Cardiovascular and cerebrovascular disease screening method based on big data

Abstract

The invention relates to the technical field of disease screening, in particular to a cardiovascular and cerebrovascular disease screening method based on big data, which is used for positioning and capturing cells for screening cardiovascular and cerebrovascular diseases. Performing behavior tracking on the target cells marked by the nanoparticles in the target area; the method further comprises the following steps: completing cardiovascular and cerebrovascular disease screening according to a behavior tracking result; the target cells related to cardiovascular and cerebrovascular diseases can be accurately captured in a blood sample by combining the nanoparticles with the antibody and utilizing the dynamic magnetic field and laser regulation, the screening accuracy is improved, and the interference of non-target cells is reduced; the diffusion range and survival time of the target cells are accurately tracked, the diffusion dynamic state and physiological state of the target cells can be accurately identified and tracked through multi-scale image sequence processing and self-adaptive threshold segmentation, and the monitoring precision of cell behaviors is enhanced; and secondary verification is carried out through a cosine similarity analysis mechanism, so that the accuracy of a screening result can be effectively improved, and misjudgment or missed judgment is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of disease screening, and specifically to a method for screening cardiovascular and cerebrovascular diseases based on big data. Background Art

[0002] Cardiovascular and cerebrovascular disease screening usually includes a series of non-invasive and invasive tests to detect cardiovascular and cerebrovascular system lesions at an early stage. However, at this stage, screening for cardiovascular diseases faces the following challenges: Currently, commonly used screening methods for cardiovascular and cerebrovascular diseases, such as blood biochemical tests and electrocardiograms, can provide certain diagnostic information, but they are often unable to accurately monitor lesions at the cellular level, and subtle changes in the early stages of the disease are difficult to detect. Therefore, the accuracy and sensitivity of screening are still low, and there may be risks of missed diagnosis and misdiagnosis. In the process of cell screening, how to accurately capture target cells is a key technical challenge. Existing cell capture methods often face the problem of miscapture of non-target cells or low capture efficiency. In addition, traditional capture methods fail to effectively combine multiple control methods, resulting in the failure to fully optimize the accuracy and efficiency of the capture process. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] To solve the above technical problems, the present invention provides the following technical solution: a method for screening cardiovascular and cerebrovascular diseases based on big data, comprising the following steps: Collect blood samples from people to be screened, use nanoparticles to mark target cells, set the target area by adjusting the magnitude of the magnetic field gradient, and use the magnetic field force to control the directional movement of target cells to the target area. The characteristics are: Track the behavior of target cells marked by nanoparticles in the target area, including diffusion range tracking, specifically: Collect image data containing target cells in the target area, construct the image data into a multi-scale image sequence, fuse edge feature maps of different scales, generate a comprehensive diffusion boundary feature map, and perform adaptive segmentation to determine the diffusion range boundary of the target cells; And, survival time tracking, specifically: The activity is determined by collecting the fluorescence intensity of the target cells, the survival state of the current cells is judged according to the activity, and an activity decay model is constructed to determine the survival time of the target cells, including the survival time under the linear decay model and the survival time under the exponential decay model; Also includes, The behavior tracking results are constructed into feature vectors, and adaptive weight coefficients are introduced to reconstruct the feature vectors. The feature vectors are combined to complete the screening of cardiovascular and cerebrovascular diseases, and the screening results are re-verified in combination with the feedback verification mechanism.

[0005] As a preferred embodiment of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the target area is set by adjusting the magnitude of the magnetic field gradient as follows: By setting the magnetic field gradient The size of the nanoparticles forms a target area for guiding the movement of cells labeled with nanoparticles. , specifically: Set target area The position coordinates are , the initial position coordinates of the target cells marked by nanoparticles are , by setting the magnitude of the magnetic field gradient, the target area is set, then, , in, Indicates the target area Location coordinates, represents the initial position coordinates of the target cells marked by nanoparticles, represents the magnetic field gradient.

