean of the determinant of a matrix; The variance of the determinant of the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history; ε Represents the minimum constant, used to prevent the independent variable of the logarithmic function from being 0; x represents the base of the preset logarithmic function, and, x ≥2.

[0133] The working principle of this technical solution is to extract the operating status parameters of the second edge computing device in real time per unit time, including CPU utilization, memory utilization, and processing queue length. These parameters reflect the performance of the device at different points in time. The operating status parameters for each unit time are used to construct a corresponding parameter matrix A. Each row of matrix A represents all parameter values ​​within a unit time. The structure of matrix A allows for subsequent mathematical operations to extract key information.

[0134] Extract and integrate the parameter matrix A corresponding to each unit time unit experienced by the second edge computing device, as well as the parameter matrix A corresponding to the current unit time unit. This provides a comprehensive data foundation for calculating the load index. Using the parameter matrix A corresponding to the current unit time unit and historical data, calculate the load index K using the above formula. The formula involves the maximum singular number and norm of the parameter matrix A, the determinant of the ATA matrix, and the median, mean, and variance of the determinant in the historical data. A minimum constant ε and the logarithmic function base x are introduced to ensure the stability and accuracy of the calculation.

[0135] The above technical solution achieves the following benefits: By comprehensively considering multiple operating status parameters, such as CPU utilization, memory utilization, and processing queue length, as well as historical data, the current load status of the second edge computing device can be more accurately assessed. The load index calculation method takes into account the diversity and dynamic nature of data, improving the accuracy and reliability of the assessment. This technical solution can adjust the load index calculation in real time based on the device's operating status parameters, thereby enabling dynamic monitoring and assessment of device load. This allows the system to promptly respond to load changes and take appropriate measures to optimize resource allocation and avoid overload. By accurately assessing device load, the system can more intelligently allocate tasks and resources, avoiding system crashes or performance degradation caused by overloading a single device. This improves the stability and reliability of the entire system, ensuring that the processing of critical data, such as medical images, is not affected. Furthermore, when the load index exceeds a preset threshold, the system can automatically initiate anomaly detection or task offload mechanisms, shifting some tasks to other devices. This optimizes resource utilization and improves the system's overall processing capacity and efficiency. This technical solution can be flexibly configured and expanded according to actual needs, adapting to application scenarios of varying scale and complexity. By adjusting the parameters and thresholds in the formula, fine control and optimization of system performance can be achieved.

[0136] Furthermore, this technical solution comprehensively reflects the device's operating status by extracting the operating status parameters (CPU utilization, memory utilization, and processing queue length) corresponding to each unit time of the second edge computing device. These parameters are key indicators for assessing device load and enable precise load management. Parameter matrix A is generated using the operating status parameters corresponding to each unit time, providing the data foundation for subsequent load index calculations. Parameter matrix A has a clear structure, making it easy to process and calculate. Furthermore, by extracting parameter matrix A corresponding to each unit time of history and the parameter matrix A corresponding to the current unit time, continuous monitoring and dynamic assessment of the device's operating status are achieved.

[0137] At the same time, the load index K is calculated using the above formula, which comprehensively considers the maximum singular number, norm, and determinant of the ATA matrix of the parameter matrix A corresponding to the current unit time, as well as the median, mean, and variance of the determinant of the parameter matrix corresponding to all unit times that have been experienced in history. The above calculation method takes into account both the current operating status and historical operating data, achieving accurate calculation of the load index. At the same time, a minimum constant ε is introduced into the formula to prevent the independent variable of the logarithmic function from being 0. This ensures the stability and reliability of the load index calculation and avoids erroneous results caused by calculation anomalies. The base x of the logarithmic function is preset, and x ≥ 2, providing flexible parameter settings for the calculation of the load index. The above setting method can be adjusted according to actual needs to adapt to different application scenarios and load management requirements.

[0138] By accurately calculating the load index, this solution provides robust data support for resource allocation and load balancing. When the load index exceeds a preset threshold, appropriate measures (such as activating backup equipment and optimizing task allocation) can be taken to reduce equipment load and improve overall system performance and stability. This technical solution is not only applicable to the current system environment but can also adapt to future expansion needs through parameter and formula adjustments. This ensures the system remains advanced and competitive, providing strong support for future technological development.

