Ultrasonic equipment parameter monitoring and adjusting method and system based on big data

Abstract

The invention relates to the technical field of data processing, in particular to an ultrasonic equipment parameter monitoring and adjusting method and system based on big data. An ultrasonic equipment parameter monitoring and adjusting method based on big data comprises the following steps: S1, acquiring related image data of a child, and respectively acquiring an activity level index and an emotion index of the child by using a behavior recognition model and an emotion recognition model according to the related image data; and S2, according to the activity level index and the emotion index of the child, obtaining an electrocardiogram gating system frequency by using an electrocardiogram frequency adjustment formula, and screening and storing the left ventricle image based on the electrocardiogram gating system frequency. According to the method, accurate functional analysis is performed on the left ventricle by using the AFI technology, and the strain time curve and the bull eye diagram of each section of the heart are generated, so that personalized evaluation and treatment are realized, and a treatment scheme is adjusted in real time by using a final scoring formula according to the heart function change of children.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method and system for monitoring and adjusting ultrasonic device parameters based on big data. Background Art

[0002] With the continuous development of medical imaging technology, ultrasound, as a non-invasive and non-radiative examination method, is widely used in the early diagnosis, functional evaluation and treatment monitoring of heart diseases. Traditional heart monitoring usually relies on STI technology. STI technology has been applied clinically for more than a decade, and the technology is relatively mature and stable. However, its research is mainly applied to adult diseases, and the threshold values of the obtained parameters are also formulated for adults. At present, there is no threshold standard for children. Automatic Functional Imaging (AFI) is a clinical application software designed and developed by GE Company based on the principle of two-dimensional speckle tracking. The latest GE's iE33 color Doppler ultrasound diagnostic system based on the spatial pixel imaging platform can provide high-definition two-dimensional images, and the image frame rate can reach 100 FPS. At the same time, it improves the analysis ability of the speckle tracking technology and can be conveniently used to analyze high-frame-rate stress echocardiogram images. Therefore, how to use AFI technology to analyze the heart function of children and provide personalized and high-precision heart health monitoring has become a technical problem to be solved urgently in the current medical imaging field. Summary of the Invention

[0003] In order to overcome the shortcomings that the AFI technology lacks parameter threshold standards for children and personalized monitoring and evaluation, the present invention provides a method and system for monitoring and adjusting ultrasonic device parameters based on big data.

[0004] The technical solution of the present invention is as follows: A method for monitoring and adjusting ultrasonic device parameters based on big data, comprising the following steps: S1: Obtain relevant image data of a child, and respectively obtain the activity level index and emotion index of the child by using a behavior recognition model and an emotion recognition model according to the relevant image data; S2: According to the activity level index and emotion index of the child, obtain the electrocardiogram gating system frequency by using an electrocardiogram frequency adjustment formula, and screen and store the left ventricular images based on the electrocardiogram gating system frequency; S3: Use AFI technology to obtain heart function parameters, divide the left ventricular myocardium, and generate strain time curves and color-coded bull's-eye diagrams of each myocardial segment according to the heart function parameters; S4: Obtain key parameters by using an ROC curve according to the heart function parameters, obtain the heart function decline threshold by comparing the key parameters with the reexamination results after myocardial nutrition treatment or drug withdrawal, and obtain the boundary value of the heart function parameters according to the heart function decline threshold; S5: Obtain the cardiac function parameters of the target child, obtain the final score of the target child according to the cardiac function parameters of the target child and the boundary values of the cardiac function parameters, and monitor and adjust the treatment of the target child according to the final score of the target child.

[0005] Preferably, the obtaining of the relevant image data of the child and the use of the behavior recognition model and the emotion recognition model according to the relevant image data to respectively obtain the activity level index and the emotion index of the child include: obtaining the relevant image data of the child, where the relevant image data includes the activity image sequence and the facial image sequence of the child, inputting the activity image sequence into the trained behavior recognition model to obtain the activity level index of the child; inputting the facial image sequence into the trained emotion recognition model to obtain the emotion index of the child, where the behavior recognition model and the emotion recognition model are trained using the CNN model.