[0006] As a preferred embodiment of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the directional movement of target cells to the target area is specifically as follows: According to Newton's second law, the speed at which target cells marked by nanoparticles move and location Dynamically changes with time and is affected by the applied magnetic field Control, then construct the motion equation of the target cell, then we have, , By integrating the constructed motion equation, we can obtain the change of the velocity and position of the target cell with time under the action of the magnetic field, and we have: Changes in speed, , Changes in position, , in, represents the magnetic force exerted on the target cell, represents the mass of target cells labeled with nanoparticles, Represents an infinitesimal time variable, representing the time from arrive Accumulate the acceleration during the time period. represents the initial position of the target cell labeled by the nanoparticles, , Indicates that at any time speed at 1000 s; By dynamically adjusting the magnetic field strength , guide the target cells labeled by nanoparticles to the target area, until all the cells labeled by nanoparticles gather in the target area Afterwards, the magnetic field is gradually turned off to achieve precise capture of the target cells.

[0007] As a preferred solution of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the fusion of edge feature maps of different scales is specifically as follows: Image data Constructed as a multi-scale image sequence, we have, , in, represents the upper limit of the scale, Indicated in The image of the first layer of the pyramid of the image data at the moment, Indicated in The image of the second layer of the pyramid of the image data at the moment, Indicated in The image of the nth layer of the pyramid of the image data at the moment, with the increase of the scale sequence, the resolution of each layer of the image is reduced by half, so as to obtain image representations of different scales; Then for each scale Image , use the edge detection algorithm to calculate the edge features and obtain the edge feature map of the current scale image ; The edge feature maps of different scales are fused to generate a comprehensive diffusion boundary feature map of image data. , then there is, , in, Indicated in scale The edge feature map extracted from Indicates The correction coefficient of the scale image is used to make positive corrections according to different scales. represents the scale sequence, represents the upper limit of the number of scales, Represents the generated comprehensive diffusion boundary feature map.

[0008] As a preferred solution of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the adaptive segmentation of the comprehensive diffusion boundary feature map is specifically as follows: For the generated comprehensive diffusion boundary feature map , according to the pixels of the integrated diffusion boundary feature map, the integrated diffusion boundary feature map is divided into multiple sub-regions, and the local brightness threshold of each sub-region is calculated, then, , in, represents the local brightness threshold, Represents the average pixel brightness in the local area, Represents the brightness standard deviation of the local area, which is the contrast of the current sub-area; At the same time, the global grayscale histogram of the image of the comprehensive diffusion boundary feature map is calculated, and the calculation result is set as the global brightness threshold ; Set the adaptive segmentation threshold according to the set global brightness threshold and local brightness threshold , then there is, , in, Indicates the set global brightness threshold, represents the local brightness threshold, Represents the adaptive segmentation threshold, which is used to implement the secondary processing of the comprehensive diffusion boundary feature map, specifically: The brightness of each pixel in the comprehensive diffusion boundary feature map Compared with the adaptive segmentation threshold, If the brightness contrast of the pixel satisfies the formula , mark the current position as the target cell diffusion area; If the brightness contrast of the pixel satisfies the formula , remove the current position from the target cell diffusion area; The secondary processing of the comprehensive diffusion boundary feature map is performed until all pixel positions have completed the secondary processing, and the final target cell diffusion area is collected, and the target cell diffusion range tracking is completed.

[0009] As a preferred embodiment of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the method of judging the survival status of the current cell according to the activity is as follows: Obtain the fluorescence intensity of the target cells through the sensor and set the initial activity of the target cells And the initial state ; Setting Activity Thresholds The activity thresholds set are based on the different survival times of the target cells and correspond to the activity thresholds at different stages, specifically: When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; And the set activity threshold satisfies the formula ; By comparing the current activity of the target cell with the activity threshold, the current survival state of the target cell is determined, specifically: Random Selection The target cell at the moment, determines the currently selected moment , in which stage of the survival time range, and select the corresponding activity threshold to judge the cell survival state at the current moment, then, If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a survival state, and the survival time of the cell is ,in, Indicates the currently selected cell from The time interval between the moment and the state of death; If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a dead state, and the survival time of the cell is ,in, Indicates the time node of the currently selected cell from the death state to The time interval between moments.

[0010] As a preferred embodiment of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the construction of the activity decay model to determine the survival time of the target cells is as follows: According to the constructed activity decay model, the time interval for the activity value of the target cell to reach the activity threshold is determined, then, When the selected cells are in the viable state, the linear decay model is used to determine the cell The time interval between the moment of survival and the moment of death , specifically: , in, express The activity value of the target cell at the moment, Represents the linear attenuation coefficient, which controls the degree of activity attenuation under the linear attenuation model. Indicates the currently selected cell from The time interval between the moment of death and the state of death, Indicates the set activity threshold; When the selected cells are in a death state, the exponential decay model is used to determine the time point from the death state to the The time interval between moments , specifically: , in, express The activity value of the target cell at the moment, Indicates the set activity threshold, Represents the exponential decay coefficient, which controls the degree of activity decay under the exponential decay model. Indicates the time node of the currently selected cell from the death state to The time interval between moments.

