Heart multi-mode digital twinning simulation method and system, electronic equipment and medium

Abstract

The invention provides a heart multi-mode digital twinning simulation method and system, electronic equipment and a medium, and belongs to the technical field of digital twinning. The method comprises the following steps: S1, collecting multi-modal data of a heart; s2, preprocessing the acquired multi-modal data to obtain heart digital data; s3, based on the heart digital data, constructing a multi-modal digital twinborn model of the heart and optimizing the multi-modal digital twinborn model; s4, performing real-time simulation on the electrophysiological activity of the heart by using the optimized multi-modal digital twin model and using a Runge-Kutta method in combination with a PSO (Particle Swarm Optimization) algorithm; s5, based on the optimized multi-mode digital twinborn model and the simulation result, simulation and planning of virtual cardiac surgical treatment are carried out; and S6, dynamically evaluating the multi-modal digital twin model, and monitoring the state change of the heart in real time. According to the heart multi-mode digital twinborn simulation method and system, the electronic equipment and the medium, efficient simulation and real-time monitoring of the heart state can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a cardiac multimodal digital twin simulation method, system, electronic equipment and medium. Background Art

[0002] With the continuous advancement of medical technology and the development of computer science, the application of digital twin technology in the medical field is becoming more and more extensive. Digital twin is a simulation technology that integrates multiple disciplines, multiple physical fields, multiple scales, and multiple probabilities. It achieves real-time monitoring and accurate prediction of the operating status of objects by establishing a virtual model that is highly consistent with the actual object. In the field of cardiac medicine, cardiac multimodal digital twin simulation technology has emerged, providing a new means for the diagnosis, treatment, and prevention of heart disease.

[0003] Traditional cardiac medical research mainly relies on experimental research and clinical observation. Although these methods can reveal the operating mechanism of the heart and the occurrence and development of diseases to a certain extent, they often have limitations such as high cost, long cycle, and high risk. The multimodal digital twin simulation technology of the heart can build a digital twin model of the heart by collecting multimodal data of the heart (such as imaging data, electrophysiological data, physiological and biochemical data, etc.), and perform real-time simulation and virtual surgery simulation based on the model. This method is not only highly accurate and reliable, but also can significantly reduce research costs and risks and improve diagnosis and treatment efficiency.

[0004] However, as a complex biological system, the structure and function of the heart are highly complex and nonlinear. Therefore, to achieve the effective application of cardiac multimodal digital twin simulation technology, a series of technical challenges need to be solved. For example, how to efficiently collect and process multimodal data of the heart, how to build an accurate cardiac digital twin model, how to achieve real-time simulation of cardiac electrophysiological activities and accurate simulation of virtual surgery, etc.

[0005] In summary, as an emerging medical technology, cardiac multimodal digital twin simulation technology has broad application prospects and far-reaching social significance. Summary of the invention

[0006] The purpose of the present invention is to provide a cardiac multimodal digital twin simulation method, system, electronic device and medium, which can realize efficient simulation and real-time monitoring of cardiac status.

[0007] To achieve the above object, the present invention provides a cardiac multimodal digital twin simulation method, comprising the following steps: S1, collect multimodal data of the heart; S2, preprocessing the collected multimodal data to obtain cardiac digital data; S3. Based on the digital data of the heart, a multimodal digital twin model of the heart is constructed and optimized; S4. Using the optimized multimodal digital twin model, the Runge-Kutta method combined with the PSO algorithm is used to simulate the electrophysiological activity of the heart in real time; S5. Simulate and plan virtual cardiac surgery based on the optimized multimodal digital twin model and simulation results; S6. Dynamically evaluate the multimodal digital twin model and monitor the changes in the heart's state in real time.

[0008] Preferably, in step S1, the multimodal data includes imaging data, electrophysiological data and physiological and biochemical data, the imaging data includes CT and MRI; the electrophysiological data is ECG data; and the physiological and biochemical data includes blood pressure and blood sugar.

[0009] Preferably, in step S2, preprocessing the collected multimodal data to obtain cardiac digital data comprises the following steps: S21, performing dimensionality reduction processing and data cleaning on the collected multimodal data to obtain preprocessed data; S22, performing low-pass filtering on the pre-processed data; S23, performing digital-to-analog conversion on the data after low-pass filtering to obtain cardiac digital data.