[0139] In summary, the above technical solution achieves precise assessment and management of the load on the second edge computing device through comprehensive operational status monitoring, the construction and utilization of a parameter matrix, the precise calculation of the load index, and flexible parameter settings. This is of great significance for improving system performance, optimizing resource allocation, and enhancing system reliability.

[0140] In one embodiment of the present invention, the process of performing initial anomaly detection by the first edge computing device and the second edge computing device includes:

[0141] C1. Extracting regions from different parts of the heart in the standardized medical image for heart attack warning to obtain a plurality of heart region images corresponding to the different parts of the heart;

[0142] C2. Acquiring feature data corresponding to different parts of each heart from the multiple heart region images, wherein the feature data includes the size and shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves;

[0143] C3. Retrieving standard data corresponding to the size of the ventricles and atria, the shapes of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves;

[0144] C4. Comparing the size, shape, wall thickness, and valve shape of the ventricles and atria contained in the feature data with standard data corresponding to the size, shape, wall thickness, and valve shape of the ventricles and atria, and obtaining a similarity value between the size, shape, wall thickness, and valve shape of the ventricles and atria contained in the feature data and the standard data corresponding to the size, shape, wall thickness, and valve shape of the ventricles and atria;

[0145] C5. Obtain an abnormality index parameter using a similarity value between the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape included in the characteristic data and standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape, wherein the abnormality index parameter is obtained by the following formula:

[0146]

[0147] in, E represents the anomaly index parameter; r Indicates the number of feature data types contained in the feature data; S i Indicates the i The similarity value between the characteristic data and its corresponding standard data; S min and S max Respectively r The minimum and maximum similarity values ​​among the feature data; w min Indicates the weight value of the feature data corresponding to the minimum similarity value; w mx express r The minimum weight among the feature data; w maxIndicates the weight value of the feature data corresponding to the maximum similarity value; w my express r The maximum weight among the feature data;

[0148] C6. Compare the abnormality index parameter with the preset abnormality index threshold. When the abnormality index parameter is lower than the preset abnormality index threshold, it is determined that there is no abnormality; when the abnormality index parameter is not lower than the preset abnormality index threshold, it is determined that there is an abnormality, and an initial abnormality detection warning is performed.

[0149] The technical solution works by precisely extracting different regions of the heart from standardized heart attack warning medical images, generating multiple cardiac region images. This step forms the foundation for subsequent analysis, ensuring accurate capture of the characteristics of each cardiac region. Key feature data is extracted from each cardiac region image, including the size and shape of the ventricles and atria, heart wall thickness, and heart valve shape. These feature data serve as important indicators for assessing heart health.

[0150] Standard data corresponding to the aforementioned feature data is retrieved. This standard data is typically derived from a large number of healthy people's heart images and represents the range of normal heart indicators. The extracted feature data is then compared with the standard data one by one, and the similarity between them is calculated. This step aims to quantify the degree of deviation of various parts of the heart from the normal state.

[0151] The abnormality index parameter is calculated using a specific formula using the similarity between the characteristic data and the standard data, combined with the weight of each characteristic data. This formula comprehensively considers the similarity and weight of multiple characteristic data to comprehensively assess the degree of cardiac abnormality.

[0152] The calculated abnormality index parameter is compared with the preset abnormality index threshold. If the abnormality index is lower than the threshold, the current heart state is determined to be normal and no abnormality exists; if it is higher than the threshold, an abnormality is determined to exist and the initial abnormality detection warning mechanism is triggered.

