Atherosclerosis marker detection data integrated analysis method and system

Abstract

The invention relates to the field of medical data analysis, in particular to an atherosclerosis marker detection data integrated analysis method and system. The method comprises the following steps: acquiring multi-dimensional biological detection index information and a sclerotic marker medical image of an atherosclerosis marker of a patient; performing adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; performing multi-time-point visual identification on the medical image of the sclerotic marker, and performing plaque geometric morphology analysis so as to generate plaque geometric morphology characteristics of each time point; and performing multi-time-point morphological change tracking and nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point so as to construct a hardened plaque time sequence morphological evolution trajectory. According to the method, personalized and efficient atherosclerosis marker detection and analysis are realized, so that the atherosclerosis prediction accuracy is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of medical data analysis, and in particular to an integrated analysis method and system for atherosclerosis marker detection data. Background Art

[0002] Atherosclerosis is a common chronic disease characterized by the appearance of atherosclerotic plaques in the blood vessel wall, which leads to vascular stenosis and hardening. In severe cases, it can cause cardiovascular and cerebrovascular diseases and even endanger life. With the aging of the population and changes in lifestyle, the incidence of atherosclerosis has increased year by year, becoming one of the main causes of death and disability worldwide. Therefore, it is particularly important to detect and evaluate the occurrence and development of atherosclerosis in a timely and accurate manner.

[0003] Traditional methods for detecting atherosclerosis usually rely on imaging examinations, blood biomarker tests and other means. Imaging examinations such as ultrasound, CT, MRI, etc. can provide intuitive images of vascular structures, helping doctors to identify and evaluate the location and size of plaques and their impact on blood flow. However, imaging examinations require high professional skills and experience from doctors, and cannot directly provide dynamic information on intravascular biomarkers. Although blood biomarker testing can provide a quantitative assessment of the early risk of atherosclerosis, traditional single markers are often difficult to fully and accurately reflect the complex pathological process of atherosclerosis, and their diagnostic effect and predictive accuracy are low.

[0004] Therefore, the demand for integrated analysis methods for atherosclerosis marker detection data is becoming increasingly prominent. How to effectively integrate and analyze data from different data sources through innovative technical solutions to provide more accurate and comprehensive disease prediction and evaluation has become a key issue in the current scientific research field. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes an integrated analysis method and system for atherosclerosis marker detection data to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides a method for integrated analysis of atherosclerosis marker detection data, comprising the following steps: Step S1: obtaining multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of the patient; performing adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; Step S2: Performing multi-time point visual recognition on the medical images of sclerosis markers and performing plaque geometry analysis to generate plaque geometry features at each time point; Step S3: tracking the morphological changes at multiple time points and performing nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; Step S4: mining the potential association of multiple indicators for the standardized biological detection information, and then fitting the evolution of the situation over time, so as to construct a multi-dimensional detection indicator situation evolution diagram; Step S5: Based on the multi-dimensional detection index trend evolution diagram, a personalized prediction of the temporal morphological evolution trajectory of the sclerotic plaque is performed for multiple time periods in the future, thereby obtaining the prediction data of the atherosclerosis state in multiple time periods; Step S6: Quantitatively analyze the atherosclerosis status prediction data for multiple time periods, and perform personalized comprehensive diagnosis to generate personalized diagnosis results. The present invention integrates different types of data (biological detection indicators and medical images) to fully understand the patient's atherosclerosis status. The multidimensionality of this information provides more angles for subsequent analysis, which helps to comprehensively evaluate the severity and development process of the disease. Through the comprehensive consideration of biological detection and imaging data, it is possible to break through the limitations of a single data source, reduce errors, and improve diagnostic accuracy, ensuring the comprehensiveness and accuracy of the analysis process. There are differences in the detection methods, ranges and units of different markers. Through adaptive standardization, these differences can be eliminated, so that the data is consistent and the comparability of various indicators is ensured. After standardization, the data is used for a variety of analysis methods, and there will be no deviation due to different data scales, ensuring the accuracy of subsequent analysis results. Through standardization, biomarker data from different sources are analyzed under the same framework to ensure the cross-domain compatibility of data and further improve the accuracy of analysis. By analyzing the imaging data at different time points, the evolution of atherosclerosis is tracked in real time, and the morphology and position changes of plaques at each moment are obtained. Image recognition at multiple time points helps doctors better understand the dynamic changes of the disease, so as to make timely intervention and treatment. Through precise geometric morphological analysis, the key features of plaques (such as size, shape, boundary smoothness, etc.) are extracted. These geometric features are key indicators for assessing whether atherosclerotic plaques are stable and whether they will rupture, which is helpful for disease prediction and risk assessment. Through multi-point morphological tracking, the trend of atherosclerotic plaques changing over time can be clearly seen. This dynamic tracking can reveal whether the plaque is growing, deforming, rupturing, etc., which helps to accurately predict the progression of the disease. Modeling plaque evolution using a nonlinear morphological change model can capture the complex laws of plaque morphological changes. Traditional linear analysis ignores this complexity, and nonlinear analysis can provide more accurate and comprehensive trend predictions, making disease assessment more reliable. Through multi-indicator potential association analysis, the complex interactions between different biomarkers are identified. This is of great significance for understanding the systemic characteristics of the disease and the key factors of disease progression. Through this method, new biomarker combinations are discovered to improve the sensitivity of early diagnosis. According to the passage of time series, the changing trends of each biomarker at different time points are fitted, which helps to predict future health conditions, discover potential risks in advance, and provide patients with more targeted monitoring. By constructing a multi-dimensional trend evolution diagram, the evolution trends of various biomarkers at different time points and their relationship with plaque morphological changes are intuitively displayed. This graphical display allows clinicians to intuitively understand the patient's disease progression and potential future risks. By combining multi-dimensional data, a personalized disease prediction model is tailored for each patient. Taking into account the changing patterns of markers and disease characteristics of different patients, personalized predictions can provide more accurate health management recommendations.By quantitatively analyzing the predicted data of multiple time periods, the risk and development trend of atherosclerosis can be accurately assessed. This quantitative analysis can provide more reliable information than a single result, helping clinicians to develop more reasonable treatment plans. Combining the patient's personal data, historical health records, and disease development trends, a comprehensive diagnosis is made to provide personalized health advice. This personalized diagnosis can maximize the treatment effect and the patient's quality of life based on the patient's specific situation.