[0010] Preferably, in step S3, constructing a multimodal digital twin model of the heart includes the following steps: S31, integrating imaging data, electrophysiological data, and physiological and biochemical data; ; in, represents the fused data; Represents CT data; represents MRI data; Represents ECG data; Indicates blood pressure data; Indicates blood sugar data; , , , , are weight coefficients, and ; S32, using post-gating technology to scan the CTA data of the whole heart and perform dynamic modeling according to the cardiac cycle; ; in, Indicates the changes in heart volume during the cardiac cycle; Indicates the basic volume; Indicates The amplitude of each harmonic; represents the angular frequency; represents a time point within the cardiac cycle; Indicates The phase of the harmonics; Indicates the number of harmonics; S33, customized biomechanical modeling; ; in, Indicates stress; represents Young's modulus; Indicates strain; S34. Build a multimodal digital twin model of the heart; ; in, Represents a multimodal digital twin model; Represents geometric structures; Represents electrophysiological properties; Indicates hemodynamic characteristics; ; ; ; in, Indicates based on and Functions for building geometric structures; Indicates based on and Constructing functions of electrophysiological properties; Indicates based on , and Constructing functions of hemodynamic properties; S35. Verify the accuracy of the multimodal digital twin model by comparing it with the actual heart data, and optimize it to obtain an optimized multimodal digital twin model; ; in, represents the optimized multimodal digital twin model; represents the learning rate; Indicates actual cardiac data.

[0011] Preferably, in step S4, the electrophysiological simulation module uses the optimized multimodal digital twin model, uses the Runge-Kutta method and combines the PSO algorithm to perform real-time simulation of the electrophysiological activity of the heart, including the following steps: S41. Use the optimized multimodal digital twin model to initialize model parameters, including heart rate , ion channel characteristics and drug concentrations in cardiomyocytes , the ion channel characteristics of myocardial cells include sodium channels , calcium channels and potassium channels ; ; in, represents the initial membrane potential; represents the initial value determined according to the electrophysiological characteristics in the optimized multimodal digital twin model; S42, defining the parameters of the PSO algorithm, including particle swarm size, inertia weight, individual learning factor and group learning factor; Initialize the particle position and velocity. The position corresponds to the parameters of the electrophysiological model, and the velocity corresponds to the rate of change of the parameters. S43, defining a fitness function for evaluating the performance of the electrophysiological model parameters represented by each particle; ; in, represents the fitness function; represents the membrane potential obtained by simulation; represents the actual observed membrane potential; Indicates the number of time points; An index representing a time point; S44, using the PSO algorithm to iteratively optimize the electrophysiological model parameters until a maximum number of iterations is reached; S45. Establish a ventricular cardiomyocyte model; ; in, represents the ion current; represents membrane potential; represents the membrane capacitance; S46, simulating the action potential of ventricular cardiomyocytes using the Runge-Kutta method; ; ; ; ; ; in, Indicates The membrane potential of the step; , , , Indicates the parameter changes after PSO optimization; represents the time step; S47. Perform electrophysiological simulation using the parameters optimized by PSO and analyze the effects of different physiological and pathological conditions on cardiac function. ; in, , , represents the ion channel conductance after PSO optimization; , , , , , represents the gating variable of the ion channel; , , Represent the equilibrium potentials of sodium, calcium, and potassium respectively.

[0012] Preferably, in step S5, the virtual surgery treatment module simulates and plans virtual cardiac surgery treatment based on the multimodal digital twin model and the simulation results, including the following steps: S51. Simulate surgical operations on the optimized multimodal digital twin model. ; in, Indicates surgical plan; represents a function that simulates surgery, indicates surgical parameters, including incision location and instrument path; S52. Evaluate surgical risks by simulating different surgical plans; ; in, represents surgical risk assessment; represents the risk assessment function; S53, using the PSO algorithm to optimize the parameters in the surgical plan, including the incision location and the instrument operation path; ; in, represents the optimal surgical parameters; Indicates the number of iterations; Indicates the population size; S54, adjusting the surgical plan according to the optimization result of the PSO algorithm; ; in, Indicates the adjusted surgical plan; Represents the function of adjusting the surgical plan; S55, performing simulation verification using the adjusted surgical plan; ; in, It indicates the evaluation of surgical effect; represents the effect evaluation function; S56, feeding back the surgical effect evaluation to the optimized multimodal digital twin model; ; in, represents the updated multimodal digital twin model; Represents the feedback function.

