Myocardial tissue electrophysiology unmarked optical detection method based on deep learning

Abstract

The invention relates to the technical field of medical health, in particular to a cardiac muscle tissue electrophysiology unmarked optical detection method based on deep learning. The method comprises the following steps: acquiring optical detection image data and electrophysiological signal data of myocardial tissue; the optical detection image data and the electrophysiological signal data are subjected to image preprocessing, so that optical-physiological signal mapping data are obtained, and image preprocessing comprises image registration, image cutting, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing; and according to the optical-physiological signal mapping data, carrying out feature signal extraction based on a mechanical contraction curve and an electrophysiological curve so as to obtain mechanical contraction curve data and electrophysiological curve data. According to the method, unmarked optical detection is adopted, so that direct interference on myocardial tissues is avoided, and the physiological state of the tissues is better maintained.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to a label-free optical detection method for myocardial tissue electrophysiology based on deep learning. Background Art

[0002] The electrocardiogram method is generally used to obtain electrophysiological data of myocardial tissue in clinical practice. This type of surface electrode detection method is contact-based and has low spatiotemporal resolution, and is not suitable for high-throughput, high-resolution applications such as cardiac drug screening and toxicity testing. Compared with electrode detection, optical detection methods of electrophysiology have the advantages of non-contact and high spatiotemporal resolution, but the traditional optical detection process relies on fluorescent markers (marking cell membrane action potentials or intracellular calcium ion concentrations), which are highly toxic to the test samples and are not conducive to long-term observations. Label-free optical detection of myocardial tissue electrophysiology is a technology used for non-invasive monitoring and evaluation of myocardial electrophysiological activity, and is particularly suitable for the diagnosis, research, and treatment evaluation of heart disease. By combining optical imaging and deep learning models, the technology can infer electrophysiological signals from the optical properties of myocardial tissue without the need to implant electrodes or use chemical markers.

[0003] However, traditional electrophysiological optical detection of myocardial tissue often has the following problems: in traditional fluorescence detection, fluorescent dyes will gradually inactivate after long-term exposure to excitation light, affecting signal quality; traditional electrode detection methods cause physical damage to cells; dyes may be internalized by cells, resulting in signal attenuation and inaccurate positioning. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a label-free optical detection method for myocardial tissue electrophysiology based on deep learning to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above purpose, a label-free optical detection method of myocardial tissue electrophysiology based on deep learning includes the following steps:

[0006] Step S1: Acquire optical detection image data and electrophysiological signal data of myocardial tissue; perform image preprocessing on the optical detection image data and electrophysiological signal data to obtain optical-physiological signal mapping data, wherein the image preprocessing includes image registration, image cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing;

[0007] Step S2: extracting characteristic signals based on the mechanical contraction curve and the electrophysiological curve according to the optical-physiological signal mapping data, thereby obtaining mechanical contraction curve data and electrophysiological curve data;

[0008] Step S3: taking the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, constructing and training the model by training the gated recurrent unit network model, thereby obtaining an electrophysiological signal prediction model, wherein the electrophysiological signal prediction model includes two hidden layers, and the width of each hidden layer is 64;

[0009] Step S4: using the electrophysiological signal prediction model to predict changes in cardiac electrophysiological activity according to the mechanical contraction curve data, thereby obtaining electrophysiological prediction data; performing prediction performance evaluation on the electrophysiological prediction data based on relative error, mean square error, and root mean square error, thereby obtaining model performance evaluation data;

[0010] Step S5: Extract characteristic indicators of the mechanical contraction curve data and the electrophysiological curve data based on DFD80 and APD80, and calculate the Pearson correlation coefficient of the characteristic indicators to obtain the correlation data between the label-free optical detection and the electrophysiological signal; optimize the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

[0011] The present invention can simultaneously monitor the mechanical contraction and electrophysiological activity of the myocardium by acquiring optical detection image data and electrophysiological signal data of myocardial tissue. This provides rich biological information for subsequent modeling and analysis. Including image registration, cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing processing, it can remove noise and interference in the data and improve the accuracy and consistency of the data. This process ensures that the optical image and electrophysiological signal data are strictly aligned in space and time, making the mapping between the two more accurate, and laying a solid foundation for subsequent modeling. By extracting key feature signals (such as mechanical contraction curves and electrophysiological curves) in optical-physiological signal mapping, complex physiological data can be converted into operable feature vectors. This enables the originally high-dimensional signal to be represented by low-dimensional features, simplifying the complexity of data analysis. The mechanical contraction curve and the electrophysiological curve can reflect the core features of the heart in contraction and electrical activity, providing strong support for the training of the subsequent model, and ensuring that the model can understand and capture the physiological changes of the heart. By taking the mechanical contraction curve as the independent variable and the electrophysiological curve as the dependent variable, a model based on a gated recurrent unit network (GRU) is constructed. GRU is suitable for processing time series data and can well capture and predict the dynamic changes of the heart. The double hidden layer design helps to capture more complex spatiotemporal relationships. The hidden layer with a width of 64 ensures that the model has sufficient capacity to learn complex patterns without causing overfitting. The model can predict the corresponding electrophysiological signals based on the input mechanical contraction curve, which provides a new method for non-invasive prediction of cardiac physiological activities, especially in the scenario of label-free optical detection. Through the trained electrophysiological signal prediction model, the electrophysiological activity of the heart can be predicted from the mechanical contraction curve. This prediction method can reduce the dependence on traditional invasive measurement methods. The prediction accuracy of the model can be evaluated from multiple angles by calculating the relative error, mean square error and root mean square error. This comprehensive performance evaluation ensures that the model has sufficient generalization ability and can run stably under different data conditions, ensuring the reliability of the results. DFD80 and APD80 are important indicators of myocardial contraction and electrical activity. Extracting these features can accurately capture the physiological state and potential lesions of the heart, providing strong data support for subsequent diagnosis and analysis. By analyzing the relationship between optical detection signals and electrophysiological signals through the Pearson correlation coefficient, the correspondence between label-free optical detection and electrophysiological activity can be quantified. This analysis can reveal the potential mechanism between the two and provide a basis for subsequent optimization. Combining model performance evaluation data and correlation data to optimize model parameters can further improve the prediction accuracy of the model. Through continuous optimization, a model with higher prediction accuracy for electrophysiological signals of myocardial tissue is finally obtained, providing reliable support for actual clinical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0013] Figure 1 It is a schematic diagram of the steps of the method for label-free optical detection of electrophysiological myocardial tissue based on deep learning of the present invention;

[0014] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0015] Figure 3 for Figure 1 Detailed step flow chart of step S3 in FIG. DETAILED DESCRIPTION

[0016] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0017] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0018] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0019] To achieve this, please refer to Figures 1 to 3 The present invention provides a label-free optical detection method for electrophysiological myocardial tissue based on deep learning, the method comprising the following steps:

[0020] Step S1: Acquire optical detection image data and electrophysiological signal data of myocardial tissue; perform image preprocessing on the optical detection image data and electrophysiological signal data to obtain optical-physiological signal mapping data, wherein the image preprocessing includes image registration, image cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing;

[0021] Step S2: extracting characteristic signals based on the mechanical contraction curve and the electrophysiological curve according to the optical-physiological signal mapping data, thereby obtaining mechanical contraction curve data and electrophysiological curve data;

[0022] Step S3: taking the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, constructing and training the model by training the gated recurrent unit network model, thereby obtaining an electrophysiological signal prediction model, wherein the electrophysiological signal prediction model includes two hidden layers, and the width of each hidden layer is 64;

[0023] Step S4: using the electrophysiological signal prediction model to predict changes in cardiac electrophysiological activity according to the mechanical contraction curve data, thereby obtaining electrophysiological prediction data; performing prediction performance evaluation on the electrophysiological prediction data based on relative error, mean square error, and root mean square error, thereby obtaining model performance evaluation data;

[0024] Step S5: Extract characteristic indicators of the mechanical contraction curve data and the electrophysiological curve data based on DFD80 and APD80, and calculate the Pearson correlation coefficient of the characteristic indicators to obtain the correlation data between the label-free optical detection and the electrophysiological signal; optimize the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

[0025] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for label-free optical detection of myocardial tissue electrophysiology based on deep learning of the present invention. In this example, the method for label-free optical detection of myocardial tissue electrophysiology based on deep learning includes the following steps:

[0026] Step S1: Acquire optical detection image data and electrophysiological signal data of myocardial tissue; perform image preprocessing on the optical detection image data and electrophysiological signal data to obtain optical-physiological signal mapping data, wherein the image preprocessing includes image registration, image cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing;

[0027] In the embodiment of the present invention, under laboratory conditions, optical detection image data of myocardial tissue is collected by combining fluorescent calcium imaging with a mechanical wave imaging system, and the electrophysiological signal data of myocardial tissue, including calcium ion concentration change signals, are synchronously recorded using a calcium imaging system. To ensure data consistency, the optical image and the electrophysiological signal are first image-aligned, and the alignment process is based on the adjustment of the field of view size, position and angle. Then, the rectangular image is cropped into a circular image using an image cropping technique, with the short side length of the rectangle as the diameter, and the center is aligned. Next, the cropped circular image is periodically enhanced, the periodic characteristics of myocardial contraction are calculated by Fourier transform, the shift step is determined, and multiple sets of cyclic shift data are generated. Subsequently, these data are subjected to time difference enhancement, spatial filtering, and intensity normalization processing, and the Bartlett filter is used for spatial filtering, and the pixel intensity is normalized to the [0,1] interval. Finally, the image is optimized by data smoothing processing to obtain optical-physiological signal mapping data to ensure the temporal and spatial consistency of the signal.

[0028] Step S2: extracting characteristic signals based on the mechanical contraction curve and the electrophysiological curve according to the optical-physiological signal mapping data, thereby obtaining mechanical contraction curve data and electrophysiological curve data;

[0029] The embodiment of the present invention extracts the mechanical contraction curve and electrophysiological curve of myocardial tissue from the obtained optical-physiological signal mapping data. First, the mechanical contraction curve is constructed by analyzing the local displacement information in the optical image and the spatial deformation trend of the myocardium. Then, the electric signal intensity fluctuation of each pixel in the optical-physiological signal mapping data is used to generate an electrophysiological curve reflecting the electrical activity of the myocardium using time as the horizontal coordinate and the electric signal intensity as the vertical coordinate. Next, the cardiac contraction cycle is divided into multiple cycle segments, the start and end time of each cycle is determined, and the peak and valley values ​​of each cycle are calibrated to generate cardiac cycle segmentation data. Finally, based on the features such as contraction amplitude and maximum contraction rate, a feature vector is obtained, the scale differences between different samples are eliminated, and the data are uniformly mapped to the standard numerical interval to obtain mechanical contraction curve data and electrophysiological curve data.

