Cardiac multimodal digital twin simulation method, system, electronic device and medium

Abstract

The present invention provides a method, system, electronic device and medium for simulating a multimodal digital twin of the heart, and belongs to the field of digital twin technology. The method includes: S1, collecting multimodal data of the heart; S2, preprocessing the collected multimodal data to obtain digital data of the heart; S3, constructing and optimizing a multimodal digital twin model of the heart based on the digital data of the heart; S4, using the optimized multimodal digital twin model, using the Runge-Kutta method and combining the PSO algorithm to simulate the electrophysiological activity of the heart in real time; S5, based on the optimized multimodal digital twin model and the simulation results, simulating and planning virtual cardiac surgery; S6, dynamically evaluating the multimodal digital twin model, and monitoring the state changes of the heart in real time. The present invention adopts the above-mentioned multimodal digital twin simulation method, system, electronic device and medium of the heart to realize efficient simulation and real-time monitoring of the heart state.

Description

Technical Field

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

[0002] With the continuous progress of medical technology and the development of computer science, digital twin technology has been increasingly widely used in the medical field. Digital twin is a simulation technology that integrates multiple disciplines, multiple physical fields, multiple scales, and multiple probabilities. It realizes real-time monitoring and accurate prediction of the operating state of an object 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 new means for the diagnosis, treatment, and prevention of heart diseases.

[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. Cardiac multimodal digital twin simulation technology can collect multimodal data of the heart (such as imaging data, electrophysiological data, physiological and biochemical data, etc.), construct a digital twin model of the heart, and perform real-time simulation and virtual surgery simulation based on this model. This method not only has high accuracy and reliability, but also can significantly reduce research costs and risks and improve the diagnosis and treatment efficiency.

[0004] However, as a complex biological system, the structure and function of the heart have high complexity and nonlinearity. Therefore, to effectively apply cardiac multimodal digital twin simulation technology, a series of technical problems need to be solved. For example, how to efficiently collect and process multimodal data of the heart, how to construct an accurate digital twin model of the heart, how to realize real-time simulation of cardiac electrophysiological activities and accurate simulation of virtual surgery, etc.

[0005] In summary, cardiac multimodal digital twin simulation technology, as an emerging medical technology, has broad application prospects and profound 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 the cardiac state.

[0007] To achieve the above purpose, the present invention provides a cardiac multimodal digital twin simulation method, including the following steps:

[0008] S1. Collect multimodal data of the heart;

[0009] S2. Preprocess the collected multimodal data to obtain cardiac digital data;

[0010] S3. Based on the cardiac digital data, construct and optimize a multimodal digital twin model of the heart;

[0011] S4. Use the optimized multimodal digital twin model, the Runge-Kutta method and the PSO algorithm to perform real-time simulation of the electrophysiological activities of the heart;

[0012] S5. Based on the optimized multimodal digital twin model and the simulation results, conduct simulation and planning of virtual cardiac surgery treatment;

[0013] S6. Dynamically evaluate the multimodal digital twin model and monitor the state changes of the heart in real time.

[0014] 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; the physiological and biochemical data includes blood pressure and blood glucose.

[0015] Preferably, in step S2, preprocessing the collected multimodal data to obtain cardiac digital data includes the following steps:

[0016] S21. Perform dimensionality reduction processing and data cleaning on the collected multimodal data to obtain preprocessed data;

[0017] S22. Perform low-pass filtering on the preprocessed data;

[0018] S23. Perform digital-to-analog conversion on the data after low-pass filtering to obtain cardiac digital data.

[0019] Preferably, in step S3, constructing a multimodal digital twin model of the heart includes the following steps:

[0020] S31. Integrate the imaging data, electrophysiological data, and physiological and biochemical data;

[0021] ;

[0022] Among them, represents the integrated data; represents CT data; represents MRI data; represents ECG data; represents blood pressure data; represents blood glucose data; , , , , Both represent weight coefficients, and ;

[0023] S32. Use the back-gating technology to scan the CTA data of the complete heart and perform dynamic modeling according to the cardiac cycle;

[0024] ;

[0025] Among them, represents the change in cardiac volume during the cardiac cycle; represents the basal volume; represents the th harmonic amplitude; represents the angular frequency; represents the time point during the cardiac cycle; represents the th harmonic phase; represents the number of harmonics;

[0026] S33. Customize biomechanical modeling;

[0027] ;

[0028] Among them, represents stress; represents Young's modulus; represents strain;

[0029] S34. Construct a multi-modal digital twin model of the heart;

[0030] ;

[0031] Among them, represents the multi-modal digital twin model; represents the geometric structure; represents the electrophysiological characteristics; represents the hemodynamic characteristics;

[0032] ;

[0033] ;

[0034] ;

[0035] Among them, represents the function for constructing the geometric structure according to and ; represents the function for constructing the electrophysiological characteristics according to and ; represents the function for constructing according to , and Construct a function of hemodynamic characteristics;

[0036] S35. Verify the accuracy of the multimodal digital twin model by comparing it with actual cardiac data, and optimize it to obtain an optimized multimodal digital twin model;

[0037] ;

[0038] Among them, represents the optimized multimodal digital twin model; represents the learning rate; represents the actual cardiac data.