[0007] In the present specification, a system for integrated analysis of atherosclerosis marker detection data is provided, which is used to execute the method for integrated analysis of atherosclerosis marker detection data as described above, comprising: A data processing module is used to obtain multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of patients; and to perform adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; The geometric morphology analysis module is used to perform multi-time point visual recognition of medical images of sclerosis markers and perform plaque geometric morphology analysis to generate the geometric morphology characteristics of plaques at each time point; The morphological trajectory evolution module is used to track the morphological changes at multiple time points and perform nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; The situation evolution module is used to mine the potential associations of multiple indicators of standardized biological detection information, and then perform time-series situation evolution fitting to construct a multi-dimensional detection indicator situation evolution diagram; The multi-period prediction module is used to make personalized predictions of the evolution trajectory of the sclerotic plaque time series morphology based on the multi-dimensional detection index trend evolution diagram, so as to obtain the prediction data of atherosclerosis status in multiple time periods; The personalized diagnosis and analysis module is used to quantitatively analyze the prediction data of atherosclerosis status in multiple time periods and perform personalized comprehensive diagnosis to generate personalized diagnosis results. The present invention systematically obtains the patient's health information by integrating various types of data, thereby improving the accuracy of disease analysis. This multi-dimensional data fusion provides a more comprehensive basis for subsequent analysis. Adaptive standardization eliminates the scale differences between data and ensures the comparability of different biomarkers and imaging data. This not only improves the efficiency of data processing, but also reduces the errors caused by inconsistent data during subsequent modeling, thereby improving the reliability of analysis. Through visual recognition of multi-time point images, the evolution of plaques can be tracked and the course of atherosclerosis can be obtained in real time. The analysis of multiple time points provides time dimension data on disease progression, which helps to understand the dynamic process of plaque development. Through geometric morphological analysis, the size, shape and other characteristics of plaques can be quantified in detail. This information is an important basis for predicting plaque stability, rupture risk and disease progression, and can provide more decision-making support for clinicians. Through multi-time point morphological tracking, the trend of plaque morphology changes over time can be accurately captured. This dynamic change provides a reliable basis for early warning of the disease. The nonlinear evolution model can capture the complex trends in plaque morphological changes, rather than simple linear relationships. This provides a deeper insight into the development of the disease, especially the prediction of emergencies such as plaque rupture. By mining the potential associations between biomarkers, new early disease predictors can be discovered, which is of great significance for accurately identifying high-risk patients. Time-series lapse analysis provides the law of changes in disease markers over time, which can provide quantifiable references for disease prognosis and early intervention, and provide clinicians with more accurate predictions. According to the multidimensional data of patients, combined with the health status of each patient, personalized disease prediction is carried out. Through predictions for future time periods, patients can understand the progress of the disease in advance, adjust treatment plans in time, and avoid the aggravation of the disease process. It can accurately predict the state of the disease at a certain point in the future, help patients and doctors develop more scientific treatment strategies, and reduce the risk of complications caused by the disease. Through quantitative analysis, the health status of patients can be quantified and a more sophisticated risk assessment can be provided. This quantitative assessment helps to develop accurate intervention strategies for patients. By combining information from multiple aspects, a personalized comprehensive diagnostic report is generated, which can provide more accurate and personalized treatment recommendations compared with traditional diagnostic methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the steps of an integrated analysis method for atherosclerosis marker detection data according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0009] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0010] The present application example provides an integrated analysis method and system for atherosclerosis marker detection data. The execution subject of the integrated analysis method and system for atherosclerosis marker detection data includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0011] See also Figures 1 to 4 The present invention provides an integrated analysis method for atherosclerosis marker detection data, the integrated analysis method for atherosclerosis marker detection data comprising the following steps: Step S1: obtaining multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of the patient; performing adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; Step S2: Performing multi-time point visual recognition on the medical images of sclerosis markers and performing plaque geometry analysis to generate plaque geometry features at each time point; Step S3: tracking the morphological changes at multiple time points and performing nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; Step S4: mining the potential association of multiple indicators for the standardized biological detection information, and then fitting the evolution of the situation over time, so as to construct a multi-dimensional detection indicator situation evolution diagram; Step S5: Based on the multi-dimensional detection index trend evolution diagram, a personalized prediction of the temporal morphological evolution trajectory of the sclerotic plaque is performed for multiple time periods in the future, thereby obtaining the prediction data of the atherosclerosis state in multiple time periods; Step S6: Quantitatively analyze the atherosclerosis status prediction data for multiple time periods, and perform personalized comprehensive diagnosis to generate personalized diagnosis results. The present invention integrates different types of data (biological detection indicators and medical images) to fully understand the patient's atherosclerosis status. The multidimensionality of this information provides more angles for subsequent analysis, which helps to comprehensively evaluate the severity and development process of the disease. Through the comprehensive consideration of biological detection and imaging data, it is possible to break through the limitations of a single data source, reduce errors, and improve diagnostic accuracy, ensuring the comprehensiveness and accuracy of the analysis process. There are differences in the detection methods, ranges and units of different markers. Through adaptive standardization, these differences can be eliminated, so that the data is consistent and the comparability of various indicators is ensured. After standardization, the data is used for a variety of analysis methods, and there will be no deviation due to different data scales, ensuring the accuracy of subsequent analysis results. Through standardization, biomarker data from different sources are analyzed under the same framework to ensure the cross-domain compatibility of data and further improve the accuracy of analysis. By analyzing the imaging data at different time points, the evolution of atherosclerosis is tracked in real time, and the morphology and position changes of plaques at each moment are obtained. Image recognition at multiple time points helps doctors better understand the dynamic changes of the disease, so as to make timely intervention and treatment. Through precise geometric morphological analysis, the key features of plaques (such as size, shape, boundary smoothness, etc.) are extracted. These geometric features are key indicators for assessing whether atherosclerotic plaques are stable and whether they will rupture, which is helpful for disease prediction and risk assessment. Through multi-point morphological tracking, the trend of atherosclerotic plaques changing over time can be clearly seen. This dynamic tracking can reveal whether the plaque is growing, deforming, rupturing, etc., which helps to accurately predict the progression of the disease. Modeling plaque evolution using a nonlinear morphological change model can capture the complex laws of plaque morphological changes. Traditional linear analysis ignores this complexity, and nonlinear analysis can provide more accurate and comprehensive trend predictions, making disease assessment more reliable. Through multi-indicator potential association analysis, the complex interactions between different biomarkers are identified. This is of great significance for understanding the systemic characteristics of the disease and the key factors of disease progression. Through this method, new biomarker combinations are discovered to improve the sensitivity of early diagnosis. According to the passage of time series, the changing trends of each biomarker at different time points are fitted, which helps to predict future health conditions, discover potential risks in advance, and provide patients with more targeted monitoring. By constructing a multi-dimensional trend evolution diagram, the evolution trends of various biomarkers at different time points and their relationship with plaque morphological changes are intuitively displayed. This graphical display allows clinicians to intuitively understand the patient's disease progression and potential future risks. By combining multi-dimensional data, a personalized disease prediction model is tailored for each patient. Taking into account the changing patterns of markers and disease characteristics of different patients, personalized predictions can provide more accurate health management recommendations.By quantitatively analyzing the predicted data of multiple time periods, the risk and development trend of atherosclerosis can be accurately assessed. This quantitative analysis can provide more reliable information than a single result, helping clinicians to develop more reasonable treatment plans. Combining the patient's personal data, historical health records, and disease development trends, a comprehensive diagnosis is made to provide personalized health advice. This personalized diagnosis can maximize the treatment effect and the patient's quality of life based on the patient's specific situation.

[0012] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of an integrated analysis method for detecting atherosclerosis markers according to the present invention. In this example, the steps of the integrated analysis method for detecting atherosclerosis markers include: Step S1: obtaining multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of the patient; performing adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; In this embodiment, after obtaining authorization from the hospital and the patient, multi-dimensional biological detection is performed, and the patient is examined using imaging techniques such as ultrasound, CT or MRI to obtain medical images of sclerosis markers. The image should include the cross-section and length of the artery and the specific location and morphological characteristics of the plaque. Ensure that the equipment settings (such as resolution and contrast agent use) during image acquisition are standardized to improve the quality and comparability of the image. Integrate biological detection indicators and medical imaging data into a unified database. Each patient should have a unique identifier for subsequent analysis and tracking. The biological indicator data should include the test date, indicator name, measurement value and unit to ensure the integrity of the data. Clean the collected data, identify and process missing values, outliers and duplicate records. Missing values ​​are processed by mean filling or interpolation, and outliers are detected and processed by box plots or Z-score methods. Select a suitable standardization method, usually using Z-score standardization or Min-Max standardization. Standardize each biological detection indicator. After calculating the mean and standard deviation of each indicator, apply the Z-score formula for conversion. Ensure that the data type remains consistent during the standardization process, and record the standardized parameters of each indicator for future de-standardization. After the standardization process is completed, check the distribution of the standardized results and draw a histogram or box plot to ensure that the mean of the data is 0 and the standard deviation is 1, thereby verifying the effectiveness of the standardization.