[0006] Preferably, the obtaining of the electrocardiogram gating system frequency using the electrocardiogram frequency adjustment formula according to the activity level index and the emotion index of the child, and the screening and storage of the left ventricular images based on the electrocardiogram gating system frequency include: obtaining the electrocardiogram gating system frequency using the electrocardiogram frequency adjustment formula according to the activity level index and the emotion index of the child, collecting a preset number of full volume images based on the electrocardiogram gating system frequency, and screening and storing the left ventricular images in the full volume images, where the electrocardiogram frequency adjustment formula is: In the formula, is the electrocardiogram gating system frequency; is the reference frequency; is the adjustment parameter; is the activity level index of the child; is the emotion index of the child.

[0007] Preferably, the collecting of a preset number of full volume images based on the electrocardiogram gating system frequency and the screening and storage of the left ventricular images in the full volume images include: collecting and storing the left ventricular images of at least the first preset number of cardiac cycles without stitching intervals; where the full volume image should completely contain the left ventricle and the left ventricular wall, and when the full volume image does not contain a complete left ventricular envelope, re - perform image collection.

[0008] Preferably, the method for obtaining cardiac function parameters using AFI technology, dividing the left ventricular myocardium, and generating strain-time curves and color-coded bull's eye diagrams for each myocardial segment according to the cardiac function parameters includes: determining the cardiac contour by the endocardial three-point positioning method and performing myocardial tracking analysis, obtaining cardiac function parameters using AFI technology, where the cardiac function parameters include left ventricular end-diastolic volume, left ventricular end-systolic volume, left ventricular global area strain, global longitudinal strain, global circumferential strain, and global radial strain data, and using AFI technology to divide the left ventricular myocardium into 17 segments. After tracking each of the 17 segments, strain-time curves and color-coded bull's eye diagrams for each myocardial segment are generated.

[0009] Preferably, obtaining key parameters using the ROC curve according to the cardiac function parameters, obtaining a cardiac function decline threshold by comparing the key parameters with the review results after myocardial nutrition therapy or drug withdrawal, and obtaining a boundary value of cardiac function parameters according to the cardiac function decline threshold includes: after standardizing the obtained cardiac function parameters, calculating the ROC curve to obtain the sensitivity and specificity of the cardiac function parameters, and taking the indicators with sensitivity and specificity greater than their respective preset threshold values as the key parameters for cardiac function evaluation. Comparing the cardiac function parameters with the review results after myocardial nutrition therapy or drug withdrawal to obtain the cardiac function decline threshold; finally, performing a Meta-analysis on the cardiac function parameters and the previous single-center and single-disease data to obtain the boundary value of cardiac function parameters for judging cardiac function impairment; where the single-center data refers to the previously collected research data on cardiac function.

[0010] Preferably, obtaining the cardiac function parameters of the target child, obtaining the final score of the target child according to the cardiac function parameters of the target child and the boundary value of the cardiac function parameters, and monitoring and adjusting the treatment of the target child according to the final score of the target child includes: using a comprehensive score formula according to the cardiac function parameters of the target child to obtain the comprehensive score of the target child; using a final score formula according to the comprehensive score to obtain the final score of the target child, and when the final score of the target child is less than or equal to the preset score threshold, treating the target child. Preferably, using a comprehensive score formula according to the cardiac function parameters of the target child to obtain the comprehensive score of the target child includes: where the comprehensive score formula is: In the formula, is the comprehensive score of the target child; is the weight coefficient; is the left ventricular global area strain of the target child; is the boundary value of the left ventricular global area strain of the target child; is the global longitudinal strain of the target child; is the overall longitudinal strain threshold value for the target child; is the overall circumferential strain of the target child; is the overall circumferential strain threshold value for the target child; is the overall radial strain of the target child; is the overall radial strain of the target child.

[0011] Preferably, using the final scoring formula according to the comprehensive score to obtain the final score of the target child, including: The final scoring formula is: In the formula, is the final score of the target child; is the weight coefficient; is the left ventricular end-diastolic volume of the target child; is the left ventricular end-systolic volume of the target child.

