Bionic pulmonary valve mold generation method and system and electronic equipment

Abstract

The invention relates to the technical field of biomedical engineering, and discloses a bionic pulmonary valve mold generation method and system and electronic equipment, and the method comprises the steps: obtaining a time-varying stress signal of a pulmonary valve; preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal; based on the preprocessed time-varying stress signal, obtaining an effective sampling frequency; based on the effective sampling frequency, curved surface coordinates of the bionic pulmonary valve are obtained; based on the curved surface coordinates, obtaining a macroscopic stress field of the bionic pulmonary valve; based on the macroscopic stress field, the local elastic modulus change rate of the bionic pulmonary valve is obtained; and determining the target bionic pulmonary valve mold based on the action value function and the local elastic modulus ladder change rate. According to the invention, the development period of the mold is shortened, the manufacturing precision is improved, and the personalized applicability of the patient mold is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of biomedical engineering technologies, and particularly to a method, a system, and an electronic device for generating a bionic pulmonary valve mold. Background Art

[0002] Tetralogy of Fallot (TOF) is the most common complex congenital heart disease, accounting for approximately 10% of all complex congenital heart diseases. Generally, the radical resection rate of TOF patients in the first-stage surgery is high and the prognosis is good. However, there are still some patients with hypoplastic pulmonary valve, who need to undergo pulmonary valvuloplasty. It is difficult to avoid pulmonary valve regurgitation in such patients after surgery, which usually occurs in the medium and short term after surgery. In severe cases, it can lead to right heart dysfunction. Some studies have shown that postoperative pulmonary valve regurgitation is an independent risk factor for clinical adverse events such as sudden death and arrhythmia, and is the main reason for the second-stage surgery after the first-stage radical resection of TOF. Delaying the occurrence time of pulmonary valve regurgitation after TOF pulmonary valvuloplasty can significantly improve the quality of life of patients.

[0003] The pulmonary valvuloplasty method is one of the key steps in the surgery for TOF patients with hypoplastic pulmonary valve. Currently, internationally, the Monocusp method or the right ventricular outflow tract valved patch method has been tried for pulmonary valve anatomical reconstruction, but neither can effectively avoid or delay the occurrence of postoperative pulmonary valve regurgitation. Although the above traditional surgical methods can achieve good results in some cases, due to the lack of a pulmonary valve reconstruction mold, the reconstruction effect has a large deviation. The manufacture of the mold often faces problems such as long cycle, high cost, and poor flexibility. Especially when facing personalized molds with complex structures, it is more difficult to achieve fine production, and the individual differences in anatomical structures and physiological characteristics of different patients are often not fully considered. Due to individual anatomical differences, a general mold may lead to poor valve adaptability and insufficient reconstruction function, making it difficult to achieve an ideal anatomical effect. Specifically, when using a general mold for valve repair, there may be poor coordination between the reconstructed valve and the right ventricle, which may further exacerbate the symptoms of valve insufficiency, resulting in postoperative sequelae and even the need for reoperation for repair.

[0004] In view of this, the present invention is specifically proposed. Summary of the Invention

[0005] To solve the above technical problems or at least partially solve the above technical problems, embodiments of the present disclosure provide a method, a system, and an electronic device for generating a bionic pulmonary valve mold, which shorten the development cycle of the mold, improve the manufacturing accuracy, and enhance the applicability of the mold for patient personalization.

[0006] In a first aspect, embodiments of the present disclosure provide a method for generating a bionic pulmonary valve mold, the method comprising:

[0007] Obtaining a time-varying stress signal of the pulmonary valve;

[0008] Preprocess the time-varying stress signal to obtain a preprocessed time-varying stress signal;

[0009] Based on the preprocessed time-varying stress signal, obtain an effective sampling frequency;

[0010] Based on the effective sampling frequency, obtain the surface coordinates of the bionic pulmonary valve;

[0011] Based on the surface coordinates, obtain the macroscopic stress field of the bionic pulmonary valve;

[0012] Based on the macroscopic stress field, obtain the local elastic modulus change rate of the bionic pulmonary valve;

[0013] Based on the action value function and the local elastic modulus gradient, determine the target bionic pulmonary valve mold.