[0013] Step S2: Performing multi-time point visual recognition on the medical images of sclerosis markers and performing plaque geometry analysis to generate plaque geometry features at each time point; In this embodiment, relevant image data are extracted from the patient's medical image database. These image data come from ultrasound, CT or MRI, ensuring that the image quality is good and has sufficient resolution (for example, the resolution of CT images should reach 1mm³, and the resolution of ultrasound images should reach more than 500μm). The images at each time point should be clearly marked to facilitate subsequent comparison and analysis. The extracted images are preprocessed, including denoising, contrast enhancement and normalization. Techniques such as high-pass filtering and histogram equalization are used to improve the clarity and contrast of the image. Through open source image processing libraries (such as OpenCV): import cv2 # Read the image image = cv2.imread('image_path') # Denoise denoised_image = cv2.fastNlMeansDenoising(image, None, 30, 7, 21) # Histogram equalization equalized_image = cv2.equalizeHist(denoised_image) Select appropriate image recognition algorithms for plaque detection and segmentation. Use deep learning models such as convolutional neural networks (CNN) or U-Net, which have excellent performance in medical image analysis and are particularly suitable for processing complex plaque morphology. Use annotated image datasets to train deep learning models. The dataset should contain a variety of plaque types and morphologies to improve the generalization ability of the model. During model training, use cross-validation methods to monitor the performance of the model to ensure the accuracy and robustness of the model. During training, set hyperparameters (such as learning rate, batch size, etc.) and use appropriate loss functions (such as cross entropy loss function) for optimization. Use the trained model to detect plaques on the images at each time point. Calculate the output through forward propagation to obtain the boundary and area of ​​the plaque. This process should record the pixel coordinates of the plaque and its corresponding shape features. Perform geometric shape feature analysis on the segmented plaques and extract the following features: Area: the total number of pixels of the plaque in the image. Perimeter: the length of the plaque boundary, calculated through boundary points. Shape factor: calculate the circularity of the plaque, aspect ratio: the ratio of the length and width of the plaque, reflecting the degree of stretching of the plaque. The extracted geometric feature information (such as area, perimeter, shape factor, etc.) is organized into a data frame (DataFrame), ensuring that the feature information at each time point is clearly visible. Each row should contain a timestamp, a patch ID, and the corresponding geometric feature.

[0014] Step S3: tracking the morphological changes at multiple time points and performing nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; In this embodiment, a suitable algorithm is selected to track the changes in plaque morphology, usually using dynamic time warping (DTW) or morphological analysis methods. DTW is suitable for processing data with time series characteristics and can capture the trend of morphological changes between different time points. The geometric features of each plaque at different time points are analyzed using the selected algorithm. First, the geometric feature vector of each time point is calculated, and then the DTW algorithm is applied to calculate the similarity between the time series to identify the changes between adjacent time points. The change results of the plaque at different time points are recorded in a data frame, and a change trajectory diagram is generated. The visualization results use a line graph or a scatter plot to show the changes of the plaque on the time axis, which is convenient for observing the evolution trend of the plaque. Select a suitable nonlinear model for the evolution analysis of the morphological trend trajectory. Common methods include polynomial regression, spline regression or Gaussian process regression. These models can handle complex nonlinear relationships and are suitable for describing the changes in plaque morphology over time. Use the sorted plaque geometric feature data to build a nonlinear regression model. For each plaque, select a suitable feature as an independent variable (such as time, area, etc.) and fit it as a dependent variable. For example, using a polynomial regression model, set different polynomial orders and select the best model through cross-validation. During the training process, monitor the model's fit (such as R² value) to ensure its accuracy. After the model is fitted, generate a time-series morphological evolution trajectory for each plaque. Analyze the model results and observe the changing trend of plaque morphology (such as growth, shrinkage, shape variation, etc.). Visualize the evolution trajectory and generate dynamic charts to show the dynamic changes of plaque morphology over time, which is convenient for clinicians to analyze and make decisions.

[0015] Step S4: mining the potential association of multiple indicators for the standardized biological detection information, and then fitting the evolution of the situation over time, so as to construct a multi-dimensional detection indicator situation evolution diagram; In this embodiment, all standardized biological detection indicator data are collected, including blood lipids, blood sugar, inflammatory markers, etc. These data should cover all relevant time points to ensure their integrity and consistency. The biological indicators at each time point should be organized in the form of a data frame to ensure that the data is clear and easy to read. Clean the data, identify and process missing values ​​and outliers. Missing values ​​are processed by mean filling or interpolation, and outliers can be detected by the Z-score method. The cleaning process ensures the accuracy and stability of subsequent analysis. Select a suitable statistical analysis method to mine potential associations among multiple indicators. Commonly used methods include Pearson correlation coefficient analysis or Spearman rank correlation coefficient, which can effectively identify linear or nonlinear associations between indicators. Calculate the correlation for each pair of indicators in the standardized data. Record the correlation results in a new data frame, and generate a correlation heat map to visualize the association between indicators. Use the Seaborn library to draw a heat map: import seaborn as sns import matplotlib.pyplot as plt plt.figure(figsize=(10, 8)) sns.heatmap(correlation_matrix, annot=1, fmt='.2f', cmap='coolwarm') plt.title('Correlation Heatmap of Biological Indicators') plt.show() Select an appropriate time series model for trend evolution fitting. Commonly used models include autoregressive integrated moving average (ARIMA) or long short-term memory (LSTM), which can effectively capture trends and seasonality in time series data. Divide the integrated data set into a training set and a test set, usually 70% for training and 30% for testing. Ensure the randomness of the data to improve the generalization ability of the model. Use the training set to train the selected time series model. For the ARIMA model, determine the optimal p, d, and q parameters and select them using the AIC or BIC criteria. For the LSTM model, set appropriate hyperparameters (such as learning rate, batch size) and use cross-validation to monitor model performance.

[0016] After training, the model effect is evaluated on the test set, using the mean square error (MSE) or root mean square error (RMSE) as the evaluation indicator: from sklearn.metrics import mean_squared_error predictions = model.predict(X_test) mse = mean_squared_error(y_test, predictions) Based on the output of the fitting model, a trend evolution diagram of multi-dimensional detection indicators is generated. The visualization results include time series diagrams, which show the changing trend of each indicator at different time points, facilitating clinical analysis and decision-making.

[0017] Step S5: Based on the multi-dimensional detection index trend evolution diagram, a personalized prediction of the temporal morphological evolution trajectory of the sclerotic plaque is performed for multiple time periods in the future, thereby obtaining the prediction data of the atherosclerosis state in multiple time periods; In this embodiment, the temporal morphological evolution trajectory data of the sclerotic plaque is collected, including the geometric features (such as area, perimeter, shape factor, etc.) at each time point. These data should be combined with biological indicators to form a data set containing multi-dimensional features. Data cleaning is performed to process missing values ​​and outliers to ensure the integrity and accuracy of the data. Missing values ​​can be processed using mean filling or interpolation, and outliers can be detected and eliminated by methods such as Z-score. Select a suitable prediction model for personalized prediction of multiple time periods in the future. Commonly used models include long short-term memory networks (LSTM), support vector machines (SVM) or random forests. These models can process time series data and are suitable for capturing the complex relationship between plaque morphology and biological indicators. The integrated data set is divided into a training set and a test set. Usually 70% is used for training and 30% is used for testing. In the training set, ensure that biological indicators and plaque features at multiple time points are included to improve the learning effect of the model. Use the training set to train the selected personalized prediction model. For the LSTM model, set appropriate hyperparameters such as learning rate and batch size, and use cross-validation method to monitor model performance. During the training process, the loss functions of training and validation are monitored to prevent overfitting. After the model training is completed, the plaque geometry and biological indicator data at the last known time point are used as input to generate prediction data for multiple time periods in the future. These time periods are set according to clinical needs, such as status predictions for the next 3 months, 6 months, and 12 months. The input data is passed into the trained model to generate prediction data for the atherosclerosis status at future time points. These prediction data should include changes in the geometric characteristics of the plaque, expected values ​​of relevant biological indicators, etc., to form a comprehensive prediction result. The generated prediction results are recorded in a data frame to ensure that the prediction information for each time period is clear and visible. The changing trend of the future atherosclerosis status is displayed through visualization tools (such as charts or heat maps) to facilitate clinicians to analyze and make decisions.

