Blood vessel state evaluation method and system based on nondestructive ultrasonic detection

Abstract

The invention discloses a blood vessel state evaluation method and system based on nondestructive ultrasonic detection. The method comprises the following steps: acquiring ultrasonic images and blood pressure data corresponding to a target blood vessel tissue in a plurality of time periods; according to the ultrasonic image, calculating a blood vessel wall hardness feature corresponding to the target blood vessel tissue in each time period; according to the blood pressure data, blood pressure fluctuation characteristics corresponding to the target vascular tissue in each time period are calculated; and determining a state evaluation result corresponding to the target vascular tissue according to correlation analysis between the vascular wall hardness feature and the blood pressure fluctuation feature corresponding to each time period. Therefore, accurate vascular tissue health assessment based on multi-modal time sequence data can be realized, the accuracy and foresight of early judgment of the cardiovascular state are improved, and the risk of misjudgment of the vascular state caused by a single index or static analysis is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for assessing vascular status based on non-destructive ultrasound detection. Background Technology

[0002] With the rapid growth in demand for early cardiovascular health screening, medical institutions are increasingly emphasizing the use of ultrasound data for accurate assessment of vascular tissue health. A key technical challenge is improving diagnostic foresight to reduce the risk of misjudgment of vascular status. Current technologies typically acquire ultrasound images of the target vascular tissue at a single time point, using manual evaluation or simple parametric calculations to assess vascular wall stiffness and provide a health status conclusion. However, existing solutions lack the ability to extract temporal features from ultrasound images and blood pressure data across multiple time periods, as well as dynamic correlation analysis of stiffness and fluctuation characteristics. This makes it difficult to accurately determine the health status of vascular tissue and capture dynamic changes in blood vessels, resulting in insufficient accuracy and foresight in the assessment. Misjudgments of vascular status are easily caused by isolated indicators or neglect of temporal sequence, limiting the reliability and clinical value of early cardiovascular screening. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for assessing vascular status based on non-destructive ultrasound detection, which can realize accurate assessment of vascular tissue health based on multimodal time-series data, improve the accuracy and foresight of early judgment of cardiovascular status, and reduce the risk of misjudgment of vascular status due to single indicators or static analysis.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a method for assessing vascular status based on non-destructive ultrasound detection, the method comprising: Acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods; Based on the ultrasound images, the vessel wall stiffness characteristics of the target vascular tissue in each time period are calculated. Based on the blood pressure data, calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period; Based on the correlation analysis between the blood vessel wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period, the state assessment result corresponding to the target blood vessel tissue is determined.

[0005] As an optional implementation, in the first aspect of the invention, calculating the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the ultrasound image includes: The ultrasound image corresponding to each time period is input into a feature calculation model corresponding to at least two feature types, so as to obtain at least two tissue feature parameters of the target vascular tissue in each time period. Based on the at least two tissue feature parameters, the vessel wall stiffness characteristics of the target vascular tissue in each time period are calculated.

[0006] As an optional implementation, in the first aspect of the present invention, the characteristic type of the tissue characteristic parameter is a vascular compliance parameter, an elastic modulus parameter, a distensibility parameter, or a calcified plaque-related parameter; the vascular compliance parameter includes at least one of delayed compliance parameter, systolic blood pressure compliance parameter, diastolic blood pressure compliance parameter, and mean blood pressure compliance parameter; the elasticity model parameter includes at least one of bulk elastic modulus parameter, Young's elastic modulus parameter, and Petersen elastic modulus parameter.

[0007] As an optional implementation, in the first aspect of the invention, the feature calculation model is used to perform the following steps: For each time period, all ultrasound images corresponding to that time period are sorted from early to late based on their corresponding acquisition time points to obtain the corresponding image sequence data. The image sequence data is input into a trained LSTM neural network model to obtain the tissue feature parameters of the target vascular tissue corresponding to that time period. The LSTM neural network is trained using a training dataset that includes multiple training vascular image sequences and corresponding feature type parameter annotations.

[0008] As an optional implementation, in the first aspect of the invention, calculating the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the at least two tissue characteristic parameters includes: Based on the preset correspondence between tissue features and blood vessel wall stiffness parameters, the blood vessel wall stiffness parameter corresponding to each tissue feature parameter is determined. Calculate the parameter matrix composed of the blood vessel wall stiffness parameters corresponding to all the tissue feature parameters for each time period to obtain the blood vessel wall stiffness characteristics of the target blood vessel tissue for each time period.