[0039] Preferably, in step S4, the electrophysiological simulation module uses the optimized multimodal digital twin model, and uses the Runge-Kutta method and combines it with the PSO algorithm to perform real-time simulation of the electrophysiological activities of the heart, including the following steps:

[0040] S41. Use the optimized multimodal digital twin model to initialize the model parameters, including heart rate , ion channel characteristics of cardiomyocytes, and drug concentration , and the ion channel characteristics of cardiomyocytes include sodium channels , calcium channels , and potassium channels ;

[0041] ;

[0042] Among them, represents the initial membrane potential; represents the initial value determined according to the electrophysiological characteristics in the optimized multimodal digital twin model;

[0043] S42. Define the parameters of the PSO algorithm, including the particle swarm size, inertia weight, individual learning factor, and population learning factor;

[0044] Initialize the particle position and velocity, where the position corresponds to the parameters of the electrophysiological model, and the velocity corresponds to the change rate of the parameters;

[0045] S43. Define the fitness function for evaluating the performance of the electrophysiological model parameters represented by each particle;

[0046] ;

[0047] Among them, represents the fitness function; represents the membrane potential obtained by simulation; represents the actually observed membrane potential; Indicates the number of time points; Indicates the index of the time point;

[0048] S44. Iteratively optimize the electrophysiological model parameters using the PSO algorithm until the maximum number of iterations is reached;

[0049] S45. Establish a ventricular myocardial cell model;

[0050] ;

[0051] Among them, Indicates the ionic current; Indicates the membrane potential; Indicates the membrane capacitance;

[0052] S46. Use the Runge-Kutta method to simulate the action potential of ventricular myocardial cells;

[0053] ;

[0054] ;

[0055] ;

[0056] ;

[0057] ;

[0058] Among them, Indicates the membrane potential at the step; , , Indicates the change in the parameters optimized by PSO; Indicates the time step;

[0059] S47. Perform electrophysiological simulation using the parameters optimized by PSO and analyze the effects of different physiological and pathological conditions on cardiac function;

[0060] ;

[0061] Among them, , , Indicates the ionic channel conductance optimized by PSO; , , , , , Indicates the gating variable of the ionic channel; , , respectively represent the equilibrium potentials of sodium, calcium, and potassium.

[0062] Preferably, in step S5, the virtual surgery treatment module performs simulation and planning of virtual heart surgery treatment based on the multimodal digital twin model and simulation results, including the following steps:

[0063] S51. Simulate surgical operations on the optimized multimodal digital twin model;

[0064] ;

[0065] where, represents the surgical plan; represents the function of simulating the surgery, represents the surgical parameters, including the incision position and the instrument path;

[0066] S52. Evaluate the surgical risks by simulating different surgical plans;

[0067] ;

[0068] where, represents the surgical risk assessment; represents the risk assessment function;

[0069] S53. Optimize the parameters in the surgical plan, including the incision position and the instrument operation path, using the PSO algorithm;

[0070] ;

[0071] where, represents the optimal surgical parameters; represents the number of iterations; represents the population size;

[0072] S54. Adjust the surgical plan according to the optimization results of the PSO algorithm;

[0073] ;

[0074] where, represents the adjusted surgical plan; represents the function of adjusting the surgical plan;

[0075] S55. Perform simulation verification using the adjusted surgical plan;

[0076] ;

[0077] where, represents the surgical effect evaluation; represents the effect evaluation function;

[0078] S56. Feed the surgical effect evaluation back to the optimized multi-modal digital twin model;

[0079] ;

[0080] Among them, represents the updated multi-modal digital twin model; represents the feedback function.