[0014] In a second aspect, an embodiment of the present disclosure further provides a bionic pulmonary valve mold generation system, which includes:

[0015] A signal acquisition module for acquiring the time-varying stress signal of the pulmonary valve;

[0016] A preprocessing module for preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal;

[0017] A frequency acquisition module for obtaining an effective sampling frequency based on the preprocessed time-varying stress signal;

[0018] A coordinate acquisition module for obtaining the surface coordinates of the bionic pulmonary valve based on the effective sampling frequency;

[0019] A stress field acquisition module for obtaining the macroscopic stress field of the bionic pulmonary valve based on the surface coordinates;

[0020] A change rate acquisition module for obtaining the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field;

[0021] A mold acquisition module for determining the target bionic pulmonary valve mold based on the action value function and the local elastic modulus change rate.

[0022] In a third aspect, an embodiment of the present disclosure further provides an electronic device, which includes: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the bionic pulmonary valve mold generation method as described above is implemented.

[0023] In a fourth aspect, embodiments of the present disclosure also provide a machine-readable medium that stores a computer program which, when executed by a processor, implements the bionic pulmonary valve mold generation method described above.

[0024] Embodiments of the present disclosure provide a bionic pulmonary valve mold generation method, system, and electronic device. The method includes: obtaining a time-varying stress signal of the pulmonary valve; preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal; obtaining an effective sampling frequency based on the preprocessed time-varying stress signal; obtaining the curved surface coordinates of the bionic pulmonary valve based on the effective sampling frequency; obtaining the macroscopic stress field of the bionic pulmonary valve based on the curved surface coordinates; obtaining the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field; and determining a target bionic pulmonary valve mold based on the action value function and the local elastic modulus gradient change rate. By preprocessing the time-varying stress signal, the present disclosure improves data integrity and accuracy; further filters the preprocessed time-varying stress signal using a first formula to avoid deviation in subsequent analysis caused by the presence of noise and improve data quality; then obtains the dynamic geometric characteristics of the pulmonary valve using a second formula to avoid model distortion caused by boundary problems, enabling the entire modeling to more realistically reflect the actual geometric characteristics and dynamic behavior of the valve; further optimizes the actual stress state using a third formula and a fourth formula, and finally shortens the mold development cycle, improves manufacturing accuracy, and enhances the applicability of patient mold personalization through the action value function. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and that the original elements and elements are not necessarily drawn to scale.

[0026] Figure 1 It is a flowchart of a bionic pulmonary valve mold generation method in an embodiment of the present disclosure.

[0027] Figure 2 It is a structural schematic diagram of a bionic pulmonary valve mold generation system in an embodiment of the present disclosure.

[0028] Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0031] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0032] In view of the above problems, embodiments of the present disclosure provide a method for generating a bionic pulmonary valve mold, which shortens the development cycle of the mold, improves the manufacturing accuracy, and enhances the applicability of the patient mold personalization.

[0033] Figure 1 It is a flowchart of a method for generating a bionic pulmonary valve mold in the embodiments of the present disclosure. This method can be executed by a bionic pulmonary valve mold generation system, which can be implemented in a software and / or hardware manner and can be configured in an electronic device. As Figure 1 shown, the method can specifically include the following steps:

[0034] S110: Obtain the time-varying stress signal of the pulmonary valve.

[0035] Specifically, the time-varying stress signal of the pulmonary valve can be collected by different technical means or sensors. For example, the time-varying stress signal can be obtained by recording the dynamic stress changes of the valve during the heartbeat cycle through a mechanical sensor; specifically, the dynamic stress of the valve can be directly measured by a microelectromechanical systems (MEMS) sensor array, or the wavelength can be obtained through a fiber Bragg grating (FBG) sensor implanted or attached to the surface of the pulmonary valve, and then the local strain can be reflected through the wavelength shift and converted into a stress signal. In this article, the signal can be an analog signal, a data signal, or any other signal type that can be processed. The data type can be text data, voice data, image data, or any other data type that can be processed.

[0036] S120: Preprocess the time-varying stress signal to obtain a preprocessed time-varying stress signal.

[0037] Preprocessing is to extract biomechanical features with high signal-to-noise ratio and eliminate the mutation values caused by equipment interference or motion artifacts in the time-varying stress signals collected by mechanical sensors.

[0038] Specifically, refer to Table 1: Time (ms) Original stress value Noise / artifact type 0 12.5 Normal 1 13.1 Normal 2 500.0 Motion artifact (mutation) 3 14.2 Normal 4 12.8 Normal 5 13.5 High-frequency noise (jitter)

[0039] In a specific embodiment, preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal includes:

[0040] Performing outlier processing on the time-varying stress signal to obtain a preprocessed time-varying stress signal.

