Myocardial strain analysis method and device based on multi-dimensional demand

Abstract

The invention discloses a myocardial strain analysis method and device based on a multi-dimensional demand, and relates to the technical field of data intelligent analysis, the method comprises the following steps: obtaining user data corresponding to a to-be-analyzed user, the user data at least comprising user ultrasonic data of the to-be-identified user; determining target demand information based on the multi-dimensional demand information; executing a data analysis operation on the user data based on the target demand information to obtain a data analysis result; inputting the data analysis result into a predetermined data processing model, and executing data processing operation on the data analysis result through the data processing model to obtain target processing data; and analyzing the target processing data to obtain a myocardial strain analysis result corresponding to the to-be-analyzed user. Therefore, by implementing the method, the myocardial strain can be subjected to multi-dimensional analysis to meet multi-dimensional requirements, so that the intelligence and the efficiency of analyzing the myocardial strain can be improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent analysis technology, and in particular to a myocardial strain analysis method and device based on multi-dimensional requirements. Background Art

[0002] Myocardial strain refers to the percentage length change of the local myocardium in a specified direction relative to the stress-free state (end diastole). It can be used to quantitatively describe the diastolic and systolic function of the left ventricle, showing the potential for identifying subclinical left ventricular dysfunction. In recent years, artificial intelligence technology has experienced a leap-forward development, and its application in the medical field has become more and more extensive. However, the current analysis of myocardial strain still relies on manual analysis, which has technical problems such as low intelligence and low efficiency of analysis. It can be seen that it is particularly important to provide a new myocardial strain analysis method to improve the intelligence and efficiency of the analysis. Summary of the invention

[0003] The present invention provides a myocardial strain analysis method and device based on multi-dimensional requirements, which can perform multi-dimensional analysis on myocardial strain to meet multi-dimensional requirements, thereby facilitating improving the intelligence and efficiency of myocardial strain analysis.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a myocardial strain analysis method based on multi-dimensional requirements, the method comprising:

[0005] Acquire user data corresponding to the user to be analyzed, wherein the user data at least includes user ultrasonic data of the user to be identified;

[0006] Determine target demand information based on multi-dimensional demand information;

[0007] Performing a data analysis operation on the user data based on the target demand information to obtain a data analysis result;

[0008] Inputting the data analysis result into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data;

[0009] The target processing data is analyzed to obtain a myocardial strain analysis result corresponding to the user to be analyzed.

[0010] As an optional implementation manner, in the first aspect of the present invention, before performing a data parsing operation on the user data based on the target demand information and obtaining a data parsing result, the method further includes:

[0011] When a data management request is detected, determining user login data corresponding to the data management request, and judging whether the user login data satisfies a preset data management condition;

[0012] When it is determined that the user login data satisfies the preset data management condition, the target case data matching the data management request is determined from the user data, and the data management operation corresponding to the target case data is determined based on the data management request, and an update operation matching the data management operation is performed on the target case data to update the user data, and trigger the execution of the data analysis operation based on the target demand information to perform the data analysis result on the user data.

[0013] As an optional implementation manner, in the first aspect of the present invention, performing a data parsing operation on the user data based on the target demand information to obtain a data parsing result includes:

[0014] Based on the target demand information, target parsing parameters are determined, and a data parsing operation matching the target parsing parameters is performed on the user data to obtain target parsing data;

[0015] Determining a target data format corresponding to the target parsed data, and judging whether the target data format matches a preset reference data format;

[0016] When it is determined that the target data format does not match the preset benchmark data format, the format difference parameters between the target data format and the preset benchmark data format are determined, and based on the format difference parameters, a data conversion operation is performed on the target parsed data to obtain target converted data, and a data parsing result is generated based on all the target converted data.

[0017] As an optional implementation, in the first aspect of the present invention, the step of inputting the data analysis result into a predetermined data processing model so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data includes:

[0018] Inputting the data analysis result into a predetermined myocardial segmentation model, so as to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data;

[0019] The first processed data is input into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and target processed data is generated based on the first processed data and the second processed data.

[0020] As an optional implementation, in the first aspect of the present invention, the data analysis result includes at least a full sequence of ultrasound images corresponding to a target cardiac cycle, and the data analysis result is input into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data, including:

[0021] Inputting the full sequence ultrasound image corresponding to the target cardiac cycle into a predetermined myocardial segmentation model, so as to perform a pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain a pixel classification result, wherein the pixel classification result at least includes a background pixel category and a myocardial pixel category;

[0022] Based on the pixel classification result, first processed data is generated; wherein the first processed data at least includes the target sequence image corresponding to the target cardiac cycle.

[0023] As an optional implementation, in the first aspect of the present invention, the step of inputting the first processed data into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and generating target processed data based on the first processed data and the second processed data, includes:

[0024] Inputting the first processed data into a predetermined optical flow estimation model, so as to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model, to obtain second processed data, wherein the second processed data at least includes an optical flow estimation result corresponding to the target sequence image;

[0025] A computing operation is performed on the first processed data and the second processed data to obtain target processed data.

[0026] As an optional implementation, in the first aspect of the present invention, after the data analysis result is input into a predetermined data processing model to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data, the method further includes:

[0027] Based on the target processed data and predetermined benchmark indicator information, determine the myocardial region data in the target processed data, and calculate the average myocardial strain value corresponding to the target cardiac cycle according to all the determined myocardial region data;

[0028] Visual analysis data is generated according to the average myocardial strain value, and the visual analysis data is output to a predetermined display terminal.

[0029] The second aspect of the present invention discloses a myocardial strain analysis device based on multi-dimensional requirements, the device comprising:

[0030] An acquisition module, used to acquire user data corresponding to the user to be analyzed, wherein the user data at least includes user ultrasonic data of the user to be identified;

[0031] A determination module, used to determine target demand information based on multi-dimensional demand information;

[0032] A parsing module, used to perform a data parsing operation on the user data based on the target demand information to obtain a data parsing result;

[0033] An input module, used for inputting the data analysis result into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data;

[0034] The analysis module is used to analyze the target processing data to obtain the myocardial strain analysis result corresponding to the user to be analyzed.

[0035] As an optional implementation, in the second aspect of the present invention, the determination module is further configured to, before the parsing module performs a data parsing operation on the user data based on the target demand information and obtains a data parsing result, when a data management request is detected, determine the user login data corresponding to the data management request;

[0036] The device also includes:

[0037] A judgment module, used to judge whether the user login data meets the preset data management conditions;

[0038] The determination module is also used to determine the target case data matching the data management request from the user data when the judgment module determines that the user login data satisfies the preset data management condition, and determine the data management operation corresponding to the target case data based on the data management request, and perform an update operation matching the data management operation on the target case data to update the user data, and trigger the parsing module to perform the data parsing operation on the user data based on the target demand information to obtain the data parsing result.