[0013] Preferably, in step S6, the dynamic evaluation module dynamically evaluates the digital twin model of the heart and monitors the state changes of the heart in real time, including the following steps: S61, the dynamic assessment module first needs to collect the latest heart data, including real-time imaging data, electrophysiological data, physiological and biochemical data; S62, comparing the real-time collected data with the data in the multimodal digital twin model, and analyzing the difference between the model and the actual heart state; S63, the dynamic evaluation module monitors the state changes of the heart in real time, including the geometric structure, electrophysiological characteristics, and hemodynamic characteristics of the heart; S64. During the monitoring process, when any abnormal data or data that deviates from the normal range is found, the dynamic assessment module will issue an early warning; S65. The results of the dynamic evaluation will be fed back to the multimodal modeling module and the electrophysiological simulation module. Based on the evaluation results, the multimodal digital twin model will be further optimized to improve the accuracy of the model and the reliability of the simulation.

[0014] The present invention also provides a cardiac multimodal digital twin simulation system, comprising: A data acquisition module, used for acquiring multimodal data of the heart; A data preprocessing module is used to preprocess the collected multimodal data to obtain cardiac digital data; Multimodal modeling module, used to build and optimize a multimodal digital twin model of the heart based on digital heart data; The electrophysiological simulation module is used to use the optimized multimodal digital twin model to perform real-time simulation of the electrophysiological activity of the heart using the Runge-Kutta method combined with the PSO algorithm; Virtual surgery module, which is used to simulate and plan virtual cardiac surgery based on the optimized multimodal digital twin model and simulation results; The dynamic evaluation module is used to dynamically evaluate the multimodal digital twin model and monitor the state changes of the heart in real time.

[0015] The present invention also provides a computer device, comprising: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned cardiac multimodal digital twin simulation method when executing the computer program.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned cardiac multimodal digital twin simulation method when executed by a processor.

[0017] Therefore, the present invention adopts the above-mentioned cardiac multimodal digital twin simulation method, system, electronic device and medium, and the beneficial technical effects are as follows: (1) By collecting multimodal data of the heart (including imaging data, electrophysiological data, and physiological and biochemical data), the present invention can build a digital twin model that is highly consistent with the actual heart. This helps doctors understand the structure and function of the heart more accurately.

[0018] In the simulation and planning of virtual cardiac surgery, doctors can conduct multiple surgical rehearsals based on the digital twin model to optimize surgical plans and reduce surgical risks.

[0019] (2) Realize real-time monitoring and early warning of cardiac function: The dynamic assessment module can monitor the changes in the heart's state in real time, including the heart's geometric structure, electrophysiological characteristics, and hemodynamic characteristics. Once any abnormal data or data that deviates from the normal range is found, the system will issue an early warning, helping doctors to promptly detect and deal with potential heart problems.

[0020] (3) Promote the in-depth development of heart disease research: The cardiac multimodal digital twin simulation method provided by the present invention provides a new platform for the study of heart diseases. Researchers can conduct more in-depth research on this basis to explore the pathogenesis and treatment methods of heart diseases, and promote the in-depth development of heart disease research.

[0021] (4) Improving the level of intelligence in medical services: By combining digital twin technology with modern medical technology, the present invention improves the intelligent level of medical services. Doctors can more conveniently obtain patients' heart data, conduct more accurate simulation and analysis, and thus formulate more personalized treatment plans.

