Cell electrophysiological signal recognition method and device, electronic equipment and storage medium

Abstract

This application belongs to the technical field of cell electrophysiological signal recognition, and discloses a method, device, electronic device, and storage medium for cell electrophysiological signal recognition. The method includes: acquiring the original electrophysiological signal of cardiomyocytes, mechanical data of the interaction between a mechanical probe and cardiomyocytes, and illumination parameters of an optical imaging system; identifying mechanical artifact signals associated with the mechanical data from the original electrophysiological signal; determining the instantaneous mechanical stiffness of the cardiomyocytes based on the mechanical artifact signals to identify the current pulsation stage of the cardiomyocytes; calculating the photothermal artifact signals in the original electrophysiological signal according to the pulsation stage and illumination parameters; separating the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signal to obtain the true electrophysiological signal of the cardiomyocytes; the above method improves the accuracy of electrophysiological signal recognition of cardiomyocytes.

Description

Technical Field

[0001] This application relates to the technical field of cell electrophysiological signal recognition, and more specifically, to a cell electrophysiological signal recognition method, device, electronic device, and storage medium. Background Technology

[0002] In single-cell multimodal data acquisition, multiple sensors, such as electrophysiological sensors, optical imaging systems, and mechanical measurement probes, are typically used simultaneously to comprehensively acquire cellular physiological information. However, when these sensors operate concurrently, they can interfere with each other, resulting in a large number of artifacts in the acquired raw electrophysiological signals, thus affecting the accurate assessment of the true physiological state of the cells.

[0003] Specifically, the illumination light from an optical imaging system induces a photothermal effect in cells, altering the activity of ion channels on the cell membrane and distorting the waveform of electrophysiological signals. Simultaneously, the mechanical pressure generated by the mechanical probe in contact with the cell activates mechanosensitive channels, introducing additional noise into the electrophysiological signals—namely, mechanical artifacts. These artifacts are not static but dynamically change with the cell's state (e.g., the systolic or diastolic phase of cardiomyocytes), making them difficult to distinguish from genuine cellular physiological signals.

[0004] Traditional artifact signal processing methods, such as simple time-triggered or fixed-parameter compensation strategies, often fail to accurately establish temporal correlations between multimodal data or adjust compensation parameters in real time according to the dynamic state of cells. Therefore, they struggle to effectively separate these dynamically changing artifact signals from the original electrophysiological signals, thus failing to reconstruct true cellular electrophysiological information. This severely limits our in-depth understanding of cellular physiological mechanisms and the diagnosis of related diseases.

[0005] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, electronic device, and storage medium for identifying cell electrophysiological signals. By identifying mechanical artifact signals from the original electrophysiological signals, the instantaneous mechanical stiffness of cardiomyocytes is determined to identify the pulsation phase. Then, photothermal artifact signals are calculated based on the pulsation phase and illumination parameters to separate the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals, thereby obtaining the true electrophysiological signals of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that are difficult to effectively separate artifact signals generated by mutual interference from multiple sensors, resulting in the inability to accurately obtain true cell physiological information. By dynamically identifying the pulsation phase of the cell and adjusting the calculation and separation strategy of the artifact signals accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal identification of cardiomyocytes.

[0007] In a first aspect, this application provides a method for recognizing cellular electrophysiological signals, used to identify electrophysiological signals of cardiomyocytes, comprising the following steps:

[0008] Acquire raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between mechanical probes and cardiomyocytes, and illumination parameters of the optical imaging system;

[0009] Mechanical artifact signals associated with the mechanical data are identified from the raw electrophysiological signals;

[0010] Based on the mechanical artifact signal, the instantaneous mechanical stiffness of the cardiomyocyte is determined to identify the current beating stage of the cardiomyocyte;

[0011] Based on the pulsation phase and the illumination parameters, the photothermal artifact signal in the original electrophysiological signal is calculated;

[0012] The mechanical artifact signal and the photothermal artifact signal are separated from the original electrophysiological signal to obtain the real electrophysiological signal of the myocardial cells.

[0013] The cell electrophysiological signal recognition method provided in this application can identify the electrophysiological signals of cardiomyocytes. By identifying the mechanical artifact signals from the original electrophysiological signals, the instantaneous mechanical stiffness of the cardiomyocytes is determined to identify the pulsation phase. Then, the photothermal artifact signals are calculated based on the pulsation phase and illumination parameters to separate the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals, thereby obtaining the true electrophysiological signals of the cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that it is difficult to effectively separate artifact signals generated by the mutual interference of multiple sensors, resulting in the inaccurate acquisition of true cell physiological information. By dynamically identifying the pulsation phase of the cell and adjusting the calculation and separation strategy of the artifact signals accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal recognition of cardiomyocytes.

[0014] Optionally, mechanical artifact signals associated with the mechanical data are identified from the raw electrophysiological signals, including:

[0015] The raw electrophysiological signals are preprocessed to obtain preprocessed raw electrophysiological signals;

[0016] The mechanical data is time-aligned with the preprocessed raw electrophysiological signal to determine the signal fluctuations generated when the mechanical data is applied in the preprocessed raw electrophysiological signal, thereby identifying mechanical artifact signals.

[0017] Optionally, based on the mechanical artifact signal, the instantaneous mechanical stiffness of the cardiomyocyte is determined to identify the current beating stage of the cardiomyocyte, including:

[0018] Calculate the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal;

[0019] The instantaneous mechanical stiffness of the cardiomyocytes is determined based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope.

[0020] Based on the instantaneous mechanical stiffness, the current pulsation stage of the myocardial cell is determined.

[0021] The cell electrophysiological signal recognition method provided in this application can identify the electrophysiological signals of cardiomyocytes. By analyzing the characteristics of mechanical artifact signals, the instantaneous mechanical stiffness of cardiomyocytes can be dynamically evaluated, thereby accurately identifying the pulsation stage and providing key cell state information for subsequent photothermal artifact signal calculation.

[0022] Optionally, the instantaneous mechanical stiffness of the cardiomyocyte is calculated based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope, including:

[0023] Pre-construct a mechanical stiffness level calculation model;

[0024] The instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope are input into the mechanical stiffness level calculation model to calculate the instantaneous mechanical stiffness of the myocardial cells.