[0009] As an optional implementation, in the first aspect of the present invention, calculating the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data includes: For each time period, determine all the blood pressure data corresponding to that time period and the corresponding data acquisition time point; The multinomial fitting algorithm is used to fit all the blood pressure data and the corresponding data acquisition time points to obtain the set of coefficients for the change of blood pressure over time in the corresponding time period, so as to obtain the blood pressure fluctuation characteristics of the target vascular tissue in the corresponding time period.

[0010] As an optional implementation, in the first aspect of the present invention, determining the state assessment result corresponding to the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period includes: The blood vessel wall stiffness characteristics and blood pressure fluctuation characteristics of the target blood vessel tissue in all the time periods are sorted from early to late according to the time period to obtain the stiffness characteristic sequence and the blood pressure characteristic sequence. Calculate the correlation parameter between the hardness feature sequence and the blood pressure feature sequence; The hardness feature sequence is input into the trained hardness health prediction model to obtain the output hardness state parameters. The blood pressure feature sequence is input into the trained blood pressure health prediction model to obtain the output blood pressure status parameters; The average values ​​of the stiffness state parameter and the blood pressure state parameter are calculated, and the product of the average value and the correlation parameter is calculated to obtain the state assessment result corresponding to the target vascular tissue.

[0011] As an optional implementation, in the first aspect of the present invention, the method further includes: When the status assessment result is lower than a preset result threshold, the user age of the user corresponding to the target vascular tissue is obtained; The historical status evaluation results of multiple historical users whose age difference with the user's age is less than a preset threshold are selected from the historical database. Calculate the average of the result differences between the state assessment result and each of the historical state assessment results to obtain the difference parameter; Calculate the age parameter that is proportional to the difference parameter; The difference between the user's age and the age parameter is calculated to obtain the vascular age parameter corresponding to the target vascular tissue.

[0012] A second aspect of this invention discloses a vascular condition assessment system based on non-destructive ultrasound detection, the system comprising: The acquisition module is used to acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods; The first calculation module is used to calculate the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the ultrasound image. The second calculation module is used to calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data. The determination module is used to determine the state assessment result corresponding to the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period.

[0013] As an optional implementation, in a second aspect of the invention, the first calculation module calculates the specific method by which it calculates the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the ultrasound image, including: The ultrasound image corresponding to each time period is input into a feature calculation model corresponding to at least two feature types, so as to obtain at least two tissue feature parameters of the target vascular tissue in each time period. Based on the at least two tissue feature parameters, the vessel wall stiffness characteristics of the target vascular tissue in each time period are calculated.

[0014] As an optional implementation, in a second aspect of the invention, the characteristic type of the tissue characteristic parameter is a vascular compliance parameter, an elastic modulus parameter, a distensibility parameter, or a calcified plaque-related parameter; the vascular compliance parameter includes at least one of delayed compliance parameter, systolic blood pressure compliance parameter, diastolic blood pressure compliance parameter, and mean blood pressure compliance parameter; the elasticity model parameter includes at least one of bulk elastic modulus parameter, Young's elastic modulus parameter, and Petersen elastic modulus parameter.

[0015] As an optional implementation, in a second aspect of the invention, the feature calculation model is used to perform the following steps: For each time period, all ultrasound images corresponding to that time period are sorted from early to late based on their corresponding acquisition time points to obtain the corresponding image sequence data. The image sequence data is input into a trained LSTM neural network model to obtain the tissue feature parameters of the target vascular tissue corresponding to that time period. The LSTM neural network is trained using a training dataset that includes multiple training vascular image sequences and corresponding feature type parameter annotations.

[0016] As an optional implementation, in a second aspect of the invention, the specific method by which the first calculation module calculates the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the at least two tissue feature parameters includes: Based on the preset correspondence between tissue features and blood vessel wall stiffness parameters, the blood vessel wall stiffness parameter corresponding to each tissue feature parameter is determined. Calculate the parameter matrix composed of the blood vessel wall stiffness parameters corresponding to all the tissue feature parameters for each time period to obtain the blood vessel wall stiffness characteristics of the target blood vessel tissue for each time period.