[0011] As a preferred solution of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention, the feedback verification mechanism performs a secondary verification on the screening results as follows: , in, represents the reconstructed feature vector, Represents the feature vector corresponding to the cell in the historical data, represents the Euclidean norm of the current cell feature vector, Represents the Euclidean norm of the feature vector corresponding to the cell in the historical data, Represents the cosine similarity between the two, which is used to complete the secondary verification of the current cell corresponding to the person to be screened, then, When the calculated cosine similarity satisfies the formula When , it means that the current cell is highly similar to the historical cell, and the person to be screened corresponding to the current cell is a patient with cardiovascular and cerebrovascular disease; When the calculated cosine similarity satisfies the formula , it means that the current cell is not similar to the historical cell, and the person to be screened corresponding to the current cell is not a patient with cardiovascular and cerebrovascular disease.

[0012] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a cardiovascular and cerebrovascular disease screening method based on big data when executing the computer program.

[0013] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a cardiovascular and cerebrovascular disease screening method based on big data.

[0014] Beneficial effects of the present invention: The present invention combines nanoparticles and antibodies and uses dynamic magnetic fields and laser regulation to accurately capture target cells related to cardiovascular and cerebrovascular diseases in blood samples. This precise capture improves the accuracy of screening and reduces interference from non-target cells. High-resolution microscopy and image analysis algorithms are used to accurately track the diffusion range and survival time of target cells. Multi-scale image sequence processing and adaptive threshold segmentation can accurately identify and track the diffusion dynamics and physiological state of target cells, enhancing the monitoring accuracy of cell behavior. By adaptively adjusting the weight coefficients of diffusion range and survival time, and flexibly adjusting the feature weights of the model according to the external environment (such as temperature and light changes), the adaptability and robustness of the disease screening system are improved, and the negative impact of environmental factors on the screening results is avoided; The secondary verification through the cosine similarity analysis mechanism can effectively improve the accuracy of the screening results, reduce misjudgments or missed judgments, and especially cope with the impact of environmental changes, further enhancing the reliability of the screening system; Based on the constructed feature vector, combined with adaptive weight adjustment and historical data verification, intelligent screening of cardiovascular and cerebrovascular diseases is achieved. The output results of the scoring model can effectively determine whether the person to be screened is at risk of cardiovascular and cerebrovascular diseases, thereby achieving efficient disease screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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. Among them: Figure 1 This is a schematic diagram of the overall method steps of the cardiovascular and cerebrovascular disease screening method based on big data of the present invention. DETAILED DESCRIPTION

[0016] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0018] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0019] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0020] Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0021] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0022] Example 1, reference Figure 1 , is an embodiment of the present invention, providing a cardiovascular and cerebrovascular disease screening method based on big data, comprising the following steps, S1: Target cell positioning capture.

[0023] Specifically, the target cell positioning capture is based on the blood sample of the person to be screened, and the target cells are positioned and captured using a positioning capture algorithm. The target cells are cells used to screen cardiovascular and cerebrovascular diseases. The positioning capture algorithm combines nanoparticles with antibodies and uses dynamic regulation of magnetic fields and lasers to achieve precise capture of target cells.

[0024] Furthermore, the positioning capture algorithm integrates multifunctional nanoparticle design and dynamic magnetic regulation to achieve precise capture of target cells, which is specifically implemented as follows: Collect blood samples from people to be screened , including, target cell collection and disrupting cell aggregation , while preparing the nanoparticle collection for capturing target cells ; Based on the collection of nanoparticles, the target cells in the blood sample are located and captured, specifically: For the input blood sample, the nanoparticles carrying antibodies corresponding to the target cell antigens are fused with the blood sample, then, When the blood sample contains target cells, the target cell antigens fuse with the antibodies carried by the nanoparticles, thereby labeling the nanoparticles on the target cells; Until all target cells are labeled with nanoparticles; After all target cells are labeled with nanoparticles, unbound free nanoparticles are removed by centrifugation to obtain a sample containing only target cells labeled with nanoparticles. (Nanoparticle labeling) It should be noted that in order to further improve the accuracy of target cell capture, the controllability of the magnetic field is used to guide the target cells labeled with nanoparticles to the target area. The target area is used for subsequent screening of cardiovascular and cerebrovascular diseases to achieve accurate capture of the target cells. The specific capture is as follows: The target cell sample labeled with nanoparticles is placed in a dynamic magnetic field environment, and the magnetic field is activated to activate the magnetic capture mechanism. By setting the magnetic field gradient The size of the nanoparticles forms a target area for guiding the movement of cells labeled with nanoparticles. , specifically: Set target area The position coordinates are , the initial position coordinates of the target cells marked by nanoparticles are , by setting the magnitude of the magnetic field gradient, the target area is set, then, , in, Indicates the target area Location coordinates, represents the initial position coordinates of the target cells marked by nanoparticles, represents the magnetic field gradient.