[0153] The effect of the above technical solution is: through precise region extraction and feature data acquisition, combined with comparison and analysis with standard data, it can more accurately assess the health of the heart and improve the accuracy of heart attack warnings. The above technical solution takes into account the comprehensive evaluation of multiple parts of the heart and multiple feature data, which can more comprehensively reflect the overall condition of the heart and reduce the possibility of missed diagnosis and misdiagnosis. Once an abnormality is detected, the system can immediately trigger the early warning mechanism, providing doctors with timely diagnostic basis and intervention recommendations, and enabling early detection and treatment of heart disease. By automating the initial abnormality detection process, the workload of doctors can be reduced, the utilization efficiency of medical resources can be improved, and more patients can receive effective medical services in a timely manner. The application of the above technical solution has promoted the development of medical image processing and edge computing technologies, providing strong support for the intelligent and precise development of the medical field.

[0154] Furthermore, by precisely extracting regional images of different cardiac regions from standardized medical images and acquiring characteristic data corresponding to each region (such as the size and shape of the ventricles and atria, heart wall thickness, and heart valve shape), this provides a detailed data foundation for subsequent abnormality detection. This precise region extraction and feature data acquisition method improves the accuracy and reliability of abnormality detection. By comparing the extracted feature data with standard data and calculating similarity values, the degree of difference between each cardiac region and its normal state can be intuitively reflected. This comparison method not only identifies potential abnormalities but also provides a basis for quantitative assessment of the degree of abnormality.

[0155] The abnormality index parameter is calculated by comprehensively considering the similarity and weighting of multiple feature data (such as the size and shape of the ventricles and atria, heart wall thickness, and heart valve shape). This comprehensive calculation method provides a more comprehensive and objective reflection of the overall degree of cardiac abnormality, avoiding the biased and misleading nature of single feature data. Flexible abnormality determination is performed based on the comparison of the abnormality index parameter with a preset abnormality index threshold. If the abnormality index parameter is below the threshold, no abnormality is detected; if it is above the threshold, an abnormality is detected, and an initial abnormality detection warning is issued. This determination mechanism ensures both accurate abnormality detection and timely warnings, providing timely and effective support for subsequent abnormality handling.

[0156] The above technical solution enables accurate early warning of heart attacks. Once abnormalities are detected in various parts of the heart, a warning signal is promptly issued, alerting medical staff and patients to take necessary intervention measures. This improves the accuracy and timeliness of heart attack warnings, reducing the risk and harm of heart attacks. Precise abnormality detection and early warning can avoid unnecessary waste of medical resources and excessive testing. Furthermore, patients with abnormalities can receive timely, targeted treatment and management, thereby reducing medical costs and improving efficiency.

[0157] In summary, the above technical solution achieves accurate early warning of heart attacks through precise region extraction, feature data acquisition, standard data comparison, abnormality index parameter calculation, and abnormality determination. This can effectively improve the accuracy and timeliness of heart attack warnings, optimize medical resource allocation, and reduce medical costs, possessing significant practical application value and social significance.

[0158] In one embodiment of the present invention, the central server includes a data receiving module, a data processing module, a risk assessment module, and an early warning module; wherein the signal input end of the data receiving module is the signal input end of the central server; the signal output end of the data receiving module is connected to the signal input end of the data processing module; the signal output end of the data processing module is connected to the signal input end of the risk assessment module; and the signal output end of the risk assessment module is connected to the signal input end of the early warning module;

[0159] The data receiving module is configured to receive, in real time, the standardized medical image for heart attack warning that does not meet the initial warning requirements when the standardized medical image for heart attack warning does not meet the initial warning requirements;

[0160] The data processing module is configured to perform data preprocessing on the standardized medical image for heart attack warning that does not meet the initial warning requirements to obtain a preprocessed medical image; wherein the data preprocessing includes noise reduction and data cleaning;

[0161] The risk assessment module is used to perform a heart attack risk assessment based on the preprocessed medical image to obtain a risk assessment result;

[0162] The early warning module is used to issue a heart attack warning when the risk assessment result indicates that there is a risk of heart attack.