[0030] Step S3: taking the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, constructing and training the model by training the gated recurrent unit network model, thereby obtaining an electrophysiological signal prediction model, wherein the electrophysiological signal prediction model includes two hidden layers, and the width of each hidden layer is 64;

[0031] The embodiment of the present invention uses mechanical contraction curve data as an independent variable and electrophysiological curve data as a dependent variable to construct and train a gated recurrent unit (GRU) network model. First, the training set, validation set and test set are divided based on a ratio of 80:10:10. Then, the GRU model is initialized, which includes an input layer, two hidden layers (each layer contains 64 GRU units) and an output layer. The input layer receives the time step information of the mechanical contraction curve data, and the hidden layer extracts timing features and integrates complex patterns. The hyperparameters are set as follows: learning rate is 0.001, optimizer type is Adam, batch size is 32, and number of training rounds is 100. The training data is input into the GRU model, the predicted value is calculated by forward propagation, and the weight is adjusted by back propagation to reduce the error. During the training process, the model is continuously iterated and optimized, and finally an electrophysiological signal prediction model is obtained, which has a high spatiotemporal prediction accuracy.

[0032] Step S4: using the electrophysiological signal prediction model to predict changes in cardiac electrophysiological activity according to the mechanical contraction curve data, thereby obtaining electrophysiological prediction data; performing prediction performance evaluation on the electrophysiological prediction data based on relative error, mean square error, and root mean square error, thereby obtaining model performance evaluation data;

[0033] The embodiment of the present invention uses a trained electrophysiological signal prediction model to predict cardiac electrophysiological activity for new mechanical contraction curve data. The model compares the predicted electrophysiological signal data with the actually measured electrophysiological signal through forward propagation calculation, and calculates the relative error, mean square error (MSE) and root mean square error (RMSE). For example, in one application, the relative error between the actual data and the predicted data was 3%, the MSE was 0.005, and the RMSE was 0.07. Based on these error indicators, model performance evaluation data is generated, and multi-scale performance tests are performed. The prediction performance of the model is excellent in different time scales and signal amplitude ranges. Finally, a comparison chart of the predicted data and the actual data is presented visually, and the distribution of the prediction error is analyzed to ensure the accuracy and stability of the model.

[0034] Step S5: Extract characteristic indicators of the mechanical contraction curve data and the electrophysiological curve data based on DFD80 and APD80, and calculate the Pearson correlation coefficient of the characteristic indicators to obtain the correlation data between the label-free optical detection and the electrophysiological signal; optimize the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

[0035] The embodiment of the present invention performs DFD80 feature extraction on the mechanical contraction curve data, and performs APD80 feature extraction on the electrophysiological curve data to obtain corresponding feature data. Then, the Pearson correlation coefficient is used to calculate the correlation between the mechanical contraction feature data and the electrophysiological feature data. For example, in a set of experimental data, the correlation coefficient is 0.85, indicating that the two have a strong linear relationship. The mean, standard deviation and confidence interval of the correlation data are further calculated to obtain correlation statistics. Based on these data, the quantitative correlation between label-free optical detection and electrophysiological signals is evaluated. Finally, combined with the model performance evaluation data and the correlation data, the parameters of the electrophysiological signal prediction model are adjusted to optimize the prediction accuracy of the model to ensure its efficient prediction of the electrophysiological activity of myocardial tissue.

[0036] The present invention can simultaneously monitor the mechanical contraction and electrophysiological activity of the myocardium by acquiring optical detection image data and electrophysiological signal data of myocardial tissue. This provides rich biological information for subsequent modeling and analysis. Including image registration, cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing processing, it can remove noise and interference in the data and improve the accuracy and consistency of the data. This process ensures that the optical image and electrophysiological signal data are strictly aligned in space and time, making the mapping between the two more accurate, and laying a solid foundation for subsequent modeling. By extracting key feature signals (such as mechanical contraction curves and electrophysiological curves) in optical-physiological signal mapping, complex physiological data can be converted into operable feature vectors. This enables the originally high-dimensional signal to be represented by low-dimensional features, simplifying the complexity of data analysis. The mechanical contraction curve and the electrophysiological curve can reflect the core features of the heart in contraction and electrical activity, providing strong support for the training of the subsequent model, and ensuring that the model can understand and capture the physiological changes of the heart. By taking the mechanical contraction curve as the independent variable and the electrophysiological curve as the dependent variable, a model based on a gated recurrent unit network (GRU) is constructed. GRU is suitable for processing time series data and can well capture and predict the dynamic changes of the heart. The double hidden layer design helps to capture more complex spatiotemporal relationships. The hidden layer with a width of 64 ensures that the model has sufficient capacity to learn complex patterns without causing overfitting. The model can predict the corresponding electrophysiological signals based on the input mechanical contraction curve, which provides a new method for non-invasive prediction of cardiac physiological activities, especially in the scenario of label-free optical detection. Through the trained electrophysiological signal prediction model, the electrophysiological activity of the heart can be predicted from the mechanical contraction curve. This prediction method can reduce the dependence on traditional invasive measurement methods. The prediction accuracy of the model can be evaluated from multiple angles by calculating the relative error, mean square error and root mean square error. This comprehensive performance evaluation ensures that the model has sufficient generalization ability and can run stably under different data conditions, ensuring the reliability of the results. DFD80 and APD80 are important indicators of myocardial contraction and electrical activity. Extracting these features can accurately capture the physiological state and potential lesions of the heart, providing strong data support for subsequent diagnosis and analysis. By analyzing the relationship between optical detection signals and electrophysiological signals through the Pearson correlation coefficient, the correspondence between label-free optical detection and electrophysiological activity can be quantified. This analysis can reveal the potential mechanism between the two and provide a basis for subsequent optimization. Combining model performance evaluation data and correlation data to optimize model parameters can further improve the prediction accuracy of the model. Through continuous optimization, a model with higher prediction accuracy for electrophysiological signals of myocardial tissue is finally obtained, providing reliable support for actual clinical applications.

[0037] Preferably, step S1 comprises the following steps:

[0038] Step S11: collecting optical detection image data of myocardial tissue under experimental conditions through an optical imaging system, wherein the optical imaging system is specifically a fluorescent calcium imaging combined with a mechanical wave imaging system;

[0039] Step S12: synchronously collecting electrophysiological signal data of myocardial tissue using a calcium imaging system, wherein the electrophysiological signal data includes a calcium ion concentration change signal;

[0040] Step S13: performing image registration on the optical detection image data and the electrophysiological signal data based on the field of view size, position and angle, so as to obtain image consistency data;

[0041] Step S14: performing image cropping processing on the image consistent data to obtain circular consistent image data, wherein the image cropping processing specifically crops the original rectangular field of view into a circular area with the center of the rectangle as the circle center and the short side length of the rectangle as the diameter;

[0042] Step S15: performing periodic cyclic shift and superposition on the circular consistent image data, thereby obtaining periodic enhanced data;

[0043] Step S16: performing signal enhancement and optimization processing based on time difference enhancement, spatial filtering, intensity normalization and data smoothing processing on the periodic enhancement data, so as to obtain optical-physiological signal mapping data.

[0044] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in the embodiment of the present invention, step S1 includes the following steps:

[0045] Step S11: collecting optical detection image data of myocardial tissue under experimental conditions through an optical imaging system, wherein the optical imaging system is specifically a fluorescent calcium imaging combined with a mechanical wave imaging system;

[0046] In the embodiment of the present invention, under experimental conditions, optical detection of myocardial tissue is performed by combining a fluorescent calcium imaging system with a mechanical wave imaging system. The experiment is set up in a constant temperature environment of 37°C to ensure the stability of the physiological state. The fluorescent calcium imaging system irradiates the myocardial tissue with excitation light of a specific wavelength, records the flow of calcium ions in the cells, and forms a fluorescent image. The mechanical wave imaging system captures the mechanical movement of the myocardium during contraction and relaxation. The imaging frequency is set to 100 frames per second to ensure accurate capture of rapid contraction and relaxation of the heart, and ultimately obtain optical detection image data with high temporal resolution.

[0047] Step S12: synchronously collecting electrophysiological signal data of myocardial tissue using a calcium imaging system, wherein the electrophysiological signal data includes a calcium ion concentration change signal;

[0048] While acquiring optical image data, the calcium imaging system of the embodiment of the present invention synchronously collects electrophysiological signal data of myocardial tissue. The calcium ion concentration change signal is reflected by the change in fluorescence intensity after being labeled with a calcium-sensitive dye, and these signals represent changes in the action potential of myocardial cells. In the experiment, the acquisition frequency of the calcium ion concentration change is consistent with that of the optical imaging system, which is also 100 frames per second to ensure signal synchronization. These optical signals are converted into digital signals through a photoelectric converter to form electrophysiological signal data, which includes the rising and falling phases of calcium ions, reflecting the contraction and relaxation process of the myocardium.

[0049] Step S13: performing image registration on the optical detection image data and the electrophysiological signal data based on the field of view size, position and angle, so as to obtain image consistency data;

[0050] The embodiment of the present invention performs image registration on the collected optical detection image data and electrophysiological signal data, with the aim of eliminating errors at different time points and spatial positions. The image registration process is adjusted based on the size, position and angle of the field of view. First, clear and obvious structural feature points in the optical image and electrophysiological signal data are selected as reference points, and then the images are adjusted through a registration algorithm based on nearest neighbor interpolation to ensure the consistency of each frame image in the time series. The field of view size is set to 10x10 mm by the initial imaging system, and the error after registration is less than 1 pixel, obtaining precisely aligned image consistent data.

[0051] Step S14: performing image cropping processing on the image consistent data to obtain circular consistent image data, wherein the image cropping processing specifically crops the original rectangular field of view into a circular area with the center of the rectangle as the circle center and the short side length of the rectangle as the diameter;

[0052] After image registration is completed, the embodiment of the present invention performs image cropping processing on the image consistency data. First, the center point of the rectangular field of view is determined, and the center point is set as the center of the cropped circular image. Next, the short side length of the rectangular field of view is used as the diameter of the cropped circle, and the pixels on both sides of the short side are used as boundaries to crop a circular area concentric with it. The circular area retains the core part of the myocardial tissue while avoiding the interference of edge blur or distortion. Finally, circular consistent image data is obtained, and the circular diameter is about 5 mm, ensuring that the data is concentrated in the important myocardial area.