[0041] Specifically, based on the above embodiment, the outlier detected at the 2nd ms in Table 1 can be directly eliminated to obtain the preprocessed time-varying stress signal; or the outlier detected at the 2nd ms in Table 1 can be replaced. For example, the adjacent points of the outlier, that is, the mean value of the previous and subsequent frames (correction value), are used for replacement. The correction value = (13.1 + 14.2) / 2 = 13.65 kPa. The set of the replaced time-varying stress signal and the original normal time-varying stress signal is used as the preprocessed time-varying stress signal.

[0042] S130: Based on the preprocessed time-varying stress signal, obtain the effective sampling frequency.

[0043] Exemplarily, the frequency components of the preprocessed time-varying stress signal may change with time (such as the high-frequency transients caused by the opening and closing of valves in the cardiac cycle). The frequency may cause oversampling (wasting resources), fixed sampling, or undersampling. It can be dynamically calculated by a formula to adapt to the instantaneous characteristics of the signal (such as noise level, attenuation rate), thereby optimizing the sampling efficiency. For example, the time-varying stress signal can be preprocessed by the first formula to obtain the effective sampling frequency.

[0044] In a specific embodiment, the first formula is used to process the preprocessed time-varying stress signal to obtain the effective sampling frequency. The expression of the first formula is:

[0045]

[0046] Wherein, represents the effective sampling frequency, represents the time period between any two time points of the preprocessed time-varying stress signal, represents the sampling time, represents the preprocessed time-varying stress signal, represents the baseline noise, represents the signal sensitivity coefficient, represents the time decay factor, Represents the time points of the preprocessed time-varying stress signal.

[0047] Specifically, the response time of the quantum dot sensor limits the maximum available sampling rate of the system ( <\[1 / \ \]). The first formula normalizes the signal to frequency by . In the first formula, the original signal (i.e., the preprocessed time-varying stress signal) is subjected to baseline noise removal , linear compression and time-domain attenuation and other operations, aiming to suppress noise and extract the effective components of the signal.

[0048] In this embodiment, by processing the preprocessed time-varying stress signal and using the arctangent function to process the stress signal, it is like filtering a layer of impurities from the data, successfully eliminating the interference caused by baseline noise . This can make the data more pure, avoid deviations in subsequent analysis due to the existence of noise, and improve the data quality. Using the signal sensitivity coefficient and the time attenuation factor to reduce the influence of noise, further improve the reliability of the signal, adding a layer of protection to the signal, so that the subsequent research on the signal can more accurately reflect the real situation, providing a solid data guarantee for the smooth progress of the subsequent steps.

[0049] S140: Based on the effective sampling frequency, obtain the curved surface coordinates of the bionic pulmonary valve.

[0050] Furthermore, on the basis of the above embodiment, relevant formulas and parameters can be used to fully consider the influence of various factors such as curvature, spatial attenuation, and boundary effects on the valve shape, so that the model can finely present the curved surface changes of the valve under different physiological states such as different cardiac cycles, providing a key basis for subsequent analysis of the relationship between the mold shape and stress, etc. and optimizing the geometric design of the mold.

[0051] In a specific embodiment, the second formula is used to process the effective sampling frequency to obtain the curved surface coordinates of the bionic pulmonary valve, where the expression of the second formula is:

[0052]

[0053] Among them, represents the curved surface coordinates of the bionic pulmonary valve, used to describe the geometric shape changes of the valve at different positions and times, represents the time points of the preprocessed time-varying stress signal, used to describe the dynamic state of the valve at different time points, represents the curvature coupling coefficient, Indicates the slope at a local position on the surface , Indicates the cardiac angular frequency Indicates the spatial attenuation weight Indicates the local position of the surface, i.e., the spatial position or the coordinates or position of the valve surface along a specific spatial direction Indicates the boundary effect suppression factor