[0163] The working principle of the above technical solution is as follows: When a standardized medical image used for heart attack warning does not meet the initial warning requirements, the image is sent in real time to the data receiving module of the central server. The data receiving module serves as the signal input terminal of the central server and is responsible for receiving image data that does not meet the initial conditions. The received image data is then transmitted to the data processing module for preprocessing. This preprocessing process includes noise reduction and data cleaning, aiming to improve image quality and remove noise and irrelevant information, so that the subsequent risk assessment module can perform more accurate analysis. The preprocessed medical image is then sent to the risk assessment module. This module uses advanced algorithms and models to conduct in-depth image analysis to assess the patient's heart attack risk. This process may involve image recognition, feature extraction, and machine learning technologies to identify abnormal image features associated with heart attack. Based on the output of the risk assessment module, the warning module determines whether the patient is at risk of heart attack. If the assessment indicates a risk, the warning module immediately triggers a warning mechanism, alerting doctors or relevant medical personnel so that they can take timely intervention measures.

[0164] The effect of this technical solution is that by preprocessing and in-depth analysis of medical images that do not meet initial warning requirements, it can more accurately assess a patient's heart attack risk, reduce false positives and missed alerts, and improve the accuracy of warnings. The system can receive and process medical image data in real time, ensuring that abnormalities are detected promptly before a heart attack occurs, buying doctors valuable time for treatment. The entire warning process is highly automated, reducing the need for manual intervention and improving work efficiency and accuracy. Doctors can focus more on patient treatment and care without spending a lot of time manually analyzing image data. Warning results can provide doctors with important clinical decision-making basis, helping them better assess patients' conditions and develop personalized treatment plans. The implementation of this technical solution has promoted the application and development of medical image processing and artificial intelligence technologies in the field of heart disease warning, providing strong support for intelligent and precise medical care.

[0165] In one embodiment of the present invention, the process of the risk assessment module performing heart attack risk assessment based on the preprocessed medical image includes:

[0166] S1. If the initial warning requirements are not met, retrieve the pre-processed medical image corresponding to the non-compliance with the initial warning requirements;

[0167] S2. Retrieving a standardized medical image for heart attack warning from the patient's historical records corresponding to the pre-processed medical image that does not meet the initial warning requirements;

[0168] S3. Sorting the medical images according to the acquisition time of the standardized medical images for heart attack warning in the patient's historical records to generate a medical image set;

[0169] S4. Perform heart attack risk assessment using the abnormality index parameters of every two adjacent medical images in the medical image set.

[0170] The step of using the abnormality index parameters of every two adjacent medical images in the medical image set to perform a heart attack risk assessment includes:

[0171] S401, extracting abnormality index parameters of every two adjacent medical images in the medical image set;

[0172] S402: Compare the abnormality index parameters of each two adjacent medical images to obtain abnormality index parameter differences, and extract from the abnormality index parameter differences the abnormality index parameter differences corresponding to the abnormality index parameter of the earlier medical image being lower than the abnormality index parameter of the later medical image;

[0173] S403, comparing the abnormality index parameter difference corresponding to each abnormality index parameter of the preceding medical image being lower than the abnormality index parameter of the subsequent medical image with a preset difference threshold;

[0174] S404: When the abnormality index parameter of the earlier medical image is lower than the abnormality index parameter of the later medical image, and the corresponding abnormality index parameter difference exceeds a preset difference threshold, the earlier medical image and the later medical image corresponding to the abnormality index parameter difference exceeding the preset difference threshold are marked as a target abnormal image group;

[0175] S405, retrieving similarity values ​​of the sizes of the ventricles and atria, the shapes of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images preceding and following the target abnormal image group;

[0176] S406. Obtain a risk determination value using the similarity values ​​of the sizes of the ventricles and atria, the shapes of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images preceding and following the target abnormal image groups. The risk determination value is obtained using the following formula:

[0177]

[0178] in, Y Indicates the risk assessment value; x represents the base of the preset logarithmic function, and, x ≥2; βrepresents a positive offset, and the positive offset has a value range of 0.28-3.63; k Indicates the number of target abnormal image groups; t j Indicates the j The time interval between the subsequent medical images in the target abnormal image group and the current moment T time difference; Q represents the similarity parameter corresponding to all target abnormal image groups, and the similarity parameter is obtained by the following formula:

[0179]

[0180] in, Q Represents the similarity parameter corresponding to all target abnormal image groups; k Indicates the number of target abnormal image groups; r j Indicates the j The number of feature data types contained in the feature data of a target abnormal image group; S hi and S xi Indicates the j The first medical image and the second medical image corresponding to the target abnormal image group i The similarity value between the feature data and its standard data; E hj and E xj Indicates the j Abnormal index parameters corresponding to the medical image before and the medical image after of the target abnormal image group;

[0181] S407: When the risk determination value exceeds a preset risk determination threshold, it is determined that there is a risk of a heart attack, and a heart attack warning is issued.