[0012] Preferably, a big data-based ultrasonic device parameter monitoring and adjustment system includes: An image data acquisition module for acquiring relevant image data of a child, where the relevant image data includes an activity image sequence and a facial image sequence; An index acquisition module for using a behavior recognition model and an emotion recognition model according to the relevant image data to respectively obtain the activity level index and emotion index of the child; An electrocardiogram gating system adjustment module for using an electrocardiogram frequency adjustment formula according to the activity level index and emotion index of the child to obtain the electrocardiogram gating system frequency, and screening and storing left ventricular images based on the electrocardiogram gating system frequency; A cardiac function parameter acquisition and analysis module for using AFI technology to acquire cardiac function parameters, dividing the left ventricular myocardium, and generating strain-time curves and color-coded bull's-eye diagrams of each myocardial segment according to the cardiac function parameters; A cardiac function parameter threshold extraction module for using an ROC curve according to the cardiac function parameters to obtain key parameters, comparing the key parameters with the review results after myocardial nutrition treatment or drug withdrawal to obtain the cardiac function decline threshold, and obtaining the cardiac function parameter threshold according to the cardiac function decline threshold; A comprehensive score and final score calculation module for acquiring the cardiac function parameters of the target child, and obtaining the final score of the target child according to the cardiac function parameters of the target child and the cardiac function parameter thresholds; A treatment monitoring and adjustment module for monitoring and adjusting the treatment of the target child according to the final score of the target child.

[0013] The beneficial effects are: 1. The present invention dynamically adjusts the frequency of the electrocardiogram gating system according to the activity level and emotional state of children. By applying the electrocardiogram frequency adjustment formula, it can more effectively capture the dynamic changes of the heart without affecting the quality of the heart image. Especially for children, a special group, the accuracy of heart monitoring has been significantly improved. 2. Through the AFI technology, precise functional analysis of the left ventricle can be carried out, and strain-time curves and bull's-eye diagrams of each segment of the heart can be generated. It can not only more precisely reflect the overall function of the heart, but also conduct zonal analysis on the heart muscles in different regions, thus realizing personalized evaluation and treatment. 3. Using the ROC curve analysis method to extract key heart function parameters and conduct real-time evaluation according to the heart function decline threshold, timely detect changes in heart function, and conduct comparative analysis by combining clinical data with reexamination results to ensure the scientificity and accuracy of the evaluation. In addition, using the comprehensive score and final score formula, according to the changes in the heart function of children, the treatment plan is adjusted in real time to ensure the personalization of treatment and the maximization of the effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flowchart of a method for monitoring and adjusting ultrasonic device parameters based on big data according to the present invention. Figure 2 It is a flowchart of a system for monitoring and adjusting ultrasonic device parameters based on big data according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Embodiment 1: A method for monitoring and adjusting ultrasonic device parameters based on big data, as Figure 1 shown, includes the following steps: S1: Obtain relevant image data of children, and use a behavior recognition model and an emotion recognition model according to the relevant image data to respectively obtain the activity level index and emotion index of children; Obtain relevant image data of children. The relevant image data includes the activity image sequence and facial image sequence of children. Based on the activity image sequence, input it into the trained behavior recognition model to obtain the activity level index of children; input the facial image sequence into the trained emotion recognition model to obtain the emotion index of children, where the behavior recognition model and emotion recognition model are trained using the CNN model.

[0017] It should be noted that the image information about children is collected through a camera. The moving image sequence refers to the image sequence of the physical movement of children; the facial image sequence refers to the image data obtained through facial recognition technology, which reflects the facial expressions and emotional states of children; the behavior recognition model analyzes the moving image sequence of children based on a convolutional neural network to identify the specific activity level of children and obtain an activity level index. The activity level index can reflect the activity of children during the acquisition period, such as the amount of exercise and the amplitude of movements; the emotion recognition model, based on the deep learning algorithm of CNN, analyzes the facial image sequence of children to identify the emotional state of children, such as happy, angry, worried, and thus obtains an emotion index. The emotion index can reflect the fluctuations of children's emotions, usually representing the intensity or change trend of emotions in a digital way; through a large number of labeled children's moving images and facial expression images, the CNN model is trained to automatically identify the activity information and emotional expressions of children in the images.

[0018] S2: According to the activity level index and emotion index of children, use the electrocardiogram frequency adjustment formula to obtain the electrocardiogram gating system frequency, and screen and store the left ventricular images based on the electrocardiogram gating system frequency; According to the activity level index and emotion index of children, use the electrocardiogram frequency adjustment formula to obtain the electrocardiogram gating system frequency, collect a preset number of full-volume images based on the electrocardiogram gating system frequency, and screen and store the left ventricular images in the full-volume images, where the electrocardiogram frequency adjustment formula is: In the formula, is the electrocardiogram gating system frequency; is the reference frequency; is the adjustment parameter; is the activity level index of children; is the emotion index of children.