[0039] As an optional implementation, in the second aspect of the present invention, the parsing module performs a data parsing operation on the user data based on the target demand information, and a specific manner of obtaining a data parsing result includes:

[0040] Based on the target demand information, target parsing parameters are determined, and a data parsing operation matching the target parsing parameters is performed on the user data to obtain target parsing data;

[0041] Determining a target data format corresponding to the target parsed data, and judging whether the target data format matches a preset reference data format;

[0042] When it is determined that the target data format does not match the preset benchmark data format, the format difference parameters between the target data format and the preset benchmark data format are determined, and based on the format difference parameters, a data conversion operation is performed on the target parsed data to obtain target converted data, and a data parsing result is generated based on all the target converted data.

[0043] As an optional implementation, in the second aspect of the present invention, the input module inputs the data analysis result into a predetermined data processing model to perform a data processing operation on the data analysis result through the data processing model, and the specific method of obtaining the target processed data includes:

[0044] Inputting the data analysis result into a predetermined myocardial segmentation model, so as to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data;

[0045] The first processed data is input into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and target processed data is generated based on the first processed data and the second processed data.

[0046] As an optional implementation, in the second aspect of the present invention, the data analysis result at least includes a full sequence of ultrasound images corresponding to a target cardiac cycle, and the input module inputs the data analysis result into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model. The specific method of obtaining the first processed data includes:

[0047] Inputting the full sequence ultrasound image corresponding to the target cardiac cycle into a predetermined myocardial segmentation model, so as to perform a pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain a pixel classification result, wherein the pixel classification result at least includes a background pixel category and a myocardial pixel category;

[0048] Based on the pixel classification result, first processed data is generated; wherein the first processed data at least includes the target sequence image corresponding to the target cardiac cycle.

[0049] As an optional implementation, in the second aspect of the present invention, the input module inputs the first processed data into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and based on the first processed data and the second processed data, generates target processed data in a specific manner including:

[0050] Inputting the first processed data into a predetermined optical flow estimation model, so as to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model, to obtain second processed data, wherein the second processed data at least includes an optical flow estimation result corresponding to the target sequence image;

[0051] A computing operation is performed on the first processed data and the second processed data to obtain target processed data.

[0052] As an optional embodiment, in the second aspect of the present invention, the determination module is further used to input the data analysis result into a predetermined data processing model in the input module, so as to perform a data processing operation on the data analysis result through the data processing model, and after obtaining the target processed data, determine the myocardial region data in the target processed data based on the target processed data and predetermined benchmark indicator information, and calculate the average myocardial strain value corresponding to the target cardiac cycle according to all the determined myocardial region data;

[0053] The device also includes:

[0054] A generating module is used to generate visual analysis data according to the average myocardial strain value, and output the visual analysis data to a predetermined display terminal.

[0055] The third aspect of the present invention discloses another myocardial strain analysis device based on multi-dimensional requirements, the device comprising:

[0056] A memory storing executable program code;

[0057] a processor coupled to the memory;

[0058] The processor calls the executable program code stored in the memory to execute the myocardial strain analysis method based on multi-dimensional requirements disclosed in the first aspect of the present invention.

[0059] A fourth aspect of the present invention discloses a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the myocardial strain analysis method based on multi-dimensional requirements disclosed in the first aspect of the present invention.

[0060] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0061] In an embodiment of the present invention, user data corresponding to the user to be analyzed is obtained, wherein the user data at least includes the user ultrasound data of the user to be identified; based on the multi-dimensional demand information, the target demand information is determined; based on the target demand information, a data analysis operation is performed on the user data to obtain a data analysis result; the data analysis result is input into a predetermined data processing model to perform a data processing operation on the data analysis result through the data processing model to obtain target processing data; the target processing data is analyzed to obtain a myocardial strain analysis result corresponding to the user to be analyzed. It can be seen that the implementation of the present invention can perform multi-dimensional analysis on myocardial strain to meet multi-dimensional requirements, thereby facilitating the improvement of the intelligence and efficiency of myocardial strain analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0063] Figure 1 It is a flow chart of a myocardial strain analysis method based on multi-dimensional requirements disclosed in an embodiment of the present invention;

[0064] Figure 2 It is a flow chart of another myocardial strain analysis method based on multi-dimensional requirements disclosed in an embodiment of the present invention;

[0065] Figure 3 It is a structural schematic diagram of a myocardial strain analysis device based on multi-dimensional requirements disclosed in an embodiment of the present invention;

[0066] Figure 4 It is a structural schematic diagram of another myocardial strain analysis device based on multi-dimensional requirements disclosed in an embodiment of the present invention;

[0067] Figure 5 It is a structural schematic diagram of another myocardial strain analysis device based on multi-dimensional requirements disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0069] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0070] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0071] The present invention discloses a myocardial strain analysis method and device based on multi-dimensional requirements, which can perform multi-dimensional analysis on myocardial strain to meet multi-dimensional requirements, thereby facilitating the improvement of the intelligence and efficiency of myocardial strain analysis. The following are detailed descriptions.

[0072] Embodiment 1

[0073] See also Figure 1 , Figure 1 : is a flow chart of a myocardial strain analysis method based on multi-dimensional requirements disclosed in an embodiment of the present invention. Figure 1 The described myocardial strain analysis method based on multi-dimensional requirements can be applied to a myocardial strain analysis device based on multi-dimensional requirements, wherein the myocardial strain analysis device based on multi-dimensional requirements can be integrated in a cloud server or a local server, and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the myocardial strain analysis method based on multi-dimensional requirements may include the following operations:

[0074] 101. Obtain user data corresponding to the user to be analyzed.

[0075] In the embodiment of the present invention, the user data at least includes user ultrasonic data of the user to be identified.

[0076] In the embodiment of the present invention, optionally, the user data corresponding to the user to be analyzed may be obtained in real time, may be obtained periodically according to a preset time period, or may be obtained when the myocardial strain of the user to be analyzed needs to be analyzed, which is not specifically limited in the embodiment of the present invention.

[0077] In an embodiment of the present invention, optionally, the user data corresponding to the user to be analyzed may also include one or more of user attribute data and user case data; the user ultrasound data includes ultrasound image data of the user to be analyzed; wherein the ultrasound image data includes cardiac ultrasound image data of the user to be analyzed.

[0078] 102. Determine target demand information based on multi-dimensional demand information.

[0079] In the embodiment of the present invention, the multi-dimensional demand information may optionally include one or more of analysis speed demand information, analysis type demand information, and analysis duration demand information. Further, the multi-dimensional demand information may also optionally include one or more of voice demand information, image demand information, and video demand information, which is not specifically limited in the embodiment of the present invention.

[0080] In the embodiment of the present invention, optionally, the target demand information may include demand information corresponding to all dimensions in the multi-dimensional demand information. Further optionally, the target demand information may include demand information with a higher demand coefficient in the multi-dimensional demand information.

[0081] 103. Perform data analysis operations on user data based on target demand information to obtain data analysis results.