[0054] The second formula characterizes the dynamic changes of the valve surface. The parameters and As coupling coefficients, they respectively represent the influence of curvature and the effect of spatial attenuation Indicates the cardiac angular frequency, which affects the motion pattern of the valve Is used to suppress the perturbation caused by the boundary effect. Therefore, through the parameters and Respectively reflect the influence of curvature and the effect of spatial attenuation, enabling the modeling to meticulously depict the morphological changes of the valve under different physiological states. Introducing the cardiac angular frequency To affect the motion pattern of the valve, which enables the model to capture the complex motion details of the valve during the cardiac cycle. It helps to more accurately simulate the motion of the valve in the real human body environment. Using the boundary effect suppression factor To suppress the perturbation caused by the boundary effect, ensuring the stability and accuracy of the model in the boundary region. Avoiding model distortion caused by boundary problems, enabling the entire modeling to more realistically reflect the actual geometric characteristics and dynamic behavior of the valve

[0055] In this embodiment, by dynamically adjusting the three-dimensional dynamic geometric model of the valve, the morphological changes of the valve during the cardiac cycle are simulated, and the geometric morphological characteristics of the valve at different physiological stages are predicted. Optimize the model to adjust the shape and size of the mold, so that the manufactured bionic valve is more in line with the human anatomical characteristics and physiological movement laws in terms of geometric structure, ensuring that it can work in coordination with the surrounding tissue organs after implantation and reducing the risk of complications caused by shape mismatch

[0056] S150: Based on the surface coordinates, obtain the macroscopic stress field of the bionic pulmonary valve

[0057] Exemplarily, on the basis of the above embodiment, the bond potential energy of the th molecule , the local strain rate of the th molecule and the strain rate threshold Act together to promote the calculation of the effective stress. At the same time, the additional scale coupling coefficient λ and the microscopic stress critical value Further enhanced the applicability of the model. Thus, it linked the stress transfer at the molecular level with the macroscopic stress field, bridging the communication between the microscopic world and the macroscopic world, enabling the understanding of the generation and distribution laws of macroscopic stress from the microscopic molecular level, and comprehensively considering the bond potential energy of the th molecule , the local strain rate of the th molecule and the strain rate threshold

[0058] and other factors, and was able to accurately calculate the effective stress.

[0058] In a specific embodiment, the third formula is used to process the surface coordinates to obtain the macroscopic stress field of the bionic pulmonary valve, where the expression of the third formula is:

[0059]

[0060] wherein, represents the macroscopic stress field of the bionic pulmonary valve, represents the maximum value of , represents the change rate of the bond potential energy of the th molecule, represents the bond potential energy of the th molecule, represents the local strain rate, represents the local position of the surface, that is, the spatial position or the coordinates or position of the valve surface along a specific spatial direction, represents the strain rate threshold, represents the scale coupling coefficient,

[0061] This embodiment guides the selection of die materials and the structural design by using these laws, ensuring that the performance of the material at the microscopic level can meet the macroscopic mechanical requirements, improving the durability and reliability of the bionic valve, and ensuring that it can withstand a complex physiological stress environment during long-term use without damage or functional degradation.

[0062] S160: Based on the macroscopic stress field, obtain the local elastic modulus change rate of the bionic pulmonary valve.

[0063] Specifically, the local elastic modulus can be intelligently regulated by the light intensity distribution to achieve dynamic changes in the properties of the mold material in space and time. In the practical application of the bionic pulmonary valve forming mold, according to the mechanical requirements of different regions of the pulmonary valve, the elastic modulus of the mold material can be precisely adjusted by controlling the light intensity distribution, so that the flexibility and strength of each part of the manufactured valve reach the best balance, better simulating the mechanical response characteristics of the real pulmonary valve and enhancing its opening and closing functions and blood compatibility in blood circulation.

[0064] In a specific embodiment, the fourth formula is used to process the macroscopic stress field to obtain the change rate of the local elastic modulus of the bionic pulmonary valve. The expression of the fourth formula is as follows:

[0065]

[0066] Wherein, represents the change rate of the local elastic modulus of the bionic pulmonary valve, represents the energy diffusion coefficient, represents the gradient symbol, represents the local elastic modulus, represents the light response gain, represents the non-linear saturation factor, represents the light intensity distribution, represents the characteristic length of the mold.