[0182] The working principle of the above technical solution is as follows: if the initial warning requirements are not met, the corresponding pre-processed medical images are first retrieved. Then, all standardized medical images used for heart attack warning in the patient's history are retrieved and sorted by acquisition time to generate an ordered set of medical images.

[0183] Anomaly index parameters are extracted from every two adjacent medical images in the medical image collection. The anomaly index parameters of these adjacent images are compared to identify instances where the anomaly index parameter of the earlier medical image is lower than that of the later medical image. The difference between these two parameters is then calculated. This difference is then compared with a preset difference threshold to identify target abnormal image groups with significantly increased anomaly indices.

[0184] For each target abnormal image group, similarity values ​​for the size, shape, heart wall thickness, and heart valve shape of the ventricles and atria of the preceding and succeeding medical images are retrieved. Using these similarity values, combined with factors such as time difference and the number of feature data types, a risk assessment value is calculated using a specific formula. This formula accounts for the combined effects of a logarithmic function, a positive offset, time difference, and similarity parameters. The calculated risk assessment value is compared with a preset risk assessment threshold to determine whether there is a risk of heart attack. If the risk assessment value exceeds the preset threshold, the system determines that there is a risk of heart attack and triggers a heart attack warning mechanism.

[0185] The effect of the above technical solution is that by comprehensively considering the changes in abnormal index parameters in a patient's historical medical images and the changes in the similarity of features in various parts of the heart, the above technical solution can more accurately assess the risk of heart attack. By monitoring and analyzing medical image data in real time, the above technical solution can promptly detect abnormalities before a heart attack occurs, providing doctors with early warnings and thus buying more time for treatment. The above technical solution performs risk assessment based on the patient's historical medical image data, which can reflect the patient's individual characteristics and changes in condition, and realize personalized assessment. The entire risk assessment process is highly automated, reducing the need for human intervention and improving work efficiency. At the same time, by processing large amounts of medical image data through computer algorithms, assessment results can be obtained more quickly. The risk assessment results can provide doctors with important clinical decision-making basis, helping them to better assess the patient's condition and develop personalized treatment plans.

[0186] On the other hand, by extracting the abnormality index parameters of each adjacent medical image in a medical image set and comparing their differences, the changing trends of cardiac abnormalities can be precisely monitored. This method helps detect subtle changes in cardiac conditions, enabling timely intervention. By focusing on instances where the abnormality index parameters of earlier medical images are lower than those of later images, indicating a worsening abnormality trend, this method identifies target abnormal image groups. This method can screen for images of genuine concern, reducing unnecessary analysis. Furthermore, a complex mathematical formula is used to calculate a risk assessment value using the similarity values ​​of the size and shape of the ventricles and atria, heart wall thickness, and heart valve shape in the medical images included in the target abnormal image group, as well as time factors. This method comprehensively considers multiple factors, including the changing trend of cardiac abnormalities, the severity of the abnormality, and time urgency, to more accurately assess the risk of heart attack. Parameters in the above formula, such as the logarithmic function base x and the positive offset β, can be adjusted to suit different application scenarios and risk assessment requirements. This flexibility enables the above technical solution to be more widely applied in various heart attack risk assessment scenarios.

