Method and system for simulating the process of necrotizing fasciitis based on an animal model

Abstract

The present invention discloses a method and system for simulating the process of necrotizing fasciitis based on an animal model. The method includes animal model selection, infection experiment design, experimental data collection, simulation system construction, and simulation of the process of necrotizing fasciitis. The present invention relates to the technical field of simulating the process of necrotizing fasciitis, specifically a method and system for simulating the process of necrotizing fasciitis based on an animal model. This solution uses an experimental analysis method of necrotizing fasciitis based on an animal model for pre-experiment preparation of interference process simulation; uses a method of multi-modal fusion by combining artificial features and slice image features for data preprocessing; uses a deep neural network method combined with an improved infection process modeling for the construction of the simulation system, providing certain support and exploration for the research direction of necrotizing fasciitis.

Description

Technical Field

[0001] The present invention relates to the technical field of necrotizing fasciitis process simulation, and specifically refers to a method and system for simulating the necrotizing fasciitis process based on an animal model. Background Art

[0002] The method for simulating the necrotizing fasciitis process based on an animal model is a technology that uses experimental animals to simulate and study this severe infectious disease of necrotizing fasciitis. By inducing a similar pathological process of human necrotizing fasciitis in animals, researchers can observe in detail the progression of the disease, immune response, pathological changes, and treatment effects. The main function of this method is to help scientists understand the pathological mechanism of the disease, evaluate the effectiveness of new drugs and treatment strategies, and provide theoretical support and experimental basis for clinical applications.

[0003] However, in the existing methods for simulating the necrotizing fasciitis process, there are technical problems that the traditional research and analysis process of necrotizing fasciitis relies on human pathogen analysis, which leads to scarce experimental data and increases the difficulty of analysis; in the existing methods for simulating the necrotizing fasciitis process, there is a technical problem that the data characteristics of the process simulation are complex and diverse, so it relies on a good data preprocessing process; in the existing methods for simulating the necrotizing fasciitis process, there are technical problems that the complexity of the process simulation of necrotizing fasciitis is relatively high and the prediction indicators involved are difficult to set, which increases the technical difficulty and is also difficult to effectively combine and experiment with the animal model. Summary of the Invention

[0004] In view of the above situation, to overcome the defects of the prior art, the present invention provides a method and system for simulating the process of necrotizing fasciitis based on an animal model. In the existing methods for simulating the process of necrotizing fasciitis, the traditional research and analysis process of necrotizing fasciitis relies on human pathogen analysis, which leads to scarce experimental data and increases the difficulty of analysis. This solution creatively uses an experimental analysis method for necrotizing fasciitis based on an animal model for pre-experimental preparation of interference process simulation. By selecting mice as the modeling animals, the quantity and quality of experimental data for necrotizing fasciitis are improved, providing good data support for subsequent research and practice. In the existing methods for simulating the process of necrotizing fasciitis, the data characteristics of the process simulation are complex and diverse, so a good data preprocessing process is relied on. This solution creatively uses a method of multi-modal fusion combining artificial features and slice image features for data preprocessing, providing a better data source for subsequent model prediction. In the existing methods for simulating the process of necrotizing fasciitis, the process simulation of necrotizing fasciitis is highly complex and the prediction indicators involved are difficult to set, increasing the technical difficulty and making it difficult to effectively combine with the animal model for experiments. This solution creatively uses a method of combining a deep neural network method for improving infection process modeling to construct a simulation system. By screening and setting parameter combinations of prediction targets through infection process modeling, and then combining specific experiments and parameter combinations of the animal model for subsequent model improvement and loss function design, it helps to study the pathogenesis and treatment plan of necrotizing fasciitis through animal experiments, providing certain support and exploration for the research direction of necrotizing fasciitis.

[0005] The technical solution adopted by the present invention is as follows: The method for simulating the process of necrotizing fasciitis based on an animal model provided by the present invention includes the following steps:

[0006] Step S1: Selection of animal model;

[0007] Step S2: Design of infection experiment;

[0008] Step S3: Collection of experimental data;

[0009] Step S4: Construction of simulation system;

[0010] Step S5: Simulation of the process of necrotizing fasciitis.

[0011] Further, in step S1, the selection of the animal model is used to select an appropriate animal model for the research on simulating the process of necrotizing fasciitis. Specifically, a mouse animal model is selected for the process simulation experiment, and through strain extraction and culture, animal grouping and animal model construction are carried out to obtain an animal model for simulating the process of necrotizing fasciitis;

[0012] The animal model for simulating the necrotizing fasciitis process specifically includes experimental animal grouping data, bacterial suspension preparation data, and basic model data.

[0013] Furthermore, in step S2, the infection experiment design is used to select the pathogen of necrotizing fasciitis for the infection experiment. Specifically, an infection experiment environment is constructed and the necrotizing fasciitis infection process experiment is carried out, and through pathological analysis, resonance examination, and post-processing, the infection experiment process data is obtained, which specifically includes the following steps:

[0014] Step S21: Process experiment. Specifically, based on the animal model for simulating the necrotizing fasciitis process, the necrotizing fasciitis infection process experiment is carried out to obtain the original experimental data.