[0082] In the embodiment of the present invention, optionally, the data analysis operation may include one or more of a data clearing operation, a data conversion operation, a data integration operation, a data aggregation operation, and a data mining operation.

[0083] 104. Input the data analysis result into a predetermined data processing model, so as to perform data processing operations on the data analysis result through the data processing model to obtain target processed data.

[0084] In the embodiment of the present invention, optionally, the data processing model may include a myocardial segmentation model and an optical flow estimation model.

[0085] The myocardial segmentation model is used to classify pixels of the full sequence of ultrasound images in a complete cardiac cycle to assist in the localization of myocardial regions;

[0086] The optical flow estimation model is used to perform optical flow estimation on the entire sequence of images from the starting frame to other sequence frames in the complete cardiac cycle. The optical flow estimation result is at least used to represent the displacement vector at each pixel position at each moment and can be used to calculate the final myocardial strain.

[0087] 105. Analyze the target processing data to obtain the myocardial strain analysis result corresponding to the user to be analyzed.

[0088] In an embodiment of the present invention, optionally, myocardial strain analysis is a technology for evaluating myocardial function, which can provide important information about the heart's contraction and relaxation capabilities; further, the myocardial strain analysis results may include one or more of the volume and function indicators of the left ventricle and right ventricle corresponding to the user to be analyzed, myocardial strain value, strain rate, myocardial stress value, peak value and time of myocardial strain, and distribution and change of strain.

[0089] It can be seen that implementation Figure 1 The described myocardial strain analysis method based on multi-dimensional requirements can obtain user data of the user to be analyzed and determine target requirement information based on the multi-dimensional requirement information, perform data analysis operations on the user data based on the target requirement information to obtain data analysis results, input the data analysis results into the data processing model to obtain target processing data, and analyze the target processing data to obtain the myocardial strain analysis results. By obtaining the specific ultrasound data of the user to be analyzed and combining the multi-dimensional requirement information, the accuracy and personalization of the analysis results can be ensured, which is conducive to improving the accuracy and reliability of the analysis. The use of a predetermined data processing model can greatly improve the efficiency of data processing, and is conducive to improving the intelligence of data processing. The data is processed by the data processing model and the target processing data is analyzed to obtain the myocardial strain analysis results, which can be conducive to improving the accuracy and reliability of the myocardial strain analysis results, and is conducive to improving the intelligence and efficiency of the myocardial strain analysis results, so that the corresponding health status and cardiac function of the user to be analyzed can be more intuitively and accurately known based on the myocardial strain analysis results.

[0090] Embodiment 2

[0091] See also Figure 2 , Figure 2 is a flow chart of another myocardial strain analysis method based on multi-dimensional requirements disclosed in an embodiment of the present invention. Figure 2 The described myocardial strain analysis method based on multi-dimensional requirements can be applied to a myocardial strain analysis device based on multi-dimensional requirements, wherein the myocardial strain analysis device based on multi-dimensional requirements can be integrated in a cloud server or a local server, and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the myocardial strain analysis method based on multi-dimensional requirements may include the following operations:

[0092] 201. Obtain user data corresponding to the user to be analyzed.

[0093] 202. Determine target demand information based on multi-dimensional demand information.

[0094] 203. When a data management request is detected, determine the user login data corresponding to the data management request, and judge whether the user login data meets the preset data management conditions.

[0095] In the embodiment of the present invention, optionally, when no data management request is detected, step 205 may be directly triggered to be executed.

[0096] In an embodiment of the present invention, optionally, the user login data may include the terminal IP address, terminal login times, terminal login duration, terminal login address, and terminal of the user terminal corresponding to the data management request sent. Furthermore, the user login data may also include one or more of the user login name, user login verification information, and user login time corresponding to the data management request sent.

[0097] In the embodiment of the present invention, optionally, the above-mentioned determining whether the user login data meets the preset data management condition may include:

[0098] Determine the data management authority coefficient corresponding to the data management request based on the user login data, and determine the data management authority threshold according to the preset data management conditions;

[0099] Determine whether the data management authority coefficient is greater than or equal to the data management authority threshold;

[0100] When it is determined that the data management authority coefficient is greater than or equal to the data management authority threshold, it is determined that the user login data meets the preset data management conditions; when it is determined that the data management authority coefficient is less than the data management authority threshold, it is determined that the user login data does not meet the preset data management conditions.

[0101] 204. When it is determined that the user login data meets the preset data management conditions, the target case data matching the data management request is determined from the user data, and the data management operation corresponding to the target case data is determined based on the data management request, and an update operation matching the data management operation is performed on the target case data to update the user data.

[0102] In the embodiment of the present invention, further optionally, when it is determined that the user login data does not meet the preset data management conditions, the process can be terminated.

[0103] In the embodiment of the present invention, optionally, the data management operation may include one or more of a case data adding operation, a case data modifying operation, a case data deleting operation, and a case data screening operation.

[0104] In an embodiment of the present invention, optionally, for example, when the data management operation includes a case data deletion operation, target case data matching the data management request is screened out from all user data, and all target case data are deleted from the user data to update the user data, wherein the updated user data is the user data after all target case data are deleted.

[0105] 205. Perform a data analysis operation on the user data based on the target demand information to obtain a data analysis result.

[0106] 206. Input the data analysis result into a predetermined data processing model, so as to perform data processing operations on the data analysis result through the data processing model to obtain target processed data.

[0107] 207. Analyze the target processing data to obtain a myocardial strain analysis result corresponding to the user to be analyzed.

[0108] In the embodiment of the present invention, for detailed descriptions of steps 201 to 202 and steps 205 to 207, please refer to other descriptions of steps 101 to 105 in the first embodiment, and the embodiment of the present invention will not be repeated here.

[0109] It can be seen that implementation Figure 2The described myocardial strain analysis method based on multi-dimensional requirements can determine the corresponding user login data and judge whether the preset data management conditions are met when a data management request is detected. If so, the target case data matching the data management request is determined from the user data and the corresponding data management operation is determined. An update operation matching the data management operation is performed on the target case data to update the user data. By verifying whether the user login data meets the preset data management conditions, the security of the user data can be effectively protected. Only users who meet the conditions can access and update the data, thereby reducing the risk of data leakage or misoperation. After updating the target case data, data parsing operations are performed to ensure that the analysis is based on the latest and most accurate data. , which is conducive to improving the reliability and effectiveness of the analysis results, can update the target case data according to the data management request, is conducive to improving the flexibility of performing processing operations on the data, can adjust the data according to the actual needs, so as to better meet the personalized needs, and update the target case data before the data is analyzed. It can avoid unnecessary modification and adjustment of the data during the analysis process, which can be conducive to improving the operation efficiency and the intelligence of data processing, so as to improve the accuracy and reliability of the myocardial strain analysis results, and improve the intelligence and efficiency of the myocardial strain analysis results, and then based on the myocardial strain analysis results, the corresponding health status and cardiac function of the user to be analyzed can be more intuitively and accurately known.