[0017] As an optional implementation, in a second aspect of the invention, the second calculation module calculates the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data, including: For each time period, determine all the blood pressure data corresponding to that time period and the corresponding data acquisition time point; The multinomial fitting algorithm is used to fit all the blood pressure data and the corresponding data acquisition time points to obtain the set of coefficients for the change of blood pressure over time in the corresponding time period, so as to obtain the blood pressure fluctuation characteristics of the target vascular tissue in the corresponding time period.

[0018] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method by which it determines the state assessment result corresponding to the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period, including: The blood vessel wall stiffness characteristics and blood pressure fluctuation characteristics of the target blood vessel tissue in all the time periods are sorted from early to late according to the time period to obtain the stiffness characteristic sequence and the blood pressure characteristic sequence. Calculate the correlation parameter between the hardness feature sequence and the blood pressure feature sequence; The hardness feature sequence is input into the trained hardness health prediction model to obtain the output hardness state parameters. The blood pressure feature sequence is input into the trained blood pressure health prediction model to obtain the output blood pressure status parameters; The average values ​​of the stiffness state parameter and the blood pressure state parameter are calculated, and the product of the average value and the correlation parameter is calculated to obtain the state assessment result corresponding to the target vascular tissue.

[0019] As an optional implementation, in a second aspect of the invention, the system is further configured to perform the following steps: When the status assessment result is lower than a preset result threshold, the user age of the user corresponding to the target vascular tissue is obtained; The historical status evaluation results of multiple historical users whose age difference with the user's age is less than a preset threshold are selected from the historical database. Calculate the average of the result differences between the state assessment result and each of the historical state assessment results to obtain the difference parameter; Calculate the age parameter that is proportional to the difference parameter; The difference between the user's age and the age parameter is calculated to obtain the vascular age parameter corresponding to the target vascular tissue.

[0020] A third aspect of this invention discloses another vascular condition assessment system based on non-destructive ultrasound detection, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the vascular status assessment method based on non-destructive ultrasound detection disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the vascular condition assessment method based on non-destructive ultrasound detection disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires ultrasound images and blood pressure data of target vascular tissue at multiple time periods, calculates vascular wall stiffness characteristics and blood pressure fluctuation characteristics, and performs correlation analysis to determine the status assessment results. This enables accurate vascular tissue health assessment based on multimodal time-series data, improves the accuracy and foresight of early cardiovascular status judgment, and reduces the risk of misjudgment of vascular status due to single indicators or static analysis. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of a vascular status assessment method based on non-destructive ultrasound detection disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a vascular condition assessment system based on non-destructive ultrasound detection disclosed in an embodiment of the present invention.

[0026] Figure 3This is a schematic diagram of another vascular condition assessment system based on non-destructive ultrasound detection disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a method and system for vascular condition assessment based on non-destructive ultrasound detection. By acquiring ultrasound images and blood pressure data of the target vascular tissue at multiple time periods, it calculates vascular wall stiffness characteristics and blood pressure fluctuation characteristics, and performs correlation analysis to determine the condition assessment result. This enables accurate vascular tissue health assessment based on multimodal time-series data, improving the accuracy and predictability of early cardiovascular condition judgment and reducing the risk of misjudgment of vascular condition due to single indicators or static analysis. Detailed descriptions follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a schematic flowchart of a vascular condition assessment method based on non-destructive ultrasound detection disclosed in an embodiment of the present invention. Wherein, Figure 1The described vascular condition assessment method based on non-destructive ultrasound detection can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). Figure 1 As shown, this vascular condition assessment method based on non-destructive ultrasound detection may include the following operations: 101. Obtain ultrasound images and blood pressure data of the target vascular tissue at multiple time periods.

[0032] Optionally, the multiple time cycles can be a complete cardiac cycle consisting of the systolic and diastolic phases, or multiple consecutive cardiac cycles; the present invention does not limit this.

[0033] Optionally, the ultrasound image can be a B-mode grayscale image, an M-mode motion curve, or a color Doppler blood flow image; the present invention does not limit this.

[0034] Optionally, the blood pressure data can be synchronously collected cuff blood pressure or continuous non-invasive blood pressure monitoring values; this invention does not limit the data.

[0035] 102. Based on the ultrasound images, calculate the vessel wall stiffness characteristics of the target vascular tissue at each time period.

[0036] Optionally, the blood vessel wall stiffness characteristic can be elastic modulus, stiffness index, or pulse wave conduction velocity; this invention does not limit it.

[0037] 103. Based on blood pressure data, calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period.