[0018] Step S6: Quantitatively analyze the atherosclerosis status prediction data for multiple time periods, and perform personalized comprehensive diagnosis to generate personalized diagnosis results. In this embodiment, the collected data is sorted to ensure that the prediction data of each patient is concentrated together and sorted by time period. Check the missing values ​​and outliers in the data, and the missing values ​​are processed using a filling method (such as mean filling). The outliers are detected and eliminated by methods such as Z-score to ensure the accuracy of subsequent analysis. Descriptive statistical analysis is performed on the prediction data of atherosclerosis status in each time period. Calculate the mean, standard deviation, maximum value, minimum value and other statistics of each time period to evaluate the state changes in different time periods. For example: calculate the mean of plaque area in different time periods and observe its trend over time. Calculate the standard deviation of the level of inflammatory markers to understand its degree of variation in the patient population. Use correlation analysis methods (such as Pearson correlation coefficient or Spearman rank correlation coefficient) to evaluate the potential association between each biological indicator in the prediction data. By calculating the correlation matrix, identify indicators that show significant correlation in different time periods, so as to facilitate the basis for subsequent comprehensive diagnosis. Organize the quantitative analysis results into a report, recording the key statistical indicators and correlation analysis results of each time period. Visualize the data for easy understanding, such as using charts to show the changes in plaque area and trends of biological indicators in different time periods. Select a suitable comprehensive evaluation model and combine biological indicators, plaque geometric characteristics and the patient's clinical background information for personalized comprehensive diagnosis. The model is a score-based evaluation system, such as the Framingham risk score or the SCORE model, which assesses the risk of cardiovascular events based on multiple risk factors. The predicted data of atherosclerosis status of each patient at different time periods are summarized to form a personalized input data set. The input data should include various biological indicators, plaque characteristics, patient age, gender and other information. Input the prepared data into the selected comprehensive evaluation model to calculate the personalized risk score of each patient at different time periods. According to the evaluation results of the model, the patients are divided into different risk levels (such as low risk, medium risk, high risk), and corresponding diagnostic recommendations are generated.

[0019] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: obtaining multi-dimensional biological detection index information of the patient's atherosclerosis markers and medical images of atherosclerosis markers; Step S12: performing intelligent marker classification on the multi-dimensional biological detection indicator information to obtain marker intelligent classification data; Step S13: Screening key markers according to the marker intelligent classification data, and extracting multi-dimensional biological detection index information of the key markers; Step S14: Adaptively standardize the multi-dimensional biological detection index information of the key markers to obtain standardized biological detection information.

[0020] In this embodiment, after obtaining authorization from the hospital and the patient, multidimensional biological tests are performed, including blood biochemical indicators (such as cholesterol, triglycerides, C-reactive protein, etc.), which can reflect biomarkers of atherosclerosis. The samples are standardized in the laboratory to ensure that the collection process complies with bioethical and experimental standards. Imaging examinations (such as ultrasound, CT or MRI) are used to obtain the patient's arteriosclerosis imaging data. Ensure the clarity and resolution of the image for subsequent image analysis. The imaging data should be marked with the patient's basic information and clinical background for data integration. The collected biological detection indicators and medical imaging data are formatted to ensure that all data can be processed on the same platform. Use data management software (such as Excel or SQL database) to import and integrate data. The collected data is checked for integrity and consistency, and missing values, outliers and duplicate records are removed to ensure data quality. For biological detection indicators, a reasonable range is set to exclude obviously erroneous physiological values. Feature selection is performed on multidimensional biological detection indicators to identify key indicators related to atherosclerosis. Potential markers are determined through literature review and expert consultation. Preprocess the bioassay indicators, including missing value filling, data normalization and standardization, to ensure that different features are on the same scale for subsequent analysis. Select appropriate machine learning algorithms for marker classification, such as random forest, support vector machine (SVM) or neural network. Random forest is suitable for processing high-dimensional data and can effectively perform feature selection and classification. Divide the data set into a training set (80%) and a test set (20%), use the training set to train the selected model, and adjust the model's hyperparameters (such as the number of trees, maximum depth, etc.). Evaluate the model and use indicators such as accuracy, F1 score, and ROC curve to evaluate the performance of the model. Select the model with the best performance and apply it to the test set for marker intelligent classification. Store the classification results in a database to generate marker intelligent classification data, including the category label, prediction probability and other information of each marker, for subsequent analysis. Set key marker screening criteria based on the intelligent classification results, such as selecting markers with a prediction probability higher than 0.75, or evaluate the relevance of markers based on the opinions of clinical experts. The threshold method or ranking method can be used to sort the markers according to their importance scores (such as Gini importance or information gain), and the top N markers can be selected as key markers. The multi-dimensional bioassay indicator information of the selected key markers is extracted from the original data set, including the specific values ​​of each marker and related clinical information. The extracted key marker information is integrated with the basic information of the patient to generate a comprehensive data table containing key markers and their corresponding indicators. Select an appropriate standardization method, such as Z-score standardization or Min-Max standardization.Z-score standardization is applicable to features of various distributions, converting each feature value into a form with a mean of 0 and a standard deviation of 1, while Min-Max standardization scales the data to the interval [0, 1]. Adaptive standardization: Dynamically select the standardization method based on the distribution characteristics of key markers. For most features, Z-score standardization is used; for features with obvious skewed distribution, Min-Max standardization is used. Use Python's Scikit-learn library for standardization. For each marker, calculate its mean and standard deviation and convert them according to the formula. The standardized data will be stored in a new data frame to facilitate subsequent analysis and evaluation of the standardized data distribution, ensure that the data of each marker is on the same scale, and avoid deviations during model training. Use visualization tools (such as Seaborn) to draw data distribution graphs before and after standardization to ensure good standardization results.

[0021] In this embodiment, the specific steps of step S14 are: Perform parameterized data recognition on the multi-dimensional biological detection indicator information of key markers, and calculate the average parameter threshold to obtain the parameterized average threshold; Perform abnormal outlier data detection based on parameterized average threshold and mark abnormal outlier data points; Perform outlier filtering and cleaning on abnormal outlier data points to obtain cleaning optimization indicator information; Conduct multi-dimensional difference index analysis on cleaning optimization index information to generate difference data between multi-dimensional data; Adaptive standardization processing is performed based on the difference data between multi-dimensional data to obtain standardized biological detection information.

[0022] In this embodiment, a suitable parameterization method is selected, such as standardization or discretization. The standardization method can use Z-score standardization to convert the data into a form with a mean of 0 and a standard deviation of 1; discretization can divide continuous data into discrete intervals.

[0023] Implementing parameterized identification: Use Python's Pandas library to parameterize the selected biological detection indicators. Use the StandardScaler class for standardization: from sklearn.preprocessing import StandardScaler scaler = StandardScaler() standardized_data = scaler.fit_transform(raw_data) Calculate the mean and standard deviation of each parameterized indicator to generate a parameterized average threshold. Use Pandas' mean() and std() methods for calculation.

[0024] mean_values ​​= standardized_data.mean(axis=0) std_values ​​= standardized_data.std(axis=0) The parameterized average threshold is set according to the mean and standard deviation. The threshold range is set as: threshold = mean ± 2 × standard deviation, which is used for subsequent abnormal outlier data detection.