[0110] In an optional embodiment, performing a data analysis operation on the user data based on the target demand information to obtain a data analysis result includes:

[0111] Based on the target demand information, target parsing parameters are determined, and a data parsing operation matching the target parsing parameters is performed on the user data to obtain target parsing data;

[0112] Determine the target data format corresponding to the target parsed data, and judge whether the target data format matches the preset reference data format;

[0113] When it is determined that the target data format does not match the preset benchmark data format, the format difference parameters between the target data format and the preset benchmark data format are determined, and based on the format difference parameters, a data conversion operation is performed on the target parsed data to obtain target converted data, and a data parsing result is generated based on all the target converted data.

[0114] In this optional embodiment, optionally, determining the target resolution parameters based on the target requirement information may include: determining a data transmission protocol based on the target requirement information, and determining the target resolution parameters based on the data transmission protocol.

[0115] In this optional embodiment, optionally, the target parsed data may include data obtained after performing data decoding on the user data.

[0116] In this optional embodiment, further optionally, when it is determined that the target data format matches the preset reference data format, the process may be terminated.

[0117] In this optional embodiment, optionally, performing a data parsing operation on user data that matches the target parsing parameters may be performed through a protocol parsing module; performing a data conversion operation on the target parsed data to obtain the target converted data may be performed through a format conversion module. For example, the data acquisition module is used to provide an interface and driver for input data, the protocol parsing module decodes the input data based on different data transmission protocols, and the format conversion module is used to convert the source data format into a data format readable by the software system or operating system, such as ultrasound acquisition images with different frame rates and resolutions from various models of ultrasound equipment.

[0118] It can be seen that the implementation of this optional embodiment can determine the target parsing parameters based on the target demand information and perform matching data parsing operations on the user data to obtain target parsing data, determine the target data format corresponding to the target parsing data and judge whether the target data format matches the benchmark data format. If they do not match, the format difference parameters are determined and a data conversion operation is performed on the target parsing data to obtain target conversion data and then generate a data parsing result. By determining the target parsing parameters based on the target demand information, it can be ensured that the data parsing operation is target-oriented, and invalid data processing processes are avoided, thereby improving the efficiency and accuracy of data parsing. After determining the data format of the target parsing data, the system will perform a matching check with the preset benchmark data format, which can ensure that the parsed data meets the expected format requirements, providing support for subsequent data analysis and application. It provides a standardized data foundation. When the target data format does not match the benchmark data format, the system can automatically determine the format difference parameters and perform data conversion operations based on these parameters, which can help improve the adaptability and flexibility of data processing. Moreover, through the conversion and integration of the target analysis data, the data analysis results finally generated not only include all the target conversion data, but also ensure the integrity and accuracy of the data, which can provide reliable data support for subsequent data analysis and application, and help improve the operating efficiency and the intelligence of data processing, so as to improve the accuracy and reliability of the myocardial strain analysis results, and improve the intelligence and efficiency of the myocardial strain analysis results, so as to more intuitively and accurately know the corresponding health status and cardiac function of the user to be analyzed based on the myocardial strain analysis results.

[0119] In another optional embodiment, the data analysis result is input into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data, including:

[0120] Inputting the data analysis result into a predetermined myocardial segmentation model, so as to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data;

[0121] The first processed data is input into a predetermined optical flow estimation model, so as to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and generate target processed data based on the first processed data and the second processed data.

[0122] In this optional embodiment, the myocardial segmentation model is optionally used to perform pixel classification on a full sequence of ultrasound images in a complete cardiac cycle to obtain output results, and to assist in myocardial region positioning and strain index calculation based on the output results.

[0123] In this optional embodiment, optionally, the optical flow estimation model is used to perform optical flow estimation on the entire sequence of images from the starting frame to other sequence frames in the complete cardiac cycle, and output the motion optical flow of the user to be analyzed in the left ventricular myocardial area in combination with the output results of the myocardial segmentation model to obtain the optical flow results.

[0124] In this optional embodiment, optionally, the target processed data can at least be used to calculate a myocardial strain value in a myocardial strain result.

[0125] It can be seen that the implementation of this optional embodiment can input the data analysis result into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processing data, input the first processing data into a predetermined optical flow estimation model to perform a second processing operation on the first processing data through the optical flow estimation model to obtain second processing data, and generate target processing data based on the first processing data and the second processing data, and can segment the myocardial area from the background or other areas through the myocardial segmentation model, which can improve the accuracy and reliability of image area segmentation, and can accurately estimate the movement of pixels in an image or video sequence through the optical flow estimation model, which is beneficial to improving the accuracy of estimating image sequences. The collaborative work of the myocardial segmentation model and the optical flow estimation model can extract more comprehensive information about the structure and function of the heart, and improve the multi-model joint analysis method to more accurately reflect the health status of the heart than a single model. Through automated and precise data processing, doctors can obtain accurate information about the health status of the heart more quickly, thereby improving the efficiency and accuracy of diagnosis, which is conducive to improving operational efficiency and the intelligence of data processing, thereby improving the accuracy and reliability of the myocardial strain analysis results, as well as improving the intelligence and efficiency of the myocardial strain analysis results, and then more intuitively and accurately knowing the corresponding health status and heart function of the user to be analyzed based on the myocardial strain analysis results.

[0126] In yet another optional embodiment, the data analysis result includes at least a full sequence of ultrasound images corresponding to the target cardiac cycle, and the data analysis result is input into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data, including:

[0127] Inputting the full sequence ultrasound image corresponding to the target cardiac cycle into a predetermined myocardial segmentation model, so as to perform pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain a pixel classification result, wherein the pixel classification result at least includes a background pixel category and a myocardial pixel category;

[0128] Based on the pixel classification result, first processed data is generated; wherein the first processed data at least includes a target sequence image corresponding to a target cardiac cycle.

[0129] In this optional embodiment, optionally, the target cardiac cycle may include a complete cardiac cycle corresponding to the user to be analyzed; wherein a complete cardiac cycle refers to the entire process experienced by the cardiovascular system from the start of one heartbeat to the start of the next heartbeat; further optionally, the full sequence of ultrasound images may include all ultrasound images corresponding to the target cardiac cycle, from the starting frame image to the last frame image.

[0130] In this optional embodiment, the target sequence of images may be, optionally, a full sequence of ultrasound images corresponding to a target cardiac cycle, or may be a target number of ultrasound images in the full sequence of ultrasound images.

[0131] In this optional embodiment, optionally, the first processed data may also include left ventricular myocardium segmentation mask data, wherein the left ventricular myocardium segmentation mask data is generally used in medical image processing, particularly in cardiac ultrasound or MRI image analysis, to automatically or semi-automatically identify the boundary of the left ventricular myocardium. These data are generally in the form of an image or matrix, in which each pixel or voxel (in a 3D image) is marked as belonging to the left ventricular myocardium or background (non-myocardial tissue). Further, the left ventricular myocardium segmentation mask data can be used to assist in the calculation of strain indicators in the myocardial region positioning and optical flow estimation results.