[0053] Step S15: performing periodic cyclic shift and superposition on the circular consistent image data, thereby obtaining periodic enhanced data;

[0054] The embodiment of the present invention performs periodic cyclic shift and superposition processing on the circular consistent image data obtained by cutting. First, the periodic characteristics of myocardial contraction are extracted by calculating Fourier transform, and the main frequency components of the cardiac cycle are obtained. Then, according to the period length of the periodic signal, the image data is cyclically shifted, and each shift takes the period length as the step length to generate multiple groups of shifted data. These shifted data are superimposed together to form a periodic enhanced data set. This process can enhance the periodic change characteristics in the signal, making the rhythm of myocardial contraction and relaxation more obvious.

[0055] Step S16: performing signal enhancement and optimization processing based on time difference enhancement, spatial filtering, intensity normalization and data smoothing processing on the periodic enhancement data, so as to obtain optical-physiological signal mapping data.

[0056] The embodiment of the present invention performs a series of signal enhancement and optimization processing on the obtained periodic enhanced data. First, time difference enhancement is performed to adjust the time delay of each pixel point and eliminate the timing deviation caused by the difference in signal propagation speed between each frame image. Then, a spatial filter based on the Bartlett window is used to spatially filter the image data to filter out the interference of high-frequency noise. Next, the pixel intensity of the image is normalized to unify all signal values ​​into the range of [0,1]. Finally, a Savitzky-Golay smoothing filter is applied to smooth the data to reduce the impact of noise on the signal, obtain optical-physiological signal mapping data, and ensure the continuity and consistency of the signal.

[0057] The fluorescent calcium imaging system of the present invention can efficiently capture the changes in calcium ion concentration in myocardial cells, reflect the electrophysiological activity of the heart, and can synchronously obtain mechanical motion information in combination with mechanical wave imaging, providing more physical parameters for subsequent modeling. This joint imaging method provides dual data support, so that the electrophysiological characteristics of myocardial tissue and its association with mechanical motion can be captured more accurately during model training. The synchronously collected calcium signal can directly reflect the dynamic changes of calcium ions in cardiac excitation-contraction coupling. Since calcium ions are the key regulators of myocardial cell contraction, the synchronous acquisition of electrophysiological signals and calcium signals ensures the accuracy of time matching between electrical signals and optical images in subsequent analysis, and reduces the timing error in data processing. Image registration ensures that images at different time points and angles can be accurately aligned. Doing so can eliminate displacement or angle deviation caused by experimental settings or tissue movement, and ensure image and signal consistency during subsequent analysis, which is particularly important for constructing accurate optical-physiological signal mapping. By converting a rectangular area into a circular area by cropping, distortion or invalid information that may exist at the edge of the field of view can be eliminated, thereby improving the overall quality and analysis accuracy of image data. This processing simplifies the data structure and facilitates subsequent periodic analysis and signal enhancement processing. Through periodic enhancement, the periodic features in the image can be amplified, making the repetitive movements of the heart such as contraction and relaxation in the signal more significant. This enhancement process improves the model's sensitivity to periodic phenomena and helps to better extract the key contraction and electrical activity features of the myocardium. By enhancing dynamic changes through time differences, the subtle timing features in the signal are amplified, making it easier to capture instantaneous changes in myocardial activity, remove image noise, retain important spatial features, and ensure that the signal is clearer; standardization processing makes the intensity values ​​of different pixels within a uniform scale range, which helps to eliminate intensity differences in the data and improve the consistency of the model; it reduces random fluctuations in the signal, improves the stability and reliability of the signal, and provides cleaner input data for subsequent model training.

[0058] Preferably, step S15 comprises the following steps:

[0059] Step S151: performing Fourier transform on the circular consistent image data and determining the main cycle of myocardial tissue contraction, thereby obtaining periodic characteristic data;

[0060] The embodiment of the present invention performs Fourier transform processing on circular consistent image data, with the goal of extracting the main periodic features of myocardial tissue contraction. First, each frame of the image is converted into a frequency domain signal, and the amplitude spectrum of each frequency component in the image is calculated by fast Fourier transform (FFT). Then, based on the amplitude spectrum, the most significant frequency peak is determined, and this frequency represents the main period of myocardial tissue contraction. In order to enhance accuracy, image data of multiple time periods can be selected for Fourier transform, and the average value of the periodic features can be obtained to obtain stable periodic feature data. The main period at this time is usually between 1 Hz and 2 Hz, corresponding to a heart rate of 60-120 beats per minute.

[0061] Step S152: determining the cyclic shift step length according to the periodic characteristic data, thereby obtaining shift step length data;

[0062] The embodiment of the present invention determines the step length of the cyclic shift according to the periodic characteristic data. The cyclic shift step length is the frame number interval calculated based on the myocardial contraction cycle. In a specific implementation, the main cycle of the myocardium (in seconds) is combined with the imaging frame rate (e.g., 100 frames / second) to calculate the corresponding number of frames in one cycle. For example, if the periodic characteristic data is 1.2 seconds, a complete cycle contains 120 frames of images. These frame numbers are evenly divided into several steps, for example, one step length for every 20 frames, thereby obtaining the shift step length data, which will be used for subsequent cyclic shift processing.

[0063] Step S153: cyclically shifting the circular consistent image data input signal according to the shift step data to generate multiple groups of shifted image data, thereby obtaining a cyclically shifted data set;

[0064] The embodiment of the present invention performs cyclic shifting on the circular consistent image data based on the shift step data. Each frame of the image is shifted backward by the number of frames corresponding to the step, and this operation is repeated until the entire myocardial contraction cycle is covered. For example, assuming that a cycle is 120 frames and the shift step is 20 frames, image data with different shift amounts such as 20 frames, 40 frames, and 60 frames are generated in sequence to form multiple shifted image sets. This process ensures that the dynamic changes in the myocardial contraction process are captured, and the multiple sets of shifted data generated represent the myocardial states at different times, and finally a cyclic shifted data set containing multiple time points is obtained.

[0065] Step S154: Perform pixel-level weighted superposition on the images in the cyclic shift data set to obtain periodic enhanced data, wherein the weights are allocated in inverse proportion to the shift amount.

[0066] The embodiment of the present invention performs pixel-level weighted superposition on the cyclic shift data set to enhance the periodic signal of myocardial contraction. First, different weights are assigned to each group of shifted images, and the weight value is inversely proportional to the shift amount, that is, the smaller the shift step, the greater the image weight, and the larger the shift amount, the smaller the image weight. For example, the image weight with a step size of 20 frames can be set to 0.9, the image weight with a step size of 40 frames is set to 0.8, and so on. Then, the weighted average of each frame image at the same pixel position is performed, and the final value of each pixel point is calculated to obtain periodic enhanced data. In this way, the noise and irregular changes in the original data are weakened, the periodic signal is strengthened, and finally a clear myocardial contraction rhythm image is obtained.

[0067] The Fourier transform of the present invention is a powerful tool for frequency domain analysis, which can decompose the signal in time (or space) into different frequency components and highlight the periodic changes. Through Fourier transform, the main cycle of myocardial contraction can be accurately identified, thereby capturing the dominant characteristics of cardiac motion. This process simplifies complex signals into periodic components, facilitates subsequent shift processing, and improves the sensitivity to myocardial contraction characteristics. According to the extracted periodic characteristics, the step size of the cyclic shift is set to ensure that each shift is equivalent to a specific time point in the myocardial contraction cycle, thereby ensuring that the shifted image remains consistent with the periodic characteristics. This step size selection is crucial to ensure that the subsequently generated shifted data set contains sufficient information changes but does not destroy the original periodic structure; in this way, it can ensure that all shift operations are coordinated with the myocardial contraction process and reduce noise interference. Through multiple cyclic shifts, the myocardial contraction process can be observed from different angles to form a data set containing multiple groups of shifted images. This data enhancement method can not only enrich the training data set, but also better capture the complete dynamic characteristics of myocardial tissue throughout the cycle. Circular shifting is equivalent to multiple sampling of myocardial contraction in time, which increases the robustness to time changes and enhances the ability to capture periodic phenomena. Through pixel-level weighted superposition, the key information in different shifted data can be effectively fused to further amplify the periodic features. The weight distribution in weighted superposition is based on the inverse of the shift amount, which means that images with larger shift amounts have less impact on the final result, while images with smaller shift amounts have larger weights, thereby maintaining the integrity of the core features of the period. This strategy helps to eliminate unnecessary noise caused by shifting, strengthen periodic information, improve the signal quality of the image, and provide clearer input data for subsequent signal extraction and modeling.

[0068] Preferably, step S16 comprises the following steps:

[0069] Step S161: setting time difference parameters for periodic enhancement data according to actual cell waveform conduction velocity, thereby obtaining time difference parameter data;

[0070] The embodiment of the present invention sets the time difference parameter for the periodic enhancement data according to the actual cell waveform conduction velocity in the myocardial tissue. First, the conduction velocity of myocardial cells is usually between 0.3 and 1.0 m / s, depending on the specific experimental conditions. Based on the known conduction velocity and the physical size of the myocardial tissue, the time difference of the conduction signal between different pixels is calculated. For example, if the conduction velocity of the myocardium is 0.5 m / s and the spatial resolution of the imaging system is 100 microns / pixel, the signal conduction time difference between adjacent pixels is approximately 0.2 milliseconds. Based on these calculations, the time difference between different pixel points is set to obtain the time difference parameter data for subsequent processing.

[0071] Step S162: calculating the absolute value of the difference between the current value of each pixel position and the value at a past time point determined according to the time difference parameter data according to the periodic enhancement data, thereby obtaining the time difference enhancement data;

[0072] The embodiment of the present invention calculates the absolute value of the difference between the value of each pixel at the current time point and the value at the past time point based on the time difference parameter data. Specifically, for each pixel point, the intensity value at the current moment is obtained, and the intensity value at the corresponding past moment is determined based on the time difference parameter. Then, the intensity difference between the two moments is calculated, and its absolute value is taken to obtain enhanced data reflecting the time difference. For example, if the intensity of a pixel point at the current moment is 0.8, and the intensity at the past moment is 0.6, then its time difference enhancement data is |0.8-0.6|=0.2. The goal of this processing step is to highlight the changing trend of the signal and reduce the impact of static signals.

[0073] Step S163: performing a spatial filtering process based on a Bartlett filter on the time difference enhancement data, thereby obtaining spatial filtering data;

[0074] The embodiment of the present invention performs spatial filtering processing based on the Bartlett filter on the time difference enhancement data. The Bartlett filter is a weighted average filter, and the weight decreases linearly, gradually decreasing from the center to the outside. The specific operation is to apply the Bartlett filter to each pixel point and its adjacent area, and calculate the weighted average of each pixel in the area, the weight of the central pixel is the largest, and the weight of the surrounding pixels gradually decreases. For example, the filter window size is 3x3 pixels, the weight of the central pixel is set to 1, and the weights of the surrounding 8 pixels are set to 0.5 or lower. After being processed by the Bartlett filter, the noise in the time difference enhancement data will be effectively smoothed, and the local continuity of the signal will be enhanced, thereby obtaining spatial filtered data.