[0025] Choose a suitable anomaly detection algorithm, such as a Z-score-based method, or use machine learning methods such as Isolation Forest and LOF (Local Outlier Factor). The Z-score method is suitable for small-scale data sets, while Isolation Forest is more suitable for large-scale data sets. Use the Z-score method to detect outliers. Calculate the Z-score of each data point and compare it with the set threshold. If the absolute value of the Z-score is greater than the set threshold, it is marked as an abnormal data point.

[0026] z_scores = (standardized_data - mean_values) / std_values outliers = (np.abs(z_scores)>2).any(axis=1) Mark the detected abnormal outlier data points in the data frame for subsequent processing. For example, add a column is_outlier to the original data frame and mark it as 1 or 0.

[0027] Use simple filtering methods to remove outlier data points marked as abnormal, or choose to fill the values ​​of these data points with the median or mean to reduce their impact on the overall data analysis. Use the drop() method of the Pandas library to remove data points marked as abnormal to ensure the integrity of the cleaned data. For indicators marked as abnormal, use the fillna() method to fill them with the median or mean. If you choose to fill with the median, cleaned_data.fillna(cleaned_data.median(), inplace=1) Select appropriate statistical analysis methods, such as t-test, analysis of variance (ANOVA), or multivariate linear regression, to compare the differences in indicators between different groups. Compare the biological detection indicators between different groups (such as healthy group and pathological group), use the ttest_ind() function of the SciPy library to perform a t-test, and calculate the p-value to evaluate the significance of the difference. Record the results of the difference analysis (including t-value, p-value, effect size, etc.) in a data frame to generate a difference data result table.

[0028] Select an adaptive normalization method, such as Z-score-based normalization or Min-Max normalization. Adaptive normalization should take into account the distribution characteristics of the data and the results of differential analysis. Use Scikit-learn's StandardScaler or MinMaxScaler for final data normalization.

[0029] from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() standardized_final_data = scaler.fit_transform(cleaned_data) Check the standardized data to ensure that all indicators are on the same scale, and use visualization tools (such as Seaborn) to draw the data distribution before and after standardization.

[0030] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: performing global contrast enhancement on the medical image of the sclerosis marker, thereby constructing a global contrast optimized image; Step S22: performing multi-time point visual recognition on the global contrast optimized image, marking atherosclerotic plaques at multiple time points; Step S23: performing plaque edge detection on atherosclerotic plaques at multiple time points and marking the plaque edge contour line; Step S24: performing semantic segmentation of the image boundary according to the edge contour of the plaque, thereby extracting the plaque area image at each time point; Step S25: performing plaque geometric morphology analysis on the plaque region image at each time point, thereby generating plaque geometric morphology features at each time point.

[0031] In this embodiment, medical image data of sclerosis markers are extracted from a medical image database to ensure that the image quality and resolution meet the analysis requirements. The selected images should have a resolution of at least 512x512 pixels to ensure the accuracy of subsequent processing. Ensure that the images are saved in a common format (such as DICOM or PNG) so that they can be read and processed using image processing tools. Select a global contrast enhancement algorithm, such as histogram equalization or adaptive histogram equalization (CLAHE). CLAHE can effectively enhance local contrast and reduce noise, and is particularly suitable for processing medical images. Each image is processed using the CLAHE algorithm to enhance its contrast. After processing, check the histogram distribution of the image to ensure that the contrast is significantly improved. The enhanced image should be able to show the characteristics of the sclerotic plaque more clearly. Visualize the images before and after contrast enhancement, and confirm the contrast improvement by comparing the histograms. Ideally, the enhanced image histogram should be more uniform and cover a wider grayscale range. Select a suitable image recognition algorithm, such as a deep learning convolutional neural network (CNN) or a traditional image processing method (such as threshold segmentation). For tasks that require high accuracy, using a pre-trained deep learning model (such as U-Net) is an effective choice. If using a deep learning model, prepare a labeled training set. After training, use the model to process the global contrast optimized image to identify and mark atherosclerotic plaques. Based on the model's prediction results, generate a binary mask image at each time point to mark the location of the atherosclerotic plaque for subsequent analysis and processing. Use the Canny edge detection algorithm or the Sobel operator for edge detection, both of which can effectively identify edge features in the image. Implement edge detection: Apply the Canny edge detection algorithm to the marked plaque area. The algorithm identifies obvious edges by calculating the gradient of grayscale changes in the image and marks the edge contour of the plaque. Ensure the accuracy and completeness of edge detection by visualizing the edge detection results. Compare the original image and the edge-detected image to confirm that the edges of the plaque are clearly marked. Choose a suitable semantic segmentation algorithm, such as U-Net or FCN (Fully Convolutional Network). These algorithms can effectively extract plaque areas based on edge information. Perform image segmentation based on the edge contour of the plaque and extract the plaque area image at each time point. Overlay the segmentation result with the original image to verify whether the extracted area is accurate. Ensure that the extracted plaque area meets expectations and record the segmentation results at each time point for subsequent analysis. Determine the geometric features to be extracted, such as the area, perimeter, shape factor, aspect ratio, etc. of the plaque. These features help describe the geometric morphology of the plaque and its changes. Perform geometric morphological analysis on each extracted plaque area image and calculate the relevant features of each plaque. Calculate indicators such as area and perimeter through image processing tools. Organize the geometric morphological features of the plaque at each time point into a table to facilitate subsequent data analysis and comparison.These features will be used to analyze the evolution and clinical relevance of plaques.

[0032] In this embodiment, the specific steps of step S21 are: Perform image noise analysis on medical images of sclerosis markers and extract multiple image noise points; Mining pixel features of multiple image noise points one by one to generate pixel-level features of each noise point; Perform dynamic filtering and denoising based on the pixel-level features of each noise point to generate filtered and denoised medical images; Perform multi-region decomposition on the filtered denoised medical image to generate multiple sub-image blocks; Performing image block histogram equalization processing on the multiple sub-image blocks one by one, thereby generating multiple histogram equalized sub-image blocks; Global contrast enhancement is performed based on multiple histogram equalized sub-image blocks to construct a global contrast optimized image.

[0033] In this embodiment, a suitable noise analysis algorithm, such as median filtering or Gaussian filtering, is selected to identify noise in the image. Median filtering performs well in removing salt and pepper noise, while Gaussian filtering is suitable for Gaussian noise. First, the medical image is preprocessed, including image denoising and enhancement, to improve the accuracy of subsequent noise analysis. The image is processed using the selected algorithm to identify the position and intensity of the noise in the image. Through the threshold segmentation method, the part with pixel intensity exceeding a certain threshold is marked as a noise point. Determine the pixel features to be extracted, such as brightness, contrast, texture features (such as entropy, variance, etc.), which are helpful in evaluating the nature and impact of the noise. For each extracted noise point, pixel-level feature mining is performed. The extracted feature value is obtained by calculating the statistical information of the pixels in its local neighborhood. The pixel-level features of each noise point are stored in a data table for subsequent analysis and comparison. Select a dynamic filtering algorithm, such as adaptive filtering or bilateral filtering, which can dynamically adjust the filtering parameters according to the noise features, thereby effectively removing noise. According to the characteristics of each noise point, an adaptive filtering algorithm is applied to process the original medical image to reduce the impact of noise on image quality. Evaluate the quality of the filtered image to check whether the noise is effectively suppressed and to ensure that important structures are not blurred. Determine the size and method of decomposition, such as fixed-size or adaptive, to ensure that each sub-image block contains sufficient structural information. Divide the processed medical image into multiple sub-image blocks according to the set rules. Each sub-image block should retain local details. Record the location information of each sub-image block for subsequent processing and analysis. Select a histogram equalization algorithm to enhance the contrast of each sub-image block. Use traditional histogram equalization or CLAHE. Perform histogram equalization on each sub-image block to enhance its local contrast. After equalization, check the histogram distribution of each sub-image block to ensure that the equalization effect is good. Save the equalized sub-image blocks for subsequent global contrast enhancement. Select a global contrast enhancement algorithm, such as global histogram equalization or adaptive histogram equalization (CLAHE), to improve the overall visual effect of the image. Merge all equalized sub-image blocks and apply the global contrast enhancement algorithm to generate the final global contrast optimized image. Visualize the final image and confirm the improvement in contrast by comparing the histograms of the original and optimized images, and assess the image clarity and detail.