[0019] It should be noted that the electrocardiogram gating system is a system for synchronizing echocardiogram acquisition. Usually, image acquisition is carried out according to the rhythm of the heart. The working frequency of the system will affect the quality and accuracy of image acquisition. Through the activity level index and emotion index of children, an adjusted electrocardiogram gating frequency is calculated using the electrocardiogram frequency adjustment formula, so as to ensure that the most suitable image data can be obtained under various conditions. Based on the adjusted electrocardiogram gating system frequency, a preset number of full-volume images are acquired and screened and stored. Among them, the full-volume image refers to an image that can cover the complete heart and all parts of the heart, ensuring that the health information of all regions of the heart is acquired, especially the left ventricular image, which is an important image for diagnosing heart function. During the image acquisition process, if the image does not completely contain the left ventricle and its wall surface, the image acquisition needs to be carried out again to ensure the quality and integrity of the obtained data; when the child shows a high activity level or excited emotion, the adjusted electrocardiogram gating frequency becomes higher, and at this time the system will speed up the image acquisition frequency to ensure that clear and accurate heart images can still be obtained under the high activity state of the child; when the child's emotion index is low or in a calm state, the system frequency adjustment slows down, and the acquisition process is more stable, reducing unnecessary image noise.

[0020] Acquire and store left ventricular images of at least the first preset number of cardiac cycles without stitching intervals; among them, the full-volume image should completely contain the left ventricle and the left ventricular wall. When the full-volume image does not contain a complete left ventricular envelope, the image acquisition is carried out again.

[0021] It should be noted that in the process of acquiring the full-volume image in this embodiment, it is ensured that there is no stitching interval in the acquired image in the left ventricular region. The acquired image needs to cover at least three cardiac cycles, and the images of each cycle are completely connected and seamless, avoiding image interruption or data loss.

[0022] S3: Use the AFI technique to obtain cardiac function parameters, divide the left ventricular myocardium, and generate the strain-time curve and color-coded bull's-eye diagram of each myocardial segment according to the cardiac function parameters; Determine the cardiac contour and perform myocardial tracking analysis through the endocardial three-point positioning method, use the AFI technique to obtain cardiac function parameters, the cardiac function parameters include left ventricular end-diastolic volume, left ventricular end-systolic volume, left ventricular global area strain, global longitudinal strain, global circumferential strain and global radial strain data, and use the AFI technique to divide the left ventricular myocardium into seventeen segments. After tracking each of the seventeen segments respectively, generate the strain-time curve and color-coded bull's-eye diagram of each myocardial segment.

[0023] It should be noted that through the AFI technology, the following cardiac function parameters can be obtained: left ventricular end-diastolic volume, left ventricular end-systolic volume, left ventricular global area strain, global longitudinal strain, global circumferential strain, and global radial strain data, which help doctors evaluate the pumping function of the heart and the health status of the myocardium and are key indicators for cardiac function diagnosis; after using the AFI technology, the left ventricular myocardium will be divided into seventeen segments, and each segment will be independently tracked and analyzed. These segments cover different regions of the left ventricle to separately evaluate the myocardial function of each region. The strain-time curve of each segment will be plotted based on the strain data obtained by the AFI technology, reflecting the strain changes of the segment during the entire cardiac cycle; by analyzing the strain-time curve of each segment, the system will generate a color-coded bull's-eye diagram, which shows the strain values of each segment, and usually different colors are used to represent different strain degrees.

[0024] S4: Obtain key parameters using the ROC curve based on the cardiac function parameters, obtain the heart function decline threshold by comparing the key parameters with the reexamination results after myocardial nutrition treatment or drug withdrawal, and obtain the cardiac function parameter boundary value based on the heart function decline threshold; Based on the obtained cardiac function parameters, after standardizing the cardiac function parameters, calculate the ROC curve to obtain the sensitivity and specificity of the cardiac function parameters, and use the indicators with sensitivity and specificity greater than the corresponding preset thresholds as the key parameters for heart function evaluation. Compare the cardiac function parameters with the reexamination results after myocardial nutrition treatment or drug withdrawal to obtain the heart function decline threshold; finally, perform a Meta-analysis on the cardiac function parameters and the previous single-center and single-disease data to obtain the cardiac function parameter boundary value for judging heart function impairment; among them, the single-center data refers to the previously collected research data on cardiac function.