[0025] Optionally, determining the current beating stage of the cardiomyocyte based on the instantaneous mechanical stiffness includes:

[0026] Determine whether the instantaneous mechanical stiffness is greater than or equal to a preset stiffness threshold.

[0027] If so, the myocardial cells are determined to be in a high-stiffness state, and the current pulsation phase of the myocardial cells is identified as the systolic phase.

[0028] If not, then the myocardial cells are determined to be in a low-stiffness state, and the current pulsation phase of the myocardial cells is identified as diastole.

[0029] Optionally, the photothermal artifact signal in the original electrophysiological signal is calculated based on the pulsation phase and the illumination parameters, including:

[0030] Based on the pulsation phase, the corresponding lighting intensity compensation coefficient is determined;

[0031] The photothermal artifact signal in the original electrophysiological signal is calculated based on the lighting parameters and the lighting intensity compensation coefficient.

[0032] The cell electrophysiological signal recognition method provided in this application can recognize the electrophysiological signals of cardiomyocytes. By dynamically adjusting the illumination intensity compensation coefficient through the pulsation phase of cardiomyocytes, the photothermal artifact signal can be calculated more accurately, overcoming the limitations of traditional fixed parameter compensation.

[0033] Secondly, this application provides a cell electrophysiological signal recognition device for recognizing electrophysiological signals of cardiomyocytes, including:

[0034] The acquisition module is used to acquire raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between the mechanical probe and cardiomyocytes, and illumination parameters of the optical imaging system;

[0035] The identification module is used to identify mechanical artifact signals associated with the mechanical data from the original electrophysiological signals.

[0036] The determination module is used to determine the instantaneous mechanical stiffness of the cardiomyocyte based on the mechanical artifact signal, so as to identify the current beating stage of the cardiomyocyte;

[0037] The calculation module is used to calculate the photothermal artifact signal in the original electrophysiological signal based on the pulsation phase and the illumination parameters.

[0038] The separation module is used to separate the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal to obtain the real electrophysiological signal of the myocardial cells.

[0039] This cell electrophysiological signal recognition device identifies the instantaneous mechanical stiffness of cardiomyocytes by recognizing mechanical artifact signals from the original electrophysiological signals to identify the pulsation phase. It then calculates photothermal artifact signals based on the pulsation phase and illumination parameters to separate the mechanical and photothermal artifact signals from the original electrophysiological signals, thus obtaining the true electrophysiological signals of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods where it is difficult to effectively separate artifact signals generated by interference from multiple sensors, leading to inaccurate acquisition of true cell physiological information. By dynamically recognizing the pulsation phase of cells and adjusting the artifact signal calculation and separation strategy accordingly, it can more accurately restore the true cell electrophysiological information, improving the accuracy of electrophysiological signal recognition for cardiomyocytes.

[0040] Thirdly, this application provides an electronic device including a processor and a memory, the memory storing a computer program executable by the processor, wherein when the processor executes the computer program, it performs the steps of the cell electrophysiological signal recognition method described above.

[0041] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the cell electrophysiological signal recognition method described above.

[0042] Beneficial effects: The cell electrophysiological signal recognition method, device, electronic device, and storage medium provided in this application determine the instantaneous mechanical stiffness of cardiomyocytes by identifying mechanical artifact signals obtained from the original electrophysiological signals to identify the pulsation phase. Then, based on the pulsation phase and illumination parameters, photothermal artifact signals are calculated to separate mechanical and photothermal artifact signals from the original electrophysiological signals, thereby obtaining the true electrophysiological signals of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that it is difficult to effectively separate artifact signals generated by mutual interference of multiple sensors, resulting in the inaccurate acquisition of true cell physiological information. By dynamically identifying the pulsation phase of cells and adjusting the calculation and separation strategy of artifact signals accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal recognition of cardiomyocytes. Attached Figure Description

[0043] Figure 1 A flowchart of a cell electrophysiological signal recognition method provided in an embodiment of this application.

[0044] Figure 2 This is a schematic diagram of the structure of the cell electrophysiological signal recognition device provided in the embodiments of this application.

[0045] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0046] Labeling Explanation: 1. Acquisition Module; 2. Identification Module; 3. Determination Module; 4. Calculation Module; 5. Separation Module; 301. Processor; 302. Memory; 303. Communication Bus. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0048] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0049] Please refer to Figure 1 , Figure 1 This application provides a method for recognizing cellular electrophysiological signals in some embodiments, used to identify electrophysiological signals of cardiomyocytes, including:

[0050] Step S1: Obtain the raw electrophysiological signals of cardiomyocytes, the mechanical data of the interaction between the mechanical probe and cardiomyocytes, and the illumination parameters of the optical imaging system;

[0051] Step S2: Identify the mechanical artifact signals associated with the mechanical data from the raw electrophysiological signals;

[0052] Step S3: Based on the mechanical artifact signal, determine the instantaneous mechanical stiffness of the cardiomyocytes to identify the current beating stage of the cardiomyocytes;

[0053] Step S4: Calculate the photothermal artifact signal in the original electrophysiological signal based on the pulsation phase and illumination parameters;

[0054] Step S5: Separate the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal to obtain the real electrophysiological signal of myocardial cells.

[0055] This cell electrophysiological signal recognition method identifies the instantaneous mechanical stiffness of cardiomyocytes by recognizing mechanical artifact signals from the original electrophysiological signals to identify the pulsation phase. Then, it calculates photothermal artifact signals based on the pulsation phase and illumination parameters to separate the mechanical and photothermal artifact signals from the original electrophysiological signals, thereby obtaining the true electrophysiological signals of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that are difficult to effectively separate artifact signals generated by interference from multiple sensors, resulting in the inaccurate acquisition of true cell physiological information. By dynamically recognizing the pulsation phase of cells and adjusting the calculation and separation strategy of artifact signals accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal recognition of cardiomyocytes.

[0056] Specifically, in step S1, the raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between the mechanical probe and cardiomyocytes, and illumination parameters of the optical imaging system are acquired. The raw electrophysiological signals refer to the unprocessed electrical signals directly collected from cardiomyocytes by the electrophysiological sensor, which include the actual electrical activity of the cardiomyocytes and various interference signals (i.e., artifact signals). The mechanical data refer to the mechanical response data measured during the interaction between the mechanical probe and cardiomyocytes, such as pressure and deformation; these data reflect the mechanical state of the cardiomyocytes. The illumination parameters refer to the lighting conditions used by the optical imaging system when imaging cardiomyocytes, such as light intensity, wavelength, and duration; these parameters are closely related to the generation of photothermal artifacts.