[0081] 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:

[0082] S61. The dynamic evaluation module first needs to collect the latest heart data, including real-time imaging data, electrophysiological data, and physiological and biochemical data;

[0083] S62. Compare the real-time collected data with the data in the multi-modal digital twin model, and analyze the differences between the model and the actual heart state;

[0084] 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;

[0085] S64. During the monitoring process, when any abnormal or data deviating from the normal range is found, the dynamic evaluation module will issue a warning;

[0086] S65. The results of the dynamic evaluation will be fed back to the multi-modal modeling module and the electrophysiological simulation module. According to the evaluation results, the multi-modal digital twin model will be further optimized to improve the accuracy of the model and the reliability of the simulation.

[0087] The present invention also provides a cardiac multi-modal digital twin simulation system, including:

[0088] A data acquisition module for acquiring multi-modal data of the heart;

[0089] A data preprocessing module for preprocessing the acquired multi-modal data to obtain cardiac digital data;

[0090] A multi-modal modeling module for constructing and optimizing a multi-modal digital twin model of the heart based on the cardiac digital data;

[0091] An electrophysiological simulation module for using the optimized multi-modal digital twin model to perform real-time simulation of the electrophysiological activities of the heart using the Runge-Kutta method and combining with the PSO algorithm;

[0092] A virtual surgery treatment module for simulating and planning virtual heart surgery treatment based on the optimized multi-modal digital twin model and simulation results;

[0093] A dynamic evaluation module for dynamically evaluating the multi-modal digital twin model and real-time monitoring of the state changes of the heart.

[0094] The present invention also provides a computer device, comprising: a memory and a processor; the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned heart multi-modal digital twin simulation method are implemented.

[0095] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned heart multi-modal digital twin simulation method are implemented.

[0096] Therefore, the present invention adopts the above-mentioned heart multi-modal digital twin simulation method, system, electronic device and medium, and the beneficial technical effects are as follows:

[0097] (1) By collecting multi-modal data of the heart (including imaging data, electrophysiological data and physiological and biochemical data), the present invention can construct a digital twin model that is highly consistent with the actual heart. This helps doctors to more accurately understand the structure and function of the heart.

[0098] In the simulation and planning of virtual heart surgery treatment, doctors can conduct multiple surgical rehearsals based on the digital twin model, optimize the surgical plan, and reduce the surgical risk.

[0099] (2) Realize real-time monitoring and early warning of heart function:

[0100] The dynamic evaluation module can real-time monitor the state changes of the heart, including the geometric structure, electrophysiological characteristics and hemodynamic characteristics of the heart. Once any abnormal or data deviating from the normal range is found, the system will issue an early warning, which helps doctors to timely discover and handle potential heart problems.

[0101] (3) Promote the in-depth development of heart disease research:

[0102] The heart multi-modal digital twin simulation method provided by the present invention provides a new platform for the research of heart diseases. Researchers can conduct more in-depth research on this basis, explore the pathogenesis, treatment methods, etc. of heart diseases, and promote the in-depth development of heart disease research.

[0103] (4) Improve the intelligent level of medical services:

[0104] 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 simulations and analyses, and thus formulate more personalized treatment plans.

[0105] (5) Reduce medical costs and improve medical efficiency:

[0106] The simulation and planning of virtual cardiac surgery can reduce the uncertainties and risks in actual surgeries, thereby reducing the surgical failure rate and the incidence of complications. This helps reduce medical costs and improve medical efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] Figure 1 is a flowchart of the cardiac multimodal digital twin simulation method of the present invention;

[0108] Figure 2 is a flowchart of data preprocessing;

[0109] Figure 3 is a flowchart of constructing a multimodal digital twin model;

[0110] Figure 4 is a flowchart of real-time simulation of electrophysiological activities;

[0111] Figure 5 is a flowchart of virtual surgery treatment simulation and planning;

[0112] Figure 6 is a flowchart of dynamic evaluation. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0113] The technical solutions of the present invention will be further described below with reference to the drawings and embodiments.

[0114] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs.

[0115] Embodiment 1

[0116] As Figure 1 shown, it is a flowchart of a cardiac multimodal digital twin simulation method of the present invention, which specifically includes the following steps:

[0117] S1. Collect multimodal data of the heart.

[0118] The multimodal data includes image data, electrophysiological data, and physiological and biochemical data.

[0119] Use advanced medical imaging technologies, such as 320-slice CT and 3.0T MRI, to obtain the cardiac image data of patients. At the same time, electrophysiological data are recorded in real time through an electrocardiogram (ECG) device, and physiological and biochemical data such as blood pressure and blood glucose are collected through continuous monitoring devices. These data will provide the basis for constructing an accurate digital twin model of the heart.