[0025] It should be noted that the ROC curve is a tool for evaluating the performance of a classification model, which can display the sensitivity and specificity of the model at different thresholds. In the present invention, the ROC curve is used to evaluate the effectiveness of cardiac function parameters, so as to select the key parameters crucial for cardiac function assessment. The specific steps are as follows: Standardize the obtained cardiac function parameters, that is, normalize the parameters to make the dimensions of each parameter unified for easy comparison; Calculate the ROC curve based on the standardized cardiac function parameters to obtain the sensitivity (true positive rate) and specificity (false negative rate) of each parameter at different thresholds; Select the key parameters whose sensitivity and specificity are both higher than the preset threshold by comparing the sensitivity and specificity; After screening out the key parameters, compare these key parameters with the reexamination results of children after myocardial nutrition treatment or drug withdrawal to obtain the cardiac function decline threshold, and the cardiac function decline threshold is the standard for judging whether the cardiac function has significantly declined; Finally, use the Meta-analysis method to collect and statistically analyze the data from multiple data sources to obtain the boundary value of cardiac function parameters. Through Meta-analysis, a more accurate boundary value of cardiac function parameters is obtained, so as to provide a standard reference for diagnosis and treatment.

[0026] S5: Obtain the cardiac function parameters of the target child, and based on the cardiac function parameters of the target child and the boundary value of the cardiac function parameters, obtain the final score of the target child, and monitor and adjust the treatment of the target child according to the final score of the target child.

[0027] Use the comprehensive score formula according to the cardiac function parameters of the target child to obtain the comprehensive score of the target child; Use the final score formula according to the comprehensive score to obtain the final score of the target child, and when the final score of the target child is less than or equal to the preset score threshold, treat the target child.

[0028] It should be noted that compare the final score of the target child with the preset score threshold. When the final score of the target child is less than or equal to the preset score threshold, treat the target child, and adjust the treatment plan in a timely manner according to the change of cardiac function for personalized intervention.

[0029] The comprehensive score formula is as follows: In the formula, is the comprehensive score of the target child; is the weight coefficient; is the left ventricular global area strain of the target child; is the boundary value of the left ventricular global area strain of the target child; is the global longitudinal strain of the target child; is the boundary value of the global longitudinal strain of the target child; is the overall circumferential strain of the target child; is the critical value of the overall circumferential strain of the target child; is the overall radial strain of the target child; is the overall radial strain of the target child.

[0030] It should be noted that (left ventricular global area strain) is an important parameter reflecting the overall function of the left ventricle and represents the functional changes of the left ventricle during cardiac contraction; is the critical value of the left ventricular global area strain of the target child, obtained from the critical values of cardiac function parameters after Meta-analysis; (global longitudinal strain) is a parameter describing the longitudinal contraction function of the myocardium; is the critical value of the overall longitudinal strain of the target child, obtained from the critical values of cardiac function parameters after Meta-analysis; (overall circumferential strain) is used to evaluate the systolic ability of the myocardium in the circumferential direction; is the critical value of the overall circumferential strain of the target child, obtained from the critical values of cardiac function parameters after Meta-analysis; (overall radial strain) is an index describing the radial systolic ability of the myocardium; is the overall radial strain of the target child, obtained from the critical values of cardiac function parameters after Meta-analysis.

[0031] Among them, the final scoring formula is: In the formula, is the final score of the target child; is the weight coefficient; is the left ventricular end-diastolic volume of the target child; is the left ventricular end-systolic volume of the target child.

[0032] It should be noted that (left ventricular end-diastolic volume): refers to the volume of the left ventricle at the end of diastole and reflects the filling ability of the heart; (left ventricular end-systolic volume): refers to the volume of the left ventricle at the end of systole and reflects the emptying ability of the heart.