[0038] Optionally, the blood pressure fluctuation characteristic can be the systolic-diastolic pressure difference, the blood pressure variation coefficient, or the pulse pressure; the present invention does not limit this.

[0039] 104. Based on the correlation analysis between the vascular wall stiffness characteristics and blood pressure fluctuation characteristics corresponding to each time period, determine the state assessment results corresponding to the target vascular tissue.

[0040] Optionally, the status assessment result can be a vascular health score or risk level, which is not limited in this invention.

[0041] As can be seen, the above-described embodiments of the invention acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods, calculate the characteristics of vascular wall stiffness and blood pressure fluctuations, and perform correlation analysis to determine the status assessment results. This enables accurate vascular tissue health assessment based on multimodal time-series data, improves the accuracy and foresight of early judgment of cardiovascular status, and reduces the risk of misjudgment of vascular status caused by a single indicator or static analysis.

[0042] As an optional embodiment, the step above, calculating the vessel wall stiffness characteristics of the target vascular tissue at each time period based on the ultrasound image, includes: The ultrasound image corresponding to each time period is input into the feature calculation model corresponding to at least two feature types respectively, so as to obtain at least two tissue feature parameters of the target vascular tissue in each time period. Calculate the vessel wall stiffness characteristics of the target vascular tissue at each time period based on at least two tissue characteristic parameters.

[0043] Optionally, the tissue characteristic parameters can be vascular compliance parameters, elastic modulus parameters, extensibility parameters, or calcified plaque-related parameters.

[0044] Optionally, vascular compliance parameters include at least one of delayed compliance parameters, systolic blood pressure compliance parameters, diastolic blood pressure compliance parameters, and mean blood pressure compliance parameters.

[0045] Optionally, the elastic model parameters include at least one of the bulk modulus parameter, Young's modulus parameter, and Petersen's modulus parameter.

[0046] As can be seen, through the above optional embodiments, by inputting ultrasound images of each time period into feature calculation models corresponding to multiple feature types to output tissue feature parameters and calculate blood vessel wall stiffness features, accurate quantitative assessment of stiffness based on multi-model fusion is achieved, improving the comprehensiveness and accuracy of blood vessel wall stiffness feature extraction and reducing the risk of stiffness assessment deviation caused by a single feature model.

[0047] As an optional embodiment, the feature calculation model in the above steps is used to perform the following steps: For each time period, all ultrasound images corresponding to that time period are sorted from early to late based on their corresponding acquisition time points to obtain the corresponding image sequence data. Image sequence data is input into a trained LSTM neural network model to obtain the tissue feature parameters of the target vascular tissue at that time period.

[0048] Optionally, the LSTM neural network is trained using a training dataset that includes multiple training vascular image sequences and corresponding feature type parameter annotations.

[0049] Optionally, the LSTM neural network model can be a 3-layer long short-term memory network with 256 hidden units in each layer, with added bidirectional structure and attention mechanism, using mean squared error loss function, trained on 80,000 vascular ultrasound sequences for 100 training epochs, with parameter prediction error less than 4.2%, which is not limited in this invention.

[0050] As can be seen, through the above optional embodiments, by sorting time-period ultrasound images into an image sequence and inputting it into a trained LSTM neural network model to output tissue feature parameters, accurate dynamic capture of features based on time-series image sequences can be achieved, improving the continuity and reliability of vascular tissue feature calculation and reducing the risk of feature distortion caused by isolated image analysis.

[0051] As an optional embodiment, the step described above, calculating the vessel wall stiffness characteristics of the target vascular tissue at each time period based on at least two tissue characteristic parameters, includes: Based on the preset correspondence between tissue characteristics and blood vessel wall stiffness parameters, determine the blood vessel wall stiffness parameter corresponding to each tissue characteristic parameter. Calculate the parameter matrix composed of the blood vessel wall stiffness parameters corresponding to all tissue feature parameters for each time period to obtain the blood vessel wall stiffness characteristics of the target blood vessel tissue for each time period.

[0052] Optionally, the relationship between these parameters can be an empirical formula, such as hardness index = k1 × thickness + k2 × patch load. This invention does not limit this.

[0053] Optionally, the parameter matrix can be a matrix of time period number × hardness parameter dimension, which is not limited in this invention.