[0034] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: tracking the morphological changes at multiple time points according to the geometric morphological features of the plaque at each time point, so as to obtain the morphological change tracking data of the sclerotic plaque; Step S32: performing adjacent time difference calculation on the morphological change tracking data of the sclerotic plaque, thereby obtaining morphological difference data at multiple adjacent time intervals; Step S33: performing morphological change trend analysis on the morphological difference data of multiple adjacent time intervals to obtain the temporal morphological change trend of the sclerotic plaque; Step S34: Perform nonlinear morphological trend trajectory evolution on the temporal morphological change trend of the sclerotic plaque to construct a temporal morphological evolution trajectory of the sclerotic plaque.

[0035] In this embodiment, the geometric morphological feature data of the plaque at each time point are collected. These features include the area, perimeter, shape factor, aspect ratio, etc. of the plaque. Ensure that these data are organized in chronological order for subsequent analysis. The morphological feature information of each time point is stored in a data structure, such as a data frame (DataFrame), in which each row represents the plaque feature at a time point, and the column includes a timestamp and the corresponding geometric feature. Change calculation: The morphological features of each time point are calculated to track the changes of the plaque from one time point to the next. For example, calculate the percentage change of the area at adjacent time points: percentage change = area (t+1) − area t / area t × 100%, and record the change from each time point to the next time point in the data frame to form "morphological change tracking data" for subsequent analysis. Determine the specific method for calculating the difference between adjacent time points, for example, using absolute difference or relative change rate to characterize the change. For each geometric feature (such as area, perimeter, etc.), calculate the difference between adjacent time points. Select an appropriate trend analysis method and use methods such as linear regression analysis, moving average or time series analysis to identify the trend of morphological changes. Apply the selected trend analysis method to the morphological difference data. If linear regression is used, use time as the independent variable and morphological difference as the dependent variable, fit a trend line and calculate the slope. Visualize the analysis results and plot the relationship between time and morphological difference to intuitively display the morphological change trend of the plaque. Based on the slope and correlation of the trend line, interpret the acceleration or slowdown of morphological changes and evaluate the evolution trend of the plaque. Select a suitable nonlinear model, such as polynomial regression, spline regression, or neural network model, to fit complex morphological change trajectories. Construct a nonlinear model based on the time-series morphological change data. Train the model to fit the morphological change data and predict future morphological change trends. Generate a morphological evolution trajectory and visualize the evolution path of the plaque through the model output. Spline curves or polynomial curves are used to describe the evolution trend of the plaque. Verify whether the generated evolution trajectory is reasonable and compare it with the actual observed data. Based on the model output, analyze the evolution law of plaque morphology and explore potential connections with clinical relevance.

[0036] In this embodiment, step S4 includes the following steps: Step S41: performing multi-indicator potential association mining on standardized biological detection information to obtain potential association features between multiple indicators; Step S42: Calculate the time series change rate of each indicator of the standardized biological detection information to generate the time series change rate of each detection indicator; Step S43: performing a change range analysis based on the standardized biological detection information to obtain a change range of the detection index; Step S44: performing time series change characteristic analysis based on the time series change rate and the change amplitude of each detection indicator to obtain the time series change characteristics of the multi-dimensional detection indicators; Step S45: fitting the time-series evolution of the time-series variation characteristics of the multi-dimensional detection indicators according to the potential correlation characteristics among the multiple indicators, thereby constructing a multi-dimensional detection indicator trend evolution diagram.

[0037] In this embodiment, relevant indicator data is extracted from standardized biological detection information. Ensure that the data is collected in the same time frame, usually including various biochemical indicators (such as cholesterol, triglycerides, inflammatory markers, etc.), and the time point of each indicator should be consistent. Arrange the data into a format suitable for analysis, such as a data frame (DataFrame), where each row represents a time point and is listed as a different detection indicator. Select a suitable statistical analysis method, such as correlation analysis (Pearson or Spearman correlation coefficient) or multivariate linear regression analysis, to mine the potential correlation characteristics between indicators. Calculate the correlation coefficient between each pair of indicators and identify the significantly correlated indicator pairs. Set a threshold (such as the absolute value of the correlation coefficient is greater than 0.5) to screen potential correlation features. Record the correlation results in the data frame, generate a correlation matrix, and visualize it through a heat map to intuitively understand the degree of correlation between indicators. For each standardized detection indicator, calculate the rate of change at each time point to generate the rate of change data. Ensure that no time point is missed in the calculation process, especially when dealing with long time series data. Record the rate of change of each indicator in the data frame for subsequent analysis and comparison, ensure that the data format is clear, and associate it with the original indicator data. Determine the method for calculating the magnitude of change, using absolute magnitude and relative magnitude. The absolute magnitude calculation formula is: magnitude of change = indicator max − indicator min. For each standardized detection indicator, calculate its maximum and minimum values ​​during the entire observation period to obtain the magnitude of change. Ensure that all time points are considered in the calculation process. Organize the magnitude of change data into a table and record the magnitude of change for each indicator for subsequent comparison and analysis. Select appropriate analysis methods, such as cluster analysis or principal component analysis (PCA), to extract the temporal change characteristics of multidimensional detection indicators. Based on the change rate and change magnitude, perform clustering or PCA analysis to identify groups of indicators with similar change characteristics. Use k-means clustering or hierarchical clustering methods to analyze the similarities and differences between indicators. Present the analysis results in a chart to ensure that the temporal change characteristics of the multidimensional detection indicators can be clearly displayed for subsequent interpretation and application. Select an appropriate fitting model, such as a time series model (such as ARIMA) or a machine learning model (such as random forest) to predict future situation evolution. Use the previously mined potential correlation features to build and train a model to fit the temporal change characteristics of the multidimensional detection indicators. Ensure that sufficient training data is used to improve the prediction accuracy of the model. Generate a situation evolution diagram based on the output of the fitted model to show the changing trends of multiple indicators in the future time period. Use visualization tools to ensure that the diagram is clear and easy to understand for clinicians and researchers to use.

[0038] In this embodiment, the specific steps of step S5 are: Step S51: Based on the multi-dimensional detection index trend evolution diagram, a deep dynamic change correlation analysis is performed on the temporal morphological evolution trajectory of the sclerotic plaque, so as to obtain the dynamic evolution law of biological information-plaque evolution; Step S52: performing end-to-end iterative learning on the biological information-plaque evolution dynamic evolution law to generate a plaque trajectory dynamic evolution model; Step S53: Perform personalized predictions for multiple time periods in the future based on the plaque trajectory dynamic evolution model, thereby obtaining atherosclerosis status prediction data for multiple time periods.