[0025] At the same time, by dynamically adjusting the magnetic field strength Different magnetic field strength distributions are formed at different time points, so that the target cells marked by nanoparticles move from the initial position to the target area, thereby completing the precise capture of the target cells. Specifically: According to Newton's second law, the speed at which target cells marked by nanoparticles move and location Dynamically changes with time and is affected by the applied magnetic field Control, then construct the motion equation of the target cell, then we have, , By integrating the constructed motion equation, we can obtain the change of the velocity and position of the target cell with time under the action of the magnetic field, and we have: Changes in speed, , Changes in position, , in, represents the magnetic force exerted on the target cell, represents the mass of target cells labeled with nanoparticles, Represents an infinitesimal time variable, representing the time from arrive Accumulate the acceleration during the time period. represents the initial position of the target cell labeled by the nanoparticles, , Indicates that at any time speed at 1000 s; By dynamically adjusting the magnetic field strength , guide the target cells labeled by nanoparticles to the target area, until all the cells labeled by nanoparticles gather in the target area Afterwards, the magnetic field is gradually turned off to achieve precise capture of the target cells.

[0026] It should be noted that during the capture process, the signal strength of the target area is monitored in real time. As the target cells gather, the signal strength in the target area gradually increases, setting the upper limit of the signal strength in the target area. , if the monitored signal strength satisfies the formula When , it means that the number of cells that can be aggregated in the current target area has reached the upper limit. By setting the magnetic field gradient size, a new target area is re-formed until all cells labeled with nanoparticles are accurately captured.

[0027] S2: Mark and track the target cells that have completed positioning.

[0028] Specifically, the marking and tracking of the located target cells is to track the behavior of the cells marked by the nanoparticles in the target area, including diffusion range tracking and survival time tracking, so as to facilitate the subsequent screening of cardiovascular and cerebrovascular diseases.

[0029] Furthermore, the diffusion range tracking is to use a high-resolution microscope to take multiple images of the target area at consecutive time nodes, and to track the diffusion range of the target cells in the target area through an image analysis algorithm, which is specifically implemented as follows: Use a high-resolution microscope to take multiple images of the target area at consecutive time points to complete the image data of the target cells in the target area. collection of , Indicates the time point of shooting; The collected image data is preprocessed using Gaussian filtering and median filtering to make the image data smooth and keep the boundaries clear. Gaussian filtering and median filtering are well-known prior arts in the art and will not be described in detail here. For image data at multiple time nodes, the image data at one time node is randomly selected for explanation in this embodiment. In practical applications, the image data at all time nodes need to be processed, and then, Image data Constructed as a multi-scale image sequence, we have, , in, represents the upper limit of the scale, Indicated in The image of the first layer of the pyramid of the image data at the moment, Indicated in The image of the second layer of the pyramid of the image data at the moment, Indicated in The image of the nth layer of the pyramid of the image data at the moment, with the increase of the scale sequence, the resolution of each layer of the image is reduced by half, so as to obtain image representations of different scales; Then for each scale Image , use the edge detection algorithm to calculate the edge features and obtain the edge feature map of the current scale image ; The edge feature maps of different scales are fused to generate a comprehensive diffusion boundary feature map of image data. , then there is, , in, Indicated in scale The edge feature map extracted from Expressing the The correction coefficient of the scale image is used to make positive corrections according to different scales. represents the scale sequence, represents the upper limit of the number of scales, Represents the generated comprehensive diffusion boundary feature map.