[0054] As can be seen, through the above optional embodiments, by calculating the parameter matrix based on the correspondence between tissue features and blood vessel wall stiffness parameters as blood vessel wall stiffness features, a precise matrix mapping from multiple tissue features to stiffness features is achieved, improving the structured representation and comparability of stiffness features, and reducing the risk of stiffness calculation errors caused by fuzzy parameter correspondence.

[0055] As an optional embodiment, the step above, calculating the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on blood pressure data, includes: For each time period, determine all blood pressure data corresponding to that time period and the corresponding data acquisition time point; The polynomial fitting algorithm is used to fit all blood pressure data and the corresponding data acquisition time points to obtain the set of coefficients for the change of blood pressure over time in the corresponding time period, so as to obtain the blood pressure fluctuation characteristics of the target vascular tissue in the corresponding time period.

[0056] Optionally, the polynomial fitting algorithm can be a third-order polynomial least squares fitting, resulting in four coefficients representing the fluctuation curve; this invention does not impose any limitations on this.

[0057] As can be seen, through the above optional embodiments, the set of coefficients obtained by fitting blood pressure data with time points using a polynomial fitting algorithm is used as the blood pressure fluctuation feature, thereby achieving accurate nonlinear modeling of blood pressure changes over time, improving the dynamics and predictability of blood pressure fluctuation features, and reducing the risk of distortion of fluctuation features caused by simple statistics.

[0058] As an optional embodiment, the step above, determining the state assessment result of the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and blood pressure fluctuation characteristics corresponding to each time period, includes: The vessel wall stiffness characteristics and blood pressure fluctuation characteristics of the target vascular tissue in all time periods are sorted from early to late according to the time period to obtain the stiffness feature sequence and blood pressure feature sequence. Calculate the correlation parameters between the hardness feature sequence and the blood pressure feature sequence; Input the hardness feature sequence into the trained hardness health prediction model to obtain the output hardness state parameters; Input the blood pressure feature sequence into the trained blood pressure health prediction model to obtain the output blood pressure state parameters; The average values ​​of stiffness and blood pressure parameters are calculated, and the product of the average values ​​and the correlation parameters is calculated to obtain the state assessment results of the target vascular tissue.

[0059] Optionally, the correlation parameter can be the Pearson correlation coefficient or the mutual information value; this invention does not limit it.

[0060] Optionally, the hardness health prediction model can be a fully connected neural network with an input dimension of sequence length × feature dimension, 512-256-128 hidden layers, and an output health score of 0-100. It can be trained on 120,000 sequences. This invention does not limit the model.

[0061] Optionally, the structure of this blood pressure health prediction model is similar to that of the stiffness model and is specifically used for blood pressure fluctuation assessment; however, this invention does not limit it.

[0062] As can be seen, through the above optional embodiments, by sorting the blood vessel wall stiffness characteristics and blood pressure fluctuation characteristics sequences to calculate the correlation parameters, and then inputting them into the output state parameters of the stiffness and blood pressure health prediction models respectively, the state assessment results are obtained by combining the correlation product. This achieves a precise comprehensive assessment of blood vessel state based on correlation and dual-model fusion, improves the objectivity and comprehensiveness of the assessment results, and reduces the risk of misjudgment of state due to neglect of correlation.

[0063] As an optional embodiment, the method further includes the following steps: When the status assessment result is lower than the preset result threshold, obtain the user age of the user corresponding to the target vascular tissue; The historical status assessment results of multiple historical users whose age difference with the user's age is less than a preset threshold are selected from the historical database. The average difference between the state assessment results and each historical state assessment result is calculated to obtain the difference parameter. Calculate the age parameter that is proportional to the difference parameter; The difference between the user's age and the age parameter is calculated to obtain the vascular age parameter corresponding to the target vascular tissue.

[0064] Optionally, this difference parameter reflects the degree of vascular aging compared to people of the same age, but this invention does not limit it.

[0065] As can be seen, through the above optional embodiments, by calculating the difference parameter and generating the vascular age parameter based on the user's age when the status assessment result is lower than the threshold, accurate vascular aging assessment based on age matching and difference quantification is achieved, which improves the personalization and early warning value of vascular health management and reduces the risk of generalization of health assessment due to failure to consider age factors.

[0066] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a vascular condition assessment system based on non-destructive ultrasound detection, as disclosed in an embodiment of the present invention. Figure 2 The described vascular condition assessment system based on non-destructive ultrasound detection can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, this vascular condition assessment system based on non-destructive ultrasound detection may include: The acquisition module 201 is used to acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods.