[0039] In this embodiment, relevant biological indicators and temporal morphological evolution data of hardened plaques are extracted from the multidimensional detection indicator trend evolution diagram. These data should include biological indicators (such as cholesterol, blood sugar, etc.) and geometric features of plaques (such as area, perimeter, etc.) at each time point. The extracted data are integrated into a comprehensive data set to ensure that the biological information at each time point matches the corresponding plaque characteristics. The data format should be a data frame (DataFrame), each row represents a time point, and the columns are different biological indicators and plaque characteristics. Multivariate regression analysis or dynamic time warping (DTW) is selected as the method of association analysis. Multivariate regression can reveal the linear relationship between biological indicators and plaque evolution, while DTW is suitable for processing time series data and can identify similarities between different time series. Use the selected analysis method for data analysis. For example, if multivariate regression is used, a model is constructed with biological indicators as independent variables and geometric features of plaques as dependent variables to analyze the impact of biological information on plaque evolution. Through the model results, the biological indicators that significantly affect plaque evolution are identified, and the corresponding regression graphs or time series graphs are drawn to visualize the dynamic relationship between biological information and plaque morphological evolution. Choose a deep learning framework suitable for modeling, such as recurrent neural networks (RNN) or long short-term memory networks (LSTM). These models are suitable for processing time series data and can capture dynamic features in the data. Divide the comprehensive dataset into training and test sets, usually 70% for training and 30% for testing. Ensure that the data is randomly divided to avoid overfitting of the model. Standardize the input features (such as Z-score standardization) to improve the convergence speed and prediction accuracy of the model. Ensure that the mean of each feature is 0 and the standard deviation is 1. Iteratively train the selected deep learning model using the training set. Set an appropriate learning rate (such as 0.001) and batch size (such as 32), and use cross-validation to monitor the performance of the model. Evaluate the performance of the model on the test set, using mean square error (MSE) or root mean square error (RMSE) as the evaluation metric to ensure the generalization ability of the model. Choose an appropriate forecasting method, usually based on the trained dynamic evolution model for future time periods. Use the sliding window method to take past observations as input and predict future values. Generate predictions for future time points by using the trained model and inputting the biological indicators and plaque characteristics of the last known time period. You can set the prediction time period (such as the next 3, 6, or 12 months). Combine the prediction results with the original data to form a complete time series to facilitate doctors and researchers to analyze the progression of atherosclerosis. Generate prediction charts using visualization tools (such as Matplotlib) to show the changing trend of future states. Verify the prediction results, compare the actual observed values ​​with the predicted values, and analyze the accuracy of the prediction.

[0040] In this embodiment, step S6 includes the following steps: Step S61: quantitatively analyzing the atherosclerosis status prediction data of multiple time periods to generate status prediction analysis data for each time period; Step S62: performing risk prediction on the state prediction analysis data of each time period to generate pathological risk prediction data of each time period; Step S63: Performing personalized comprehensive diagnosis based on the pathological risk prediction data of each time period to generate a personalized diagnosis result; Step S64: Perform dynamic feedback optimization on the plaque trajectory dynamic evolution model according to the personalized diagnosis result, thereby constructing a dynamic feedback optimization model.

[0041] In this embodiment, the state prediction data of each time period are collected, including the size, morphology, density and other characteristics of the plaque. Next, these data are processed by statistical analysis methods (such as mean, standard deviation, confidence interval, etc.). Multivariate regression analysis is used to evaluate the impact of different factors on the progression of atherosclerosis. For example, biomarkers such as age, gender, and blood lipid levels are used as independent variables, and the development of plaques is analyzed as a dependent variable. Experimental parameters include sample size, confidence level of analysis (such as 95%), and selection of regression model (such as linear regression or logistic regression). After quantitative analysis, the state prediction analysis data of each time period will be obtained to describe the relationship between the change trend of plaques and related biological information, laying the foundation for risk prediction. Risk prediction is performed on the state prediction analysis data of each time period. Based on the state data generated in step S61, a machine learning algorithm (such as random forest, support vector machine, etc.) is used to construct a risk assessment model. First, the state prediction data is divided into a training set and a test set for model training and verification. During the training process, appropriate feature variables (such as plaque size, morphological changes and biomarkers) are selected as input, and the corresponding risk status (such as high risk, medium risk, low risk) is used as output. The accuracy of the model is evaluated by cross-validation method to ensure its reliability in risk prediction. Experimental parameters include the proportion of training sets (such as 70% training, 30% testing), model evaluation indicators (such as accuracy, sensitivity, specificity) and hyperparameter optimization. Based on the pathological risk prediction data of each time period, personalized comprehensive diagnosis is performed. First, the pathological risk prediction results of each patient are collected and combined with clinical data (such as medical history, family history, lifestyle, etc.) for comprehensive analysis. A decision tree or fuzzy logic system is used to combine the risk prediction results with the specific situation of the patient to accurately assess the health risk of each patient. By formulating a diagnostic model, different risk factors are weighted to obtain personalized comprehensive diagnostic results. Experimental parameters include the depth of the decision tree, the number of nodes and the number of fuzzy logic rules. According to the generated personalized diagnosis results, the dynamic evolution model of plaque trajectory is dynamically feedback optimized. First, specific data and feedback information from personalized diagnosis are collected to analyze their impact on the plaque evolution model. By introducing a feedback mechanism, the model parameters are adjusted to improve the accuracy of prediction. For example, the Bayesian optimization method is used to update the prior knowledge of the model according to new clinical data, thereby gradually improving the performance of the model. Experimental parameters include adjustment amplitude, feedback cycle, and model evaluation indicators (such as root mean square error, R² value, etc.).

[0042] In this embodiment, a system for integrated analysis of atherosclerosis marker detection data is provided, which is used to execute the method for integrated analysis of atherosclerosis marker detection data as described above, including: A data processing module is used to obtain multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of patients; and to perform adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; The geometric morphology analysis module is used to perform multi-time point visual recognition of medical images of sclerosis markers and perform plaque geometric morphology analysis to generate the geometric morphology characteristics of plaques at each time point; The morphological trajectory evolution module is used to track the morphological changes at multiple time points and perform nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; The situation evolution module is used to mine the potential associations of multiple indicators of standardized biological detection information, and then perform time-series situation evolution fitting to construct a multi-dimensional detection indicator situation evolution diagram; The multi-period prediction module is used to make personalized predictions of the evolution trajectory of the sclerotic plaque time series morphology based on the multi-dimensional detection index trend evolution diagram, so as to obtain the prediction data of atherosclerosis status in multiple time periods; The personalized diagnosis and analysis module is used to quantitatively analyze the prediction data of atherosclerosis status in multiple time periods and perform personalized comprehensive diagnosis to generate personalized diagnosis results. The present invention systematically obtains the patient's health information by integrating various types of data, thereby improving the accuracy of disease analysis. This multi-dimensional data fusion provides a more comprehensive basis for subsequent analysis. Adaptive standardization eliminates the scale differences between data and ensures the comparability of different biomarkers and imaging data. This not only improves the efficiency of data processing, but also reduces the errors caused by inconsistent data during subsequent modeling, thereby improving the reliability of analysis. Through visual recognition of multi-time point images, the evolution of plaques can be tracked and the course of atherosclerosis can be obtained in real time. The analysis of multiple time points provides time dimension data on disease progression, which helps to understand the dynamic process of plaque development. Through geometric morphological analysis, the size, shape and other characteristics of plaques can be quantified in detail. This information is an important basis for predicting plaque stability, rupture risk and disease progression, and can provide more decision-making support for clinicians. Through multi-time point morphological tracking, the trend of plaque morphology changes over time can be accurately captured. This dynamic change provides a reliable basis for early warning of the disease. The nonlinear evolution model can capture the complex trends in plaque morphological changes, rather than simple linear relationships. This provides a deeper insight into the development of the disease, especially the prediction of emergencies such as plaque rupture. By mining the potential associations between biomarkers, new early disease predictors can be discovered, which is of great significance for accurately identifying high-risk patients. Time-series lapse analysis provides the law of changes in disease markers over time, which can provide quantifiable references for disease prognosis and early intervention, and provide clinicians with more accurate predictions. According to the multidimensional data of patients, combined with the health status of each patient, personalized disease prediction is carried out. Through predictions for future time periods, patients can understand the progress of the disease in advance, adjust treatment plans in time, and avoid the aggravation of the disease process. It can accurately predict the state of the disease at a certain point in the future, help patients and doctors develop more scientific treatment strategies, and reduce the risk of complications caused by the disease. Through quantitative analysis, the health status of patients can be quantified and a more sophisticated risk assessment can be provided. This quantitative assessment helps to develop accurate intervention strategies for patients. By combining information from multiple aspects, a personalized comprehensive diagnostic report is generated, which can provide more accurate and personalized treatment recommendations compared with traditional diagnostic methods.