[0057] The raw electrophysiological signals can be directly acquired from cardiomyocytes using microelectrode arrays or patch-clamp techniques. Mechanical data can be measured in real-time using mechanical probes such as atomic force microscopy (AFM) or microforce sensors in contact with cardiomyocytes. The illumination parameters of the optical imaging system can be directly read from the system's control software.

[0058] Specifically, in step S2, mechanical artifact signals associated with the mechanical data are identified from the raw electrophysiological signals, including:

[0059] The raw electrophysiological signals are preprocessed to obtain the preprocessed raw electrophysiological signals;

[0060] The mechanical data was time-aligned with the preprocessed raw electrophysiological signal to identify signal fluctuations generated when the mechanical data was applied and to identify mechanical artifact signals.

[0061] In step S2, the raw electrophysiological signal is preprocessed to eliminate or reduce noise, baseline drift, or other non-physiological interferences, thereby improving the signal-to-noise ratio and the accuracy of subsequent analysis. For example, preprocessing may include, but is not limited to: using digital filtering techniques such as low-pass, high-pass, or band-pass filtering to remove noise within a specific frequency range; performing baseline correction to eliminate slow signal drift; or applying advanced signal processing methods such as wavelet denoising and empirical mode decomposition to separate noise components. Through preprocessing, a cleaner and more easily analyzed preprocessed raw electrophysiological signal can be obtained.

[0062] Timing the mechanical data with the preprocessed raw electrophysiological signals ensures an accurate temporal correspondence between the mechanical data of the mechanical probe interacting with cardiomyocytes and the electrophysiological signals of the cardiomyocytes. This allows for the identification of instantaneous signal fluctuations in the raw electrophysiological signals caused by the contact between the mechanical probe and cardiomyocytes, thus revealing the mechanical artifact signals within the raw electrophysiological signals. Since the mechanical artifact signals are caused by the interaction between the mechanical probe and cardiomyocytes, their manifestation in the electrophysiological signals is synchronous with the changes in the mechanical data. Therefore, precise temporal alignment can effectively correlate the mechanical data with the corresponding mechanical artifact signals in the electrophysiological signals, identifying the signal fluctuations generated each time mechanical data is applied as mechanical artifact signals. Temporal alignment can be achieved in various ways. For example, if the mechanical data and electrophysiological signals are acquired through a synchronous acquisition system, they are inherently time-synchronous; if the acquisition systems are not synchronized, post-processing alignment can be performed using signal processing algorithms (such as cross-correlation analysis, feature point matching, etc.).

[0063] Specifically, in step S3, based on the mechanical artifact signal, the instantaneous mechanical stiffness of the cardiomyocytes is determined to identify the current beating stage of the cardiomyocytes, including:

[0064] Calculate the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal;

[0065] The instantaneous mechanical stiffness of cardiomyocytes is determined based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope.

[0066] Based on instantaneous mechanical stiffness, the current beating stage of the myocardial cells is determined.

[0067] In step S3, the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal are calculated. The instantaneous peak amplitude of the mechanical artifact signal refers to the maximum amplitude value reached by the mechanical artifact signal at a specific time point, reflecting the instantaneous deformation or stress intensity of cardiomyocytes under the action of a mechanical probe. The average frequency refers to the average oscillation frequency of the mechanical artifact signal within a preset time window, characterizing the rhythmicity of cardiomyocyte beating or the dynamic characteristics of the mechanical response. The rate of change of the signal envelope refers to the rate at which the envelope of the mechanical artifact signal changes over time, reflecting the speed of the mechanical response of cardiomyocytes or the dynamic trend of stiffness changes. The calculation of these parameters aims to extract quantitative indicators directly related to the mechanical properties of cardiomyocytes from the complex mechanical artifact signal.

[0068] In an optional embodiment, in step S3, determining the instantaneous mechanical stiffness of the cardiomyocytes based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope includes:

[0069] A table of correspondences between mechanical stiffness levels is pre-constructed;

[0070] The instantaneous mechanical stiffness of myocardial cells is determined from the mechanical stiffness level correspondence table based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope.

[0071] In step S3, by pre-constructing a mechanical stiffness level correspondence table, the complex, multi-dimensional signal characteristics (instantaneous peak amplitude, average frequency, and signal envelope rate of change) are transformed into directly queryable mechanical stiffness levels. This allows the instantaneous mechanical stiffness of cardiomyocytes to be quickly and accurately determined by directly looking up the table after obtaining the instantaneous peak amplitude, average frequency, and signal envelope rate of change of the cardiomyocytes. Instantaneous mechanical stiffness refers to the ability of cardiomyocytes to resist deformation at a specific moment, and its magnitude reflects the contractile state of the cardiomyocytes.

[0072] The mechanical stiffness level correspondence table is a pre-established data structure that associates characteristic parameters such as the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of mechanical artifact signals exhibited by cardiomyocytes under different states with the corresponding mechanical stiffness levels. This correspondence table can be constructed and calibrated through experimental measurements, numerical simulations, or expert experience. For example, electrophysiological signals and mechanical data can be collected from cardiomyocyte samples with different stiffness levels, and the corresponding instantaneous peak amplitude, average frequency, and rate of change of the signal envelope can be analyzed to establish a mapping relationship between these characteristics and mechanical stiffness levels. The mechanical stiffness levels can be divided into multiple discrete levels, such as "low stiffness" and "high stiffness," with more refined numerical ranges set.

[0073] When the three values ​​of the input variables (i.e., instantaneous peak amplitude, average frequency, and signal envelope rate of change) do not have exactly the same value in the numerical correspondence table, the value with the smallest difference from the input variables (smallest individual difference or smallest average difference) can be selected from the mechanical stiffness level correspondence table to determine the corresponding mechanical stiffness level.

[0074] In another optional embodiment, in step S3, the instantaneous mechanical stiffness of the cardiomyocytes is determined based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope, including:

[0075] Pre-construct a mechanical stiffness level calculation model;

[0076] The instantaneous peak amplitude, average frequency, and rate of change of the signal envelope are input into the mechanical stiffness level calculation model to calculate the instantaneous mechanical stiffness of the myocardial cells.