[0067] The embodiments of the present disclosure describe the relationship between the local elastic modulus and the light intensity distribution, etc. through partial differential equations, and can accurately control the distribution of the properties such as the elastic modulus of the mold material in space and time according to different lighting conditions, so that the mechanical properties of the mold better meet the requirements of the actual pulmonary valve in different physiological scenarios, so as to achieve the effect of optimizing the mold performance. Describing the local elastic modulus through partial differential equations Based on the light intensity distribution of the dynamic change, the intelligent regulation of the material properties can be realized, so that it can automatically adjust its own elastic modulus according to different lighting conditions to meet different use requirements and mechanical environments. The energy diffusion coefficient represents the energy transfer efficiency in the material. By accurately describing and utilizing it, the efficient transfer and distribution of energy in the material can be ensured, so that the material can better play its due function and improve the use efficiency and effect of the material. Introducing the light response gain and the non-linear saturation factor involves the non-linear characteristics of the light response, and can accurately describe the non-linear response behavior of the material under different light intensities, providing more possibilities for the optimized design of the pulmonary valve forming mold.

[0068] S170: Determine the target bionic pulmonary valve mold based on the action value function and the local elastic modulus change rate.

[0069] Specifically, the action value function and the comprehensive consideration of the state and action can be adopted, combined with information such as the gradient of the objective function, to be able to adjust the optimization direction and strategy in real time according to the feedback during the optimization process, ensuring that the finally obtained mold optimization scheme reaches the optimal state under the requirements of various performance indicators, and further improving the performance and applicability of the mold.

[0070] In a specific embodiment, determining the target bionic pulmonary valve mold based on the action value function and the local elastic modulus change rate includes: determining the action value at the th iteration based on the action value function and the local elastic modulus change rate;

[0071] When the difference between the action value at the th iteration and the action value at the th iteration is the smallest, determine the mold parameters;

[0072] Determine the target bionic pulmonary valve mold based on the mold parameters.

[0073] Among them, the expression of the action value function is:

[0074]

[0075] Among them, represents the action value at the th iteration, represents the action value at the th iteration, represents the stress state vector, represents the action space vector, represents the gradient of the objective function, represents the learning rate, represents the immediate reward, with a value of 1, 0, or -1, represents the maximum expected value at the next moment, represents the stress state vector at the next moment, represents the action space vector at the next moment.

[0076] Among them, =1 means that when a certain action is executed, the system performs well, meets or approaches the expected goal, for example, when the valve shape and stress state reach the ideal values. It represents "reward" or "positive feedback".

[0077] = 0 indicates that when the action is neither significantly superior nor significantly inferior, without any particular good or bad performance, such as when the system state is stable, without significant improvement or deterioration, it belongs to a neutral or non-feedback situation.

[0078] =-1 indicates that after performing a certain action, the system performs poorly and deviates from the target. For example, the valve stress is abnormal or the morphological deviation is large, and it receives "punishment" or "negative feedback".

[0079] Exemplarily, the difference between the action value at the (k + 1)-th iteration and the action value at the k-th iteration is determined through the action value function and the local elastic modulus change rate, and the difference is continuously adjusted and optimized until it is minimized to obtain the die parameters (i.e., the stress state vector and the action space vector ).

[0080] In this embodiment, the optimization of the stress state vector and the action space vector can be guided by the gradient of the objective function , and at the same time, the boundary effect suppression factor (i.e., the discount factor) γ is combined to balance the long-term and short-term benefits, avoiding the optimization deviation caused by the system only pursuing immediate interests or over-focusing on long-term goals during the optimization process. This enables the system to consider short-term benefits while taking into account long-term development, ensuring the comprehensiveness and sustainability of the optimization results.

[0081] In summary, the embodiments of the present disclosure provide a method, system, and electronic device for generating a bionic pulmonary valve mold. The method includes: obtaining the time-varying stress signal of the pulmonary valve; preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal; obtaining an effective sampling frequency based on the preprocessed time-varying stress signal; obtaining the surface coordinates of the bionic pulmonary valve based on the effective sampling frequency; obtaining the macroscopic stress field of the bionic pulmonary valve based on the surface coordinates; obtaining the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field; and determining the target bionic pulmonary valve mold based on the action value function and the local elastic modulus gradient change rate. The present disclosure preprocesses the time-varying stress signal to improve data integrity and accuracy; further filters the preprocessed time-varying stress signal through the first formula to avoid deviation in subsequent analysis caused by the existence of noise and improve data quality; then obtains the dynamic geometric characteristics of the pulmonary valve through the second formula, avoiding model distortion caused by boundary problems, enabling the entire modeling to more realistically reflect the actual geometric characteristics and dynamic behavior of the valve; further optimizes the actual stress state using the third formula and the fourth formula, and finally shortens the development cycle of the mold, improves manufacturing accuracy, and enhances the applicability of the mold to patient personalization through the action value function.