[0132] It can be seen that the implementation of this optional embodiment can input the full sequence ultrasound image corresponding to the target cardiac cycle into the myocardial segmentation model to perform pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain pixel classification results, generate first processing data based on the pixel classification results, and classify the full sequence ultrasound image at the pixel level through the myocardial segmentation model, which can accurately distinguish the myocardial tissue and the background area. Compared with the traditional myocardial segmentation, which usually requires doctors to manually outline the myocardial boundary, this is a time-consuming and error-prone process. By using a predetermined myocardial segmentation model, the full sequence ultrasound image can be automatically segmented, thereby greatly speeding up the workflow, which can improve the accuracy and reliability of myocardial segmentation while improving the intelligence and efficiency of myocardial segmentation, and is conducive to improving the accuracy and reliability of subsequent generation of target processing data and generation of myocardial strain analysis results, thereby improving the efficiency and accuracy of diagnosis, and is conducive to improving the operation efficiency and the intelligence of data processing, so that it can be conducive to improving the accuracy and reliability of obtaining myocardial strain analysis results, and is conducive to improving the intelligence and efficiency of obtaining myocardial strain analysis results, and then it can be more intuitively and accurately known based on the myocardial strain analysis results. The corresponding health status and cardiac function of the user to be analyzed.

[0133] In yet another optional embodiment, the first processed data is input into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and target processed data is generated based on the first processed data and the second processed data, including:

[0134] Inputting the first processed data into a predetermined optical flow estimation model to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model to obtain second processed data, wherein the second processed data at least includes an optical flow estimation result corresponding to the target sequence image;

[0135] A calculation operation is performed on the first processed data and the second processed data to obtain target processed data.

[0136] In this optional embodiment, the predetermined optical flow estimation model is optionally an unsupervised model; further, the optical flow estimation model is an important technology in computer vision, which is used to estimate the motion of each pixel in the image between consecutive frames; optical flow estimation is a method based on the spatiotemporal gradient of pixel intensity data in an image sequence, which is used to calculate the motion information of objects in the image. Its principle is based on the assumption of constant brightness, that is, the grayscale value of pixels between adjacent frames does not change over time. According to this assumption, optical flow estimation aims to find the displacement of each pixel in the image sequence in time, that is, the motion trajectory of the pixel.

[0137] In this optional embodiment, the target sequence image may optionally include a full sequence image from a starting frame to other sequence frames in the target cardiac cycle; further, its optical flow result represents a displacement vector at each pixel position at that moment and is used to calculate the final myocardial strain value.

[0138] In this optional embodiment, optionally, performing a calculation operation on the first processed data and the second processed data to obtain the target processed data can be performing a calculation operation on the first processed data and the second processed data and calculating in combination with the strain index to obtain a final myocardial strain value, wherein the target processed data at least includes the myocardial strain value of the user to be analyzed.

[0139] It can be seen that the implementation of this optional embodiment can input the first processed data into a predetermined optical flow estimation model to perform an optical flow estimation operation on the target sequence image corresponding to the first processed data through the optical flow estimation model to obtain the second processed data, and perform a calculation operation on the first processed data and the second processed data to obtain the target processed data. Through the predetermined optical flow estimation model, the optical flow estimation operation can be accurately performed on the first processed data, and the displacement of pixels in the image sequence can be accurately calculated based on the constant brightness assumption and the motion model through the optical flow estimation model, thereby describing the motion information in the image, and the second processed data is combined with the original first processed data, and the calculation operation can be performed to obtain Richer target processing data not only retains the information of the original image, but also adds information about the movement of objects in the image, making the target processing data more valuable for analysis, helping to further improve the accuracy and stability of optical flow estimation, and making the generated target processing data more reliable and useful, thereby improving the efficiency and accuracy of diagnosis, and helping to improve operational efficiency and the intelligence of data processing, so as to improve the accuracy and reliability of myocardial strain analysis results, as well as the intelligence and efficiency of myocardial strain analysis results, and then more intuitively and accurately knowing the corresponding health status and cardiac function of the user to be analyzed based on the myocardial strain analysis results.

[0140] In yet another optional embodiment, after the data analysis result is input into a predetermined data processing model to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data, the method further includes:

[0141] Based on the target processed data and the predetermined benchmark indicator information, the myocardial region data in the target processed data is determined, and the average myocardial strain value corresponding to the target cardiac cycle is calculated according to all the determined myocardial region data;

[0142] Visual analysis data is generated according to the average myocardial strain value, and the visual analysis data is output to a predetermined display terminal.

[0143] In this optional embodiment, optionally, the visualization analysis data may include visualization data corresponding to the optical flow data, wherein the calculation result of the optical flow is a two-dimensional vector field with two channels, and the vectors at each position represent the offset of the pixel in each dimension, including the size and direction. In order to intuitively evaluate the effect of the optical flow algorithm, visualizing the calculation result of the optical flow field is a simple and effective processing method. Common optical flow visualization methods include optical flow arrow diagrams and optical flow chromaticity diagrams. The optical flow arrow diagram uses arrow symbols to represent the optical flow, wherein the direction and length of the arrows represent the direction and size of each optical flow vector, respectively. This method is clear and easy to observe, but due to the low density of the arrow diagram, this method is generally suitable for the visualization of sparse optical flow. The optical flow chromaticity diagram refers to coloring the result of the optical flow calculation through a specific color model and visualizing it in the form of a pseudo-color map (RGB color map), wherein the hue represents the direction of movement, and the saturation represents the speed of movement or the size of the offset. This method can clearly cover each pixel, so it is often used for the visualization of dense optical flow.

[0144] In this optional embodiment, optionally, the average myocardial strain value corresponding to the target cardiac cycle may include an average myocardial strain value on the left ventricular myocardial area of ​​the entire sequence of ultrasound images from the start frame to other sequence frames in the target cardiac cycle.

[0145] In this optional embodiment, the predetermined reference indicator information may optionally include a predetermined myocardial strain indicator.

[0146] In this optional embodiment, the predetermined display terminal may optionally include a display terminal such as a smart phone, a smart computer, a smart tablet, an LED display screen, etc. that can be used to display visual data.

[0147] It can be seen that the implementation of this optional embodiment can determine the myocardial area data in the target processing data based on the target processing data and the benchmark indicator information, and calculate the average myocardial strain value corresponding to the target cardiac cycle based on the myocardial area data, generate visual analysis data according to the average myocardial strain value and output the visual analysis data to the display terminal. By determining the myocardial area data based on the target processing data and the benchmark indicator information, and calculating the corresponding average myocardial strain value, a high-precision evaluation of myocardial function can be achieved, and the automatic generation of visual analysis data and output to the display terminal can be improved, so that the strain of the myocardium can be intuitively understood, which is conducive to improving the intelligence of data analysis and improving the accuracy and reliability of the myocardial strain analysis results viewed by the user to be analyzed, as well as improving the convenience of the user to be analyzed to view the myocardial strain analysis results.