[0015] Step S22: Histopathological analysis of the infected tissue. Specifically, mice at the time period with the most obvious infection are modeled and the histopathological analysis of the infected tissue is carried out to obtain the histopathological analysis data set.

[0016] Step S23: Magnetic resonance examination of the infection focus in mice. Specifically, the infected mice are anesthetized and magnetic resonance examination is carried out, and imaging analysis of key parts is carried out to obtain the magnetic resonance detection data.

[0017] Step S24: Collection of infection experiment process data. Specifically, combining the original experimental data, the scanning analysis experimental data, and the magnetic resonance detection data, the infection experiment process data is obtained.

[0018] Furthermore, in step S3, the experimental data collection is used to collect the basic data required by the necrotizing fasciitis process simulation system and perform data optimization and enhancement. Specifically, based on the data in the animal model for simulating the necrotizing fasciitis process and the infection experiment process data, through experimental data collection, the original process simulation data is obtained, and the original process simulation data is preprocessed to obtain the optimized process simulation data.

[0019] The steps of the experimental data collection and data preprocessing include:

[0020] Step S31: Experimental data collection. Specifically, from the infection experiment process data, the original data set required for simulating the necrotizing fasciitis process is collected to obtain the original process simulation data.

[0021] Step S32: Data integrity check. Specifically, the missing, duplicate, and outlier detection is carried out on the original process simulation data to obtain the integrity check data set.

[0022] Step S33: Outlier processing. Specifically, the outliers in the integrity check data set are filled by the Z-score filling method to obtain the outlier processing data set.

[0023] Step S34: Slice feature extraction. Specifically, a standard convolutional neural network is used to extract the features of the slice images from the scan analysis experimental data in the original process simulation data, obtaining slice feature data;

[0024] Step S35: Numerical data feature extraction. Specifically, an artificial feature extraction method is used to extract artificial features of the numerical data from the abnormal processing data set, obtaining numerical feature data;

[0025] Step S36: Multi-modal feature fusion. Specifically, by performing feature selection and feature fusion on the slice feature data and the numerical feature data, integrated necrotizing fasciitis process simulation feature data is obtained;

[0026] Step S37: Data integration. Specifically, the integrated necrotizing fasciitis process simulation feature data is integrated to obtain process simulation optimized data.

[0027] Furthermore, in step S4, the simulation system construction is used for the design of the necrotizing fasciitis process simulation system. Specifically, based on the process simulation optimized data, a deep neural network method combined with improved infection process modeling is used to construct the simulation system, obtaining a necrotizing fasciitis process simulation model;

[0028] The deep neural network combined with improved infection process modeling specifically includes an infection process module, a neural ordinary differential equation solver, a basic deep neural network subnet, and a process combination optimization loss function;

[0029] The infection process module is used to generate relevant parameters for the necrotizing fasciitis process simulation by segmenting the infection process and set the target combination of prediction parameters for the process simulation;

[0030] The neural ordinary differential equation solver is used to enhance the fitting performance of the deep neural network model for the necrotizing fasciitis process simulation;

[0031] The basic deep neural network subnet is used as the basic prediction subnet for the necrotizing fasciitis process simulation;

[0032] The process combination optimization loss function is used to improve the model performance by minimizing the loss;

[0033] The steps of using the deep neural network method combined with improved infection process modeling to construct the simulation system and obtain the necrotizing fasciitis process simulation model include:

[0034] Step S41: Construct the infection process module. Specifically, perform infection process modeling to obtain the parameter combination of the infection process model, and use the parameter combination of the infection process model as the infection process module. The calculation formula is: ;

[0035] In the formula, is the parameter combination of the infection process model, used to represent the infection process module, is the infection transmission rate parameter, used to represent the transmission rate of the pathogen of necrotizing fasciitis, W is the weight parameter of the basic subnet of the deep neural network, is the incubation period rate parameter, used to represent the time rate of contacting the pathogen and starting to be infected, is the tissue destruction rate parameter, used to represent the rate of the infection developing to tissue destruction, is the treatment success rate parameter, used to represent the rate of the infected person recovering after receiving treatment, is the disease deterioration rate parameter, used to represent the rate of the infection changing from the early stage to a more severe stage, is the mortality rate parameter, used to represent the mortality rate caused by necrotizing fasciitis not being treated in time;

[0036] Step S42: Construct a neural ordinary differential solver. Specifically, through the neural ordinary differential solver, calculate the vector representation of the necrotizing fasciitis process simulation according to the time step. The calculation formula is: ;

[0037] In the formula, Z(t + 1) is the vector representation of the necrotizing fasciitis process simulation at time t + 1, t is the time step index, f(·) is the neural network identification function, specifically referring to the deep neural network, Z(t) is the vector representation of the necrotizing fasciitis process simulation at time t, is the parameter combination of the infection process model at time t, and W is the weight parameter of the basic subnet of the deep neural network;

[0038] Step S43: Construct the basic subnet of the deep neural network. Specifically, construct the basic subnet of the deep neural network including the input layer, hidden layer and output layer, and improve the hidden layer by combining the infection process module and the neural ordinary differential solver to construct the basic subnet of the deep neural network;

[0039] Step S44: Construct a process combination optimization loss function for optimizing the overall loss of the model by combining the infection process module. The calculation formula is: ;