[0030] It should be noted that in order to further improve the accuracy of tracking the diffusion range of target cells, adaptive threshold segmentation is performed on the generated comprehensive diffusion boundary feature map to improve the accuracy of diffusion range tracking and increase the application scenarios of this technical solution. The specific implementation is as follows: For the generated comprehensive diffusion boundary feature map According to the pixels of the integrated diffusion boundary feature map, the integrated diffusion boundary feature map is divided into a plurality of sub-regions. The network is explained to calculate the local brightness threshold of each sub-region, then, , in, represents the local brightness threshold, Represents the average pixel brightness in the local area, Represents the brightness standard deviation of the local area, which is the contrast of the current sub-area; At the same time, the global grayscale histogram of the image of the comprehensive diffusion boundary feature map is calculated, and the calculation result is set as the global brightness threshold ; Set the adaptive segmentation threshold according to the set global brightness threshold and local brightness threshold , then there is, , in, Indicates the set global brightness threshold, represents the local brightness threshold, Represents the adaptive segmentation threshold, which is used to implement the secondary processing of the comprehensive diffusion boundary feature map, specifically: The brightness of each pixel in the comprehensive diffusion boundary feature map Compared with the adaptive segmentation threshold, If the brightness contrast of the pixel satisfies the formula , mark the current position as the target cell diffusion area; If the brightness contrast of the pixel satisfies the formula , remove the current position from the target cell diffusion area; The secondary processing of the comprehensive diffusion boundary feature map is performed until all pixel positions have completed the secondary processing, and the final target cell diffusion area is collected, and the target cell diffusion range tracking is completed.

[0031] Furthermore, the survival time tracking is to accurately estimate the survival time of the cells by monitoring the activity state of the target cells and updating the state according to the real-time activity monitoring data. The detection of the activity state of the target cells is to monitor the physiological state of the target cells in real time and dynamically determine whether the target cells are in a survival state based on the state threshold. The specific implementation is as follows: Obtain the fluorescence intensity of the target cells through the sensor and set the initial activity of the target cells And the initial state ; Setting Activity Thresholds The activity thresholds set are based on the different survival times of the target cells and correspond to the activity thresholds at different stages, specifically: When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; And the set activity threshold satisfies the formula ; By comparing the current activity of the target cell with the activity threshold, the current survival state of the target cell is determined, specifically: Random Selection The target cell at the moment, determines the currently selected moment , in which stage of the survival time range, and select the corresponding activity threshold to judge the cell survival state at the current moment, then, If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a survival state, and the survival time of the cell is ,in, Indicates the currently selected cell from The time interval between the moment and the state of death; If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a dead state, and the survival time of the cell is ,in, Indicates the time node of the currently selected cell from the death state to The time interval between moments.

[0032] It should be noted that in order to further determine The value of cell state conversion time was analyzed again, and the specific analysis is as follows: Since the determination of the survival state of the target cell is based on the activity value, the determination of the time interval between the cell's survival state and the cell's death state can be converted into the time interval for the cell's activity value to reach the activity threshold, then, The activity decay model is constructed to determine the time interval for the activity value of the target cell to reach the activity threshold, specifically: According to the state of the target cells, different activity decay models are constructed, including a linear decay model and an exponential decay model. The linear decay model is used to determine the decay of the activity of the target cells when they are in a viable state. Then, ,

[0033] in, Indicates the initial activity of the target cell. Represents the linear attenuation coefficient, which controls the degree of activity attenuation under the linear attenuation model. It is set by the implementer according to the actual application scenario. represents the decay time, express Activity value of target cells at each moment; The exponential decay model is used to determine the decay of activity after target cell death, then, ,

[0034] in, express The activity value of the target cell at the moment, Indicates the set activity threshold, Represents the exponential decay coefficient, which controls the degree of activity decay under the exponential decay model. It is set by the implementer according to the actual application scenario. represents the decay time, Indicates the time interval corresponding to the activity threshold, which is determined by the decay time, specifically: When the decay time satisfies the formula hour, The value satisfies the formula ; When the decay time satisfies the formula hour, The value satisfies the formula ; When the decay time satisfies the formula hour, The value satisfies the formula ; According to the constructed activity decay model, the time interval for the activity value of the target cell to reach the activity threshold is determined, then, When the selected cells are in the viable state, the linear decay model is used to determine the cell The time interval between the moment of survival and the moment of death , specifically: ,

[0035] in, express The activity value of the target cell at the moment, Represents the linear attenuation coefficient, which controls the degree of activity attenuation under the linear attenuation model. It is set by the implementer according to the actual application scenario. Indicates the currently selected cell from The time interval between the moment of death and the state of death, Represents the set activity threshold, at which the cell survival time is ; When the selected cells are in a death state, the exponential decay model is used to determine the time point from the death state to the The time interval between moments , specifically: ,

[0036] in, express The activity value of the target cell at the moment, Indicates the set activity threshold, Represents the exponential decay coefficient, which controls the degree of activity decay under the exponential decay model. It is set by the implementer according to the actual application scenario. Indicates the time node of the currently selected cell from the death state to The time interval between the moments, at which the cell survival time is .