[0077] In step S3, machine learning algorithms (such as Support Vector Machines (SVM), neural networks, and random forests) can be used in advance to collect and analyze data from a large number of cardiomyocyte samples with known mechanical stiffness levels. A mechanical stiffness level calculation model can then be established. This model can learn and capture the deep, nonlinear relationship between instantaneous peak amplitude, average frequency, and the rate of change of the signal envelope and instantaneous mechanical stiffness, enabling dynamic and adaptive calculation of instantaneous mechanical stiffness based on multidimensional features. This model-based calculation method makes the assessment of instantaneous mechanical stiffness of cardiomyocytes more refined and accurate. The machine learning algorithm used is an existing algorithm and will not be detailed here.

[0078] Specifically, in step S3, based on the instantaneous mechanical stiffness, the current beating stage of the myocardial cell is determined, including:

[0079] Determine whether the instantaneous mechanical stiffness is greater than or equal to a preset stiffness threshold.

[0080] If so, it is determined that the myocardial cells are in a high-stiffness state, and the current pulsation phase of the myocardial cells is identified as the systolic phase;

[0081] If not, then the myocardial cells are determined to be in a low-stiffness state, and the current pulsation phase of the myocardial cells is identified as diastole.

[0082] In step S3, by comparing the instantaneous mechanical stiffness of cardiomyocytes with a preset stiffness threshold, the inherent mechanical property differences exhibited by cardiomyocytes in different beating phases (systole and diastole) can be effectively utilized. During cardiomyocyte contraction, the cytoskeleton and actin-myosin crosslinking are enhanced, resulting in a significant increase in overall cell stiffness; while during diastole, these structures relax, and cell stiffness decreases accordingly. By setting an appropriate stiffness threshold, this stiffness change can be accurately captured, thereby dividing the beating cycle of cardiomyocytes into systole and diastole. That is, when the instantaneous mechanical stiffness is greater than or equal to the preset stiffness threshold, the cardiomyocyte is determined to be in a high-stiffness state, and the current beating phase of the cardiomyocyte is identified as the systole phase; when the instantaneous mechanical stiffness is less than the preset stiffness threshold, the cardiomyocyte is determined to be in a low-stiffness state, and the current beating phase of the cardiomyocyte is identified as the diastole phase.

[0083] The preset stiffness threshold can be understood as the critical stiffness value that distinguishes between the systolic and diastolic phases of myocardial cells. This threshold can be pre-set and calibrated based on a large amount of experimental data, physiological models, or expert experience to ensure that it accurately reflects the mechanical properties of myocardial cells at different pulsation stages. For example, this threshold can be determined by measuring the stiffness of healthy myocardial cells in systolic and diastolic states and taking the average value or a specific percentile.

[0084] Specifically, in step S4, the photothermal artifact signal in the original electrophysiological signal is calculated based on the pulsation phase and illumination parameters, including:

[0085] Based on the pulsation phase, determine the corresponding lighting intensity compensation coefficient;

[0086] Based on the lighting parameters and the lighting intensity compensation coefficient, the photothermal artifact signal in the original electrophysiological signal is calculated.

[0087] In step S4, by introducing an illumination intensity compensation coefficient determined based on the pulsation phase, the differences in the response of cardiomyocytes to optical illumination under different physiological states can be characterized more precisely. During systole and diastole, the internal structure, density, and light absorption and scattering characteristics of cardiomyocytes may change, directly affecting the generation of the photothermal effect. By setting or calculating corresponding illumination intensity compensation coefficients for different pulsation phases, the dynamic influence of these physiological states can be effectively incorporated into the calculation of the photothermal artifact signal. Thus, the combined use of illumination parameters and illumination intensity compensation coefficients makes the calculation of the photothermal artifact signal no longer static. The photothermal artifact signal is the non-physiological fluctuation in the electrophysiological signal caused by the photothermal effect of cardiomyocytes induced by the illumination light of the optical imaging system during the acquisition of the original electrophysiological signal of cardiomyocytes. The photothermal artifact signal does not change with time and is only related to the illumination intensity (the source signal that generates the photothermal artifact signal) and the pulsation phase of the cardiomyocytes (the degree of absorption of the source signal).

[0088] The illumination intensity compensation factor is a correction factor used to correct or adjust the calculation of photothermal artifact signals. Its purpose is to more accurately reflect the actual response of cardiomyocytes to optical illumination (i.e., the degree of light intensity absorption) during a specific pulsation phase. This compensation factor can be obtained in advance through experimental calibration, numerical simulation, or machine learning and stored in a lookup table or model. For example, different illumination intensity compensation factors can be determined for the systolic and diastolic phases of cardiomyocytes. When the pulsation phase is identified as the systolic phase, the illumination intensity compensation factor corresponding to the systolic phase will be used, with each increase of 1 milliwatt per square millimeter of illumination intensity causing a potential drift of 10 microvolts; when the pulsation phase is identified as the diastolic phase, the illumination intensity compensation factor corresponding to the diastolic phase will be used, with each increase of 1 milliwatt per square millimeter of illumination intensity causing a potential drift of 5 microvolts.

[0089] Based on the current light intensity in the lighting parameters and the lighting intensity compensation coefficient obtained above, the potential value to be compensated is calculated, and the photothermal artifact signal in the original electrophysiological signal is obtained.

[0090] Alternatively, in an optional embodiment, a photothermal artifact model can be pre-built using machine learning algorithms (such as existing algorithms like Support Vector Machines (SVM), neural networks, and random forests). This model takes different pulsation phases and illumination parameters as input data and outputs corresponding photothermal artifact signals obtained through extensive experimental calibration (e.g., by turning the optical imaging system on and off to generate different light intensities to obtain the original electrophysiological signals and generate corresponding signal fluctuations, thereby determining the corresponding photothermal artifact signals). It can predict the characteristics of photothermal artifacts based on different pulsation phases and illumination parameters, while simultaneously determining the corresponding illumination intensity compensation coefficient during the calculation process. During systole and diastole, the response of myocardial cells to the photothermal effect may differ; therefore, the calculation method for photothermal artifacts needs to be adjusted according to the current pulsation phase. Simultaneously, the light intensity in the illumination parameters directly affects the intensity of the photothermal artifacts. By inputting the current pulsation phase and the light intensity of the illumination parameters into the pre-built photothermal artifact model, the corresponding photothermal artifact signal can be calculated.