[0040] In the formula, L is the process combination optimization loss function, T is the total number of time steps, t is the time step index, min is the function for obtaining the minimum value, is the parameter combination of the infection process model, and X t is the real data, used to represent the real data obtained from the experiment before the necrotizing fasciitis process simulation, is the predicted data, which is used to represent the predicted data obtained from the necrotizing fasciitis process simulation model, I t is the total number of actual treatments, is the total number of predicted treatments, CR t is the total number of actual deteriorations, is the total number of predicted deteriorations, D t is the total number of actual deaths, is the total number of predicted deaths;

[0041] Step S45: Training of the necrotizing fasciitis process simulation model, specifically, by constructing the infection process module, the neural ordinary differential equation solver, the basic subnet of the deep neural network, and the process combination optimization loss function, model training is carried out to obtain the necrotizing fasciitis process simulation model Model NF 。

[0042] Furthermore, in step S5, the necrotizing fasciitis process simulation is used to simulate the necrotizing fasciitis process by combining animal model experimental data and a deep learning model. Specifically, the necrotizing fasciitis process simulation model is used to perform a necrotizing fasciitis process simulation based on the animal model to obtain necrotizing fasciitis process simulation prediction data;

[0043] The necrotizing fasciitis process simulation prediction data specifically refers to the data of the change of the predicted infection process model parameter combination with the time step.

[0044] The system for simulating the necrotizing fasciitis process based on an animal model provided by the present invention includes an infection experiment module, a data collection module, a simulation construction module, and a process simulation module;

[0045] The infection experiment module is used to select an animal model and design an infection experiment. Through the selection of the animal model and the design of the infection experiment, a necrotizing fasciitis process simulation animal model and infection experiment process data are obtained, and the necrotizing fasciitis process simulation animal model and infection experiment process data are sent to the data collection module;

[0046] The data collection module is used to collect experimental data. Through the collection of experimental data, process simulation optimization data is obtained, and the process simulation optimization data is sent to the simulation construction module;

[0047] The simulation construction module is used to construct a process simulation system for necrotizing fasciitis. Through the construction of the simulation system, a necrotizing fasciitis process simulation model is obtained, and the necrotizing fasciitis process simulation model is sent to the process simulation module;

[0048] The process simulation module is used to simulate the necrotizing fasciitis process. Through the simulation of the necrotizing fasciitis process, necrotizing fasciitis process simulation prediction data is obtained.

[0049] The beneficial effects achieved by the present invention using the above solution are as follows:

[0050] (1) In view of the technical problem in the existing simulation methods for necrotizing fasciitis that the traditional research and analysis processes of necrotizing fasciitis rely on human pathogen analysis, which leads to scarce experimental data and increases the difficulty of analysis, this solution creatively adopts an experimental analysis method for necrotizing fasciitis based on an animal model for pre-experimental preparation of the interference process simulation. By selecting mice as the modeling animals, the quantity and quality of experimental data for necrotizing fasciitis are improved, providing good data support for subsequent research and practice;

[0051] (2) In view of the technical problem in the existing simulation methods for necrotizing fasciitis that the data characteristics of the process simulation are complex and diverse, and thus rely on a good data preprocessing process, this solution creatively adopts a method of multi-modal fusion combining artificial features and slice image features for data preprocessing, providing a better data source for subsequent model prediction;

[0052] (3) In view of the technical problem in the existing simulation methods for necrotizing fasciitis that the process simulation of necrotizing fasciitis has a high complexity and the prediction indicators involved are difficult to set, increasing the technical difficulty and also making it difficult to effectively combine and experiment with the animal model, this solution creatively adopts a method of combining a deep neural network with improved infection process modeling to construct a simulation system. By screening and setting the parameter combinations of the prediction targets through infection process modeling, and then combining the specific experiments and parameter combinations of the animal model for subsequent model improvement and loss function design, it helps to study the pathogenesis and treatment plan of necrotizing fasciitis through animal experiments, providing certain support and exploration for the research direction of necrotizing fasciitis. Brief Description of the Drawings

[0053] Figure 1 It is a schematic flowchart of the method for simulating the process of necrotizing fasciitis based on an animal model provided by the present invention;

[0054] Figure 2 It is a schematic diagram of the system for simulating the process of necrotizing fasciitis based on an animal model provided by the present invention;

[0055] Figure 3 It is a schematic flowchart of the infection experiment design in step S2;

[0056] Figure 4 It is a schematic flowchart of the experimental data collection in step S3;

[0057] Figure 5 It is a schematic flowchart of the construction of the simulation system in step S4;

[0058] Figure 6 It is a schematic diagram of the body temperature measurement result in step S2;

[0059] Figure 7 It is a schematic diagram of the infection range measurement result in step S2.

[0060] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. Detailed implementation manners

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0062] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0063] Embodiment 1, refer to Figure 1 , the method for simulating the process of necrotizing fasciitis based on an animal model provided by the present invention includes the following steps:

[0064] Step S1: Selection of the animal model;

[0065] Step S2: Design of the infection experiment;

[0066] Step S3: Collection of experimental data;

[0067] Step S4: Construction of the simulation system;

[0068] Step S5: Simulation of the process of necrotizing fasciitis.