[0033] Embodiment 2: On the basis of Embodiment 1, a big data-based ultrasonic device parameter monitoring and adjustment system includes: An image data acquisition module for obtaining relevant image data of children, where the relevant image data includes an activity image sequence and a facial image sequence; An index acquisition module for respectively obtaining the activity level index and the emotion index of children according to the relevant image data using a behavior recognition model and an emotion recognition model; An electrocardiogram gating system adjustment module, which is used to obtain the electrocardiogram gating system frequency according to the activity level index and emotional index of a child by using an electrocardiogram frequency adjustment formula, and screen and store left ventricular images based on the electrocardiogram gating system frequency; A cardiac function parameter acquisition and analysis module, which is used to acquire cardiac function parameters by using AFI technology, divide the left ventricular myocardium, and generate strain time curves and color-coded bull's-eye diagrams of each myocardial segment according to the cardiac function parameters; A cardiac function parameter threshold extraction module, which is used to obtain key parameters by using an ROC curve according to cardiac function parameters, obtain a cardiac function decline threshold by comparing the key parameters with the review results after myocardial nutrition treatment or after drug withdrawal, and obtain cardiac function parameter thresholds according to the cardiac function decline threshold; A comprehensive score and final score calculation module, which is used to acquire the cardiac function parameters of a target child and obtain the final score of the target child according to the cardiac function parameters of the target child and the cardiac function parameter thresholds; A treatment monitoring and adjustment module, which is used to monitor and adjust the treatment of a target child according to the final score of the target child. The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for monitoring and adjusting ultrasonic equipment parameters based on big data, characterized in that: The following steps are involved: S1: Obtain relevant image data of the child, and use a behavior recognition model and an emotion recognition model according to the relevant image data to respectively obtain an activity level index and an emotion index of the child; S2: according to the activity level index and the emotion index of the child, using the ECG frequency adjustment formula to obtain the ECG gating system frequency, and screening and storing the left ventricle image based on the ECG gating system frequency; S3: using AFI technology to obtain cardiac function parameters, and after dividing the left ventricular myocardium, generating strain time curves and color-coded bull's eye diagrams of each myocardial segment according to the cardiac function parameters; S4: using the ROC curve to obtain key parameters according to the cardiac function parameters, obtaining a threshold value of cardiac function decline according to the comparison between the key parameters and the re-examination results after myocardial nutrition therapy or after drug withdrawal, and obtaining a cardiac function parameter boundary value according to the threshold value of cardiac function decline; S5: Obtain cardiac function parameters of the target child, obtain a final score of the target child based on the cardiac function parameters of the target child and the cardiac function parameter thresholds, and monitor and adjust treatment of the target child based on the final score of the target child.

2. The method for monitoring and adjusting ultrasonic equipment parameters based on big data according to claim 1, characterized in that: The method of obtaining relevant image data of the child, and using a behavior recognition model and an emotion recognition model according to the relevant image data to respectively obtain an activity level index and an emotion index of the child, comprises: obtaining relevant image data of the child, wherein the relevant image data comprises an activity image sequence and a facial image sequence of the child, and inputting the activity image sequence into a trained behavior recognition model to obtain the activity level index of the child; and inputting the facial image sequence into a trained emotion recognition model to obtain the emotion index of the child, wherein the behavior recognition model and the emotion recognition model are trained using a CNN model.

3. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 1, characterized in that: The method of obtaining an electrocardiogram gating system frequency using an electrocardiogram frequency adjustment formula according to the child's activity level index and the child's emotion index, and screening and storing the left ventricle image based on the electrocardiogram gating system frequency includes: obtaining an electrocardiogram gating system frequency using an electrocardiogram frequency adjustment formula according to the child's activity level index and the child's emotion index, acquiring a preset number of full-volume images based on the electrocardiogram gating system frequency, and screening and storing the left ventricle image in the full-volume image, wherein the electrocardiogram frequency adjustment formula is: In the formula, is the ECG gating system frequency; is the reference frequency; To adjust the parameters; is the activity level index for children; Emotional index for children.

4. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 3, characterized in that: The method of acquiring a preset number of full-volume images based on the frequency of the electrocardiogram gating system and screening and storing the left ventricular images in the full-volume images includes: acquiring and storing left ventricular images of at least a first preset number of cardiac cycles without splicing intervals; wherein the full-volume image should completely include the left ventricle and the left ventricular wall, and when the full-volume image does not include the complete left ventricular envelope, re-acquisition of the image.

5. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 1, characterized in that: The method uses AFI technology to obtain cardiac function parameters, and after dividing the left ventricular myocardium, generates a strain time curve and a color-coded bull's eye diagram of each myocardial segment according to the cardiac function parameters, including: determining the cardiac contour through an endocardial three-point positioning method and performing myocardial tracking analysis, using AFI technology to obtain cardiac function parameters, the cardiac function parameters including left ventricular end-diastolic volume, left ventricular end-systolic volume, left ventricular global area strain, global longitudinal strain, global circumferential strain and global radial strain data, and using AFI technology to divide the left ventricular myocardium into seventeen segments, and after tracking the seventeen segments respectively, generating a strain time curve and a color-coded bull's eye diagram of each myocardial segment.