[0091] Specifically, in step S5, signal processing techniques, such as digital filtering, adaptive noise cancellation, or blind source separation algorithms, are used to subtract the identified mechanical artifact signals and the calculated photothermal artifact signals from the original electrophysiological signal, thereby obtaining a pure, real electrophysiological signal. This real electrophysiological signal can be used for subsequent high-precision studies such as pulsation waveform analysis and action potential parameter extraction.

[0092] As can be seen from the above, this method for identifying cell electrophysiological signals acquires the original electrophysiological signals of cardiomyocytes, the mechanical data of the interaction between the mechanical probe and the cardiomyocytes, and the illumination parameters of the optical imaging system. It then identifies the mechanical artifact signals associated with the mechanical data from the original electrophysiological signals. Based on these mechanical artifact signals, it determines the instantaneous mechanical stiffness of the cardiomyocytes to identify the current pulsation stage of the cardiomyocytes. According to the pulsation stage and illumination parameters, it calculates the photothermal artifact signals in the original electrophysiological signals. Finally, it separates the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals to obtain the true electrophysiological signals of the cardiomyocytes. Thus, by identifying the mechanical artifact signals from the original electrophysiological signals... The mechanical artifact signal is obtained to determine the instantaneous mechanical stiffness of cardiomyocytes to identify the pulsation phase. Then, based on the pulsation phase and illumination parameters, the photothermal artifact signal is calculated to separate the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal, thereby obtaining the true electrophysiological signal of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that are difficult to effectively separate artifact signals generated by the mutual interference of multiple sensors, which leads to the inaccurate acquisition of true cell physiological information. By dynamically identifying the pulsation phase of the cell and adjusting the calculation and separation strategy of the artifact signal accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal identification of cardiomyocytes.

[0093] refer to Figure 2 This application provides a cell electrophysiological signal recognition device for recognizing electrophysiological signals of cardiomyocytes, comprising:

[0094] Acquisition module 1 is used to acquire raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between mechanical probes and cardiomyocytes, and illumination parameters of the optical imaging system;

[0095] The identification module 2 is used to identify mechanical artifact signals associated with mechanical data from the raw electrophysiological signals;

[0096] Module 3 is used to determine the instantaneous mechanical stiffness of cardiomyocytes based on mechanical artifact signals, in order to identify the current beating stage of the cardiomyocytes;

[0097] Calculation module 4 is used to calculate the photothermal artifact signal in the original electrophysiological signal based on the pulsation phase and illumination parameters;

[0098] Separation module 5 is used to separate mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals to obtain the true electrophysiological signals of myocardial cells.

[0099] This cell electrophysiological signal recognition device identifies the instantaneous mechanical stiffness of cardiomyocytes by recognizing mechanical artifact signals from the original electrophysiological signals to identify the pulsation phase. It then calculates photothermal artifact signals based on the pulsation phase and illumination parameters to separate the mechanical and photothermal artifact signals from the original electrophysiological signals, thus obtaining the true electrophysiological signals of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods where it is difficult to effectively separate artifact signals generated by interference from multiple sensors, leading to inaccurate acquisition of true cell physiological information. By dynamically recognizing the pulsation phase of cells and adjusting the artifact signal calculation and separation strategy accordingly, it can more accurately restore the true cell electrophysiological information, improving the accuracy of electrophysiological signal recognition for cardiomyocytes.

[0100] Specifically, during execution, module 1 acquires the raw electrophysiological signals of cardiomyocytes, the mechanical data of the interaction between the mechanical probe and the cardiomyocytes, and the illumination parameters of the optical imaging system. The raw electrophysiological signals refer to the unprocessed electrical signals directly collected from the cardiomyocytes by the electrophysiological sensors, containing the actual electrical activity of the cardiomyocytes as well as various interference signals (i.e., artifact signals). The mechanical data refers to the mechanical response data measured during the interaction between the mechanical probe and the cardiomyocytes, such as pressure and deformation; these data reflect the mechanical state of the cardiomyocytes. The illumination parameters refer to the lighting conditions used by the optical imaging system when imaging the cardiomyocytes, such as light intensity, wavelength, and duration; these parameters are closely related to the generation of photothermal artifacts.

[0101] The raw electrophysiological signals can be directly acquired from cardiomyocytes using microelectrode arrays or patch-clamp techniques. Mechanical data can be measured in real-time using mechanical probes such as atomic force microscopy (AFM) or microforce sensors in contact with cardiomyocytes. The illumination parameters of the optical imaging system can be directly read from the system's control software.

[0102] Specifically, when the identification module 2 identifies the mechanical artifact signals associated with the mechanical data from the raw electrophysiological signals, it performs the following:

[0103] The raw electrophysiological signals are preprocessed to obtain the preprocessed raw electrophysiological signals;

[0104] The mechanical data was time-aligned with the preprocessed raw electrophysiological signal to identify signal fluctuations generated when the mechanical data was applied and to identify mechanical artifact signals.

[0105] The identification module 2 preprocesses the raw electrophysiological signal to eliminate or reduce noise, baseline drift, or other non-physiological interference, thereby improving the signal-to-noise ratio and the accuracy of subsequent analysis. For example, preprocessing may include, but is not limited to: using digital filtering techniques such as low-pass, high-pass, or band-pass filtering to remove noise within a specific frequency range; performing baseline correction to eliminate slow signal drift; or applying advanced signal processing methods such as wavelet denoising and empirical mode decomposition to separate noise components. Through preprocessing, a cleaner and more easily analyzed preprocessed raw electrophysiological signal can be obtained.

[0106] Timing the mechanical data with the preprocessed raw electrophysiological signals ensures an accurate temporal correspondence between the mechanical data of the mechanical probe interacting with cardiomyocytes and the electrophysiological signals of the cardiomyocytes. This allows for the identification of instantaneous signal fluctuations in the raw electrophysiological signals caused by the contact between the mechanical probe and cardiomyocytes, thus revealing the mechanical artifact signals within the raw electrophysiological signals. Since the mechanical artifact signals are caused by the interaction between the mechanical probe and cardiomyocytes, their manifestation in the electrophysiological signals is synchronous with the changes in the mechanical data. Therefore, precise temporal alignment can effectively correlate the mechanical data with the corresponding mechanical artifact signals in the electrophysiological signals, identifying the signal fluctuations generated each time mechanical data is applied as mechanical artifact signals. Temporal alignment can be achieved in various ways. For example, if the mechanical data and electrophysiological signals are acquired through a synchronous acquisition system, they are inherently time-synchronous; if the acquisition systems are not synchronized, post-processing alignment can be performed using signal processing algorithms (such as cross-correlation analysis, feature point matching, etc.).