[0037] It should be noted that for the diffusion range tracking and survival time tracking of the target cells, the two are constructed as new feature vectors , then there is, ,in, represents the diffusion range tracking result, Represents the survival time tracking results, Represents the constructed feature vector, which is used for subsequent screening of cardiovascular and cerebrovascular diseases.

[0038] S3: Conduct intelligent screening for cardiovascular and cerebrovascular diseases based on the tag tracking results.

[0039] Specifically, the intelligent screening of cardiovascular and cerebrovascular diseases is to use the constructed feature vector as a parameter, and to construct a cardiovascular and cerebrovascular disease screening scoring model, and to complete the screening of cardiovascular and cerebrovascular diseases according to the output results of the cardiovascular and cerebrovascular disease screening scoring model, which is specifically implemented as follows: For the constructed feature vector ,In order to improve the application scenarios of the overall technical solution, the feature vector is adaptively weighted and reconstructed, then, ,

[0040] in, represents the diffusion range tracking result, Represents the survival time tracking results, represents the reconstructed feature vector, Represents the adaptive weight coefficient, which is regulated by dynamic environment information, specifically: The initial weight coefficient satisfies the formula , at this time, the target cells are in a normal state, and the influence of diffusion range and survival time are in a balanced state; When external environmental factors change, including changes in temperature and light, the cells are in a state of stress, increasing the weight coefficient corresponding to the diffusion range. , reduce the weight coefficient corresponding to the survival time ; The implementation personnel shall dynamically adjust the adaptive weight coefficient according to the actual application scenario; Based on the reconstructed feature vector, a cardiovascular and cerebrovascular disease screening scoring model is constructed, then: ,

[0041] in, represents the reconstructed feature vector, represents the scoring function, Represents the output of the scoring model, which is used to complete the screening of cardiovascular and cerebrovascular diseases, specifically: Set the scoring threshold based on the cell history data of patients with cardiovascular and cerebrovascular diseases , used to determine whether the patient is suffering from cardiovascular and cerebrovascular diseases; If the comparison between the output of the scoring model and the scoring threshold satisfies the formula , indicating that the person to be screened corresponding to the current cell is not a patient with cardiovascular and cerebrovascular diseases; If the comparison between the output of the scoring model and the scoring threshold satisfies the formula , indicating that the person to be screened corresponding to the current cell has the risk of cardiovascular and cerebrovascular diseases, triggering the feedback verification mechanism for secondary verification, then, For the diffusion range and survival time of the target cell corresponding to the current score, the secondary verification is completed by comparing the similarity between the current cell state and the cells in the historical data. The cells in the historical data are cells with the same diffusion range and survival time in patients with cardiovascular and cerebrovascular diseases. Specifically, the cosine similarity between the two is tested to complete the secondary verification, which is: ,

[0042] in, represents the reconstructed feature vector, Represents the feature vector corresponding to the cell in the historical data, represents the Euclidean norm of the current cell feature vector, Represents the Euclidean norm of the feature vector corresponding to the cell in the historical data, Represents the cosine similarity between the two, which is used to complete the secondary verification of the current cell corresponding to the person to be screened, then, When the calculated cosine similarity satisfies the formula When , it means that the current cell is highly similar to the historical cell, and the person to be screened corresponding to the current cell is a patient with cardiovascular and cerebrovascular disease; When the calculated cosine similarity satisfies the formula , it means that the current cell is not similar to the historical cell, and the person to be screened corresponding to the current cell is not a patient with cardiovascular and cerebrovascular disease.

[0043] It should be noted that through the adjustment of adaptive weight coefficients, the weight coefficients of diffusion range and survival time can be flexibly adjusted according to the environmental changes of cells, thereby improving the accuracy and robustness of disease screening. At the same time, the set feedback verification mechanism can reduce misjudgment caused by environmental changes and further improve the accuracy of cardiovascular and cerebrovascular disease screening.