6. The method for monitoring and adjusting ultrasonic equipment parameters based on big data according to claim 1, characterized in that: The method of obtaining key parameters using ROC curves according to cardiac function parameters, obtaining a threshold value for decreased cardiac function by comparing the key parameters with the results of reexamination after myocardial nutritional therapy or after drug withdrawal, and obtaining a cutoff value for cardiac function parameters according to the cutoff value for decreased cardiac function includes: standardizing the cardiac function parameters according to the obtained cardiac function parameters, calculating the ROC curve to obtain the sensitivity and specificity of the cardiac function parameters, and using the indicators with sensitivity and specificity greater than the corresponding preset thresholds as key parameters for cardiac function assessment, comparing the cardiac function parameters with the results of reexamination after myocardial nutritional therapy or after drug withdrawal, and obtaining a threshold value for decreased cardiac function; finally, performing a Meta-analysis on the cardiac function parameters and previous single-center and single-disease data to obtain the cutoff value for cardiac function parameters for judging impaired cardiac function; wherein the single-center data refers to previously collected research data on cardiac function.

7. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 1, characterized in that: The method of obtaining the cardiac function parameters of the target child, obtaining the final score of the target child according to the cardiac function parameters of the target child and the cardiac function parameter thresholds, and monitoring and adjusting the treatment of the target child according to the final score of the target child includes: using a comprehensive scoring formula according to the cardiac function parameters of the target child to obtain the comprehensive score of the target child; using a final scoring formula according to the comprehensive score to obtain the final score of the target child, and treating the target child when the final score of the target child is less than or equal to a preset scoring threshold.

8. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 7, characterized in that: The step of using a comprehensive scoring formula according to the cardiac function parameters of the target child to obtain a comprehensive score for the target child includes: wherein the comprehensive scoring formula is: In the formula, A composite score for the target child; is the weight coefficient; The left ventricular global area strain was the target child; It is the left ventricular global area strain cut-off value for the target children; to target children's overall longitudinal strain; is the global longitudinal strain cutoff value for the target child; The overall circumferential strain for the target child; is the global circumferential strain cutoff value for the target child; The global radial strain for the target child; is the global radial strain of the target child.

9. The method for monitoring and adjusting ultrasonic equipment parameters based on big data as claimed in claim 7, characterized in that: The method of using a final scoring formula according to the comprehensive score to obtain a final score for the target child includes: wherein the final scoring formula is: In the formula, Provide a final score for the target child; is the weight coefficient; The left ventricular end-diastolic volume was the target child; The left ventricular end-systolic volume is the target child.

10. An ultrasonic equipment parameter monitoring and adjustment system based on big data, a method for ultrasonic equipment parameter monitoring and adjustment based on big data as claimed in any one of claims 1 to 9, characterized in that: include: An image data acquisition module is used to obtain relevant image data of children, wherein the relevant image data includes a moving image sequence and a facial image sequence; An index acquisition module, used to obtain the activity level index and the emotion index of the child respectively using a behavior recognition model and an emotion recognition model according to relevant image data; An electrocardiogram gating system adjustment module is used to obtain an electrocardiogram gating system frequency using an electrocardiogram frequency adjustment formula according to the activity level index and the emotion index of the child, and to filter and store the left ventricle image based on the electrocardiogram gating system frequency; A cardiac function parameter acquisition and analysis module, which is used to acquire cardiac function parameters using AFI technology, and to generate strain time curves and color-coded bull's eye diagrams of each myocardial segment according to the cardiac function parameters after dividing the left ventricular myocardium; A cardiac function parameter boundary value extraction module is used to obtain key parameters according to cardiac function parameters using ROC curves, obtain a cardiac function decline threshold value according to the key parameters and the reexamination results after myocardial nutrition therapy or drug withdrawal, and obtain a cardiac function parameter boundary value according to the cardiac function decline threshold value; A comprehensive score and final score calculation module, used to obtain the cardiac function parameters of the target child, and obtain the final score of the target child according to the cardiac function parameters of the target child and the cardiac function parameter thresholds; The treatment monitoring and adjustment module is used to monitor and adjust the treatment of the target child according to the final score of the target child.

Images