[0148] In yet another optional embodiment, before analyzing the target processing data to obtain the myocardial strain analysis result corresponding to the user to be analyzed, the method further includes:

[0149] Obtain data service requirements, and determine data encapsulation parameters for target processing data based on the data service requirements;

[0150] According to the data encapsulation parameters, a data encapsulation operation is performed on the target processed data to obtain target encapsulated data;

[0151] Among them, analyzing the target processing data to obtain the myocardial strain analysis results corresponding to the user to be analyzed includes:

[0152] Analyze the target package data to obtain the myocardial strain analysis results corresponding to the user to be analyzed.

[0153] In this optional embodiment, optionally, the data service requirement may include one or more of a data interface service requirement and a data transmission service requirement.

[0154] In this optional embodiment, the target encapsulated data may optionally include data matching the data service requirements.

[0155] In this optional embodiment, for example, data service requirements may include abstracting and encapsulating requirements through engineering development technologies such as microservices and modularization, and providing complete functional interfaces and solutions to the outside world, which belongs to the top-level design in system architecture design. Based on the demand analysis results of this system, the application service layer mainly provides application service interfaces for modules such as case data management, ultrasound data management, and indicator calculation to the upper-level terminals.

[0156] It can be seen that the implementation of this optional embodiment can obtain data service requirements and determine data encapsulation parameters of target processing data, perform data encapsulation operations on target processing data according to data encapsulation parameters to obtain target encapsulation data, and analyze the target encapsulation data to obtain the myocardial strain analysis results of the user to be analyzed. By obtaining and determining data encapsulation parameters based on data service requirements, the pertinence and accuracy of data processing can be ensured, thereby providing more flexible and personalized services. The data encapsulation operation converts the target processing data into structured and standardized target encapsulation data, which helps to simplify the subsequent data analysis process. The data encapsulation operation can also enhance data security. By limiting direct access to the original data, the encapsulated data can provide a secure interface to access and process the data, reduce the risk of data leakage and unauthorized access, and thus help improve the security of data processing, and also help improve the intelligence and accuracy of data processing to obtain myocardial strain analysis results.

[0157] Embodiment 3

[0158] See also Figure 3 , Figure 3Schematic diagram of a myocardial strain analysis device based on multi-dimensional requirements disclosed in an embodiment of the present invention. Figure 3 As shown, the myocardial strain analysis device based on multi-dimensional requirements may include:

[0159] An acquisition module 301 is used to acquire user data corresponding to the user to be analyzed, wherein the user data at least includes user ultrasonic data of the user to be identified;

[0160] A determination module 302 is used to determine target demand information based on the multi-dimensional demand information;

[0161] The parsing module 303 is used to perform a data parsing operation on the user data based on the target demand information to obtain a data parsing result;

[0162] An input module 304 is used to input the data analysis result into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data;

[0163] The analysis module 305 is used to analyze the target processing data to obtain the myocardial strain analysis result corresponding to the user to be analyzed.

[0164] It can be seen that implementation Figure 3 The described device can obtain user data of the user to be analyzed and determine target demand information based on multi-dimensional demand information, perform data analysis operations on the user data based on the target demand information to obtain data analysis results, input the data analysis results into the data processing model to obtain target processing data, and analyze the target processing data to obtain myocardial strain analysis results. By obtaining specific ultrasound data of the user to be analyzed and combining the multi-dimensional demand information, the accuracy and personalization of the analysis results can be ensured, which is conducive to improving the accuracy and reliability of the analysis. The use of a predetermined data processing model can greatly improve the efficiency of data processing, and is conducive to improving the intelligence of data processing. Processing the data through the data processing model and analyzing the target processing data to obtain the myocardial strain analysis results can be conducive to improving the accuracy and reliability of the myocardial strain analysis results, as well as improving the intelligence and efficiency of the myocardial strain analysis results, and thus the corresponding health status and cardiac function of the user to be analyzed can be more intuitively and accurately known based on the myocardial strain analysis results.

[0165] In an optional embodiment, if Figure 4 As shown, the determination module 302 is further used to determine the user login data corresponding to the data management request when a data management request is detected before the analysis module 303 performs a data analysis operation on the user data based on the target demand information and obtains the data analysis result;

[0166] The device also includes:

[0167] The judgment module 306 is used to judge whether the user login data meets the preset data management conditions;

[0168] The determination module 302 is also used to determine the target case data that matches the data management request from the user data when the judgment module 306 determines that the user login data meets the preset data management conditions, and determine the data management operation corresponding to the target case data based on the data management request, and perform an update operation on the target case data that matches the data management operation to update the user data, and trigger the analysis module 303 to perform a data analysis operation on the user data based on the target demand information to obtain a data analysis result.

[0169] It can be seen that implementation Figure 4 The described device can determine the corresponding user login data when a data management request is detected and judge whether the preset data management conditions are met. If so, the target case data matching the data management request is determined from the user data and the corresponding data management operation is determined. An update operation matching the data management operation is performed on the target case data to update the user data. By verifying whether the user login data meets the preset data management conditions, the security of the user data can be effectively protected. Only users who meet the conditions can access and update the data, thereby reducing the risk of data leakage or misoperation. After the target case data is updated, the data parsing operation is performed to ensure that the analysis is based on the latest and most accurate data, which is conducive to improving the analysis. The reliability and effectiveness of the analysis results can be improved, and the target case data can be updated according to the data management request, which is conducive to improving the flexibility of executing data processing operations, and the data can be adjusted according to actual needs to better meet personalized needs. The target case data is updated before data analysis, which can avoid unnecessary modification and adjustment of the data during the analysis process, which can be conducive to improving the operation efficiency and the intelligence of data processing, so as to improve the accuracy and reliability of the myocardial strain analysis results, and improve the intelligence and efficiency of the myocardial strain analysis results, so as to more intuitively and accurately know the corresponding health status and cardiac function of the user to be analyzed based on the myocardial strain analysis results.

[0170] In another optional embodiment, Figure 4 As shown, the parsing module 303 performs a data parsing operation on the user data based on the target demand information, and the specific method of obtaining the data parsing result includes:

[0171] Based on the target demand information, target parsing parameters are determined, and a data parsing operation matching the target parsing parameters is performed on the user data to obtain target parsing data;

[0172] Determine the target data format corresponding to the target parsed data, and judge whether the target data format matches the preset reference data format;

[0173] When it is determined that the target data format does not match the preset benchmark data format, the format difference parameters between the target data format and the preset benchmark data format are determined, and based on the format difference parameters, a data conversion operation is performed on the target parsed data to obtain target converted data, and a data parsing result is generated based on all the target converted data.