[0082] Figure 2Schematic diagram of the structure of the bionic pulmonary valve mold generation system in the embodiments of the present disclosure. As Figure 2 shown, the system includes a signal acquisition module 210, a preprocessing module 220, a frequency acquisition module 230, a coordinate acquisition module 240, a stress field acquisition module 250, a change rate acquisition module 260, and a mold acquisition module 270.

[0083] The signal acquisition module 210 is configured to acquire the time-varying stress signal of the pulmonary valve.

[0084] The preprocessing module 220 is configured to preprocess the time-varying stress signal to obtain a preprocessed time-varying stress signal.

[0085] The frequency acquisition module 230 is configured to obtain an effective sampling frequency based on the preprocessed time-varying stress signal.

[0086] The coordinate acquisition module 240 is configured to obtain the surface coordinates of the bionic pulmonary valve based on the effective sampling frequency.

[0087] The stress field acquisition module 250 is configured to obtain the macroscopic stress field of the bionic pulmonary valve based on the surface coordinates.

[0088] The change rate acquisition module 260 is configured to obtain the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field.

[0089] The mold acquisition module 270 is configured to determine the target bionic pulmonary valve mold based on the action value function and the local elastic modulus gradient.

[0090] In an alternative embodiment, the preprocessing module 220 is further configured to perform outlier processing on the time-varying stress signal to obtain a preprocessed time-varying stress signal.

[0091] In an alternative embodiment, the frequency acquisition module 230 is further configured to process the preprocessed time-varying stress signal using a first formula to obtain an effective sampling frequency, where the expression of the first formula is:

[0092]

[0093] where represents the effective sampling frequency, represents the time period between any two time points of the preprocessed time-varying stress signal, represents the sampling time, represents the preprocessed time-varying stress signal, represents the baseline noise, represents the signal sensitivity coefficient, represents the time decay factor, represents the time point of the preprocessed time-varying stress signal.

[0094] In an alternative embodiment, the coordinate acquisition module 240 is further configured to process the effective sampling frequency using a second formula to obtain the curved surface coordinates of the bionic pulmonary valve, where the expression of the second formula is:

[0095]

[0096] where, represents the curved surface coordinates of the bionic pulmonary valve, which are used to describe the geometric shape changes of the valve at different positions and times, represents the time point for preprocessing the time-varying stress signal, which is used to describe the dynamic state of the valve at different time points, represents the curvature coupling coefficient, represents at the local position of the curved surface the slope at, represents the cardiac angular frequency, represents the spatial attenuation weight, represents the local position of the curved surface, that is, the spatial position or the coordinates or position of the valve curved surface along a specific spatial direction, represents the boundary effect suppression factor.

[0097] In an alternative embodiment, the stress field acquisition module 250 is further configured to process the curved surface coordinates using a third formula to obtain the macroscopic stress field of the bionic pulmonary valve, where the expression of the third formula is:

[0098]

[0099] where, represents the macroscopic stress field of the bionic pulmonary valve, represents the maximum value of, represents the change rate of the bond potential energy of the th molecule, represents the bond potential energy of the th molecule, represents the local position of the curved surface, that is, the spatial position or the coordinates or position of the valve curved surface along a specific spatial direction, represents the th molecule's local strain rate, represents the strain rate threshold, represents the scale coupling coefficient, represents the microscopic stress critical value.

[0100] In an optional embodiment, the change rate acquisition module 260 is further configured to process the macroscopic stress field using a fourth formula to obtain a change rate of the local elastic modulus of the bionic pulmonary valve, wherein the fourth formula is expressed as:

[0101]

[0102] in, represents the rate of change of the local elastic modulus of the bionic pulmonary valve, represents the energy diffusion coefficient, represents the gradient symbol, represents the local elastic modulus, represents the photoresponse gain, represents the nonlinear saturation factor, represents the light intensity distribution, Indicates the characteristic length of the mold.

[0103] In an optional embodiment, the mold acquisition module 270 is further configured to determine the first The action value at the iteration;

[0104] When The action value at the iteration When the difference of action values in the iteration is the smallest, the mold parameters are determined;

[0105] Based on the mold parameters, a target bionic pulmonary valve mold is determined.