[0067] The first calculation module 202 is used to calculate the vascular wall stiffness characteristics of the target vascular tissue at each time period based on the ultrasound image.

[0068] The second calculation module 203 is used to calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data.

[0069] The determination module 204 is used to determine the state assessment result of the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and blood pressure fluctuation characteristics corresponding to each time period.

[0070] As can be seen, the above-described embodiments of the invention acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods, calculate the characteristics of vascular wall stiffness and blood pressure fluctuations, and perform correlation analysis to determine the status assessment results. This enables accurate vascular tissue health assessment based on multimodal time-series data, improves the accuracy and foresight of early judgment of cardiovascular status, and reduces the risk of misjudgment of vascular status caused by a single indicator or static analysis.

[0071] As an optional embodiment, the first calculation module calculates the specific method by which it calculates the vessel wall stiffness characteristics of the target vascular tissue at each time period based on the ultrasound image, including: The ultrasound image corresponding to each time period is input into the feature calculation model corresponding to at least two feature types respectively, so as to obtain at least two tissue feature parameters of the target vascular tissue in each time period. Calculate the vessel wall stiffness characteristics of the target vascular tissue at each time period based on at least two tissue characteristic parameters.

[0072] As can be seen, through the above optional embodiments, by inputting ultrasound images of each time period into feature calculation models corresponding to multiple feature types to output tissue feature parameters and calculate blood vessel wall stiffness features, accurate quantitative assessment of stiffness based on multi-model fusion is achieved, improving the comprehensiveness and accuracy of blood vessel wall stiffness feature extraction and reducing the risk of stiffness assessment deviation caused by a single feature model.

[0073] As an optional embodiment, the tissue characteristic parameters are of the following types: vascular compliance parameters, elastic modulus parameters, extensibility parameters, or calcification plaque-related parameters; vascular compliance parameters include at least one of delayed compliance parameters, systolic blood pressure compliance parameters, diastolic blood pressure compliance parameters, and mean blood pressure compliance parameters; elasticity model parameters include at least one of bulk elastic modulus parameters, Young's elastic modulus parameters, and Peterson's elastic modulus parameters.

[0074] As can be seen, the above optional embodiments limit the feature types of tissue characteristic parameters so that the evaluation results of this solution can accurately characterize the comprehensive stiffness-related features of vascular tissue, assist in the accurate assessment of vascular tissue health, improve the accuracy and foresight of early judgment of cardiovascular status, and reduce the risk of misjudgment of vascular status due to single indicators or static analysis.

[0075] As an optional embodiment, the feature calculation model is used to perform the following steps: For each time period, all ultrasound images corresponding to that time period are sorted from early to late based on their corresponding acquisition time points to obtain the corresponding image sequence data. Image sequence data is input into a trained LSTM neural network model to obtain the tissue feature parameters of the target vascular tissue at that time period. The LSTM neural network is trained using a training dataset that includes multiple training vascular image sequences and corresponding feature type parameter annotations.

[0076] As can be seen, through the above optional embodiments, by sorting time-period ultrasound images into an image sequence and inputting it into a trained LSTM neural network model to output tissue feature parameters, accurate dynamic capture of features based on time-series image sequences can be achieved, improving the continuity and reliability of vascular tissue feature calculation and reducing the risk of feature distortion caused by isolated image analysis.

[0077] As an optional embodiment, the first calculation module calculates the specific method by which it calculates the vessel wall stiffness characteristics of the target vascular tissue at each time period based on at least two tissue feature parameters, including: Based on the preset correspondence between tissue characteristics and blood vessel wall stiffness parameters, determine the blood vessel wall stiffness parameter corresponding to each tissue characteristic parameter. Calculate the parameter matrix composed of the blood vessel wall stiffness parameters corresponding to all tissue feature parameters for each time period to obtain the blood vessel wall stiffness characteristics of the target blood vessel tissue for each time period.

[0078] As can be seen, through the above optional embodiments, by calculating the parameter matrix based on the correspondence between tissue features and blood vessel wall stiffness parameters as blood vessel wall stiffness features, a precise matrix mapping from multiple tissue features to stiffness features is achieved, improving the structured representation and comparability of stiffness features, and reducing the risk of stiffness calculation errors caused by fuzzy parameter correspondence.