[0022] (5) Reduce medical costs and improve medical efficiency: The simulation and planning of virtual cardiac surgery treatment can reduce the uncertainty and risk in actual surgery, thereby reducing the failure rate and complication rate of surgery. This helps to reduce medical costs and improve medical efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of the cardiac multimodal digital twin simulation method of the present invention; Figure 2 Flowchart for data preprocessing; Figure 3 Build a flow chart for a multimodal digital twin model; Figure 4 Real-time simulation flow chart for electrophysiological activities; Figure 5 Simulate and plan flowcharts for virtual surgical treatments; Figure 6 This is a dynamic evaluation flow chart. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0025] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0026] Embodiment 1 like Figure 1 FIG. 1 is a flowchart of a cardiac multimodal digital twin simulation method of the present invention, which specifically includes the following steps: S1. Collect multimodal data of the heart.

[0027] Multimodal data include imaging data, electrophysiological data, and physiological and biochemical data.

[0028] Advanced medical imaging technologies, such as 320-row CT and 3.0T MRI, are used to obtain cardiac imaging data of patients. At the same time, electrophysiological data are recorded in real time through electrocardiogram (ECG) equipment, and physiological and biochemical data such as blood pressure and blood sugar are collected through continuous monitoring equipment. These data will provide the basis for building an accurate cardiac digital twin model.

[0029] S2, such as Figure 2 As shown, preprocessing the collected multimodal data to obtain cardiac digital data includes the following steps: S21, performing dimensionality reduction processing and data cleaning on the collected multimodal data to obtain preprocessed data; S22. Apply digital signal processing technology to perform low-pass filtering on the pre-processed data to eliminate high-frequency interference and retain important physiological signals; S23. Convert the filtered data into digital signals through an analog-to-digital converter (ADC) to provide accurate digital input for the subsequent construction of the digital twin model.

[0030] S3, such as Figure 3 As shown, based on the digital data of the heart, a multimodal digital twin model of the heart is constructed and optimized, including the following steps: S31, integrating imaging data, electrophysiological data, and physiological and biochemical data; ; in, represents the fused data; Represents CT data; represents MRI data; Represents ECG data; Indicates blood pressure data; Indicates blood sugar data; , , , , are weight coefficients, and ; S32. Use post-gating technology to scan the CTA data of the complete heart, perform dynamic modeling according to the cardiac cycle, and accurately capture the dynamic changes of the heart; ; in, Indicates the changes in heart volume during the cardiac cycle; Indicates the basic volume; Indicates The amplitude of each harmonic; represents the angular frequency; represents a time point within the cardiac cycle; Indicates The phase of the harmonics; Indicates the number of harmonics; S33. Customized biomechanical modeling based on the mechanical properties of cardiac tissue, including stress, strain, and Young's modulus; ; in, Indicates stress; represents Young's modulus; Indicates strain; S34. Build a multimodal digital twin model of the heart by integrating geometric structure, electrophysiological characteristics and hemodynamic characteristics; ; in, Represents a multimodal digital twin model; Represents geometric structures; Represents electrophysiological properties; Indicates hemodynamic characteristics; ; ; ; in, Indicates based on and Functions for building geometric structures; Indicates based on and Constructing functions of electrophysiological properties; Indicates based on , and Constructing functions of hemodynamic properties; S35. Verify the accuracy of the multimodal digital twin model by comparing it with the actual heart data, and optimize the model according to the learning rate and the actual heart data to obtain the optimized multimodal digital twin model; ; in, represents the optimized multimodal digital twin model; represents the learning rate; Indicates actual cardiac data.