[0044] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0045] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0046] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0047] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0048] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0049] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A cardiovascular and cerebrovascular disease screening method based on big data, comprising the following steps: collecting a blood sample set of a person to be screened, marking target cells with nanoparticles, setting a target area by adjusting the magnitude of a magnetic field gradient, and achieving directional movement of target cells to the target area by regulating the magnetic field force, characterized in that: Track the behavior of target cells labeled with nanoparticles in the target area. Including, diffusion range tracking, specifically: collecting image data containing target cells in the target area, constructing the image data into a multi-scale image sequence, fusing edge feature maps of different scales to generate a comprehensive diffusion boundary feature map, and performing adaptive segmentation to determine the diffusion range boundary of the target cells; And, survival time tracking, specifically: determining the activity by collecting the fluorescence intensity of the target cells, judging the current survival status of the cells based on the activity, and constructing an activity decay model to determine the survival time of the target cells, including the survival time under the linear decay model and the survival time under the exponential decay model; also It includes constructing the behavior tracking results into feature vectors, introducing adaptive weight coefficients to reconstruct the feature vectors, combining the feature vectors to complete the screening of cardiovascular and cerebrovascular diseases, and combining the feedback verification mechanism to conduct secondary verification of the screening results.

2. The method for screening cardiovascular and cerebrovascular diseases based on big data according to claim 1, characterized in that: The target area is set by adjusting the magnitude of the magnetic field gradient as follows: By setting the magnetic field gradient The size of the nanoparticles forms a target area for guiding the movement of cells labeled with nanoparticles. , specifically: Set target area The position coordinates are , the initial position coordinates of the target cells marked by nanoparticles are , by setting the magnitude of the magnetic field gradient, the target area is set, then, ， in, Indicates the target area Location coordinates, represents the initial position coordinates of the target cells marked by nanoparticles, represents the magnetic field gradient.

3. The cardiovascular and cerebrovascular disease screening method based on big data according to claim 2, characterized in that: The method of completing the directional movement of the target cells to the target area is specifically as follows: According to Newton's second law, the speed at which target cells marked by nanoparticles move and location Dynamically changes with time and is affected by the applied magnetic field Control, then construct the motion equation of the target cell, then we have, ， By integrating the constructed motion equation, we can obtain the change of the velocity and position of the target cell with time under the action of the magnetic field, and we have: Changes in speed, ， Changes in position, ， in, represents the magnetic force exerted on the target cell, represents the mass of target cells labeled with nanoparticles, Represents an infinitesimal time variable, representing the time from arrive Accumulate the acceleration during the time period. represents the initial position of the target cell labeled by the nanoparticles, , Indicates that at any time speed at 1000 s; By dynamically adjusting the magnetic field strength , guide the target cells labeled by nanoparticles to the target area, until all the cells labeled by nanoparticles gather in the target area Afterwards, the magnetic field is gradually turned off to achieve precise capture of the target cells.

4. The cardiovascular and cerebrovascular disease screening method based on big data according to claim 3, characterized in that: The fusion of edge feature maps of different scales is specifically as follows: Image data Constructed as a multi-scale image sequence, we have, ,in, represents the upper limit of the scale, Indicated in The image of the first layer of the pyramid of the image data at the moment, Indicated in The image of the second layer of the pyramid of the image data at the moment, Indicated in The image of the nth layer of the pyramid of the image data at the moment, with the increase of the scale sequence, the resolution of each layer of the image is reduced by half, so as to obtain image representations of different scales; Then for each scale Image , use the edge detection algorithm to calculate the edge features and obtain the edge feature map of the current scale image ; The edge feature maps of different scales are fused to generate a comprehensive diffusion boundary feature map of image data. , then there is, ， in, Indicated in scale The edge feature map extracted from Expressing the The correction coefficient of the scale image is used to make positive corrections according to different scales. represents the scale sequence, represents the upper limit of the number of scales, Represents the generated comprehensive diffusion boundary feature map.