[0075] Step S164: performing the maximum and minimum values ​​in the time series of each pixel point on the spatial filtering data, thereby obtaining pixel intensity range data;

[0076] The embodiment of the present invention performs time series analysis on the spatial filtering data, extracts the maximum and minimum values ​​in the time series of each pixel point, and then obtains the pixel intensity range data. The specific method is to traverse the intensity values ​​of each pixel point in all time frames, and record the maximum and minimum values ​​of the pixel in the entire cycle. For example, the intensity of a pixel point in the 5th frame is 0.9, which is the maximum value; the intensity in the 20th frame is 0.1, which is the minimum value. In this way, the fluctuation range of each pixel in the time series can be determined, thereby obtaining the intensity range data of each pixel as the basis for subsequent normalization processing.

[0077] Step S165: linearly normalize each pixel point according to the pixel intensity range data, and map the value to the interval [0, 1], thereby obtaining intensity normalized data;

[0078] The embodiment of the present invention linearly normalizes the intensity value of each pixel according to the pixel intensity range data, and maps the value to the interval of [0, 1]. The formula of linear normalization is: (current value-minimum value) / (maximum value-minimum value), through which the intensity value of each pixel can be standardized to a uniform range. For example, if the minimum value of a pixel is 0.1 and the maximum value is 0.9, then its current value 0.5 is normalized to (0.5-0.1) / (0.9-0.1)=0.5. The normalized data will ensure that the intensity values ​​of all pixels are within a uniform interval, which is convenient for subsequent analysis and processing, thereby obtaining intensity normalized data.

[0079] Step S166: performing data smoothing processing on the intensity normalized data to obtain optical-physiological signal mapping data.

[0080] The embodiment of the present invention performs data smoothing on the intensity normalized data to reduce the intensity changes caused by noise or random fluctuations. The specific smoothing method used can be a moving average method or a Gaussian smoothing method. The moving average method averages each pixel point and several adjacent time points in its time series. For example, the intensity average of the three previous and next time points is taken to replace the current value. The Gaussian smoothing rule performs a weighted average on the time series according to the weight of the Gaussian function. Through smoothing, the noise can be effectively reduced, and the stability and continuity of the signal can be improved, thereby obtaining the final optical-physiological signal mapping data and ensuring the accuracy of subsequent data analysis.

[0081] The electrical signal conduction velocity of the myocardial cells of the present invention directly affects the timing of signal propagation, and the accurate setting of the time difference parameters can ensure that the differences at different time points in the signal processing process are reasonably considered. By adjusting the time difference parameters according to the actual conduction velocity, the time difference enhanced data can reflect the real electrophysiological activity changes of the myocardial cells, improve the ability to capture dynamic signals, and thus help to more accurately analyze the electrophysiological characteristics of myocardial tissue. By calculating the time difference between pixels, the signal changes at different time points are enhanced. Time difference enhancement can amplify rapidly changing signal features, such as electrophysiological activities in myocardial tissue, thereby increasing the sensitivity to short-term and drastic changes. This enhancement method can not only highlight periodic fluctuations, but also enhance the synergy of spatiotemporal information, providing clearer time series data for subsequent filtering and processing. The Bartlett filter is a simple and efficient low-pass filter that can smooth noise and irregular signal fluctuations while retaining the key features of the signal. Through spatial filtering, image noise generated during data acquisition, such as random fluctuations or high-frequency interference, can be reduced, thereby extracting smoother and coherent physiological signal data. This process enhances the spatial consistency of the signal and is particularly suitable for removing high-frequency noise in muscle tissue surface signals. By calculating the intensity range of each pixel, the fluctuation amplitude of the signal in the entire time series can be effectively identified, and the signal change characteristics of different regions in the image can be captured. This is very critical for further normalization and signal amplification, and can help determine which pixels have large electrophysiological activity fluctuations and provide a standardized range for subsequent normalization. The purpose of linear normalization is to standardize the intensity values ​​of each pixel and eliminate the distortion effect caused by inconsistent signal intensity between different pixels. In the same image, different parts of myocardial tissue may have different signal intensities. Through normalization, they can be unified into comparable scales to enhance the consistency of feature extraction. This process improves the accuracy of model training and prediction, allowing signals in different regions to be analyzed at the same amplitude. Data smoothing can further eliminate irregular changes in the signal and ensure the continuity and stability of the signal, especially when processing biological signals, where excessive sharp fluctuations may be caused by noise. Through smoothing, the main trend of the electrophysiological signal can be highlighted without being disturbed by occasional noise or small errors, thereby providing high-quality input data for the model and helping to improve the robustness of the prediction model.

[0082] Preferably, step S166 includes the following steps:

[0083] Step S1661: Calculate the power spectrum density of the intensity normalized data and determine the main frequency components of the signal, thereby obtaining frequency characteristic analysis data;

[0084] The embodiment of the present invention performs power spectral density (PSD) calculation on the intensity normalized data to determine the main frequency components of the signal. The specific operation is to perform Fourier transform on the time series of each pixel point to obtain an energy distribution diagram in the frequency domain, and determine the main frequency components of the signal by analyzing the power spectral density curve. For example, if the acquisition frequency of the myocardial signal is 1000Hz, the PSD analysis finds that the main frequency distribution is between 0.5Hz and 5Hz, which represents the main frequency characteristics of myocardial contraction and electrophysiological signals. By analyzing the data with this frequency characteristic, the parameters of the smoothing process can be further optimized.

[0085] Step S1662: determining smoothing method parameters based on Rloess according to the frequency characteristic analysis data, thereby obtaining smoothing method parameter data, wherein the window size parameter in the smoothing method parameter data is set to 20% of the acquisition frame rate;

[0086] The embodiment of the present invention analyzes data based on frequency characteristics and determines parameters based on the Rloess smoothing method. Rloess is a local regression smoothing method, and parameter settings include window size and polynomial order. In combination with frequency characteristic analysis, the smoothing window size is usually set to 20% of the acquisition frame rate. For example, if the acquisition frame rate of myocardial data is 500 frames / second, the window size is set to 100 frames to ensure that high-frequency noise can be effectively removed during the smoothing process while retaining the main signal characteristics. The polynomial order is selected according to the complexity of the signal and is usually set to 2 or 3.

[0087] Step S1663: smoothing each pixel time series of the intensity normalized data according to the smoothing method parameter data, and calculating the mean square error before and after smoothing, thereby obtaining smoothing effect evaluation data;

[0088] The embodiment of the present invention performs smoothing processing on each pixel time series of the intensity normalized data according to the smoothing method parameter data. The specific operation of the smoothing processing is to apply the Rloess method to the time series of each pixel for local regression fitting to reduce the influence of noise. After processing, the mean square error (MSE) before and after smoothing is calculated to evaluate the smoothing effect. For example, if the MSE of a pixel point before smoothing is 0.05 and the MSE after smoothing is 0.01, it means that the smoothing effect is good. Through the calculation of the mean square error, the effectiveness of the smoothing processing is further judged, and the smoothing effect evaluation data is obtained.

[0089] Step S1664: performing edge preservation processing on the pixels with poor smoothing effect according to the smoothing effect evaluation data, thereby obtaining edge preservation data, wherein the edge preservation processing specifically includes detecting mutation points and edges in the signal and performing local adjustments;

[0090] The embodiment of the present invention performs edge preservation processing on pixel points with poor smoothing effect according to the smoothing effect evaluation data. The specific method is to detect the mutation points and edge positions in the signal, and retain these signal features through local adjustment. First, the edge points are identified by detecting the mutation of the first-order derivative of the signal, and then the smoothing parameters are adjusted locally in these areas to reduce the weakening of the edge signal by the smoothing process. For example, at some key electrophysiological signal mutation positions, the window size of Rloess can be appropriately reduced to ensure that the edge features are retained, thereby obtaining edge preservation data.

[0091] Step S1665: analyzing the signal changes between adjacent frames of the edge holding data, and performing time consistency correction to obtain time correction data;

[0092] The embodiment of the present invention performs signal change analysis between adjacent frames of edge retention data and performs time consistency correction. The specific operation is to calculate the signal change rate of each pixel between adjacent frames and determine whether there is an inconsistent signal jump. For pixels with poor time consistency, interpolation correction or local smoothing is performed to make the signal more continuous in the time dimension. For example, if the signal jump of a pixel between adjacent frames exceeds a set threshold (such as 20%), the frame signal is time-corrected to obtain time-corrected data.

[0093] Step S1666: calculating the signal-to-noise ratio change before and after smoothing the time-corrected data, thereby obtaining signal-to-noise ratio improvement data;

[0094] The embodiment of the present invention calculates the change of the signal-to-noise ratio (SNR) before and after smoothing based on the time correction data. The specific operation is to calculate the signal average and noise standard deviation of each pixel time series, and calculate the signal-to-noise ratio before and after smoothing by the SNR formula (SNR = signal average / noise standard deviation). For example, the SNR of a pixel before smoothing is 10 and after processing is 20, indicating that the signal-to-noise ratio has doubled. By comparing the changes in the signal-to-noise ratio, the effect of the smoothing process is evaluated, and the signal-to-noise ratio improvement data is obtained.

[0095] Step S1667: weighted fusion of the time correction data and the intensity normalization data is performed according to the signal-to-noise ratio improved data, thereby obtaining optical-physiological signal mapping data.

[0096] The embodiment of the present invention performs weighted fusion of time correction data and intensity normalization data according to the signal-to-noise ratio improvement data. The specific method is to assign weights to the time correction data and the intensity normalization data according to the change in the signal-to-noise ratio. For example, if the SNR of a certain pixel is improved greatly, a higher weight is given to the time correction data; otherwise, a higher weight is given to the intensity normalization data. Ultimately, the data after weighted fusion will retain both the accuracy of the intensity and the consistency of time, thereby obtaining the final optical-physiological signal mapping data, ensuring the integrity and reliability of the signal data.