[0031] S4, such as Figure 4 As shown in the figure, the optimized multimodal digital twin model is used to simulate the electrophysiological activity of the heart in real time using the Runge-Kutta method combined with the PSO algorithm, including the following steps: S41. Use the optimized multimodal digital twin model to initialize model parameters, including heart rate , ion channel characteristics and drug concentrations in cardiomyocytes , the ion channel characteristics of myocardial cells include sodium channels , calcium channels and potassium channels ; ; in, represents the initial membrane potential; represents the initial value determined according to the electrophysiological characteristics in the optimized multimodal digital twin model; S42, defining the parameters of the PSO algorithm, including particle swarm size, inertia weight, individual learning factor and group learning factor; Initialize the particle position and velocity. The position corresponds to the parameters of the electrophysiological model, and the velocity corresponds to the rate of change of the parameters. S43, defining a fitness function for evaluating the performance of the electrophysiological model parameters represented by each particle, with the difference between the simulated membrane potential and the actually observed membrane potential as the main evaluation criterion; ; in, represents the fitness function; represents the membrane potential obtained by simulation; represents the actual observed membrane potential; Indicates the number of time points; An index representing a time point; S44, using the PSO algorithm to iteratively optimize the electrophysiological model parameters until a maximum number of iterations is reached; S45. Establish a ventricular cardiomyocyte model based on ion current, membrane potential and membrane capacitance; ; in, represents the ion current; represents membrane potential; represents the membrane capacitance; S46. Use the Runge-Kutta method to simulate the action potential of ventricular myocardial cells and simulate cardiac electrophysiological activities; ; ; ; ; ; in, Indicates The membrane potential of the step; , , , Indicates the parameter changes after PSO optimization; represents the time step; S47. Perform electrophysiological simulation using the parameters optimized by PSO and analyze the effects of different physiological and pathological conditions on cardiac function. ; in, , , represents the ion channel conductance after PSO optimization; , , , , , represents the gating variable of the ion channel; , , Represent the equilibrium potentials of sodium, calcium, and potassium respectively.

[0032] S5, such as Figure 5 As shown, based on the optimized multimodal digital twin model and simulation results, the simulation and planning of virtual cardiac surgery treatment includes the following steps: S51. Simulate surgical operations on the optimized multimodal digital twin model. ; The specific form is as follows: ; in, Indicates surgical plan; represents a function that simulates surgery, indicates surgical parameters, including incision location and instrument path; Represents the transformation matrix, which adjusts the model according to the surgical parameters ; S52. Evaluate surgical risks by simulating different surgical plans; ; The specific form is as follows: ; in, represents surgical risk assessment; represents the risk assessment function; , represents the risk weight; Indicates the distance from the incision to the nearest critical structure; Indicates the distance from the instrument path to the nearest critical structure; S53, using the PSO algorithm to optimize the parameters in the surgical plan, including the incision location and the instrument operation path; ; in, represents the optimal surgical parameters; Indicates the number of iterations; Indicates the population size; S54, adjusting the surgical plan according to the optimization result of the PSO algorithm; ; The specific form is as follows: ; in, Indicates the adjusted surgical plan; Represents the function of adjusting the surgical plan; S55, performing simulation verification using the adjusted surgical plan; ; The specific form is as follows: ; in, It indicates the evaluation of surgical effect; represents the effect evaluation function; , represents the effect weight; Indicates changes in blood flow; Indicates electrophysiological changes; S56, feeding back the surgical effect evaluation to the optimized multimodal digital twin model; ; The specific form is as follows: ; in, represents the updated multimodal digital twin model; represents the feedback function; Indicates the feedback strength.

[0033] S6, such as Figure 6 As shown, the multimodal digital twin model is dynamically evaluated to monitor the state changes of the heart in real time, including the following steps: S61, the dynamic assessment module first needs to collect the latest heart data, including real-time imaging data, electrophysiological data, physiological and biochemical data; S62, comparing the real-time collected data with the data in the multimodal digital twin model, and analyzing the difference between the model and the actual heart state; S63, the dynamic evaluation module monitors the state changes of the heart in real time, including the geometric structure, electrophysiological characteristics, and hemodynamic characteristics of the heart; S64. During the monitoring process, when any abnormal data or data that deviates from the normal range is found, the dynamic assessment module will issue an early warning; S65. The results of the dynamic evaluation will be fed back to the multimodal modeling module and the electrophysiological simulation module. Based on the evaluation results, the multimodal digital twin model will be further optimized to improve the accuracy of the model and the reliability of the simulation.

[0034] Embodiment 2 A cardiac multimodal digital twin simulation system, comprising: A data acquisition module, used for acquiring multimodal data of the heart; A data preprocessing module is used to preprocess the collected multimodal data to obtain cardiac digital data; Multimodal modeling module, used to build and optimize a multimodal digital twin model of the heart based on digital heart data; The electrophysiological simulation module is used to use the optimized multimodal digital twin model to perform real-time simulation of the electrophysiological activity of the heart using the Runge-Kutta method combined with the PSO algorithm; Virtual surgery module, which is used to simulate and plan virtual cardiac surgery based on the optimized multimodal digital twin model and simulation results; The dynamic evaluation module is used to dynamically evaluate the multimodal digital twin model and monitor the state changes of the heart in real time.