[0069] Embodiment 2, refer to Figure 1 and Figure 2 , in step S1, the selection of the animal model is used to select an appropriate animal model for the research on simulating the process of necrotizing fasciitis. Specifically, a mouse animal model is selected for the process simulation experiment, and through strain extraction and cultivation, animal grouping and animal model construction are carried out to obtain an animal model for simulating the process of necrotizing fasciitis;

[0070] The animal model for simulating the necrotizing fasciitis process specifically includes experimental animal grouping data, bacterial solution preparation data, and basic model data;

[0071] The experimental animal grouping data specifically includes first experimental group data, second experimental group data, third experimental group data, and control group data;

[0072] The first experimental group data specifically refers to the experimental data of injecting Streptococcus;

[0073] The second experimental group data specifically refers to the experimental data of injecting Staphylococcus aureus;

[0074] The third experimental group data specifically refers to the experimental data of injecting a mixture of Streptococcus and Staphylococcus aureus;

[0075] The control group data specifically refers to the experimental data of injecting normal saline;

[0076] The bacterial solution preparation data specifically refers to the experimental bacterial solution data obtained by preparing the bacterial solution in 4 sterile test tubes injected with an appropriate amount of normal saline; The preparation of the bacterial solution specifically includes Streptococcus lysate, Staphylococcus aureus strain lysate, and a mixed bacterial solution prepared by mixing equal amounts; The experimental bacterial solution data specifically refers to the strain concentration data measured by a turbidimeter;

[0077] The basic model data specifically refers to four groups of 10 C57BL / 6J mice each, with an equal number of females and males. Among the four groups of mice, the first three groups of mice are experimental groups, and the fourth group of mice is the control group. Basic animal model experimental data records are carried out through measuring body temperature and infection range, extracting and detecting peripheral blood cells of mice, detecting C-reactive protein and interleukin-6 in mice, and extracting RNA from mouse fascia tissue and RNA reverse transcription operations;

[0078] The measurement of body temperature and infection range specifically refers to measuring the body temperature of the experimental group and control group mice on the 1st, 3rd, 5th, 7th, 9th, and 11th days after experimental infection, and observing and measuring the infection range of the experimental group and control group mice on the 0th, 1st, 3rd, 5th, 7th, 9th, and 11th days after the experiment. The infection range specifically refers to measuring the longest distance, shortest distance, and average distance of the infection focus of each mouse with a flexible ruler, and then calculating the average infection range of each group of mice using the circular area formula;

[0079] The extraction and detection of peripheral blood cells of mice specifically refers to collecting the blood of mouse orbits with a 1 ml heparinized centrifuge tube;

[0080] The detection of C-reactive protein and interleukin-6 in mice specifically refers to the absorbance value data measured at a wavelength of 450 nm for each well of the microplate by using an enzyme-linked immunosorbent assay after extracting mouse serum and detecting C-reactive protein and interleukin-6;

[0081] The extraction of RNA from mouse fascia tissue and RNA reverse transcription specifically refer to the concentration data of target genes and internal reference genes of samples obtained through mouse tissue extraction, RNA extraction, and RNA reverse transcription.

[0082] Example 3, refer to Figure 1 、 Figure 2 、 Figure 3 、 Figure 6 and Figure 7 Based on the above example, in step S2, the infection experiment design is used to select the pathogen of necrotizing fasciitis for the infection experiment. Specifically, an infection experiment environment is constructed and an experiment on the process of necrotizing fasciitis infection is carried out, and through pathological analysis, resonance examination, and post-processing, the data of the infection experiment process are obtained, which specifically include the following steps:

[0083] Step S21: Process experiment. Specifically, according to the animal model for simulating the process of necrotizing fasciitis, an experiment on the process of necrotizing fasciitis infection is carried out to obtain the original experimental data;

[0084] Step S22: Pathological analysis of infected tissues. Specifically, mice at the time period with the most obvious infection are modeled and the pathological analysis of infected tissues is carried out to obtain a dataset of pathological analysis;

[0085] The steps of the pathological analysis of infected tissues include:

[0086] Step S221: Mouse treatment. Specifically, the successfully modeled mice are treated by cervical dislocation;

[0087] Step S222: Tissue collection and fixation. Specifically, the treated mice are fixed on a clean bench, and infected tissue samples are cut and placed in a 4% paraformaldehyde solution, and then the samples are placed in a refrigerator at 4 °C for 36 hours for fixation to obtain fixed tissue samples;

[0088] Step S223: Tissue section preparation. Specifically, the fixed tissue samples are taken out and tissues of appropriate size are cut. The tissues are sequentially placed in 70%, 80%, 90%, 95% ethanol, and absolute ethanol for 1 hour each for gradient dehydration, and the dehydrated tissues are placed in xylene for transparency treatment to obtain tissue sections;

[0089] Step S224: Paraffin embedding. Specifically, the tissue sections are placed in paraffin and embedded at 60 °C for 1 hour to obtain paraffin-embedded tissue samples;

[0090] Step S225: Slide preparation. Specifically, use a microtome to cut the paraffin-embedded tissue sample into 4-mm thick slices, flatten them on the water surface at 45 °C, then place the flattened slices on a glass slide coated with an anti-detachment agent, and bake them in an oven at 60 °C for 2 hours to obtain the original tissue section sample;