[0097] The power spectrum density analysis of the present invention helps to extract the main frequency components in the signal and evaluate the main fluctuation characteristics of the signal from the frequency domain perspective, especially in myocardial electrophysiological signals, where different frequencies correspond to different physiological processes. By analyzing the frequency characteristics, the key frequencies in the signal can be determined, thereby providing a basis for the subsequent smoothing parameter setting to ensure that these key physiological characteristics will not be weakened during smoothing. Rloess is a smoothing method based on local regression, which eliminates noise by fitting local data while retaining key changes in the signal. The window size is set to 20% of the acquisition frame rate, which can smooth short-term fluctuations to a large extent without affecting the main trend and edge information of the signal. This method makes the signal more adaptive during the smoothing process, and is particularly suitable for processing myocardial electrophysiological data containing random noise. The effect of the smoothing process can be quantitatively evaluated by calculating the mean square error. The lower the mean square error, the smaller the difference between the signal and the original signal after smoothing, and more signal features are retained. At the same time, the evaluation data provides a basis for the subsequent detection of pixels with poor smoothing effects, which helps to further adjust those signals that are not fully optimized. In some pixels, the smoothing process may cause the signal to be over-smoothed, weakening the mutation point and edge information. Therefore, edge preservation processing aims to retain the mutation points and key edge features in the signal to prevent important physiological signal features from being erased; through this processing, noise can be smoothed while mutations and boundary signals can be retained to ensure signal integrity and accuracy. Time consistency correction can ensure that signals between different frames maintain temporal continuity and reduce errors caused by time drift in data acquisition or processing. By analyzing signal changes between frames and correcting possible inconsistencies, the stability of myocardial electrophysiological signals in the time dimension is ensured. This processing is critical for subsequent improvement of signal-to-noise ratio and improvement of model prediction accuracy. The improvement of signal-to-noise ratio is one of the key indicators to measure the effect of signal processing. By calculating the improvement of signal-to-noise ratio, the effect of smoothing on denoising can be quantified. If the signal-to-noise ratio is significantly improved, it means that the smoothing and correction steps have successfully reduced noise and improved signal quality, providing better input data for subsequent analysis and model training. Through weighted fusion, the time-corrected and intensity-normalized signals are effectively combined to form higher-quality optical-physiological signal mapping data. Weighted fusion not only retains the signal strength information, but also further enhances the time consistency and signal-to-noise ratio optimization effect, thereby generating more accurate and biologically meaningful mapping data. This step ensures that the final data can accurately reflect the electrophysiological activity of myocardial tissue, providing strong support for subsequent model training and prediction.

[0098] Preferably, step S2 comprises the following steps:

[0099] Step S21: extracting the local displacement information in the image and the spatial variation trend of the myocardial contraction deformation from the optical-physiological signal mapping data, thereby constructing a mechanical contraction curve;

[0100] Step S22: mapping the electrical signal intensity fluctuation at each pixel point in the optical-physiological signal data, and taking time as the abscissa and the electrical signal intensity as the ordinate, thereby obtaining an electrophysiological curve reflecting the electrical activity characteristics of the myocardial cells;

[0101] Step S23: dividing the mechanical contraction curve and the electrophysiological curve into cardiac contraction cycles, determining the start and end time points of each cardiac cycle, and calibrating the peak and valley values, thereby obtaining cardiac cycle segmentation data;

[0102] Step S24: extracting features of the mechanical contraction curve and the electrophysiological curve in the cardiac cycle based on the contraction amplitude, the maximum contraction rate, the peak and valley values ​​of the electrical signal, and the rise time according to the cardiac cycle segmentation data, thereby obtaining feature vector data;

[0103] Step S25: performing a scale difference elimination process on the feature vector data between different samples, and mapping the data values ​​to a uniform numerical range, thereby obtaining mechanical contraction curve data and electrophysiological curve data.

[0104] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment of the present invention, step S2 includes the following steps:

[0105] Step S21: extracting the local displacement information in the image and the spatial variation trend of the myocardial contraction deformation from the optical-physiological signal mapping data, thereby constructing a mechanical contraction curve;

[0106] The embodiment of the present invention extracts the local displacement information in the optical-physiological signal mapping data. The specific operation is to detect the displacement of the myocardial tissue in each frame of the image through the optical flow algorithm to capture the movement trajectory of the myocardial tissue. Then, the displacement information is spatially interpolated to construct the spatial variation trend of the myocardial contraction deformation. By analyzing these trend changes, the displacement curve of the myocardium in different time periods can be drawn, and finally a complete mechanical contraction curve can be constructed. For example, in an experimental scenario, by detecting the local displacement of the myocardium, it is found that the maximum displacement of the myocardium in each cardiac cycle is about 1.5 mm, and the displacement curve reflects the dynamic contraction deformation process of the myocardium.

[0107] Step S22: mapping the electrical signal intensity fluctuation at each pixel point in the optical-physiological signal data, and taking time as the abscissa and the electrical signal intensity as the ordinate, thereby obtaining an electrophysiological curve reflecting the electrical activity characteristics of the myocardial cells;

[0108] The embodiment of the present invention analyzes the fluctuation of the electrical signal intensity of each pixel in the optical-physiological signal mapping data, specifically, the time series data of each pixel is selected, and the electrophysiological curve of each pixel is drawn with time as the horizontal coordinate and the electrical signal intensity as the vertical coordinate. These curves reflect the electrical activity characteristics of myocardial cells, such as the process of depolarization and repolarization. For example, in actual operation, the electrophysiological curve of a certain myocardial area shows that the electrical signal intensity rises rapidly to a peak value of 0.8V during depolarization, and the intensity slowly decreases to a valley value of 0.2V during repolarization, which can clearly reflect the changes in the electrical activity of myocardial cells.

[0109] Step S23: dividing the mechanical contraction curve and the electrophysiological curve into cardiac contraction cycles, determining the start and end time points of each cardiac cycle, and calibrating the peak and valley values, thereby obtaining cardiac cycle segmentation data;

[0110] The embodiment of the present invention divides the cardiac contraction cycle of the mechanical contraction curve and the electrophysiological curve. The specific method is to determine the start and end time points of each cardiac cycle by calculating the local extreme points in the mechanical contraction curve and the electrophysiological curve. First, determine the main peaks and valleys reflecting the cardiac cycle in the electrophysiological curve, calibrate these extreme points, and then synchronize the peak and valley positions of the mechanical contraction curve. For example, in a certain experimental data, the peak voltage of the cardiac cycle is 1.0V, the valley is 0.1V, and the cycle length is about 800 milliseconds. Through this extreme value calibration, the cardiac cycle can be clearly divided.

[0111] Step S24: extracting features of the mechanical contraction curve and the electrophysiological curve in the cardiac cycle based on the contraction amplitude, the maximum contraction rate, the peak and valley values ​​of the electrical signal, and the rise time according to the cardiac cycle segmentation data, thereby obtaining feature vector data;

[0112] The embodiment of the present invention performs feature extraction on the mechanical contraction curve and electrophysiological curve in each cycle according to the cardiac cycle segmentation data. The specific steps of feature extraction include: first, calculating the mechanical contraction amplitude (the difference between the peak value and the valley value) and the maximum contraction rate (the maximum slope of the contraction curve) of each cycle; then, calculating the peak value, valley value and rise time (the time difference from the valley value to the peak value) of the electrophysiological curve. For example, the mechanical contraction amplitude in a certain cardiac cycle is 1.2 mm, the maximum contraction rate is 2.5 mm / s, the electrophysiological peak value is 0.9V, the valley value is 0.2V, and the rise time is 150 milliseconds. The extracted characteristic values ​​constitute the characteristic vector data of the cycle.

[0113] Step S25: performing a scale difference elimination process on the feature vector data between different samples, and mapping the data values ​​to a uniform numerical range, thereby obtaining mechanical contraction curve data and electrophysiological curve data.

[0114] The embodiment of the present invention performs a process of eliminating the scale differences between different samples on the feature vector data. The specific operation is to map the data to a uniform numerical interval (such as [0, 1]) through a normalization method. For example, the numerical range of the mechanical contraction amplitude may vary greatly in different samples. The contraction amplitude of all samples is mapped to the [0, 1] interval through normalization. At the same time, the electrophysiological curve data is subjected to the same normalization process, and the peak and valley values ​​of the electrical signal are respectively mapped to between [0, 1]. After the processing is completed, the mechanical contraction curve data and the electrophysiological curve data of different samples are compared and analyzed on a uniform scale to ensure the comparability between the data.

[0115] The local displacement information and spatial variation of myocardial contraction deformation of the present invention are the core parameters reflecting the mechanical activity of the myocardium. Extracting these features can intuitively display the degree of deformation of different parts during the heart contraction process, and help understand the contraction characteristics of the myocardium. After the mechanical contraction curve is constructed, the amplitude and rate of myocardial movement can be quantitatively described, providing the necessary basic data for subsequent electrophysiological signal analysis and biomechanical modeling. The electrophysiological curve reflects the electrical activity characteristics of myocardial cells and can show the changes of electrical signals at different time points. Through this curve, the excitement and recovery process of myocardial cells in electrophysiological activities can be accurately reflected, especially when studying the spatiotemporal distribution of cardiac electrical signals, the construction of electrophysiological curves is crucial. The curve provides direct input data for the training of the ECG signal prediction model. Cardiac cycle division helps to separate specific contraction and electrical activity events in each cardiac cycle, thereby accurately analyzing the features in each cycle. By calibrating the peak and valley values, the maximum contraction and minimum relaxation moments of the heart in each cycle can be captured, providing a periodic structure for subsequent feature extraction and model training. Cycle division can also improve the accuracy of data processing and help identify abnormal cycle behavior. Feature vector extraction can extract core information from complex time series data, helping to identify and distinguish important physiological features in different cardiac cycles. By extracting features from mechanical contraction curves and electrophysiological curves, the mechanical and electrical activity states of the heart can be quantitatively described, which helps further data analysis, modeling, and prediction; this process reduces the complexity of the data while retaining key information. Due to the different scales and contraction characteristics of different heart samples, direct comparison of raw data will lead to errors. By eliminating scale differences and standardizing data, systematic differences between different samples can be eliminated, making data from different samples comparable. This step enables the model to handle data of various sizes during training, while enhancing the consistency and interpretability of feature data, facilitating subsequent model training and analysis.

[0116] Preferably, step S3 comprises the following steps:

[0117] Step S31: using the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, and matching them based on the time series to form a training data set;

[0118] The embodiment of the present invention uses the mechanical contraction curve data as the independent variable and the electrophysiological curve data as the dependent variable, and matches the two point by point through the timestamp to form a complete time series data set. The matching process is specifically: for each time point in the mechanical contraction curve, find the same time point of the corresponding electrophysiological curve to ensure that the two are aligned in the time dimension. For example, if the mechanical contraction curve value at a certain time point is 0.75 mm, and the voltage value of the electrophysiological curve is 0.65V, then the matching point at this time will be used as a sample in the training data, and the training data set formed contains thousands of similar samples, constituting time series data.

[0119] Step S32: Divide the training data set into a training set, a validation set, and a test set based on a ratio of 80:10:10;

[0120] The embodiment of the present invention divides the training data set into a training set, a validation set, and a test set in a ratio of 80:10:10. The specific operation is: first, the entire data set is randomly shuffled to avoid model bias caused by serial correlation; then, 80% of the data is used to train the model, 10% is used to verify the performance of the model, and the remaining 10% is used for the final test. For example, if the data set contains 10,000 samples, 8,000 samples will be used for model training, 1,000 for validation, and 1,000 for testing, ensuring the independence of different data sets and the consistency of data distribution.