[0187] At the same time, when the risk assessment value exceeds the preset risk assessment threshold, the system can automatically determine the risk of a heart attack and issue an early warning. This timely early warning mechanism helps medical staff and patients take necessary intervention measures in a timely manner to reduce the risk and harm of a heart attack. By carefully monitoring abnormal changes and identifying targeted abnormal image groups, combined with a comprehensive risk assessment method, this technical solution can significantly improve the accuracy and efficiency of heart attack diagnosis. This helps reduce misdiagnoses and missed diagnoses, improving medical quality and patient satisfaction. Through precise risk assessment, this technical solution can screen patients and medical images that truly require attention, thereby optimizing the allocation of medical resources. This helps avoid unnecessary waste of medical resources and improves the efficiency and quality of medical services.

[0188] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications of the present invention fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A heart attack warning system based on image recognition, characterized in that: The image recognition-based heart attack warning system includes an image acquisition and processing system, a data transmission device, a central server, and a user terminal; wherein the image acquisition and processing system is data-connected to the central server via the data transmission device; and the central server is data-connected to the user terminal via the data transmission device. The image acquisition and processing system is used to acquire medical images, perform image processing and initial anomaly detection on the medical images at the edge, obtain initial anomaly detection results, and issue an initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements; The data transmission device is used to establish a data connection and perform data transmission between the image acquisition and processing system and the central server, and between the central server and the user terminal; The central server is used to perform data processing and risk assessment on the initial anomaly detection results that do not meet the initial warning requirements and obtain risk assessment results; The user terminal is configured to receive the risk assessment results sent by the central server in real time and to visually display the risk assessment results; The image acquisition and processing system includes a plurality of medical image acquisition devices, an image standard processing module, a first edge computing device and a second edge computing device; The operation process of the first edge computing device includes: monitoring operating status parameters of the second edge computing device in real time, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length; Obtaining a load index of the current second edge computing device according to the CPU utilization, memory utilization, and processing queue length; When the load index of the second edge computing device does not exceed a preset load index threshold, sending the standardized medical image to the second edge computing device; When the load index of the second edge computing device exceeds a preset load index threshold, real-time monitoring is performed on a first duration during which the load index of the second edge computing device exceeds the preset load index threshold; When the load index of the second edge computing device exceeds a preset load index threshold for a first duration exceeding a preset time length, the first edge computing device automatically starts an initial anomaly detection function and obtains the number of image data processed by the first edge computing device based on the number of standardized medical images to be detected contained in the processing queue length of the second edge computing device and the current load index of the second edge computing device; wherein the number of image data processed is obtained by the following formula: in, N Indicates the number of image data processed, and N To round up; K represents the load index; K y Indicates the preset load index threshold; m The number of normalized medical images to be detected contained in the processing queue length; The first edge computing device retrieves, from a processing queue length of the second edge computing device according to the number of processed image data, a number of standardized medical images to be detected that is equal to the number of processed image data, as target medical images, and performs initial anomaly detection on the target medical images to obtain initial anomaly detection results; When the load index of the second edge computing device drops below a preset load index threshold, and the duration of being below the preset load index threshold exceeds a preset second duration, the first edge computing device automatically turns off the initial anomaly detection function.

2. The heart attack warning system based on image recognition according to claim 1, characterized in that: The data signal output end of the medical image acquisition device is connected to the signal input end of the image standard processing module; the signal output end of the image standard processing module is connected to the data signal input end of the first edge computing device; the signal output end of the first edge computing device is connected to the signal input end of the second edge computing device; the signal output end of the second edge computing device is the signal output end of the image acquisition and processing system.

3. The heart attack warning system based on image recognition according to claim 2, characterized in that: The medical image acquisition device is used to acquire cardiac medical images, obtain medical images for heart attack warning, and input the medical images for heart attack warning into the image standard processing module; The image standard processing module is configured to perform standardization processing on medical images acquired by multiple medical image acquisition devices, acquire standardized medical images, and send the standardized medical images to the first edge computing device; The first edge computing device is configured to monitor the operating status of the second edge computing device in real time, and determine whether to send the standardized medical image to the second edge computing device based on the operating status of the second edge computing device; and, when a load on the second edge computing device exceeds a preset load requirement, activate its own initial anomaly detection function to perform initial anomaly detection on the standardized medical image for heart attack warning simultaneously with the second edge computing device; The second edge computing device is used to perform initial anomaly detection on the standardized medical images used for heart attack warning, and to perform initial anomaly detection warning when the initial anomaly detection results meet the initial warning requirements.