[0120] S2. As Figure 2 shown, preprocess the collected multimodal data to obtain cardiac digital data, including the following steps:

[0121] S21. Perform dimensionality reduction processing and data cleaning on the collected multimodal data to obtain preprocessed data;

[0122] S22. Apply digital signal processing technology to perform low-pass filtering on the preprocessed data to eliminate high-frequency interference and retain important physiological signals;

[0123] S23. Convert the filtered data into digital signals through an analog-to-digital converter (ADC) to provide accurate digital input for subsequent digital twin model construction.

[0124] S3. As Figure 3 shown, construct and optimize a multimodal digital twin model of the heart based on the cardiac digital data, including the following steps:

[0125] S31. Integrate the image data, electrophysiological data, and physiological and biochemical data;

[0126] ;

[0127] Among them, represents the integrated data; represents CT data; represents MRI data; represents ECG data; represents blood pressure data; represents blood glucose data; , , , , all represent weight coefficients, and ;

[0128] S32. Use the back-gating technology to scan the CTA data of the complete heart and perform dynamic modeling according to the cardiac cycle to accurately capture the dynamic changes of the heart;

[0129] ;

[0130] Among them, represents the change in cardiac volume during the cardiac cycle; represents the basic volume; represents the amplitude of the nth harmonic; represents the angular frequency; represents the phase of the nth harmonic;

[0131] S33. Perform customized biomechanical modeling according to the mechanical properties of cardiac tissue, including stress, strain, and Young's modulus;

[0132] ;

[0133] wherein, represents stress; represents Young's modulus; represents strain;

[0134] S34. Construct a multi-modal digital twin model of the heart by integrating geometric structure, electrophysiological properties, and hemodynamic properties;

[0135] ;

[0136] wherein, represents the multi-modal digital twin model; represents the geometric structure; represents the electrophysiological properties; represents the hemodynamic properties;

[0137] ;

[0138] ;

[0139] ;

[0140] wherein, represents the function for constructing the geometric structure according to and ; represents the function for constructing the electrophysiological properties according to and ; represents the function for constructing the hemodynamic properties according to , and ;

[0141] S35. Verify the accuracy of the multi-modal digital twin model by comparing it with actual cardiac data, and optimize the model according to the learning rate and actual cardiac data to obtain an optimized multi-modal digital twin model;

[0142] ;

[0143] Among them, represents the optimized multi-modal digital twin model; represents the learning rate; represents the actual cardiac data.

[0144] S4. As Figure 4 shown, using the optimized multi-modal digital twin model, the Runge-Kutta method is used in combination with the PSO algorithm to perform real-time simulation of the electrophysiological activities of the heart, including the following steps:

[0145] S41. Using the optimized multi-modal digital twin model, initialize the model parameters, including the heart rate , the ion channel characteristics of cardiomyocytes, and the drug concentration , and the ion channel characteristics of cardiomyocytes include sodium channels , calcium channels , and potassium channels ;

[0146] ;

[0147] Among them, represents the initial membrane potential; represents the initial value determined according to the electrophysiological characteristics in the optimized multi-modal digital twin model;

[0148] S42. Define the parameters of the PSO algorithm, including the particle swarm size, inertia weight, individual learning factor, and swarm learning factor;

[0149] Initialize the particle position and velocity, where the position corresponds to the parameters of the electrophysiological model and the velocity corresponds to the change rate of the parameters;

[0150] S43. Define the fitness function, which is used to evaluate the performance of the electrophysiological model parameters represented by each particle, and use the difference between the simulated membrane potential and the actually observed membrane potential as the main evaluation criterion;

[0151] ;

[0152] Among them, represents the fitness function; represents the simulated membrane potential; represents the actually observed membrane potential; represents the number of time points; represents the index of the time point;

[0153] S44. Use the PSO algorithm to iteratively optimize the electrophysiological model parameters until the maximum number of iterations is reached;

[0154] S45. Establish a ventricular myocardial cell model based on ion current, membrane potential, and membrane capacitance;

[0155] ;

[0156] Wherein, represents the ion current; represents the membrane potential; represents the membrane capacitance;

[0157] S46. Use the Runge-Kutta method to simulate the action potential of ventricular myocardial cells and simulate cardiac electrophysiological activities;

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] ;

[0163] Wherein, represents the membrane potential at the th step; , , , represent the parameter changes after PSO optimization; represents the time step;

[0164] S47. Use the parameters optimized by PSO for electrophysiological simulation and analyze the effects of different physiological and pathological conditions on cardiac function;

[0165] ;

[0166] Wherein, , , represent the ion channel conductances optimized by PSO; , , , , , represent the gating variables of the ion channels; , , represent the equilibrium potentials of sodium, calcium, and potassium respectively.