[0106] The expression of the action value function is:

[0107]

[0108] in, Indicates the The action value at the iteration, Indicates the The action value at the iteration, represents the stress state vector, represents the action space vector, represents the objective function gradient, represents the learning rate, Indicates instant reward, the value is 1, 0 or -1, represents the maximum expected value at the next moment, represents the stress state vector at the next moment, Represents the action space vector at the next moment.

[0109] in, =1 indicates that when a certain action is performed, the system performs well and meets or approaches the desired goal. For example, when the valve morphology and stress state reach the ideal values. It represents "reward" or "positive feedback".

[0110] =0 indicates that when the action is neither significantly better nor significantly worse, and there is no particularly good or bad performance. For example, when the system state is stable and there is no significant improvement or deterioration, it belongs to a neutral or no-feedback situation.

[0111] =-1 indicates that when a certain action is performed, the system performs poorly and deviates from the goal. For example, when the valve stress is abnormal or the morphology deviation is large, it receives "punishment" or "negative feedback".

[0112] An artificial pulmonary valve mold generation system provided by an embodiment of the present disclosure can execute the steps in an artificial pulmonary valve mold generation method provided by the method embodiment of the present disclosure, and has the execution steps and beneficial effects, which will not be elaborated here.

[0113] Figure 3 It is a schematic structural diagram of an electronic device in an embodiment of the present disclosure. Specifically refer to Figure 3 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing the present disclosure. Figure 3 The shown electronic device is only an example and should not bring any restrictions to the functions and usage scopes of the embodiments of the present disclosure.

[0114] As Figure 3 shown, the electronic device 500 may include a processing device 501, a ROM 502, a RAM 503, a bus 504, an input / output (I / O) interface 505, an input device 506, an output device 507, a storage device 508, and a communication device 509. The processing device (such as a central processing unit, a graphics processing unit, etc.) �01 can execute various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 into the random access memory (RAM) 503 to implement an artificial pulmonary valve mold generation method as described in the embodiments of the present disclosure. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0115] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a non-transitory computer-readable medium. The computer program contains program code for performing the methods shown in the flowcharts, thereby implementing a method for generating a bionic pulmonary valve mold as described above. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, the above functions defined in the methods of the embodiments of the present disclosure are performed.

[0116] It should be noted that the computer-readable medium described above in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0117] The above computer-readable medium may be included in the above electronic device; or it may exist separately and not be assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to: obtain a time-varying stress signal of the pulmonary valve; preprocess the time-varying stress signal to obtain a preprocessed time-varying stress signal; obtain an effective sampling frequency based on the preprocessed time-varying stress signal; obtain the surface coordinates of the bionic pulmonary valve based on the effective sampling frequency; obtain the macroscopic stress field of the bionic pulmonary valve based on the surface coordinates; obtain the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field; and determine a target bionic pulmonary valve mold based on the action value function and the local elastic modulus gradient.

[0118] Optionally, when the one or more programs are executed by the electronic device, the electronic device may also perform the other steps described in the above embodiments.

[0119] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, a technical solution formed by mutually replacing the above features with (but not limited to) technical features having similar functions disclosed in the present disclosure.

Claims

1. A method for generating a bionic pulmonary valve mold, characterized in that The method for generating the bionic pulmonary valve mold includes: Obtaining the time-varying stress signal of the pulmonary valve; Preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal; Based on the preprocessed time-varying stress signal, obtaining the effective sampling frequency; Based on the effective sampling frequency, obtaining the surface coordinates of the bionic pulmonary valve; Based on the surface coordinates, obtaining the macroscopic stress field of the bionic pulmonary valve; Based on the macroscopic stress field, obtaining the local elastic modulus change rate of the bionic pulmonary valve; Based on the action value function and the local elastic modulus change rate, determining the target bionic pulmonary valve mold.

2. The method for generating a bionic pulmonary valve mold according to claim 1, wherein Preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal, including: Performing outlier processing on the time-varying stress signal to obtain a preprocessed time-varying stress signal.

3. The method for generating a bionic pulmonary valve mold according to claim 2, wherein Based on the preprocessed time-varying stress signal, obtaining the effective sampling frequency, including: Processing the preprocessed time-varying stress signal using a first formula to obtain the effective sampling frequency, where the expression of the first formula is: ； Among them, represents the effective sampling frequency, represents the time period between any two time points of the preprocessed time-varying stress signals, represents the sampling time, represents the preprocessed time-varying stress signal, represents the baseline noise, represents the signal sensitivity coefficient, represents the time decay factor, represents the time point of the preprocessed time-varying stress signal.