[0121] Step S33: initializing a gated recurrent unit network model according to the mechanical contraction curve data and the electrophysiological curve data, and setting hyperparameters of the gated recurrent unit network model based on a learning rate, an optimizer type, a batch size, and a number of training rounds, thereby obtaining an initial GRU network model;

[0122] The embodiment of the present invention initializes the gated recurrent unit (GRU) network model according to the mechanical contraction curve and electrophysiological curve data. The initialization of the model includes determining the network structure and setting the hyperparameters. The specific hyperparameters include: the learning rate is set to 0.001, the Adam optimizer is selected as the optimizer, the batch size is set to 32, and the number of training rounds is set to 100 rounds. The GRU network includes two hidden layers, and the width of each layer is set to 64 neurons to capture the dynamic characteristics in the time series. The network structure can effectively process time-dependent long-term and short-term information, and regulate the flow of information through the gating mechanism. The initialized GRU network model is ready for training.

[0123] Step S34: input the training set into the initial GRU network model for training, calculate the predicted value through forward propagation, and then adjust the weight through back propagation to reduce the prediction error, so as to obtain the trained dynamic time series prediction model;

[0124] The embodiment of the present invention inputs the training set into the initial GRU network model for training. The training process includes: first, the predicted value of each sample is calculated through forward propagation, that is, the model predicts the electrophysiological curve value according to the input mechanical contraction curve data; then, the error between the predicted value and the true electrophysiological curve value is calculated, and the mean square error (MSE) is used as the loss function; finally, the model adjusts the weight through back propagation, optimizes the model parameters to reduce the error, and the prediction accuracy of the model is gradually improved with each round of training. After 100 rounds of training, the trained dynamic time series prediction model is obtained.

[0125] Step S35: using the validation set to validate the dynamic time series prediction model, and adjusting the training strategy according to the error of the validation result, so as to obtain an adaptive spatiotemporal attention GRU model;

[0126] The embodiment of the present invention uses a validation set to verify the trained dynamic time series prediction model. The specific operation is: input the validation set into the model, and calculate the error between the predicted value and the true value. According to the performance of the validation error, adjust the parameters such as the learning rate and the number of training rounds of the model in a timely manner. For example, when it is found that the error on the validation set no longer decreases significantly, an early stopping strategy is adopted to prevent overfitting. At the same time, by introducing an adaptive spatiotemporal attention mechanism, the model can dynamically adjust the weights according to the different importance of time and space, thereby further improving the prediction accuracy of the model and forming an adaptive spatiotemporal attention GRU model.

[0127] Step S36: Performing a performance test based on mean square error and root mean square error on the adaptive spatiotemporal attention GRU model through the test set to obtain model performance evaluation data;

[0128] The embodiment of the present invention performs a performance test on the adaptive spatiotemporal attention GRU model through a test set. The specific operation is: input the test set into the model, and use the model to predict the electrophysiological curves in the test set. Then, the mean square error (MSE) and the root mean square error (RMSE) between the predicted value and the true value are calculated. For example, in a test scenario, the model's prediction results for electrophysiological activity in the cardiac cycle show that the MSE is 0.004 and the RMSE is 0.063, which better reflects the generalization ability of the model on unknown data, and finally obtains the performance evaluation data of the model.

[0129] Step S37: Perform integrated learning optimization processing on the adaptive spatiotemporal attention GRU model according to the model performance evaluation data to obtain an electrophysiological signal prediction model.

[0130] The embodiment of the present invention performs ensemble learning optimization processing on the adaptive spatiotemporal attention GRU model based on the model performance evaluation data. The specific method is to optimize the model by introducing multiple GRU models and adopting ensemble learning. For example, using algorithms such as random forest or gradient boosting decision tree, the prediction results of multiple models are weighted and fused to improve the prediction performance of the overall model. After ensemble learning processing, the final electrophysiological signal prediction model can maintain high prediction accuracy and robustness under more complex myocardial electrophysiological data.

[0131] The time series matching of the mechanical contraction curve and the electrophysiological curve in the present invention can ensure the consistency of the input and output data, and help capture the temporal relationship between cardiac contraction and electrophysiological activity; this provides a complete input-output pair for the model, so that the network can learn the mapping relationship between the two and improve the accuracy of model prediction. Reasonable division of the data set can effectively prevent the overfitting of the model. The training set is used for the preliminary training of the model, the validation set is used to adjust the hyperparameters of the model during the training process, and the test set is used to finally evaluate the performance of the model. Through the division of the data set into these three parts, the generalization ability of the model can be fully tested and the prediction effect of the model on new data can be ensured. The GRU model is suitable for processing time series data and can well capture the long-term and short-term dependencies between myocardial contraction and electrophysiological activity. Through the setting of hyperparameters, the training process of the model can be optimized. Appropriate learning rate and optimizer can accelerate model convergence, while the setting of batch size and number of training rounds ensures that the model can fully learn from the data and improve the training effect. Forward propagation allows the model to learn to predict electrophysiological signals from input data, and back propagation adjusts the weight of the model by minimizing the error. As the training progresses, the model can gradually converge to a low error state, so that the prediction accuracy is continuously improved and the prediction ability of the model is gradually optimized. Through the performance test of the validation set, the model can adjust the training strategy in time to avoid overfitting or underfitting; the introduction of the adaptive spatiotemporal attention mechanism allows the model to more effectively focus on the characteristics of key time points and spatial regions, so as to more accurately capture the dynamic relationship between mechanical contraction and electrophysiological activity and improve the prediction ability of the model. The test set is data independent of the training process and can truly evaluate the generalization performance of the model; mean square error and root mean square error are important indicators for measuring the prediction accuracy of the model. Through these indicators, the performance of the model in actual data can be quantitatively evaluated, providing a basis for further optimization and application. Ensemble learning can further improve the accuracy and stability of prediction by combining the advantages of multiple models. Fusion of multiple model results with different weights helps to eliminate the shortcomings of a single model and improve the overall prediction effect; the final electrophysiological signal prediction model has stronger generalization ability and robustness, and can accurately predict the dynamic changes of myocardial electrophysiological activity.

[0132] Preferably, step S33 includes the following steps:

[0133] The gated recurrent unit network model is initialized according to the mechanical contraction curve data and the electrophysiological curve data, wherein the gated recurrent unit network model includes an input layer, two hidden layers and an output layer. The input dimension of the input layer is the time step of the mechanical contraction curve; the number of GRU units in the first hidden layer is 64, and the task is to extract primary timing features from the input mechanical contraction curve data; the number of GRU units in the second hidden layer is 64, which receives the output from the first hidden layer and performs high-level feature integration and complex pattern recognition; the output dimension of the output layer is the time step of the electrophysiological curve; the hyperparameters of the gated recurrent unit network model are set based on the learning rate, optimizer type, batch size and number of training rounds to obtain the initial GRU network model.

[0134] The embodiment of the present invention initializes a gated recurrent unit (GRU) network model based on mechanical contraction curve data and electrophysiological curve data. First, the input dimension of the input layer is equal to the time step of the mechanical contraction curve, specifically, each time step corresponds to a feature vector, that is, each time step represents a mechanical contraction state. For this embodiment, it is assumed that the data time step of the mechanical contraction curve is 100 points, and the input dimension of the input layer is set to 100. Then, the first hidden layer contains 64 GRU units, whose task is to extract primary time series features from the input mechanical contraction curve data. The GRU unit can capture the long-term dependency of information in the time series, and through its gating mechanism, effectively filter out unimportant information. The second hidden layer also contains 64 GRU units, which are responsible for receiving the output from the first hidden layer, integrating high-level features and recognizing complex patterns, and helping the network to establish a deep relationship between mechanical contraction and electrophysiological signals. The output dimension of the output layer is equal to the time step of the electrophysiological curve, that is, each mechanical contraction time step will correspond to an electrophysiological signal output. Assuming that the time step of the electrophysiological curve is also 100, the dimension of the output layer is 100. To ensure effective learning of the model, some key hyperparameters are set here: the learning rate is set to 0.001, the Adam optimizer is selected to accelerate the convergence of the model, the batch size is set to 32, which means that 32 sets of data will be input for training in each iteration, and the number of training rounds is set to 100. In actual operation, the initialization process of the model also includes random initialization of weights, and the weights are optimized through each round of iteration to finally obtain the initial GRU network model. In a practical application scenario, such as sequence prediction of myocardial data, this structure can capture the complex relationship between mechanical contraction and electrophysiological activity.

[0135] The present invention uses the time step of the mechanical contraction curve as the input dimension, ensuring that the model can capture the timing information of myocardial contraction and reflect the dynamic changes of the mechanical contraction process. Each contraction and relaxation process of the myocardium is closely related to electrophysiological activity. Using a complete time series as input can provide sufficient information basis for the model, ensuring that the subsequent layers can accurately extract timing features. The main function of the first hidden layer is to extract primary features in the timing data, such as the basic patterns in the cardiac contraction and relaxation cycles. The 64 GRU units have sufficient expressive power to perform preliminary analysis of mechanical contraction signals in different time periods and extract the main characteristic patterns in the myocardial contraction process, such as contraction amplitude changes and frequency information. This layer helps to capture the basic relationship between mechanical movement and electrophysiological activity, laying the foundation for subsequent deep feature integration. By adding a second hidden layer, the model has higher expressive power and the ability to learn complex patterns. Although the primary features extracted by the first hidden layer can characterize the basic changes of mechanical contraction, the dynamic behavior of myocardial activity is very complex, and advanced feature integration is required through a deeper network level. The second hidden layer can identify higher-order associations between myocardial contraction and electrophysiological signals, such as more subtle waveform changes and their interactions with electrical activity, which improves the generalization ability and prediction accuracy of the model. The output dimension is set to the time step of the electrophysiological curve to ensure that the model can generate output signals corresponding to the actual myocardial electrical activity. By analyzing the mechanical contraction signal, the model can predict the electrophysiological response of the heart in each time step, and then provide a dynamic prediction of the change of electrical signals. This design makes the output of the model consistent with the electrical activity process of the heart and can reflect complex physiological phenomena. A learning rate that is too large will cause the model to skip the optimal solution during training, while a learning rate that is too small may cause the training time to be too long. With a suitable learning rate setting, the model can stably converge to the global optimal solution. The choice of optimizer type determines the way the model weights are updated. Optimizers such as Adam can adaptively adjust the learning rate, with faster convergence speed and better performance. The batch size setting affects the generalization ability and training efficiency of the model. A moderate batch size (such as 32 or 64) can ensure the stability of the model during training without causing excessive computational burden. The number of training rounds determines the degree of training of the model on the data set. A larger number of rounds can ensure that the model fully learns the data features, but also avoid overfitting.