[0107] Specifically, when determining the instantaneous mechanical stiffness of cardiomyocytes based on mechanical artifact signals to identify the current beating stage of the cardiomyocytes, module 3 performs the following:

[0108] Calculate the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal;

[0109] The instantaneous mechanical stiffness of cardiomyocytes is determined based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope.

[0110] Based on instantaneous mechanical stiffness, the current beating stage of the myocardial cells is determined.

[0111] During execution, module 3 calculates the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal. The instantaneous peak amplitude refers to the maximum amplitude value reached by the mechanical artifact signal at a specific time point, reflecting the instantaneous deformation or stress intensity of cardiomyocytes under the action of a mechanical probe. The average frequency is the average oscillation frequency of the mechanical artifact signal within a preset time window, characterizing the rhythmicity of cardiomyocyte beating or the dynamic characteristics of the mechanical response. The rate of change of the signal envelope refers to the rate at which the envelope of the mechanical artifact signal changes over time, reflecting the speed of the mechanical response of cardiomyocytes or the dynamic trend of stiffness changes. The calculation of these parameters aims to extract quantitative indicators directly related to the mechanical properties of cardiomyocytes from the complex mechanical artifact signal.

[0112] In an optional embodiment, when determining the instantaneous mechanical stiffness of the cardiomyocytes based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope, the determining module 3 performs the following:

[0113] A table of correspondences between mechanical stiffness levels is pre-constructed;

[0114] The instantaneous mechanical stiffness of myocardial cells is determined from the mechanical stiffness level correspondence table based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope.

[0115] In step S3, by pre-constructing a mechanical stiffness level correspondence table, the complex, multi-dimensional signal characteristics (instantaneous peak amplitude, average frequency, and signal envelope rate of change) are transformed into directly queryable mechanical stiffness levels. This allows the instantaneous mechanical stiffness of cardiomyocytes to be quickly and accurately determined by directly looking up the table after obtaining the instantaneous peak amplitude, average frequency, and signal envelope rate of change of the cardiomyocytes. Instantaneous mechanical stiffness refers to the ability of cardiomyocytes to resist deformation at a specific moment, and its magnitude reflects the contractile state of the cardiomyocytes.

[0116] The mechanical stiffness level correspondence table is a pre-established data structure that associates characteristic parameters such as the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of mechanical artifact signals exhibited by cardiomyocytes under different states with the corresponding mechanical stiffness levels. This correspondence table can be constructed and calibrated through experimental measurements, numerical simulations, or expert experience. For example, electrophysiological signals and mechanical data can be collected from cardiomyocyte samples with different stiffness levels, and the corresponding instantaneous peak amplitude, average frequency, and rate of change of the signal envelope can be analyzed to establish a mapping relationship between these characteristics and mechanical stiffness levels. The mechanical stiffness levels can be divided into multiple discrete levels, such as "low stiffness" and "high stiffness," with more refined numerical ranges set.

[0117] When the three values ​​of the input variables (i.e., instantaneous peak amplitude, average frequency, and signal envelope rate of change) do not have exactly the same value in the numerical correspondence table, the value with the smallest difference from the input variables (smallest individual difference or smallest average difference) can be selected from the mechanical stiffness level correspondence table to determine the corresponding mechanical stiffness level.

[0118] In another alternative embodiment, when determining the instantaneous mechanical stiffness of the cardiomyocytes based on the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope, the determining module 3 performs the following:

[0119] Pre-construct a mechanical stiffness level calculation model;

[0120] The instantaneous peak amplitude, average frequency, and rate of change of the signal envelope are input into the mechanical stiffness level calculation model to calculate the instantaneous mechanical stiffness of the myocardial cells.

[0121] During the execution of module 3, machine learning algorithms (such as Support Vector Machines (SVM), neural networks, and random forests) can be pre-utilized to establish a mechanical stiffness level calculation model by collecting and analyzing data from a large number of cardiomyocyte samples with known mechanical stiffness levels. This model can learn and capture the deep, nonlinear relationship between instantaneous peak amplitude, average frequency, and the rate of change of the signal envelope and instantaneous mechanical stiffness, enabling dynamic and adaptive calculation of instantaneous mechanical stiffness based on multidimensional features. This model-based calculation method makes the assessment of instantaneous mechanical stiffness of cardiomyocytes more refined and accurate. The machine learning algorithm used is an existing algorithm and will not be detailed here.

[0122] Specifically, when module 3 determines the current beating stage of the myocardial cells based on instantaneous mechanical stiffness, it executes the following:

[0123] Determine whether the instantaneous mechanical stiffness is greater than or equal to a preset stiffness threshold.

[0124] If so, it is determined that the myocardial cells are in a high-stiffness state, and the current pulsation phase of the myocardial cells is identified as the systolic phase;

[0125] If not, then the myocardial cells are determined to be in a low-stiffness state, and the current pulsation phase of the myocardial cells is identified as diastole.

[0126] When module 3 is executed, it effectively utilizes the inherent mechanical property differences exhibited by cardiomyocytes during different pulsation phases (systole and diastole) by comparing the instantaneous mechanical stiffness of cardiomyocytes with a preset stiffness threshold. During cardiomyocyte contraction, the cytoskeleton and actin-myosin cross-linking are enhanced, leading to a significant increase in overall cell stiffness; while during diastole, these structures relax, and cell stiffness decreases accordingly. By setting an appropriate stiffness threshold, this stiffness change can be accurately captured, thereby dividing the pulsation cycle of cardiomyocytes into systole and diastole. That is, when the instantaneous mechanical stiffness is greater than or equal to the preset stiffness threshold, the cardiomyocyte is determined to be in a high-stiffness state, and the current pulsation phase of the cardiomyocyte is identified as systole; when the instantaneous mechanical stiffness is less than the preset stiffness threshold, the cardiomyocyte is determined to be in a low-stiffness state, and the current pulsation phase of the cardiomyocyte is identified as diastole.