[0174] It can be seen that implementation Figure 4 The described device can determine target parsing parameters based on target demand information and perform matching data parsing operations on user data to obtain target parsing data, determine the target data format corresponding to the target parsing data and judge whether the target data format matches the benchmark data format. If they do not match, the format difference parameters are determined and a data conversion operation is performed on the target parsing data to obtain target conversion data and then generate a data parsing result. By determining the target parsing parameters based on the target demand information, it can be ensured that the data parsing operation is target-oriented, and invalid data processing processes are avoided, thereby improving the efficiency and accuracy of data parsing. After determining the data format of the target parsing data, the system will perform a matching check with the preset benchmark data format, which can ensure that the parsed data meets the expected format requirements, providing a standard for subsequent data analysis and application. Standardized data foundation, when the target data format does not match the benchmark data format, the system can automatically determine the format difference parameters and perform data conversion operations based on these parameters, which can help improve the adaptability and flexibility of data processing, and through the conversion and integration of target analysis data, the final generated data analysis results not only include all target conversion data, but also ensure the integrity and accuracy of the data, which can provide reliable data support for subsequent data analysis and application, and is conducive to improving operational efficiency and improving the intelligence of data processing, so as to improve the accuracy and reliability of myocardial strain analysis results, as well as improve the intelligence and efficiency of myocardial strain analysis results, and then based on the myocardial strain analysis results, the corresponding health status and cardiac function of the user to be analyzed can be more intuitively and accurately known.

[0175] In yet another optional embodiment, Figure 4 As shown, the input module 304 inputs the data analysis result into a predetermined data processing model to perform data processing operations on the data analysis result through the data processing model. The specific method of obtaining the target processed data includes:

[0176] Inputting the data analysis result into a predetermined myocardial segmentation model, so as to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data;

[0177] The first processed data is input into a predetermined optical flow estimation model, so as to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and generate target processed data based on the first processed data and the second processed data.

[0178] It can be seen that implementation Figure 4 The described device can input the data analysis result into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processing data, input the first processing data into a predetermined optical flow estimation model to perform a second processing operation on the first processing data through the optical flow estimation model to obtain second processing data, and generate target processing data based on the first processing data and the second processing data, can segment the myocardial area from the background or other areas through the myocardial segmentation model, can improve the accuracy and reliability of image area segmentation, and can accurately estimate the movement of pixels in an image or video sequence through the optical flow estimation model, which is beneficial to improving the accuracy and reliability of image sequence estimation. Reliability, the collaborative work of the myocardial segmentation model and the optical flow estimation model can extract more comprehensive information about the structure and function of the heart, and improve the multi-model joint analysis method. It can more accurately reflect the health of the heart than a single model. Through automation and precise data processing, doctors can obtain accurate information about the health of the heart more quickly, thereby improving the efficiency and accuracy of diagnosis, which is conducive to improving operational efficiency and improving the intelligence of data processing, so as to improve the accuracy and reliability of the myocardial strain analysis results, as well as improve the intelligence and efficiency of the myocardial strain analysis results, and then more intuitively and accurately know the corresponding health status and heart function of the user to be analyzed based on the myocardial strain analysis results.

[0179] In yet another optional embodiment, Figure 4 As shown, the data analysis result includes at least a full sequence of ultrasound images corresponding to the target cardiac cycle. The input module 304 inputs the data analysis result into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model. The specific method of obtaining the first processed data includes:

[0180] Inputting the full sequence ultrasound image corresponding to the target cardiac cycle into a predetermined myocardial segmentation model, so as to perform pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain a pixel classification result, wherein the pixel classification result at least includes a background pixel category and a myocardial pixel category;

[0181] Based on the pixel classification result, first processed data is generated; wherein the first processed data at least includes a target sequence image corresponding to a target cardiac cycle.

[0182] It can be seen that implementation Figure 4 The described device can input the full sequence ultrasound image corresponding to the target cardiac cycle into the myocardial segmentation model to perform pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain pixel classification results, generate first processing data based on the pixel classification results, and classify the full sequence ultrasound image at the pixel level through the myocardial segmentation model, so as to accurately distinguish the myocardial tissue and the background area. Compared with the traditional myocardial segmentation, which usually requires doctors to manually outline the myocardial boundary, this is a time-consuming and error-prone process. By using a predetermined myocardial segmentation model, the full sequence ultrasound image can be automatically segmented, thereby greatly speeding up the workflow, and can improve the accuracy and reliability of myocardial segmentation while improving the intelligence and efficiency of myocardial segmentation, and can improve the accuracy and reliability of subsequent generation of target processing data and generation of myocardial strain analysis results, thereby improving the efficiency and accuracy of diagnosis, improving the operating efficiency and improving the intelligence of data processing, so as to improve the accuracy and reliability of obtaining myocardial strain analysis results, and improve the intelligence and efficiency of obtaining myocardial strain analysis results, and then can more intuitively and accurately know the health status and cardiac function of the user to be analyzed based on the myocardial strain analysis results.

[0183] In yet another optional embodiment, Figure 4 As shown, the input module 304 inputs the first processed data into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and generates target processed data based on the first processed data and the second processed data. The specific method includes:

[0184] Inputting the first processed data into a predetermined optical flow estimation model to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model to obtain second processed data, wherein the second processed data at least includes an optical flow estimation result corresponding to the target sequence image;

[0185] A calculation operation is performed on the first processed data and the second processed data to obtain target processed data.

[0186] It can be seen that implementation Figure 4The described device can input the first processed data into a predetermined optical flow estimation model to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model to obtain second processed data, and perform a calculation operation on the first processed data and the second processed data to obtain target processed data. Through the predetermined optical flow estimation model, the optical flow estimation operation can be accurately performed on the first processed data, and the displacement of pixels in the image sequence can be accurately calculated based on the constant brightness assumption and the motion model through the optical flow estimation model, thereby describing the motion information in the image. The second processed data is combined with the original first processed data, and a richer image can be obtained by performing a calculation operation. The rich target processing data not only retains the information of the original image, but also adds information about the movement of objects in the image, making the target processing data more valuable for analysis, helping to further improve the accuracy and stability of optical flow estimation, and making the generated target processing data more reliable and useful, thereby improving the efficiency and accuracy of diagnosis, and is conducive to improving operational efficiency and the intelligence of data processing, so as to improve the accuracy and reliability of myocardial strain analysis results, as well as the intelligence and efficiency of myocardial strain analysis results, and then based on the myocardial strain analysis results, the corresponding health status and cardiac function of the user to be analyzed can be more intuitively and accurately known.

[0187] In yet another optional embodiment, Figure 4 As shown, the determination module 302 is further used to input the data analysis result into a predetermined data processing model in the input module 304, so as to perform a data processing operation on the data analysis result through the data processing model, and after obtaining the target processed data, determine the myocardial region data in the target processed data based on the target processed data and the predetermined benchmark indicator information, and calculate the average myocardial strain value corresponding to the target cardiac cycle according to all the determined myocardial region data;

[0188] The device also includes:

[0189] The generating module 307 is used to generate visual analysis data according to the average myocardial strain value, and output the visual analysis data to a predetermined display terminal.