[0043] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0044] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for integrated analysis of atherosclerosis marker detection data, characterized in that: The following steps are involved: Step S1: obtaining multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of the patient; performing adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; Step S2: Performing multi-time point visual recognition on the medical images of sclerosis markers and performing plaque geometry analysis to generate plaque geometry features at each time point; Step S3: tracking the morphological changes at multiple time points and performing nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; Step S4: mining the potential association of multiple indicators for the standardized biological detection information, and then fitting the evolution of the situation over time, so as to construct a multi-dimensional detection indicator situation evolution diagram; Step S5: Based on the multi-dimensional detection index trend evolution diagram, a personalized prediction of the temporal morphological evolution trajectory of the sclerotic plaque is performed for multiple time periods in the future, thereby obtaining the prediction data of the atherosclerosis state in multiple time periods; Step S6: Quantitatively analyze the atherosclerosis status prediction data for multiple time periods, and perform personalized comprehensive diagnosis to generate personalized diagnosis results.

2. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: obtaining multi-dimensional biological detection index information of the patient's atherosclerosis markers and medical images of atherosclerosis markers; Step S12: performing intelligent marker classification on the multi-dimensional biological detection indicator information to obtain marker intelligent classification data; Step S13: Screening key markers according to the marker intelligent classification data, and extracting multi-dimensional biological detection index information of the key markers; Step S14: Adaptively standardize the multi-dimensional biological detection index information of the key markers to obtain standardized biological detection information.

3. The method for integrated analysis of atherosclerosis marker detection data according to claim 2, characterized in that: The specific steps of step S14 are: Perform parameterized data recognition on the multi-dimensional biological detection indicator information of key markers, and calculate the average parameter threshold to obtain the parameterized average threshold; Perform abnormal outlier data detection based on parameterized average threshold and mark abnormal outlier data points; Perform outlier filtering and cleaning on abnormal outlier data points to obtain cleaning optimization indicator information; Conduct multi-dimensional difference index analysis on cleaning optimization index information to generate difference data between multi-dimensional data; Adaptive standardization processing is performed based on the difference data between multi-dimensional data to obtain standardized biological detection information.

4. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: performing global contrast enhancement on the medical image of the sclerosis marker, thereby constructing a global contrast optimized image; Step S22: performing multi-time point visual recognition on the global contrast optimized image, marking atherosclerotic plaques at multiple time points; Step S23: performing plaque edge detection on atherosclerotic plaques at multiple time points and marking the plaque edge contour line; Step S24: performing semantic segmentation of the image boundary according to the edge contour of the plaque, thereby extracting the plaque area image at each time point; Step S25: performing plaque geometric morphology analysis on the plaque region image at each time point, thereby generating plaque geometric morphology features at each time point.

5. The method for integrated analysis of atherosclerosis marker detection data according to claim 4, characterized in that: The specific steps of step S21 are: Perform image noise analysis on medical images of sclerosis markers and extract multiple image noise points; Mining pixel features of multiple image noise points one by one to generate pixel-level features of each noise point; Perform dynamic filtering and denoising based on the pixel-level features of each noise point to generate filtered and denoised medical images; Perform multi-region decomposition on the filtered denoised medical image to generate multiple sub-image blocks; Performing image block histogram equalization processing on the multiple sub-image blocks one by one, thereby generating multiple histogram equalized sub-image blocks; Global contrast enhancement is performed based on multiple histogram equalized sub-image blocks to construct a global contrast optimized image.

6. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: tracking the morphological changes at multiple time points according to the geometric morphological features of the plaque at each time point, so as to obtain the morphological change tracking data of the sclerotic plaque; Step S32: performing adjacent time difference calculation on the morphological change tracking data of the sclerotic plaque, thereby obtaining morphological difference data at multiple adjacent time intervals; Step S33: performing morphological change trend analysis on the morphological difference data of multiple adjacent time intervals to obtain the temporal morphological change trend of the sclerotic plaque; Step S34: performing nonlinear morphological trend trajectory evolution on the temporal morphological change trend of the sclerotic plaque to construct a temporal morphological evolution trajectory of the sclerotic plaque.

7. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing multi-indicator potential association mining on standardized biological detection information to obtain potential association features between multiple indicators; Step S42: Calculate the time series change rate of each indicator of the standardized biological detection information to generate the time series change rate of each detection indicator; Step S43: performing a change range analysis based on the standardized biological detection information to obtain a change range of the detection index; Step S44: performing time series change characteristic analysis based on the time series change rate and the change amplitude of each detection indicator to obtain the time series change characteristics of the multi-dimensional detection indicators; Step S45: fitting the time-series evolution of the time-series variation characteristics of the multi-dimensional detection indicators according to the potential correlation characteristics among the multiple indicators, thereby constructing a multi-dimensional detection indicator trend evolution diagram.

8. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: Based on the multi-dimensional detection index trend evolution diagram, a deep dynamic change correlation analysis is performed on the temporal morphological evolution trajectory of the sclerotic plaque, so as to obtain the dynamic evolution law of biological information-plaque evolution; Step S52: performing end-to-end iterative learning on the biological information-plaque evolution dynamic evolution law to generate a plaque trajectory dynamic evolution model; Step S53: Perform personalized predictions for multiple time periods in the future based on the plaque trajectory dynamic evolution model, thereby obtaining atherosclerosis status prediction data for multiple time periods.

9. The method for integrated analysis of atherosclerosis marker detection data according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: quantitatively analyzing the atherosclerosis status prediction data of multiple time periods to generate status prediction analysis data for each time period; Step S62: performing risk prediction on the state prediction analysis data of each time period to generate pathological risk prediction data of each time period; Step S63: Performing personalized comprehensive diagnosis based on the pathological risk prediction data of each time period to generate a personalized diagnosis result; Step S64: Perform dynamic feedback optimization on the plaque trajectory dynamic evolution model according to the personalized diagnosis result, thereby constructing a dynamic feedback optimization model.

10. An integrated analysis system for atherosclerosis marker detection data, characterized in that: The method for performing the integrated analysis of atherosclerosis marker detection data according to claim 1 comprises: A data processing module is used to obtain multi-dimensional biological detection index information of atherosclerosis markers and medical images of atherosclerosis markers of patients; and to perform adaptive standardization processing on the multi-dimensional biological detection index information to obtain standardized biological detection information; The geometric morphology analysis module is used to perform multi-time point visual recognition of medical images of sclerosis markers and perform plaque geometric morphology analysis to generate the geometric morphology characteristics of plaques at each time point; The morphological trajectory evolution module is used to track the morphological changes at multiple time points and perform nonlinear morphological trend trajectory evolution according to the geometric morphological characteristics of the plaque at each time point, so as to construct the temporal morphological evolution trajectory of the sclerotic plaque; The situation evolution module is used to mine the potential associations of multiple indicators of standardized biological detection information, and then perform time-series situation evolution fitting to construct a multi-dimensional detection indicator situation evolution diagram; The multi-period prediction module is used to make personalized predictions of the temporal morphological evolution trajectory of sclerotic plaques in the future based on the multi-dimensional detection index trend evolution diagram, so as to obtain the prediction data of atherosclerosis status in multiple time periods; The personalized diagnosis and analysis module is used to quantitatively analyze the prediction data of atherosclerosis status in multiple time periods and perform personalized comprehensive diagnosis to generate personalized diagnosis results.

Images