[0127] The preset stiffness threshold can be understood as the critical stiffness value that distinguishes between the systolic and diastolic phases of myocardial cells. This threshold can be pre-set and calibrated based on a large amount of experimental data, physiological models, or expert experience to ensure that it accurately reflects the mechanical properties of myocardial cells at different pulsation stages. For example, this threshold can be determined by measuring the stiffness of healthy myocardial cells in systolic and diastolic states and taking the average value or a specific percentile.

[0128] Specifically, when calculation module 4 calculates the photothermal artifact signal in the original electrophysiological signal based on the pulsation phase and illumination parameters, it performs the following:

[0129] Based on the pulsation phase, determine the corresponding lighting intensity compensation coefficient;

[0130] Based on the lighting parameters and the lighting intensity compensation coefficient, the photothermal artifact signal in the original electrophysiological signal is calculated.

[0131] During execution, calculation module 4, by introducing an illumination intensity compensation coefficient determined based on the pulsation phase, can more precisely characterize the differences in the response of cardiomyocytes to optical illumination under different physiological states. During contraction and relaxation, the internal structure, density, and light absorption and scattering characteristics of cardiomyocytes may change, directly affecting the generation of photothermal effects. By setting or calculating corresponding illumination intensity compensation coefficients for different pulsation phases, the dynamic influence of these physiological states can be effectively incorporated into the calculation of photothermal artifact signals. Therefore, the combined use of illumination parameters and illumination intensity compensation coefficients makes the calculation of photothermal artifact signals no longer static. The photothermal artifact signal is a non-physiological fluctuation in the electrophysiological signal caused by the photothermal effect of cardiomyocytes induced by the illumination light of the optical imaging system during the acquisition of the original electrophysiological signal of cardiomyocytes. The photothermal artifact signal does not change with time and is only related to the illumination intensity (the source signal that generates the photothermal artifact signal) and the pulsation phase of the cardiomyocytes (the degree of absorption of the source signal).

[0132] The illumination intensity compensation factor is a correction factor used to correct or adjust the calculation of photothermal artifact signals. Its purpose is to more accurately reflect the actual response of cardiomyocytes to optical illumination (i.e., the degree of light intensity absorption) during a specific pulsation phase. This compensation factor can be obtained in advance through experimental calibration, numerical simulation, or machine learning and stored in a lookup table or model. For example, different illumination intensity compensation factors can be determined for the systolic and diastolic phases of cardiomyocytes. When the pulsation phase is identified as the systolic phase, the illumination intensity compensation factor corresponding to the systolic phase will be used, with each increase of 1 milliwatt per square millimeter of illumination intensity causing a potential drift of 10 microvolts; when the pulsation phase is identified as the diastolic phase, the illumination intensity compensation factor corresponding to the diastolic phase will be used, with each increase of 1 milliwatt per square millimeter of illumination intensity causing a potential drift of 5 microvolts.

[0133] Based on the current light intensity in the lighting parameters and the lighting intensity compensation coefficient obtained above, the potential value to be compensated is calculated, and the photothermal artifact signal in the original electrophysiological signal is obtained.

[0134] Alternatively, in an optional embodiment, a photothermal artifact model can be pre-built using machine learning algorithms (such as existing algorithms like Support Vector Machines (SVM), neural networks, and random forests). This model takes different pulsation phases and illumination parameters as input data and outputs corresponding photothermal artifact signals obtained through extensive experimental calibration (e.g., by turning the optical imaging system on and off to generate different light intensities to obtain the original electrophysiological signals and generate corresponding signal fluctuations, thereby determining the corresponding photothermal artifact signals). It can predict the characteristics of photothermal artifacts based on different pulsation phases and illumination parameters, while simultaneously determining the corresponding illumination intensity compensation coefficient during the calculation process. During systole and diastole, the response of myocardial cells to the photothermal effect may differ; therefore, the calculation method for photothermal artifacts needs to be adjusted according to the current pulsation phase. Simultaneously, the light intensity in the illumination parameters directly affects the intensity of the photothermal artifacts. By inputting the current pulsation phase and the light intensity of the illumination parameters into the pre-built photothermal artifact model, the corresponding photothermal artifact signal can be calculated.

[0135] Specifically, during execution, the separation module 5 uses signal processing techniques, such as digital filtering, adaptive noise cancellation, or blind source separation algorithms, to subtract the identified mechanical artifact signals and the calculated photothermal artifact signals from the original electrophysiological signal, thereby obtaining a pure, real electrophysiological signal. This real electrophysiological signal can be used for subsequent high-precision studies such as pulsation waveform analysis and action potential parameter extraction.

[0136] As can be seen from the above, this cell electrophysiological signal recognition device acquires the original electrophysiological signals of cardiomyocytes, the mechanical data of the interaction between the mechanical probe and the cardiomyocytes, and the illumination parameters of the optical imaging system. It then identifies the mechanical artifact signals associated with the mechanical data from the original electrophysiological signals. Based on these mechanical artifact signals, it determines the instantaneous mechanical stiffness of the cardiomyocytes to identify the current pulsation stage of the cardiomyocytes. According to the pulsation stage and illumination parameters, it calculates the photothermal artifact signals in the original electrophysiological signals. Finally, it separates the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals to obtain the true electrophysiological signals of the cardiomyocytes. Thus, by identifying the mechanical artifact signals from the original electrophysiological signals... The mechanical artifact signal is obtained to determine the instantaneous mechanical stiffness of cardiomyocytes to identify the pulsation phase. Then, based on the pulsation phase and illumination parameters, the photothermal artifact signal is calculated to separate the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal, thereby obtaining the true electrophysiological signal of cardiomyocytes. This solves the technical problem in existing single-cell multimodal data acquisition methods that are difficult to effectively separate artifact signals generated by the mutual interference of multiple sensors, which leads to the inaccurate acquisition of true cell physiological information. By dynamically identifying the pulsation phase of the cell and adjusting the calculation and separation strategy of the artifact signal accordingly, the true cell electrophysiological information can be more accurately restored, improving the accuracy of electrophysiological signal identification of cardiomyocytes.