[0190] It can be seen that implementation Figure 4The described device can determine the myocardial region data in the target processing data based on the target processing data and the benchmark indicator information, and calculate the average myocardial strain value corresponding to the target cardiac cycle based on the myocardial region data, generate visual analysis data according to the average myocardial strain value and output the visual analysis data to a display terminal. By determining the myocardial region data based on the target processing data and the benchmark indicator information, and calculating the corresponding average myocardial strain value, a high-precision evaluation of myocardial function can be achieved, and the automatic generation of visual analysis data and the output to the display terminal can be improved, so that the strain of the myocardium can be intuitively understood, which is conducive to improving the intelligence of data analysis and improving the accuracy and reliability of the myocardial strain analysis results viewed by the user to be analyzed, as well as improving the convenience of the user to be analyzed in viewing the myocardial strain analysis results.

[0191] Embodiment 4

[0192] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram of the structure of another myocardial strain analysis device based on multi-dimensional requirements disclosed in an embodiment of the present invention. Figure 5 As shown, the myocardial strain analysis device based on multi-dimensional requirements may include:

[0193] A memory 401 storing executable program codes;

[0194] a processor 402 coupled to the memory 401;

[0195] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the myocardial strain analysis method based on multi-dimensional requirements described in the first embodiment of the present invention or the second embodiment of the present invention.

[0196] Embodiment 5

[0197] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the myocardial strain analysis method based on multi-dimensional requirements described in Embodiment 1 or Embodiment 2 of the present invention.

[0198] Embodiment 6

[0199] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the myocardial strain analysis method based on multi-dimensional requirements described in Embodiment 1 or Embodiment 2.

[0200] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0201] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware. Based on such an understanding, the above-mentioned technical solution can essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0202] Finally, it should be noted that the myocardial strain analysis method and device based on multi-dimensional needs disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A myocardial strain analysis method based on multi-dimensional requirements, characterized in that: The method comprises: Acquire user data corresponding to the user to be analyzed, wherein the user data at least includes user ultrasonic data of the user to be identified; Determine target demand information based on multi-dimensional demand information; Performing a data analysis operation on the user data based on the target demand information to obtain a data analysis result; Inputting the data analysis result into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data; The target processing data is analyzed to obtain a myocardial strain analysis result corresponding to the user to be analyzed.

2. The myocardial strain analysis method based on multi-dimensional requirements according to claim 1, characterized in that: Before performing a data analysis operation on the user data based on the target demand information to obtain a data analysis result, the method further includes: When a data management request is detected, determining user login data corresponding to the data management request, and judging whether the user login data satisfies a preset data management condition; When it is determined that the user login data satisfies the preset data management condition, the target case data matching the data management request is determined from the user data, and the data management operation corresponding to the target case data is determined based on the data management request, and an update operation matching the data management operation is performed on the target case data to update the user data, and trigger the execution of the data analysis operation based on the target demand information to perform the data analysis result on the user data.

3. The myocardial strain analysis method based on multi-dimensional requirements according to claim 1, characterized in that: The performing a data analysis operation on the user data based on the target demand information to obtain a data analysis result includes: Based on the target demand information, target parsing parameters are determined, and a data parsing operation matching the target parsing parameters is performed on the user data to obtain target parsing data; Determining a target data format corresponding to the target parsed data, and judging whether the target data format matches a preset reference data format; When it is determined that the target data format does not match the preset benchmark data format, the format difference parameters between the target data format and the preset benchmark data format are determined, and based on the format difference parameters, a data conversion operation is performed on the target parsed data to obtain target converted data, and a data parsing result is generated based on all the target converted data.

4. The myocardial strain analysis method based on multi-dimensional requirements according to claim 1, characterized in that: The step of inputting the data analysis result into a predetermined data processing model so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data includes: Inputting the data analysis result into a predetermined myocardial segmentation model, so as to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data; The first processed data is input into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and target processed data is generated based on the first processed data and the second processed data.

5. The myocardial strain analysis method based on multi-dimensional requirements according to claim 4, characterized in that: The data analysis result at least includes a full sequence of ultrasound images corresponding to a target cardiac cycle, and the data analysis result is input into a predetermined myocardial segmentation model to perform a first processing operation on the data analysis result through the myocardial segmentation model to obtain first processed data, including: Inputting the full sequence ultrasound image corresponding to the target cardiac cycle into a predetermined myocardial segmentation model, so as to perform a pixel classification operation on the full sequence ultrasound image through the myocardial segmentation model to obtain a pixel classification result, wherein the pixel classification result at least includes a background pixel category and a myocardial pixel category; Based on the pixel classification result, first processed data is generated; wherein the first processed data at least includes the target sequence image corresponding to the target cardiac cycle.

6. The myocardial strain analysis method based on multi-dimensional requirements according to claim 5, characterized in that: The step of inputting the first processed data into a predetermined optical flow estimation model to perform a second processing operation on the first processed data through the optical flow estimation model to obtain second processed data, and generating target processed data based on the first processed data and the second processed data, includes: Inputting the first processed data into a predetermined optical flow estimation model, so as to perform an optical flow estimation operation on a target sequence image corresponding to the first processed data through the optical flow estimation model, to obtain second processed data, wherein the second processed data at least includes an optical flow estimation result corresponding to the target sequence image; A computing operation is performed on the first processed data and the second processed data to obtain target processed data.

7. The myocardial strain analysis method based on multi-dimensional requirements according to claim 6, characterized in that: After inputting the data analysis result into a predetermined data processing model to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data, the method further includes: Based on the target processed data and predetermined benchmark indicator information, determine the myocardial region data in the target processed data, and calculate the average myocardial strain value corresponding to the target cardiac cycle according to all the determined myocardial region data; Visual analysis data is generated according to the average myocardial strain value, and the visual analysis data is output to a predetermined display terminal.

8. A myocardial strain analysis device based on multi-dimensional requirements, characterized in that: The device comprises: An acquisition module, used to acquire user data corresponding to the user to be analyzed, wherein the user data at least includes user ultrasonic data of the user to be identified; A determination module, used to determine target demand information based on multi-dimensional demand information; A parsing module, used to perform a data parsing operation on the user data based on the target demand information to obtain a data parsing result; An input module, used for inputting the data analysis result into a predetermined data processing model, so as to perform a data processing operation on the data analysis result through the data processing model to obtain target processed data; The analysis module is used to analyze the target processing data to obtain the myocardial strain analysis result corresponding to the user to be analyzed.

9. A myocardial strain analysis device based on multi-dimensional requirements, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the myocardial strain analysis method based on multi-dimensional requirements as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the myocardial strain analysis method based on multi-dimensional requirements as described in any one of claims 1-7.

Images