4. The method for generating a bionic pulmonary valve mold according to claim 3, wherein Based on the effective sampling frequency, obtaining the surface coordinates of the bionic pulmonary valve, including: Processing the effective sampling frequency using a second formula to obtain the surface coordinates of the bionic pulmonary valve, where the expression of the second formula is: ； Among them, represents the curved surface coordinates of the bionic pulmonary valve, which are used to describe the geometric shape changes of the valve at different positions and times. represents the time point for preprocessing the time-varying stress signal, which is used to describe the dynamic state of the valve at different time points. represents the curvature coupling coefficient. represents at the local position of the curved surface the slope at the position. represents the cardiac angular frequency. represents the spatial attenuation weight. represents the local position of the curved surface, that is, the spatial position or the coordinates or position of the valve curved surface along a specific spatial direction. represents the boundary effect suppression factor.

5. The method for generating a bionic pulmonary valve mold according to claim 4, wherein Based on the surface coordinates, obtaining the macroscopic stress field of the bionic pulmonary valve, including: Processing the surface coordinates using a third formula to obtain the macroscopic stress field of the bionic pulmonary valve, where the expression of the third formula is: ； Among them, represents the macroscopic stress field of the bionic pulmonary valve, represents the maximum value of represents the change rate of the bond potential energy of the th molecule, represents the th molecule's bond potential energy, represents the local strain rate, represents the local position of the surface, that is, the spatial position or the coordinates or position of the valve surface along a specific spatial direction, represents the th molecule's local strain rate, represents the strain rate threshold, represents the scale coupling coefficient, represents the microscopic stress critical value.

6. The method for generating a bionic pulmonary valve mold according to claim 5, wherein Based on the macroscopic stress field, obtaining the local elastic modulus change rate of the bionic pulmonary valve, including: Processing the macroscopic stress field using a fourth formula to obtain the local elastic modulus change rate of the bionic pulmonary valve, where the expression of the fourth formula is: ； Among them, represents the local elastic modulus change rate of the bionic pulmonary valve, represents the energy diffusion coefficient, represents the gradient symbol, represents the local elastic modulus, represents the light response gain, represents the non-linear saturation factor, represents the light intensity distribution, represents the characteristic length of the mold.

7. The method for generating a bionic pulmonary valve mold according to claim 5, wherein, The expression of the action value function is: ； Among them, represents the action value at the -th iteration, represents the action value at the -th iteration, represents the stress state vector, represents the action space vector, represents the gradient of the objective function, represents the learning rate, represents the immediate reward, with a value of 1, 0, or -1, represents the maximum expected value at the next moment, represents the stress state vector at the next moment, represents the action space vector at the next moment.

8. The method for generating a bionic pulmonary valve mold according to claim 7, wherein Based on the action value function and the local elastic modulus change rate, determining the target bionic pulmonary valve mold, including: Determine the action value at the th iteration based on the action value function and the local elastic modulus change rate; When the difference between the action value at the -th iteration and the action value at the -th iteration is minimized, the die parameters are determined; Based on the mold parameters, determining the target bionic pulmonary valve mold.

9. A bionic pulmonary valve mold generation system, characterized in that The bionic pulmonary valve mold generation system includes: A signal acquisition module for obtaining the time-varying stress signal of the pulmonary valve; A preprocessing module for preprocessing the time-varying stress signal to obtain a preprocessed time-varying stress signal; A frequency acquisition module for obtaining the effective sampling frequency based on the preprocessed time-varying stress signal; A coordinate acquisition module for obtaining the surface coordinates of the bionic pulmonary valve based on the effective sampling frequency; A stress field acquisition module for obtaining the macroscopic stress field of the bionic pulmonary valve based on the surface coordinates; A change rate acquisition module for obtaining the local elastic modulus change rate of the bionic pulmonary valve based on the macroscopic stress field; A mold acquisition module for determining the target bionic pulmonary valve mold based on the action value function and the local elastic modulus gradient.

10. An electronic device, the electronic device includes: One or more processors; A storage device, the storage device is used to store one or more programs, Wherein, when the one or more programs are executed by the one or more processors, a method for generating a bionic pulmonary valve mold according to any one of claims 1-7 is implemented.

Images