[0091] Step S226: Slide staining. Specifically, after dewaxing the original tissue section sample with xylene and hydrating it with gradient absolute ethanol, perform HE staining, stain it with hematoxylin solution, differentiate it with hydrochloric acid alcohol, blue it with ammonia water, then stain it with eosin and rinse it thoroughly with running water to obtain the stained section sample;

[0092] Step S227: Mounting and analysis. Specifically, after dehydrating the stained section sample with gradient alcohol and clearing it with xylene, add a drop of neutral gum on the glass slide, cover it with a coverslip, and analyze the section results by electron microscopy scanning to obtain the scanning analysis experimental data;

[0093] Step S23: Magnetic resonance examination of the infection focus in mice. Specifically, anesthetize the infected mice and perform magnetic resonance examination, and conduct imaging analysis of key parts to obtain magnetic resonance detection data;

[0094] The imaging analysis of the key parts specifically conducts sagittal, coronal, and transverse imaging analyses;

[0095] Step S24: Collection of data during the infection experiment. Specifically, combine the original experimental data, the scanning analysis experimental data, and the magnetic resonance detection data to obtain the data during the infection experiment.

[0096] Refer to Figure 6 , where the circular legend represents the body temperature measurement results of the first experimental group, the square legend represents the body temperature measurement results of the second experimental group, the regular triangle legend represents the body temperature measurement results of the third experimental group, the inverted triangle legend represents the body temperature measurement results of the control group, the horizontal direction represents the number of experimental days, and the vertical direction represents the body temperature value;

[0097] Refer to Figure 7 , where legend A represents the infection range results of the first experimental group, legend B represents the infection range results of the second experimental group, legend C represents the infection range results of the third experimental group, legend D represents the infection range results of the control group, the horizontal direction represents the number of experimental days, and the vertical direction represents the infection range area value;

[0098] By performing the above operations, in view of the technical problem that in the existing simulation methods for necrotizing fasciitis, the traditional research and analysis processes of necrotizing fasciitis rely on human pathogen analysis, which leads to scarce experimental data and increases the difficulty of analysis, this solution creatively adopts an experimental analysis method for necrotizing fasciitis based on an animal model to conduct pre-experimental preparations for interference process simulation. By selecting mice as the modeling animals, the quantity and quality of experimental data for necrotizing fasciitis are improved, providing good data support for subsequent research and practice.

[0099] Example 4, refer to Figure 1 、 Figure 2 and Figure 4 Based on the above example, in step S3, the experimental data collection is used to collect the basic data required for the necrotizing fasciitis process simulation system and optimize and enhance the data. Specifically, based on the data in the necrotizing fasciitis process simulation animal model and the data in the infection experiment process, through experimental data collection, the original process simulation data is obtained, and the original process simulation data is preprocessed to obtain the optimized process simulation data;

[0100] The steps of the experimental data collection and data preprocessing include:

[0101] Step S31: Experimental data collection, specifically, from the data in the infection experiment process, the original data set required for necrotizing fasciitis process simulation is collected to obtain the original process simulation data;

[0102] Step S32: Data integrity check, specifically, the missing, duplicate, and outlier detection is performed on the original process simulation data to obtain the integrity check data set;

[0103] Step S33: Outlier processing, specifically, the outliers in the integrity check data set are filled by the Z-score filling method to obtain the outlier processing data set;

[0104] Step S34: Slice feature extraction, specifically, a standard convolutional neural network is used to extract the features of the slice images from the scanned analysis experimental data in the original process simulation data to obtain the slice feature data;

[0105] Step S35: Numerical data feature extraction, specifically, the artificial feature extraction method is used to extract the artificial features of the numerical data from the outlier processing data set to obtain the numerical feature data;

[0106] Step S36: Multimodal feature fusion, specifically, by performing feature selection and feature fusion on the slice feature data and the numerical feature data, the integrated necrotizing fasciitis process simulation feature data is obtained;

[0107] Step S37: data integration, specifically, integrating the necrotizing fasciitis process simulation feature data to obtain process simulation optimization data.

[0108] By executing the above operations, in order to address the technical problem that in the existing necrotizing fasciitis process simulation methods, the data features of the process simulation are complex and diverse, and therefore rely on a good data preprocessing process, this solution creatively adopts a multimodal fusion method that combines artificial features and slice image features for data preprocessing, providing a better data source for subsequent model predictions.

[0109] Example 5, see Figure 1 , Figure 2 and Figure 5 This embodiment is based on the above embodiment. In step S4, the simulation system is constructed to design a necrotizing fasciitis process simulation system. Specifically, based on the process simulation optimization data, a deep neural network method combined with improved infection process modeling is used to construct the simulation system to obtain a necrotizing fasciitis process simulation model.