[0137] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes a processor 301 and a memory 302. The processor 301 and the memory 302 are interconnected and communicate with each other through a communication bus 303 and / or other forms of connection mechanism (not shown). The memory 302 stores a computer program executable by the processor 301. When the electronic device is running, the processor 301 executes the computer program to execute the cell electrophysiological signal recognition method in any optional implementation of the above embodiment, so as to achieve the following functions: acquiring the original electrophysiological signal of cardiomyocytes, the mechanical data of the interaction between the mechanical probe and the cardiomyocytes, and the illumination parameters of the optical imaging system; identifying the mechanical artifact signal associated with the mechanical data from the original electrophysiological signal; determining the instantaneous mechanical stiffness of the cardiomyocytes based on the mechanical artifact signal to identify the current pulsation stage of the cardiomyocytes; calculating the photothermal artifact signal in the original electrophysiological signal according to the pulsation stage and the illumination parameters; separating the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal to obtain the real electrophysiological signal of the cardiomyocytes.

[0138] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it executes the cell electrophysiological signal recognition method in any optional implementation of the above embodiments to achieve the following functions: acquiring the original electrophysiological signals of cardiomyocytes, mechanical data of the interaction between the mechanical probe and the cardiomyocytes, and illumination parameters of the optical imaging system; identifying mechanical artifact signals associated with the mechanical data from the original electrophysiological signals; determining the instantaneous mechanical stiffness of the cardiomyocytes based on the mechanical artifact signals to identify the current pulsation stage of the cardiomyocytes; calculating the photothermal artifact signals in the original electrophysiological signals according to the pulsation stage and illumination parameters; separating the mechanical artifact signals and photothermal artifact signals from the original electrophysiological signals to obtain the true electrophysiological signals of the cardiomyocytes. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0139] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0140] Furthermore, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0141] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0142] In this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations.

[0143] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for recognizing cellular electrophysiological signals, used to identify electrophysiological signals of cardiomyocytes, characterized in that, Including the following steps: Acquire raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between mechanical probes and cardiomyocytes, and illumination parameters of the optical imaging system; Mechanical artifact signals associated with the mechanical data are identified from the raw electrophysiological signals; Based on the mechanical artifact signal, the instantaneous mechanical stiffness of the cardiomyocyte is determined to identify the current beating stage of the cardiomyocyte; Based on the pulsation phase and the illumination parameters, the photothermal artifact signal in the original electrophysiological signal is calculated; The mechanical artifact signal and the photothermal artifact signal are separated from the original electrophysiological signal to obtain the real electrophysiological signal of the myocardial cells.

2. The method for recognizing cellular electrophysiological signals according to claim 1, characterized in that, Mechanical artifact signals associated with the mechanical data are identified from the raw electrophysiological signals, including: The raw electrophysiological signals are preprocessed to obtain preprocessed raw electrophysiological signals; The mechanical data is time-aligned with the preprocessed raw electrophysiological signal to determine the signal fluctuations generated when the mechanical data is applied in the preprocessed raw electrophysiological signal, thereby identifying mechanical artifact signals.

3. The method for recognizing cellular electrophysiological signals according to claim 1, characterized in that, Based on the mechanical artifact signal, the instantaneous mechanical stiffness of the cardiomyocyte is determined to identify the current beating stage of the cardiomyocyte, including: Calculate the instantaneous peak amplitude, average frequency, and rate of change of the signal envelope of the mechanical artifact signal; The instantaneous mechanical stiffness of the cardiomyocytes is determined based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope. Based on the instantaneous mechanical stiffness, the current pulsation stage of the myocardial cell is determined.

4. The method for recognizing cellular electrophysiological signals according to claim 3, characterized in that, Based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope, the instantaneous mechanical stiffness of the cardiomyocyte is calculated, including: A table of correspondences between mechanical stiffness levels is pre-constructed; The instantaneous mechanical stiffness of the myocardial cell is determined from the mechanical stiffness level correspondence table based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope.

5. The method for recognizing cellular electrophysiological signals according to claim 3, characterized in that, Based on the instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope, the instantaneous mechanical stiffness of the cardiomyocyte is calculated, including: Pre-construct a mechanical stiffness level calculation model; The instantaneous peak amplitude, the average frequency, and the rate of change of the signal envelope are input into the mechanical stiffness level calculation model to calculate the instantaneous mechanical stiffness of the myocardial cells.

6. The method for recognizing cellular electrophysiological signals according to claim 3, characterized in that, Based on the instantaneous mechanical stiffness, the current beating stage of the myocardial cell is determined, including: Determine whether the instantaneous mechanical stiffness is greater than or equal to a preset stiffness threshold. If so, the myocardial cells are determined to be in a high-stiffness state, and the current pulsation phase of the myocardial cells is identified as the systolic phase. If not, then the myocardial cells are determined to be in a low-stiffness state, and the current pulsation phase of the myocardial cells is identified as diastole.

7. The method for recognizing cellular electrophysiological signals according to claim 1, characterized in that, Based on the pulsation phase and the illumination parameters, the photothermal artifact signal in the original electrophysiological signal is calculated, including: Based on the pulsation phase, the corresponding lighting intensity compensation coefficient is determined; The photothermal artifact signal in the original electrophysiological signal is calculated based on the lighting parameters and the lighting intensity compensation coefficient.

8. A cellular electrophysiological signal recognition device for recognizing electrophysiological signals of cardiomyocytes, characterized in that, include: The acquisition module is used to acquire raw electrophysiological signals of cardiomyocytes, mechanical data of the interaction between the mechanical probe and cardiomyocytes, and illumination parameters of the optical imaging system; The identification module is used to identify mechanical artifact signals associated with the mechanical data from the original electrophysiological signals. The determination module is used to determine the instantaneous mechanical stiffness of the cardiomyocyte based on the mechanical artifact signal, so as to identify the current beating stage of the cardiomyocyte; The calculation module is used to calculate the photothermal artifact signal in the original electrophysiological signal based on the pulsation phase and the illumination parameters. The separation module is used to separate the mechanical artifact signal and the photothermal artifact signal from the original electrophysiological signal to obtain the real electrophysiological signal of the myocardial cells.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a computer program executable by the processor, wherein when the processor executes the computer program, it performs the steps of the cell electrophysiological signal recognition method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it performs the steps in the cell electrophysiological signal recognition method as described in any one of claims 1-7.

Images