4. The heart attack warning system based on image recognition according to claim 2 or 3, characterized in that: The image standardization processing process of the image standard processing module includes: receiving, in real time, raw medical image data acquired by the plurality of medical image acquisition devices, and performing noise reduction processing on the raw medical image data to obtain raw medical image data after noise reduction processing; Performing data image cropping and correction processing on the original medical image after the noise reduction processing according to preset image requirement information to obtain a medical image after cropping and correction processing; Performing initial normalization adjustment on the cropped and corrected medical image according to a preset resolution and size to obtain an initially normalized medical image; A secondary normalization adjustment is performed on the initially normalized medical image according to preset image contrast and brightness to obtain a normalized medical image.

5. The heart attack warning system based on image recognition according to claim 1, characterized in that: The process of obtaining the load index is as follows: Extracting operating status parameters corresponding to each unit time of the second edge computing device, wherein the operating status parameters include CPU utilization, memory utilization, and processing queue length; Generate a parameter matrix using the CPU utilization, memory utilization and processing queue length included in the operating status parameters corresponding to each unit time A ; Wherein, the parameter matrix A The structure is as follows: in, A represents the parameter matrix; a 11 、 a 12 … a n3 Represents the parameter matrix A All the elements included; n Indicates the number of unit times experienced by the second edge computing device; Extract the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d ; Utilize the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history A L The parameter matrix corresponding to the current unit time A d Obtain the current load index of the second edge computing device; The load index is obtained by the following formula: in, K represents the load index; σ max Represents the parameter matrix corresponding to the current unit time A d The corresponding largest singular number; Represents the parameter matrix corresponding to the current unit time A d The corresponding norm; Represents the parameter matrix corresponding to the current unit time A d Corresponding A d T A d Determinant of a matrix; and The parameter matrix A corresponding to all unit times that the second edge computing device has experienced in history L Corresponding median and mean of the determinant of a matrix; The variance of the determinant of the parameter matrix corresponding to all unit times that the second edge computing device has experienced in history; ε Represents the minimum constant, used to prevent the independent variable of the logarithmic function from being 0; x represents the base of the preset logarithmic function, and, x ≥2.

6. The heart attack warning system based on image recognition according to claim 2, characterized in that: The process of performing initial anomaly detection by the first edge computing device and the second edge computing device includes: Extracting regions from different parts of the heart in the standardized medical image used for heart attack warning to obtain a plurality of heart region images corresponding to the different parts of the heart; Acquiring characteristic data corresponding to different parts of each heart from the multiple heart region images, wherein the characteristic data includes the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves; Retrieving standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves; comparing the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the feature data with standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape, and obtaining a similarity value between the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the feature data and the standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape; An abnormality index parameter is obtained by using a similarity value between the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape contained in the characteristic data and the standard data corresponding to the size of the ventricles and atria, the shape of the ventricles and atria, the heart wall thickness, and the heart valve shape, wherein the abnormality index parameter is obtained by the following formula: in, E represents the anomaly index parameter; r Indicates the number of feature data types contained in the feature data; S i Indicates the i The similarity value between the feature data and its corresponding standard data; S min and S max Respectively r The minimum and maximum similarity values ​​among the feature data; w min Indicates the weight value of the feature data corresponding to the minimum similarity value; w mx express r The minimum weight among the feature data; w max Indicates the weight value of the feature data corresponding to the maximum similarity value; w my express r The maximum weight among the feature data; The abnormality index parameter is compared with the preset abnormality index threshold. When the abnormality index parameter is lower than the preset abnormality index threshold, it is determined that there is no abnormality; when the abnormality index parameter is not lower than the preset abnormality index threshold, it is determined that there is an abnormality, and an initial abnormality detection warning is performed.