[0136] Preferably, step S4 comprises the following steps:

[0137] Step S41: inputting the new mechanical contraction curve data into the electrophysiological signal prediction model, predicting the change of cardiac electrophysiological activity through forward propagation calculation, thereby obtaining electrophysiological prediction data;

[0138] The embodiment of the present invention inputs the new mechanical contraction curve data into the trained electrophysiological signal prediction model. Through the forward propagation method, the model calculates the change prediction value of the electrophysiological activity of the heart according to the input mechanical contraction data time step by time, and generates electrophysiological prediction data. In this process, the GRU unit inside the model infers the corresponding electrophysiological activity signal according to its previously learned rules. Taking the actual application scenario as an example, if the time step of the new mechanical contraction data is 100, the model will predict the electrical signal for each time step and output the corresponding electrophysiological signal.

[0139] Step S42: comparing the electrophysiological prediction data with the actually measured electrophysiological data, and calculating the relative error, mean square error and root mean square error, so as to obtain prediction error data;

[0140] The embodiment of the present invention compares the predicted electrophysiological signal with the electrophysiological data actually measured in the experiment, focusing on the difference between the two. Commonly used error indicators are calculated, including relative error, mean square error (MSE) and root mean square error (RMSE). These error indicators can accurately reflect the difference between the model prediction value and the actual value. For example, if the actual value of a time step is 0.8, and the predicted value of the model is 0.75, then the relative error and MSE / RMSE can be calculated according to the formula.

[0141] Step S43: performing prediction performance evaluation of the electrophysiological signal prediction model in different time scales and signal amplitude ranges according to the prediction error data, thereby obtaining multi-scale performance evaluation data;

[0142] The embodiment of the present invention evaluates the prediction performance of the electrophysiological signal prediction model at different time scales (such as short-term and long-term trends) and signal amplitude ranges (such as small signal and large signal fluctuations) based on the prediction error data. Through this multi-scale analysis, the accuracy of the model in signal prediction at different levels can be understood, for example, whether the model has good prediction performance under rapidly changing ECG signals. The evaluation results will form multi-scale performance evaluation data.

[0143] Step S44: Visualizing the prediction results based on the multi-scale performance evaluation data to obtain visualized performance evaluation data, wherein the visualization includes generating a comparison chart of the predicted value and the actual value and an error distribution chart;

[0144] The embodiment of the present invention presents multi-scale performance evaluation data in a visual way and generates a variety of charts to help researchers understand the performance of the model more intuitively. Common visualization methods include drawing a comparison curve chart of the predicted value and the actual value, as well as an error distribution chart to show the error size at different time steps. For example, in an application scenario, a line chart can be used to intuitively see whether the prediction trend of the model is consistent with the actual electrophysiological signal, as well as the error fluctuations at different time points.

[0145] Step S45: Generate a detailed model performance report for the multi-scale performance evaluation data and the visualization performance evaluation data, including the overall prediction accuracy, statistical analysis of various error indicators, and the performance of the model under different conditions, so as to obtain the model performance evaluation data.

[0146] The embodiment of the present invention generates a detailed model performance report based on the aforementioned multi-scale performance evaluation data and visualization performance evaluation data. The report covers the overall prediction accuracy, statistical analysis of various error indicators (such as average error, maximum error, etc.), and evaluates the performance of the model under different experimental conditions. For example, the report will show whether the model performs better with high-frequency electrophysiological fluctuations than with low-frequency fluctuations, whether the prediction of small-amplitude signals is more accurate, etc. This report will be used to evaluate the pros and cons of the model and help further optimize and improve the model.

[0147] The present invention can quickly and accurately predict the electrophysiological activity of the heart by using a previously trained model for forward propagation. This prediction is based on the dynamic relationship between mechanical contraction and electrophysiological activity. The model uses the timing characteristics and can efficiently simulate the complex changes of cardiac activity. The advantage of this step is that new electrophysiological data can be predicted without actual measurement, which greatly improves the efficiency of diagnosis and evaluation. By comparing the predicted data with the actual data, the accuracy of the model can be intuitively evaluated. The relative error reflects the difference ratio between the predicted data and the actual value, while the MSE and RMSE measure the degree of deviation of the predicted data respectively. Through this precise error calculation, the shortcomings of the model can be found, providing a basis for subsequent improvements. The root mean square error can further amplify the impact of large errors and help identify which time periods or scenarios the errors are concentrated in. Multi-scale performance evaluation can reflect the performance of the model in more detail. Since the timing characteristics of cardiac electrophysiological activity may show different patterns in different time ranges, evaluating the prediction effect of the model in short time intervals and long time spans can help find out whether the model is adapted to different signal changes. In addition, the analysis of the prediction ability of different signal amplitudes (such as large abnormal cardiac fluctuations and small normal activities) can improve the universality of the model under different cardiac states and enhance its clinical application value. By visualizing the prediction results with the actual data, the prediction effect of the model can be more intuitively displayed. The comparison chart can intuitively show the degree of agreement between the predicted value and the actual value, while the error distribution diagram can clearly reveal the specific distribution of the error. This visualization tool not only facilitates the rapid discovery of the advantages and disadvantages of the model, but also provides a reference for the improvement of the model, especially in the analysis of model performance at different time scales. By generating a detailed model performance report, the performance of the model in the prediction of cardiac electrophysiological signals can be systematically summarized. The report includes not only the overall accuracy evaluation, but also the specific performance at different time scales and signal amplitude ranges. Through the statistical analysis of multiple error indicators (such as relative error, mean square error, root mean square error), the performance differences of the model under different experimental conditions can be fully understood. This report provides a strong basis for the subsequent optimization and improvement of the model, and provides detailed data support for the feasibility verification of the model in clinical applications.

[0148] Preferably, step S5 comprises the following steps:

[0149] Step S51: performing DFD80 extraction on the mechanical contraction curve data to obtain mechanical contraction characteristic data; performing APD80 extraction on the electrophysiological curve data to obtain electrophysiological characteristic data;

[0150] The embodiment of the present invention extracts DFD80 (delay to peak 80%) from the mechanical contraction curve data. Specifically, DFD80 refers to the time required for the myocardial contraction curve to reach 80% of the maximum contraction amplitude from the starting position. By detecting the time value at this moment in each mechanical contraction curve, the characteristic data of the mechanical contraction is extracted. Similarly, APD80 (action potential duration 80%) is extracted from the electrophysiological curve data, which indicates the time it takes for the electrophysiological signal to drop from the peak value to 80% of the amplitude. In this way, the dynamic characteristics between myocardial electrical activity and mechanical contraction can be reflected. The process of extracting these features depends on the shape of the curve within the cardiac cycle, and the specific time points are usually defined in the electrocardiogram or optical detection data.

[0151] Step S52: Calculating the Pearson correlation coefficient of the mechanical contraction characteristic data and the electrophysiological characteristic data to obtain correlation data;

[0152] The embodiment of the present invention calculates the Pearson correlation coefficient between the mechanical contraction characteristic data and the electrophysiological characteristic data to quantitatively evaluate the correlation between the two. The calculation formula of the Pearson correlation coefficient is to divide the covariance of the two variables by the product of their standard deviations to obtain a value between -1 and 1, where 1 represents a perfect positive correlation and -1 represents a perfect negative correlation. In actual operation, each pair of data points (such as DFD80 and APD80) is first matched, and then the mechanical contraction and electrophysiological characteristics of all time points are analyzed using the correlation calculation formula to obtain correlation data.

[0153] Step S53: Calculate the average correlation coefficient, standard deviation and confidence interval of the correlation data to obtain correlation statistical data;

[0154] The embodiment of the present invention further calculates the average correlation coefficient, standard deviation and confidence interval based on the correlation data. The average correlation coefficient reflects the general level of correlation in the entire sample, the standard deviation indicates the degree of dispersion of the correlation, and the confidence interval can help evaluate the reliability of the correlation. For example, in medical applications, if the average correlation coefficient of the calculated result is high and the standard deviation is low, it indicates that mechanical contraction has a high correlation with the electrophysiological signal, and a narrow confidence interval further proves the reliability of this result.

[0155] Step S54: quantitatively evaluating the degree of correlation between the label-free optical detection and the electrophysiological signal based on correlation statistical data, thereby obtaining correlation data;

[0156] The embodiment of the present invention quantitatively evaluates the degree of correlation between label-free optical detection (such as optical cardiac imaging) and electrophysiological signals based on correlation statistics. The basis for the evaluation is the mean value and confidence interval in the correlation statistics. If the correlation is strong, it can be considered that the label-free optical signal has potential in predicting electrophysiological activity. This step is usually used in cardiac research to evaluate the correlation between different detection methods and help determine the effectiveness of non-invasive detection methods.

[0157] Step S55: Optimizing the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data, so as to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

[0158] The embodiment of the present invention optimizes the parameters of the electrophysiological signal prediction model based on the model performance evaluation data (such as error data, signal-to-noise ratio) and correlation data. Model optimization includes adjusting the model's learning rate, batch size, number of training rounds and other hyperparameters to improve the model's prediction accuracy for myocardial tissue electrophysiological signals. Specifically, the goal of the optimization is to reduce the error while maintaining a high prediction accuracy, so that the electrophysiological signal prediction model that is ultimately outputted can more accurately capture the correlation between mechanical contraction and electrical activity.

[0159] The present invention can capture the key features of cardiac contraction and electrophysiological activity by extracting DFD80 and APD80, which have important physiological significance in the functional evaluation of myocardial tissue; this extraction provides basic data for subsequent correlation analysis, ensuring the accuracy and scientificity of the analysis. Pearson correlation coefficient is a commonly used statistical method for quantifying the linear relationship between two variables. By calculating the correlation between mechanical contraction and electrophysiological signals, their mutual influence relationship in cardiac function can be revealed. Understanding the relationship between the two is helpful to identify potential physiological mechanisms and provide data support for clinical decision-making. Through statistical analysis, a more comprehensive understanding of the relationship between mechanical contraction and electrophysiological signals can be obtained. The average correlation coefficient provides an overview of the overall degree of association, while the standard deviation and confidence interval reveal the consistency and credibility of the correlation. This analysis provides important information for evaluating the reliability and applicability of the model. Through quantitative evaluation, the relationship between label-free optical detection and electrophysiological signals can be clearly understood. This evaluation not only improves the ability to interpret data, but also helps to discover the effectiveness and reliability of label-free optical detection in predicting electrophysiological signals, providing an important basis for subsequent research and application. By combining model performance evaluation with feature correlation for optimization, model parameters can be adjusted in a targeted manner to improve the model's prediction accuracy. This process not only improves the performance of the model, but also enhances its applicability under different experimental conditions. The optimized model can better adapt to the characteristics of real cardiac electrophysiological signals, thereby improving the ability to monitor and analyze the electrophysiological state of myocardial tissue.