[0110] The deep neural network combined with improved infection process modeling specifically includes an infection process module, a neural ordinary differential solver, a deep neural network basic subnet and a process combination optimization loss function;

[0111] The infection process module is used to generate relevant parameters for necrotizing fasciitis process simulation by segmenting the infection process, and to set a target combination of prediction parameters for process simulation;

[0112] The neural constant differential solver is used to enhance the fitting performance of the deep neural network model for necrotizing fasciitis process simulation;

[0113] The deep neural network basic subnet is used as a basic prediction subnet for necrotizing fasciitis process simulation;

[0114] The process combination optimizes the loss function to improve the model performance by minimizing the loss;

[0115] The step of constructing a simulation system by using a deep neural network method combined with improved infection process modeling to obtain a necrotizing fasciitis process simulation model includes:

[0116] Step S41: constructing an infection process module, specifically, modeling the infection process, obtaining an infection process module parameter combination, and using the infection process module parameter combination as the infection process module, and the calculation formula is: ;

[0117] In the formula, is the infection process model parameter combination, used to represent the infection process module, is the infection transmission rate parameter, used to represent the pathogen transmission rate of necrotizing fasciitis, and W is the weight parameter of the basic subnet of the deep neural network, is the incubation period rate parameter, used to represent the time rate of contacting the pathogen and starting to be infected, is the tissue destruction rate parameter, used to represent the rate of infection developing to tissue destruction, is the treatment success rate parameter, used to represent the rate of recovery of the infected person after receiving treatment, is the disease deterioration rate parameter, used to represent the rate of infection changing from the early stage to a more severe stage, is the mortality rate parameter, used to represent the mortality rate caused by necrotizing fasciitis failing to be treated in time;

[0118] Step S42: Construct a neural ordinary differential solver. Specifically, through the neural ordinary differential solver, calculate the simulation vector representation of the necrotizing fasciitis process according to the time step. The calculation formula is: ;

[0119] In the formula, Z(t + 1) is the simulation vector representation of the necrotizing fasciitis process at time t + 1, t is the time step index, f(·) is the neural network identification function, specifically referring to the deep neural network, and Z(t) is the simulation vector representation of the necrotizing fasciitis process at time t, is the infection process model parameter combination at time t, and W is the weight parameter of the basic subnet of the deep neural network;

[0120] Step S43: Construct the basic subnet of the deep neural network. Specifically, construct the basic subnet of the deep neural network including an input layer, a hidden layer, and an output layer, and improve the hidden layer by combining the infection process module and the neural ordinary differential solver to construct the basic subnet of the deep neural network;

[0121] The calculation formula for the improvement of the hidden layer is: ;

[0122] In the formula, is the output of the first hidden layer at the th time step, i is the time step unit index, specifically used to represent the number of days of infection of necrotizing fasciitis, ELU(·) is the hidden layer activation function, input u is the total set of input layer data, u is the total number of input layers, j is the input layer index, is the input data corresponding to the jth input layer and the weight of the first hidden layer, input j is the total data of the jth input layer, is the bias term of the first hidden layer, k1 is the unit number index of the first hidden layer;

[0123] is the output of the second hidden layer at the -th time step. ELU(·) is the activation function of the hidden layer, is the number of hidden units in the first hidden layer, k 1 is the unit number index of the first hidden layer, is the weight corresponding to the first hidden layer and the second hidden layer, is the bias term of the second hidden layer, k 2 is the unit number index of the second hidden layer;

[0124] is the output of the N-th hidden layer at the -th time step. N is the total number of hidden layers, and the specific value is 14, is the number of hidden units in the N-1-th hidden layer, k N-1 is the unit number index of the N-1-th hidden layer, is the output of the N-1-th hidden layer at the -th time step, is the bias term of the N-th hidden layer, k N is the unit number index of the N-th hidden layer;

[0125] Step S44: Construct a process combination optimization loss function for overall model loss optimization in combination with the infection process module. The calculation formula is: ;

[0126] In the formula, L is the process combination optimization loss function, T is the total number of time steps, t is the time step index, min is the function to find the minimum value, is the parameter combination of the infection process module, X t is the real data, which is used to represent the real data obtained from the experiment before the simulation of the necrotizing fasciitis process, is the predicted data, which is used to represent the predicted data obtained from the necrotizing fasciitis process simulation model, I t is the total number of real treatments, is the total number of predicted treatments, CR t is the total number of real deteriorations, is the total number of predicted deteriorations, D t is the total number of real deaths, is the total number of predicted deaths;

[0127] Step S45: Training the necrotizing fasciitis process simulation model. Specifically, the model is trained by constructing the infection process module, the neural ordinary differential equation solver, the basic subnet of the deep neural network, and the process combination optimization loss function to obtain the necrotizing fasciitis process simulation model Model NF .

[0128] By performing the above operations, in the existing necrotizing fasciitis process simulation method, there are technical problems such as the high complexity of the necrotizing fasciitis process simulation and the difficulty in setting the prediction indicators involved, which increase the technical difficulty and make it difficult to effectively combine and experiment with animal models. This solution creatively uses a deep neural network method combined with improved infection process modeling to construct a simulation system. By screening and setting the parameter combinations of the prediction targets through infection process modeling, and then combining the specific experiments and parameter combinations of the animal model for subsequent model improvement and loss function design, it helps to study the pathogenesis and treatment plan of necrotizing fasciitis through animal experiments, providing certain support and exploration for the research direction of necrotizing fasciitis.