[0035] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0036] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0037] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0038] It is worth noting that the contents not elaborated in detail in the present invention are all prior art and are well known to those skilled in the art.

[0039] Therefore, the present invention adopts the above-mentioned cardiac multimodal digital twin simulation method, system, electronic device and medium to achieve efficient simulation and real-time monitoring of the heart state.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A cardiac multimodal digital twin simulation method, characterized in that: The following steps are involved: S1, collect multimodal data of the heart; S2, preprocessing the collected multimodal data to obtain cardiac digital data; S3. Based on the digital data of the heart, a multimodal digital twin model of the heart is constructed and optimized; S4. Using the optimized multimodal digital twin model, the Runge-Kutta method combined with the PSO algorithm is used to simulate the electrophysiological activity of the heart in real time; S5. Simulate and plan virtual cardiac surgery based on the optimized multimodal digital twin model and simulation results; S6. Dynamically evaluate the multimodal digital twin model and monitor the changes in the heart's state in real time.

2. A cardiac multimodal digital twin simulation method according to claim 1, characterized in that: In step S1, the multimodal data includes imaging data, electrophysiological data and physiological and biochemical data. The imaging data includes CT and MRI; the electrophysiological data is ECG data; and the physiological and biochemical data includes blood pressure and blood sugar.

3. A cardiac multimodal digital twin simulation method according to claim 2, characterized in that: In step S2, the collected multimodal data is preprocessed to obtain cardiac digital data, including the following steps: S21, performing dimensionality reduction processing and data cleaning on the collected multimodal data to obtain pre-processed data; S22, performing low-pass filtering on the pre-processed data; S23, performing digital-to-analog conversion on the data after low-pass filtering to obtain cardiac digital data.

4. A cardiac multimodal digital twin simulation method according to claim 3, characterized in that: In step S3, a multimodal digital twin model of the heart is constructed, including the following steps: S31, integrating imaging data, electrophysiological data, and physiological and biochemical data; ； in, represents the fused data; Represents CT data; represents MRI data; Represents ECG data; Indicates blood pressure data; Indicates blood sugar data; , , , , are weight coefficients, and ; S32, using post-gating technology to scan the CTA data of the whole heart and perform dynamic modeling according to the cardiac cycle; ； in, Indicates the changes in heart volume during the cardiac cycle; Indicates the basic volume; Indicates The amplitude of each harmonic; represents the angular frequency; represents a time point within the cardiac cycle; Indicates The phase of the harmonics; Indicates the number of harmonics; S33, customized biomechanical modeling; ； in, Indicates stress; represents Young's modulus; Indicates strain; S34. Build a multimodal digital twin model of the heart; ； in, Represents a multimodal digital twin model; Represents geometric structures; Represents electrophysiological properties; Indicates hemodynamic characteristics; ； ； ； in, Indicates based on and Functions for building geometric structures; Indicates based on and Constructing functions of electrophysiological properties; Indicates based on , and Constructing functions of hemodynamic properties; S35. Verify the accuracy of the multimodal digital twin model by comparing it with the actual heart data, and optimize it to obtain an optimized multimodal digital twin model; ； in, represents the optimized multimodal digital twin model; represents the learning rate; Indicates actual cardiac data.