5. The method for screening cardiovascular and cerebrovascular diseases based on big data according to claim 4, characterized in that: The adaptive segmentation of the integrated diffusion boundary feature map is specifically as follows: For the generated comprehensive diffusion boundary feature map , according to the pixels of the integrated diffusion boundary feature map, the integrated diffusion boundary feature map is divided into multiple sub-regions, and the local brightness threshold of each sub-region is calculated, then, ， in, represents the local brightness threshold, Represents the average pixel brightness in the local area, Represents the brightness standard deviation of the local area, which is the contrast of the current sub-area; At the same time, the global grayscale histogram of the image of the comprehensive diffusion boundary feature map is calculated, and the calculation result is set as the global brightness threshold ; Set the adaptive segmentation threshold according to the set global brightness threshold and local brightness threshold , then there is, ， in, Indicates the set global brightness threshold, represents the local brightness threshold, Represents the adaptive segmentation threshold, which is used to implement the secondary processing of the comprehensive diffusion boundary feature map, specifically: The brightness of each pixel in the comprehensive diffusion boundary feature map Compared with the adaptive segmentation threshold, If the brightness contrast of the pixel satisfies the formula , mark the current position as the target cell diffusion area; If the brightness contrast of the pixel satisfies the formula , remove the current position from the target cell diffusion area; The secondary processing of the comprehensive diffusion boundary feature map is performed until all pixel positions have completed the secondary processing, and the final target cell diffusion area is collected, and the target cell diffusion range tracking is completed.

6. The method for screening cardiovascular and cerebrovascular diseases based on big data according to claim 5, characterized in that: The specific method of judging the survival status of the current cell according to the activity is as follows: Obtain the fluorescence intensity of the target cells through the sensor and set the initial activity of the target cells And the initial state ; Setting Activity Thresholds The activity thresholds set are based on the different survival times of the target cells and correspond to the activity thresholds at different stages, specifically: When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; When the survival time range of the target cells is When the activity threshold is ; And the set activity threshold satisfies the formula ; By comparing the current activity of the target cell with the activity threshold, the current survival state of the target cell is determined, specifically: Random Selection The target cell at the moment, determines the currently selected moment , in which stage of the survival time range, and select the corresponding activity threshold to judge the cell survival state at the current moment, then, If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a survival state, and the survival time of the cell is ,in, Indicates the currently selected cell from The time interval between the moment and the state of death; If the activity of the selected target cell meets the activity threshold, the formula , it means that the currently selected cell is in a dead state, and the survival time of the cell is ,in, Indicates the time node of the currently selected cell from the death state to The time interval between moments.

7. The method for screening cardiovascular and cerebrovascular diseases based on big data according to claim 6, characterized in that: The construction of the activity decay model to determine the survival time of the target cells is specifically as follows: According to the constructed activity decay model, the time interval for the activity value of the target cell to reach the activity threshold is determined, then, When the selected cells are in the viable state, the linear decay model is used to determine the cell The time interval between the moment of survival and the moment of death , specifically: ， in, express The activity value of the target cell at the moment, Represents the linear attenuation coefficient, which controls the degree of activity attenuation under the linear attenuation model. Indicates the currently selected cell from The time interval between the moment of death and the state of death, Indicates the set activity threshold; When the selected cells are in a death state, the exponential decay model is used to determine the time point from the death state to the The time interval between moments , specifically: ， in, express The activity value of the target cell at the moment, Indicates the set activity threshold, Represents the exponential decay coefficient, which controls the degree of activity decay under the exponential decay model. Indicates the time node of the currently selected cell from the death state to The time interval between moments.

8. The cardiovascular and cerebrovascular disease screening method based on big data according to claim 7, characterized in that: The feedback verification mechanism performs secondary verification on the screening results as follows: For the diffusion range and survival time of the target cell corresponding to the current score, the secondary verification is completed by comparing the similarity between the current cell state and the cell in the historical data and checking the cosine similarity between the two. Specifically: ， in, represents the reconstructed feature vector, Represents the feature vector corresponding to the cell in the historical data, represents the Euclidean norm of the current cell feature vector, Represents the Euclidean norm of the feature vector corresponding to the cell in the historical data, It represents the cosine similarity between the two, which is used to complete the secondary verification of the current cell corresponding to the person to be screened, then, When the calculated cosine similarity satisfies the formula When , it means that the current cell is highly similar to the historical cell, and the person to be screened corresponding to the current cell is a patient with cardiovascular and cerebrovascular disease; When the calculated cosine similarity satisfies the formula , it means that the current cell is not similar to the historical cell, and the person to be screened corresponding to the current cell is not a patient with cardiovascular and cerebrovascular disease.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images