[0129] Example Six, refer to Figure 1 and Figure 2 , based on the above example, in step S5, the necrotizing fasciitis process simulation is used to simulate the necrotizing fasciitis process by combining animal model experimental data and a deep learning model. Specifically, the necrotizing fasciitis process simulation model is used to perform the necrotizing fasciitis process simulation based on the animal model to obtain the necrotizing fasciitis process simulation prediction data;

[0130] The necrotizing fasciitis process simulation prediction data specifically refers to the data of the change of the parameter combination of the infection process model obtained by prediction over time steps.

[0131] Example Seven, refer to Figure 1 and Figure 2 , based on the above example, the necrotizing fasciitis process simulation system based on an animal model provided by the present invention includes an infection experiment module, a data collection module, a simulation construction module, and a process simulation module;

[0132] The infection experiment module is used to select an animal model and design an infection experiment. Through animal model selection and infection experiment design, a necrotizing fasciitis process simulation animal model and infection experiment process data are obtained, and the necrotizing fasciitis process simulation animal model and infection experiment process data are sent to the data collection module;

[0133] The data collection module is used to collect experimental data. Through experimental data collection, process simulation optimization data is obtained, and the process simulation optimization data is sent to the simulation construction module;

[0134] The simulation construction module is used to construct a process simulation system for necrotizing fasciitis. Through the construction of the simulation system, a process simulation model of necrotizing fasciitis is obtained, and the process simulation model of necrotizing fasciitis is sent to the process simulation module;

[0135] The process simulation module is used to simulate the process of necrotizing fasciitis. Through the simulation of the process of necrotizing fasciitis, process simulation prediction data of necrotizing fasciitis is obtained.

[0136] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0137] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

[0138] The above describes the present invention and its implementation manners. Such description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. All in all, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments to this technical solution without creative efforts without departing from the purpose of the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for simulating the process of necrotizing fasciitis based on an animal model, characterized in that: The method comprises the following steps: Step S1: selecting an animal model, specifically selecting a mouse animal model for a process simulation experiment, and extracting and culturing strains, performing animal grouping and animal model construction to obtain a necrotizing fasciitis process simulation animal model; Step S2: infection experiment design, specifically, constructing an infection experiment environment and conducting a necrotizing fasciitis infection process experiment, and obtaining infection experiment process data through pathological analysis, resonance examination and post-processing; Step S3: experimental data collection, specifically, obtaining process simulation raw data through experimental data collection based on the data in the necrotizing fasciitis process simulation animal model and the infection experiment process data, and performing data preprocessing on the process simulation raw data to obtain process simulation optimization data; Step S4: constructing a simulation system for designing a necrotizing fasciitis process simulation system, specifically, constructing a simulation system based on the process simulation optimization data and using a deep neural network method combined with improved infection process modeling to obtain a necrotizing fasciitis process simulation model; The deep neural network combined with improved infection process modeling specifically includes an infection process module, a neural ordinary differential solver, a deep neural network basic subnet and a process combination optimization loss function; The infection process module is used to generate relevant parameters for necrotizing fasciitis process simulation by segmenting the infection process, and to set a target combination of prediction parameters for process simulation; The neural constant differential solver is used to enhance the fitting performance of the deep neural network model for necrotizing fasciitis process simulation; The deep neural network basic subnet is used as a basic prediction subnet for necrotizing fasciitis process simulation; The process combination optimizes the loss function to improve the model performance by minimizing the loss; The steps of constructing a simulation system by using a deep neural network method combined with improved infection process modeling to obtain a necrotizing fasciitis process simulation model include: Step S41: constructing an infection process module, specifically, modeling the infection process, obtaining an infection process module parameter combination, and using the infection process module parameter combination as the infection process module, and the calculation formula is: ; In the formula, It is a combination of infection process module parameters, used to represent the infection process module. is the infection transmission rate parameter, which is used to represent the pathogen transmission rate of necrotizing fasciitis, W is the weight parameter of the basic subnetwork of the deep neural network, is the incubation rate parameter, which is used to represent the time rate from exposure to pathogens to the onset of infection. It is a tissue destruction rate parameter, which is used to indicate the rate at which infection develops to tissue destruction. is the treatment success rate parameter, which is used to indicate the recovery rate of the infected person after receiving treatment. is the disease progression rate parameter, which indicates the rate at which the infection changes from an early stage to a more severe stage. is a mortality parameter used to indicate the mortality rate caused by failure to promptly treat necrotizing fasciitis; Step S42: constructing a neural constant differential solver, specifically, using the neural constant differential solver to calculate the necrotizing fasciitis process simulation vector representation according to the time step, and the calculation formula is: ; where Z(t+1) is the vector representation of the necrotizing fasciitis process simulation at time t+1, t is the time step index, f(·) is the neural network identification function, specifically the deep neural network, and Z(t) is the vector representation of the necrotizing fasciitis process simulation at time t. is the combination of infection process module parameters at time t, W is the weight parameter of the basic subnet of the deep neural network; Step S43: constructing a basic subnet of a deep neural network, specifically constructing a basic subnet of a deep neural network including an input layer, a hidden layer and an output layer, and improving the hidden layer by combining the infection process module and the neural constant differential solver to construct the basic subnet of the deep neural network; Step S44: construct a process combination optimization loss function, which is used to optimize the overall loss of the model in combination with the infected process module. The calculation formula is: ； Where L is the process combination optimization loss function, T is the total number of time steps, t is the time step index, and min is the minimum value function. is the combination of infection process model parameters, X t is real data, used to represent the real data obtained from the experiment before the simulation of the necrotizing fasciitis process. is the predicted data, which is used to represent the predicted data obtained by the necrotizing fasciitis process simulation model. t is the total number of actual treatments, is the predicted total number of treatments, CR t is the total number of true deteriorations, is the total number of predicted deteriorations, D t is the true total number of deaths. is the total number of deaths predicted; Step S45: training the necrotizing fasciitis process simulation model, specifically, by constructing the infection process module, the neural constant differential solver, the deep neural network basic subnet and the process combination optimization loss function, performing model training to obtain the necrotizing fasciitis process simulation model Model NF ; Step S5: simulating the process of necrotizing fasciitis, specifically using the necrotizing fasciitis process simulation model to perform a necrotizing fasciitis process simulation based on an animal model to obtain necrotizing fasciitis process simulation prediction data; The necrotizing fasciitis process simulation prediction data specifically refers to the predicted infection process model parameter combination change data with time steps.