[0079] As an optional embodiment, the second calculation module calculates the specific method by which it calculates the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on blood pressure data, including: For each time period, determine all blood pressure data corresponding to that time period and the corresponding data acquisition time point; The polynomial fitting algorithm is used to fit all blood pressure data and the corresponding data acquisition time points to obtain the set of coefficients for the change of blood pressure over time in the corresponding time period, so as to obtain the blood pressure fluctuation characteristics of the target vascular tissue in the corresponding time period.

[0080] As can be seen, through the above optional embodiments, the set of coefficients obtained by fitting blood pressure data with time points using a polynomial fitting algorithm is used as the blood pressure fluctuation feature, thereby achieving accurate nonlinear modeling of blood pressure changes over time, improving the dynamics and predictability of blood pressure fluctuation features, and reducing the risk of distortion of fluctuation features caused by simple statistics.

[0081] As an optional embodiment, the determining module determines the specific method for assessing the state of the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and blood pressure fluctuation characteristics corresponding to each time period, including: The vessel wall stiffness characteristics and blood pressure fluctuation characteristics of the target vascular tissue in all time periods are sorted from early to late according to the time period to obtain the stiffness feature sequence and blood pressure feature sequence. Calculate the correlation parameters between the hardness feature sequence and the blood pressure feature sequence; Input the hardness feature sequence into the trained hardness health prediction model to obtain the output hardness state parameters; Input the blood pressure feature sequence into the trained blood pressure health prediction model to obtain the output blood pressure state parameters; The average values ​​of stiffness and blood pressure parameters are calculated, and the product of the average values ​​and the correlation parameters is calculated to obtain the state assessment results of the target vascular tissue.

[0082] As can be seen, through the above optional embodiments, by sorting the blood vessel wall stiffness characteristics and blood pressure fluctuation characteristics sequences to calculate the correlation parameters, and then inputting them into the output state parameters of the stiffness and blood pressure health prediction models respectively, the state assessment results are obtained by combining the correlation product. This achieves a precise comprehensive assessment of blood vessel state based on correlation and dual-model fusion, improves the objectivity and comprehensiveness of the assessment results, and reduces the risk of misjudgment of state due to neglect of correlation.

[0083] As an optional embodiment, the system is also used to perform the following steps: When the status assessment result is lower than the preset result threshold, obtain the user age of the user corresponding to the target vascular tissue; The historical status assessment results of multiple historical users whose age difference with the user's age is less than a preset threshold are selected from the historical database. The average difference between the state assessment results and each historical state assessment result is calculated to obtain the difference parameter. Calculate the age parameter that is proportional to the difference parameter; The difference between the user's age and the age parameter is calculated to obtain the vascular age parameter corresponding to the target vascular tissue.

[0084] As can be seen, through the above optional embodiments, by calculating the difference parameter and generating the vascular age parameter based on the user's age when the status assessment result is lower than the threshold, accurate vascular aging assessment based on age matching and difference quantification is achieved, which improves the personalization and early warning value of vascular health management and reduces the risk of generalization of health assessment due to failure to consider age factors.

[0085] Example 3 Please see Figure 3 , Figure 3 This is another vascular condition assessment system based on non-destructive ultrasound detection disclosed in the embodiments of the present invention. Figure 3 The described vascular condition assessment system based on non-destructive ultrasound detection is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). Figure 3 As shown, this vascular condition assessment system based on non-destructive ultrasound detection may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the vascular status assessment method based on non-destructive ultrasound detection described in Embodiment 1.

[0086] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the vascular condition assessment method based on non-destructive ultrasound detection described in Embodiment 1.

[0087] Example 5 This 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 cause a computer to perform the steps of the vascular condition assessment method based on non-destructive ultrasound detection described in Embodiment 1.

[0088] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0090] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0091] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0092] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0093] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0094] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0095] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0096] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0097] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0099] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0100] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0101] Finally, it should be noted that the vascular condition assessment method and system based on non-destructive ultrasound detection disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for assessing vascular status based on non-destructive ultrasound detection, characterized in that, The method includes: Acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods; Based on the ultrasound images, the vessel wall stiffness characteristics of the target vascular tissue in each time period are calculated. Based on the blood pressure data, calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period; Based on the correlation analysis between the blood vessel wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period, the state assessment result corresponding to the target blood vessel tissue is determined.

2. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 1, characterized in that, The step of calculating the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the ultrasound image includes: The ultrasound image corresponding to each time period is input into a feature calculation model corresponding to at least two feature types, so as to obtain at least two tissue feature parameters of the target vascular tissue in each time period. Based on the at least two tissue feature parameters, the vessel wall stiffness characteristics of the target vascular tissue in each time period are calculated.

3. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 2, characterized in that, The tissue characteristic parameters are of the following types: vascular compliance parameters, elastic modulus parameters, extensibility parameters, or calcified plaque-related parameters; the vascular compliance parameters include at least one of delayed compliance parameters, systolic blood pressure compliance parameters, diastolic blood pressure compliance parameters, and mean blood pressure compliance parameters; the elasticity model parameters include at least one of bulk elastic modulus parameters, Young's elastic modulus parameters, and Peterson's elastic modulus parameters.

4. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 2, characterized in that, The feature calculation model is used to perform the following steps: For each time period, all ultrasound images corresponding to that time period are sorted from early to late based on their corresponding acquisition time points to obtain the corresponding image sequence data. The image sequence data is input into a trained LSTM neural network model to obtain the tissue feature parameters of the target vascular tissue corresponding to that time period. The LSTM neural network is trained using a training dataset that includes multiple training vascular image sequences and parameter annotations of corresponding feature types.

5. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 2, characterized in that, The step of calculating the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the at least two tissue characteristic parameters includes: Based on the preset correspondence between tissue features and blood vessel wall stiffness parameters, the blood vessel wall stiffness parameter corresponding to each tissue feature parameter is determined. Calculate the parameter matrix composed of the blood vessel wall stiffness parameters corresponding to all the tissue feature parameters for each time period to obtain the blood vessel wall stiffness characteristics of the target blood vessel tissue for each time period.

6. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 1, characterized in that, The step of calculating the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data includes: For each time period, determine all the blood pressure data corresponding to that time period and the corresponding data acquisition time point; The multinomial fitting algorithm is used to fit all the blood pressure data and the corresponding data acquisition time points to obtain the set of coefficients for the change of blood pressure over time in the corresponding time period, so as to obtain the blood pressure fluctuation characteristics of the target vascular tissue in the corresponding time period.

7. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 1, characterized in that, The step of determining the state assessment result of the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period includes: The blood vessel wall stiffness characteristics and blood pressure fluctuation characteristics of the target blood vessel tissue in all the time periods are sorted from early to late according to the time period to obtain the stiffness characteristic sequence and the blood pressure characteristic sequence. Calculate the correlation parameter between the hardness feature sequence and the blood pressure feature sequence; The hardness feature sequence is input into the trained hardness health prediction model to obtain the output hardness state parameters. The blood pressure feature sequence is input into the trained blood pressure health prediction model to obtain the output blood pressure status parameters; The average values ​​of the stiffness state parameter and the blood pressure state parameter are calculated, and the product of the average value and the correlation parameter is calculated to obtain the state assessment result corresponding to the target vascular tissue.

8. The method for assessing vascular status based on non-destructive ultrasound detection according to claim 1, characterized in that, The method further includes: When the status assessment result is lower than a preset result threshold, the user age of the user corresponding to the target vascular tissue is obtained; The historical status evaluation results of multiple historical users whose age difference with the user's age is less than a preset threshold are selected from the historical database. Calculate the average of the result differences between the state assessment result and each of the historical state assessment results to obtain the difference parameter; Calculate the age parameter that is proportional to the difference parameter; The difference between the user's age and the age parameter is calculated to obtain the vascular age parameter corresponding to the target vascular tissue.

9. A vascular condition assessment system based on non-destructive ultrasound detection, characterized in that, The system includes: The acquisition module is used to acquire ultrasound images and blood pressure data of the target vascular tissue at multiple time periods; The first calculation module is used to calculate the vessel wall stiffness characteristics of the target vascular tissue in each time period based on the ultrasound image. The second calculation module is used to calculate the blood pressure fluctuation characteristics of the target vascular tissue in each time period based on the blood pressure data. The determination module is used to determine the state assessment result corresponding to the target vascular tissue based on the correlation analysis between the vascular wall stiffness characteristics and the blood pressure fluctuation characteristics corresponding to each time period.

10. A vascular condition assessment system based on non-destructive ultrasound detection, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the vascular status assessment method based on non-destructive ultrasound detection as described in any one of claims 1-8.

Images