[0160] 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 therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0161] The above description 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 label-free optical detection method for myocardial tissue electrophysiology based on deep learning, characterized in that: The following steps are involved: Step S1: Acquire optical detection image data and electrophysiological signal data of myocardial tissue; Performing image preprocessing on the optical detection image data and the electrophysiological signal data to obtain optical-physiological signal mapping data, wherein the image preprocessing includes image registration, image cropping, periodic enhancement, time difference enhancement, spatial filtering, intensity normalization and data smoothing; Step S2: extracting characteristic signals based on the mechanical contraction curve and the electrophysiological curve according to the optical-physiological signal mapping data, thereby obtaining mechanical contraction curve data and electrophysiological curve data; Step S3: taking the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, constructing and training the model by training the gated recurrent unit network model, thereby obtaining an electrophysiological signal prediction model, wherein the electrophysiological signal prediction model includes two hidden layers, and the width of each hidden layer is 64; Step S4: using the electrophysiological signal prediction model to predict changes in cardiac electrophysiological activity according to the mechanical contraction curve data, thereby obtaining electrophysiological prediction data; performing prediction performance evaluation on the electrophysiological prediction data based on relative error, mean square error, and root mean square error, thereby obtaining model performance evaluation data; Step S5: Extract characteristic indicators of the mechanical contraction curve data and the electrophysiological curve data based on DFD80 and APD80, and calculate the Pearson correlation coefficient of the characteristic indicators to obtain the correlation data between the label-free optical detection and the electrophysiological signal; optimize the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

2. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting optical detection image data of myocardial tissue under experimental conditions through an optical imaging system, wherein the optical imaging system is specifically a fluorescent calcium imaging combined with a mechanical wave imaging system; Step S12: synchronously collecting electrophysiological signal data of myocardial tissue using a calcium imaging system, wherein the electrophysiological signal data includes a calcium ion concentration change signal; Step S13: performing image registration on the optical detection image data and the electrophysiological signal data based on the field of view size, position and angle, so as to obtain image consistency data; Step S14: performing image cropping processing on the image consistent data to obtain circular consistent image data, wherein the image cropping processing specifically crops the original rectangular field of view into a circular area with the center of the rectangle as the circle center and the short side of the rectangle as the diameter; Step S15: performing periodic cyclic shift and superposition on the circular consistent image data, thereby obtaining periodic enhanced data; Step S16: performing signal enhancement and optimization processing based on time difference enhancement, spatial filtering, intensity normalization and data smoothing processing on the periodic enhancement data, so as to obtain optical-physiological signal mapping data.

3. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 2, characterized in that: Step S15 includes the following steps: Step S151: performing Fourier transform on the circular consistent image data and determining the main cycle of myocardial tissue contraction, thereby obtaining periodic characteristic data; Step S152: determining the cyclic shift step length according to the periodic characteristic data, thereby obtaining shift step length data; Step S153: cyclically shifting the circular consistent image data input signal according to the shift step data to generate multiple groups of shifted image data, thereby obtaining a cyclically shifted data set; Step S154: Perform pixel-level weighted superposition on the images in the cyclic shift data set to obtain periodic enhanced data, wherein the weights are allocated in inverse proportion to the shift amount.

4. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 3, characterized in that: Step S16 includes the following steps: Step S161: setting time difference parameters for periodic enhancement data according to actual cell waveform conduction velocity, thereby obtaining time difference parameter data; Step S162: calculating the absolute value of the difference between the current value of each pixel position and the value at a past time point determined according to the time difference parameter data according to the periodic enhancement data, thereby obtaining the time difference enhancement data; Step S163: performing a spatial filtering process based on a Bartlett filter on the time difference enhancement data, thereby obtaining spatial filtering data; Step S164: performing the maximum and minimum values ​​in the time series of each pixel point on the spatial filtering data, thereby obtaining pixel intensity range data; Step S165: linearly normalize each pixel point according to the pixel intensity range data, and map the value to the interval [0, 1], thereby obtaining intensity normalized data; Step S166: performing data smoothing processing on the intensity normalized data to obtain optical-physiological signal mapping data.

5. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 4, characterized in that: Step S166 includes the following steps: Step S1661: Calculate the power spectrum density of the intensity normalized data and determine the main frequency components of the signal, thereby obtaining frequency characteristic analysis data; Step S1662: determining smoothing method parameters based on Rloess according to the frequency characteristic analysis data, thereby obtaining smoothing method parameter data, wherein the window size parameter in the smoothing method parameter data is set to 20% of the acquisition frame rate; Step S1663: smoothing each pixel time series of the intensity normalized data according to the smoothing method parameter data, and calculating the mean square error before and after smoothing, thereby obtaining smoothing effect evaluation data; Step S1664: performing edge preservation processing on the pixels with poor smoothing effect according to the smoothing effect evaluation data, thereby obtaining edge preservation data, wherein the edge preservation processing specifically includes detecting mutation points and edges in the signal and performing local adjustments; Step S1665: analyzing the signal changes between adjacent frames of the edge holding data, and performing time consistency correction to obtain time correction data; Step S1666: calculating the signal-to-noise ratio change before and after smoothing the time-corrected data, thereby obtaining signal-to-noise ratio improvement data; Step S1667: weighted fusion of the time correction data and the intensity normalization data is performed according to the signal-to-noise ratio improved data, thereby obtaining optical-physiological signal mapping data.

6. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 5, characterized in that: Step S2 includes the following steps: Step S21: extracting the local displacement information in the image and the spatial variation trend of the myocardial contraction deformation from the optical-physiological signal mapping data, thereby constructing a mechanical contraction curve; Step S22: mapping the electrical signal intensity fluctuation at each pixel point in the optical-physiological signal data, and taking time as the abscissa and the electrical signal intensity as the ordinate, thereby obtaining an electrophysiological curve reflecting the electrical activity characteristics of the myocardial cells; Step S23: dividing the mechanical contraction curve and the electrophysiological curve into cardiac contraction cycles, determining the start and end time points of each cardiac cycle, and calibrating the peak and valley values, thereby obtaining cardiac cycle segmentation data; Step S24: extracting features of the mechanical contraction curve and the electrophysiological curve in the cardiac cycle based on the contraction amplitude, the maximum contraction rate, the peak and valley values ​​of the electrical signal, and the rise time according to the cardiac cycle segmentation data, thereby obtaining feature vector data; Step S25: performing a scale difference elimination process on the feature vector data between different samples, and mapping the data values ​​to a uniform numerical range, thereby obtaining mechanical contraction curve data and electrophysiological curve data.

7. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 6, characterized in that: Step S3 includes the following steps: Step S31: using the mechanical contraction curve data as an independent variable and the electrophysiological curve data as a dependent variable, and matching them based on the time series to form a training data set; Step S32: Divide the training data set into a training set, a validation set, and a test set based on a ratio of 80:10:10; Step S33: initializing a gated recurrent unit network model according to the mechanical contraction curve data and the electrophysiological curve data, and setting hyperparameters of the gated recurrent unit network model based on a learning rate, an optimizer type, a batch size, and a number of training rounds, thereby obtaining an initial GRU network model; Step S34: input the training set into the initial GRU network model for training, calculate the predicted value through forward propagation, and then adjust the weight through back propagation to reduce the prediction error, so as to obtain the trained dynamic time series prediction model; Step S35: using the validation set to validate the dynamic time series prediction model, and adjusting the training strategy according to the error of the validation result, so as to obtain an adaptive spatiotemporal attention GRU model; Step S36: Performing a performance test based on mean square error and root mean square error on the adaptive spatiotemporal attention GRU model through the test set to obtain model performance evaluation data; Step S37: Perform integrated learning optimization processing on the adaptive spatiotemporal attention GRU model according to the model performance evaluation data to obtain an electrophysiological signal prediction model.

8. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 7, characterized in that: Step S33 includes the following steps: The gated recurrent unit network model is initialized according to the mechanical contraction curve data and the electrophysiological curve data, wherein the gated recurrent unit network model includes an input layer, two hidden layers and an output layer. The input dimension of the input layer is the time step of the mechanical contraction curve; the number of GRU units in the first hidden layer is 64, and the task is to extract primary timing features from the input mechanical contraction curve data; the number of GRU units in the second hidden layer is 64, which receives the output from the first hidden layer and performs high-level feature integration and complex pattern recognition; the output dimension of the output layer is the time step of the electrophysiological curve; the hyperparameters of the gated recurrent unit network model are set based on the learning rate, optimizer type, batch size and number of training rounds to obtain the initial GRU network model.

9. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 8, characterized in that: Step S4 includes the following steps: Step S41: inputting the new mechanical contraction curve data into the electrophysiological signal prediction model, predicting the change of cardiac electrophysiological activity through forward propagation calculation, thereby obtaining electrophysiological prediction data; Step S42: comparing the electrophysiological prediction data with the actually measured electrophysiological data, and calculating the relative error, mean square error and root mean square error, so as to obtain prediction error data; Step S43: performing prediction performance evaluation of the electrophysiological signal prediction model in different time scales and signal amplitude ranges according to the prediction error data, thereby obtaining multi-scale performance evaluation data; Step S44: Visualizing the prediction results based on the multi-scale performance evaluation data to obtain visualized performance evaluation data, wherein the visualization includes generating a comparison chart of the predicted value and the actual value and an error distribution chart; Step S45: Generate a detailed model performance report for the multi-scale performance evaluation data and the visualization performance evaluation data, including the overall prediction accuracy, statistical analysis of various error indicators, and the performance of the model under different conditions, so as to obtain the model performance evaluation data.

10. The method for label-free optical detection of myocardial tissue electrophysiology based on deep learning according to claim 9, characterized in that: Step S5 includes the following steps: Step S51: performing DFD80 extraction on the mechanical contraction curve data to obtain mechanical contraction characteristic data; performing APD80 extraction on the electrophysiological curve data to obtain electrophysiological characteristic data; Step S52: Calculating the Pearson correlation coefficient of the mechanical contraction characteristic data and the electrophysiological characteristic data to obtain correlation data; Step S53: Calculate the average correlation coefficient, standard deviation and confidence interval of the correlation data to obtain correlation statistical data; Step S54: quantitatively evaluating the degree of correlation between the label-free optical detection and the electrophysiological signal based on correlation statistical data, thereby obtaining correlation data; Step S55: Optimizing the parameters of the electrophysiological signal prediction model according to the model performance evaluation data and the correlation data, so as to achieve the prediction accuracy of the model for the electrophysiological signal of myocardial tissue.

Images