[0167] S5. As Figure 5As shown, based on the optimized multi-modal digital twin model and simulation results, the simulation and planning of virtual heart surgery treatment are carried out, including the following steps:

[0168] S51. Simulate surgical operations on the optimized multi-modal digital twin model;

[0169] ;

[0170] The specific form is as follows:

[0171] ;

[0172] Among them, represents the surgical plan; represents the function of simulating the surgery, represents the surgical parameters, including the incision position and the instrument path; represents the transformation matrix, which adjusts the model according to the surgical parameters ;

[0173] S52. Evaluate the surgical risks by simulating different surgical plans;

[0174] ;

[0175] The specific form is as follows:

[0176] ;

[0177] Among them, represents the surgical risk assessment; represents the risk assessment function; , represents the risk weight; represents the distance from the incision to the nearest critical structure; represents the distance from the instrument path to the nearest critical structure;

[0178] S53. Optimize the parameters in the surgical plan, including the incision position and the instrument operation path, using the PSO algorithm;

[0179] ;

[0180] Among them, represents the optimal surgical parameters; represents the number of iterations; represents the population size;

[0181] S54. Adjust the surgical plan according to the optimization results of the PSO algorithm;

[0182] ;

[0183] The specific form is as follows:

[0184] ;

[0185] Among them, represents the adjusted surgical plan; represents the function for adjusting the surgical plan;

[0186] S55. Use the adjusted surgical plan for simulation verification;

[0187] ;

[0188] The specific form is as follows:

[0189] ;

[0190] Among them, represents the evaluation of surgical effects; represents the function for evaluating effects; , represents the effect weight; represents the blood flow change; represents the electrophysiological change;

[0191] S56. Feed back the evaluation of surgical effects to the optimized multimodal digital twin model;

[0192] ;

[0193] The specific form is as follows:

[0194] ;

[0195] Among them, represents the updated multimodal digital twin model; represents the feedback function; represents the feedback intensity.

[0196] S6. As shown in Figure 6 , perform dynamic evaluation on the multimodal digital twin model and monitor the state changes of the heart in real time, including the following steps:

[0197] S61. The dynamic evaluation module first needs to collect the latest heart data, including real-time imaging data, electrophysiological data, and physiological and biochemical data;

[0198] S62. Compare the real-time collected data with the data in the multimodal digital twin model and analyze the differences between the model and the actual heart state;

[0199] 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;

[0200] S64. During the monitoring process, when any abnormal or data deviating from the normal range is detected, the dynamic evaluation module will issue a warning.

[0201] S65. The results of the dynamic evaluation will be fed back to the multi-modal modeling module and the electrophysiological simulation module. According to the evaluation results, the multi-modal digital twin model will be further optimized to improve the accuracy of the model and the reliability of the simulation.

[0202] Embodiment 2

[0203] A cardiac multi-modal digital twin simulation system, comprising:

[0204] A data acquisition module for acquiring multi-modal data of the heart;

[0205] A data preprocessing module for preprocessing the acquired multi-modal data to obtain cardiac digital data;

[0206] A multi-modal modeling module for constructing and optimizing a multi-modal digital twin model of the heart based on the cardiac digital data;

[0207] An electrophysiological simulation module for using the optimized multi-modal digital twin model to perform real-time simulation of the electrophysiological activities of the heart using the Runge-Kutta method and combined with the PSO algorithm;

[0208] A virtual surgery treatment module for simulating and planning virtual cardiac surgery treatment based on the optimized multi-modal digital twin model and the simulation results;

[0209] A dynamic evaluation module for dynamically evaluating the multi-modal digital twin model and monitoring the state changes of the heart in real time.

[0210] 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, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0211] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0212] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0213] It should be noted that the content not elaborated in detail in the present invention is all prior art and well-known to those skilled in the art.

[0214] Therefore, by adopting the above-mentioned cardiac multi-modal digital twin simulation method, system, electronic device, and medium, the present invention can achieve efficient simulation and real-time monitoring of the cardiac state.

[0215] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements do not cause the modified technical solutions to deviate from the spirit and scope of the technical solutions 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 state changes of the heart in real time; 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 heart data; 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.

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 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.

5. A cardiac multimodal digital twin simulation method according to claim 4, 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.

6. A cardiac multimodal digital twin simulation system, characterized in that: The cardiac multimodal digital twin simulation method according to any one of claims 1 to 5 is implemented, 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.

7. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, it implements the steps of the cardiac multimodal digital twin simulation method described in any one of claims 1-5.

8. 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 5 are implemented.

Images