7. The heart attack warning system based on image recognition according to claim 1, characterized in that: The central server includes a data receiving module, a data processing module, a risk assessment module and an early warning module; wherein the signal input end of the data receiving module is the signal input end of the central server; the signal output end of the data receiving module is connected to the signal input end of the data processing module; the signal output end of the data processing module is connected to the signal input end of the risk assessment module; the signal output end of the risk assessment module is connected to the signal input end of the early warning module; The data receiving module is configured to receive, in real time, the standardized medical image for heart attack warning that does not meet the initial warning requirements when the standardized medical image for heart attack warning does not meet the initial warning requirements; The data processing module is configured to perform data preprocessing on the standardized medical image for heart attack warning that does not meet the initial warning requirements to obtain a preprocessed medical image; wherein the data preprocessing includes noise reduction and data cleaning; The risk assessment module is used to perform a heart attack risk assessment based on the preprocessed medical image to obtain a risk assessment result; The early warning module is used to issue a heart attack warning when the risk assessment result indicates that there is a risk of heart attack.

8. The heart attack warning system based on image recognition according to claim 7, characterized in that: The process of the risk assessment module performing heart attack risk assessment based on the preprocessed medical image includes: If the initial warning requirements are not met, retrieve the pre-processed medical images corresponding to the non-compliance with the initial warning requirements; Retrieving a standardized medical image for heart attack warning from the patient's historical record corresponding to the pre-processed medical image that does not meet the initial warning requirements; sorting the medical images according to the acquisition time of the standardized medical images for heart attack warning in the patient's historical records to generate a medical image set; Heart attack risk assessment is performed using abnormality index parameters of every two adjacent medical images in the medical image set.

9. The heart attack warning system based on image recognition according to claim 8, characterized in that: Using the abnormality index parameters of every two adjacent medical images in the medical image set to perform heart attack risk assessment includes: extracting abnormality index parameters of every two adjacent medical images in the medical image set; Comparing the abnormality index parameters of each two adjacent medical images to obtain abnormality index parameter differences, and extracting, from the abnormality index parameter differences, the abnormality index parameter differences corresponding to the abnormality index parameter of the preceding medical image being lower than the abnormality index parameter of the following medical image; Compare the abnormal index parameter difference corresponding to each abnormal index parameter of the previous medical image being lower than the abnormal index parameter of the subsequent medical image with a preset difference threshold; When the abnormal index parameter of the earlier medical image is lower than the abnormal index parameter of the later medical image, and the abnormal index parameter difference corresponding to the abnormal index parameter exceeds a preset difference threshold, the earlier medical image and the later medical image corresponding to the abnormal index parameter difference exceeding the preset difference threshold are marked as a target abnormal image group; Retrieving similarity values ​​of the sizes of the ventricles and atria, the shapes of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images preceding and following the target abnormal image group; The risk determination value is obtained by using the similarity values ​​of the size of the ventricles and atria, the shape of the ventricles and atria, the thickness of the heart wall, and the shape of the heart valves of the medical images before and after the medical images included in all target abnormal image groups; wherein the risk determination value is obtained by the following formula: in, Y Indicates the risk assessment value; x represents the base of the preset logarithmic function, and, x ≥2; β represents a positive offset, and the positive offset has a value range of 0.28-3.63; k Indicates the number of target abnormal image groups; t j Indicates the j The time interval between the subsequent medical images in the target abnormal image group and the current moment T time difference; Q represents the similarity parameter corresponding to all target abnormal image groups, and the similarity parameter is obtained by the following formula: in, Q Represents the similarity parameter corresponding to all target abnormal image groups; k Indicates the number of target abnormal image groups; r j Indicates the j The number of feature data types contained in the feature data of a target abnormal image group; S hi and S xi Indicates the j The first medical image and the second medical image corresponding to the target abnormal image group i The similarity value between the feature data and its standard data; E hj and E xj Indicates the j Abnormal index parameters corresponding to the medical image before and the medical image after of the target abnormal image group; When the risk determination value exceeds a preset risk determination threshold, it is determined that there is a risk of heart attack, and a heart attack warning is issued.

Images