5. A cardiac multimodal digital twin simulation method according to claim 4, characterized in that: In step S4, the electrophysiological simulation module uses the optimized multimodal digital twin model, the Runge-Kutta method and the PSO algorithm to perform real-time simulation of the electrophysiological activity of the heart, including the following steps: S41. Use the optimized multimodal digital twin model to initialize model parameters, including heart rate , ion channel characteristics and drug concentrations in cardiomyocytes , the ion channel characteristics of myocardial cells include sodium channels , calcium channels and potassium channels ; ； in, represents the initial membrane potential; represents the initial value determined according to the electrophysiological characteristics in the optimized multimodal digital twin model; S42, defining the parameters of the PSO algorithm, including particle swarm size, inertia weight, individual learning factor and group learning factor; Initialize the particle position and velocity. The position corresponds to the parameters of the electrophysiological model, and the velocity corresponds to the rate of change of the parameters. S43, defining a fitness function for evaluating the performance of the electrophysiological model parameters represented by each particle; ； in, represents the fitness function; represents the membrane potential obtained by simulation; represents the actual observed membrane potential; Indicates the number of time points; An index representing a time point; S44, using the PSO algorithm to iteratively optimize the electrophysiological model parameters until a maximum number of iterations is reached; S45. Establish a ventricular cardiomyocyte model; ； in, represents the ion current; represents membrane potential; represents the membrane capacitance; S46, simulating the action potential of ventricular cardiomyocytes using the Runge-Kutta method; ； ； ； ； ； in, Indicates The membrane potential of the step; , , , Indicates the parameter changes after PSO optimization; represents the time step; S47. Perform electrophysiological simulation using the parameters optimized by PSO and analyze the effects of different physiological and pathological conditions on cardiac function. ； in, , , represents the ion channel conductance after PSO optimization; , , , , , represents the gating variable of the ion channel; , , Represent the equilibrium potentials of sodium, calcium, and potassium respectively.

6. A cardiac multimodal digital twin simulation method according to claim 5, characterized in that: In step S5, the virtual surgery treatment module simulates and plans virtual cardiac surgery treatment based on the multimodal digital twin model and simulation results, including the following steps: S51. Simulate surgical operations on the optimized multimodal digital twin model. ； in, Indicates surgical plan; represents the function of simulating surgery; indicates surgical parameters, including incision location and instrument path; S52. Evaluate surgical risks by simulating different surgical plans; ； in, represents surgical risk assessment; represents the risk assessment function; S53, using the PSO algorithm to optimize the parameters in the surgical plan, including the incision location and the instrument operation path; ； in, represents the optimal surgical parameters; Indicates the number of iterations; Indicates the population size; S54, adjusting the surgical plan according to the optimization result of the PSO algorithm; ； in, Indicates the adjusted surgical plan; Represents the function of adjusting the surgical plan; S55, performing simulation verification using the adjusted surgical plan; ； in, It indicates the evaluation of surgical effect; represents the effect evaluation function; S56, feeding back the surgical effect evaluation to the optimized multimodal digital twin model; ； in, represents the updated multimodal digital twin model; Represents the feedback function.

7. A cardiac multimodal digital twin simulation method according to claim 6, characterized in that: In step S6, the dynamic evaluation module dynamically evaluates the digital twin model of the heart and monitors the state changes of the heart in real time, including the following steps: S61, the dynamic assessment module first needs to collect the latest heart data, including real-time imaging data, electrophysiological data, physiological and biochemical data; S62, comparing the real-time collected data with the data in the multimodal digital twin model, and analyzing the difference between the model and the actual heart state; S63, the dynamic evaluation module monitors the state changes of the heart in real time, including the geometric structure, electrophysiological characteristics, and hemodynamic characteristics of the heart; S64. During the monitoring process, when any abnormal data or data that deviates from the normal range is found, the dynamic assessment module will issue an early warning; S65. The results of the dynamic evaluation will be fed back to the multimodal modeling module and the electrophysiological simulation module, and the multimodal digital twin model will be further optimized based on the evaluation results.

8. A cardiac multimodal digital twin simulation system, characterized in that: include: A data acquisition module, used for acquiring multimodal data of the heart; A data preprocessing module is used to preprocess the collected multimodal data to obtain cardiac digital data; Multimodal modeling module, used to build and optimize a multimodal digital twin model of the heart based on digital heart data; The electrophysiological simulation module is used to use the optimized multimodal digital twin model to perform real-time simulation of the electrophysiological activity of the heart using the Runge-Kutta method combined with the PSO algorithm; Virtual surgery module, which is used to simulate and plan virtual cardiac surgery based on the optimized multimodal digital twin model and simulation results; The dynamic evaluation module is used to dynamically evaluate the multimodal digital twin model and monitor the state changes of the heart in real time.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the cardiac multimodal digital twin simulation method described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cardiac multimodal digital twin simulation method described in any one of claims 1 to 7 are implemented.

Images