2. The method for simulating the process of necrotizing fasciitis based on an animal model according to claim 1, characterized in that: In step S2, the infection experiment design is used to select the pathogen of necrotizing fasciitis for infection experiment, specifically to construct an infection experiment environment and conduct a necrotizing fasciitis infection process experiment, and obtain infection experiment process data through pathological analysis, resonance examination and post-processing, specifically including the following steps: Step S21: process experiment, specifically, conducting a necrotizing fasciitis infection process experiment based on the necrotizing fasciitis process simulation animal model to obtain experimental raw data; Step S22: infection tissue pathology analysis, specifically, modeling and infection tissue pathology analysis of mice in the most obvious infection period to obtain a pathology analysis data set; Step S23: MRI examination of the infected foci of mice, specifically, anesthetizing the infected mice and performing MRI examination, performing imaging analysis of key parts, and obtaining MRI detection data; Step S24: infection experiment process data collection, specifically combining the original experimental data, scanning analysis experimental data and nuclear magnetic resonance detection data to obtain infection experiment process data.

3. The method for simulating the process of necrotizing fasciitis based on an animal model according to claim 2, characterized in that: In step S3, the steps of experimental data collection and data preprocessing include: Step S31: experimental data collection, specifically collecting the original data set required for necrotizing fasciitis process simulation from the infection experimental process data to obtain process simulation original data; Step S32: data integrity check, specifically, performing missing, duplicate and outlier detection on the process simulation raw data to obtain an integrity check data set; Step S33: outlier processing, specifically, filling the outliers in the integrity check data set with a Z-score filling method to obtain an outlier processing data set; Step S34: extracting slice features, specifically using a standard convolutional neural network to extract slice image features from the scanning analysis experimental data in the process simulation raw data to obtain slice feature data; Step S35: extracting numerical data features, specifically, using an artificial feature extraction method to extract numerical data features from the abnormal processing data set to obtain numerical feature data; Step S36: multimodal feature fusion, specifically, obtaining integrated necrotizing fasciitis process simulation feature data by performing feature selection and feature fusion on the slice feature data and the numerical feature data; Step S37: data integration, specifically, integrating the necrotizing fasciitis process simulation feature data to obtain process simulation optimization data.

4. The method for simulating the process of necrotizing fasciitis based on an animal model according to claim 3, characterized in that: In step S5, the necrotizing fasciitis process simulation is used to combine the animal model experimental data and the deep learning model to simulate the necrotizing fasciitis process; In step S1, the animal model selection is used to select an appropriate animal model for the study of necrotizing fasciitis process simulation; The necrotizing fasciitis process simulation animal model specifically includes experimental animal grouping data, bacterial liquid preparation data and basic model data.

5. The method for simulating the process of necrotizing fasciitis based on an animal model according to claim 4, characterized in that: In step S22, the steps of infection tissue pathological analysis include: step S221: mouse processing; step S222: tissue collection and fixation; step S223: tissue preparation; step S224: paraffin embedding; step S225: section preparation; step S226: section staining; step S227: sealing analysis.

6. A necrotizing fasciitis process simulation system based on an animal model, used to implement the necrotizing fasciitis process simulation method based on an animal model as described in any one of claims 1 to 5, characterized in that: It includes infection experiment module, data collection module, simulation construction module and process simulation module.

7. The necrotizing fasciitis process simulation system based on an animal model according to claim 6, characterized in that: The infection experiment module is used to select an animal model and design an infection experiment, obtain a necrotizing fasciitis process simulation animal model and infection experiment process data through animal model selection and infection experiment design, and send the necrotizing fasciitis process simulation animal model and infection experiment process data to the data collection module; The data collection module is used to collect experimental data, obtain process simulation optimization data through experimental data collection, and send the process simulation optimization data to the simulation construction module; The simulation construction module is used to construct a process simulation system for necrotizing fasciitis, obtain a process simulation model for necrotizing fasciitis through simulation system construction, and send the process simulation model for necrotizing fasciitis to the process simulation module; The process simulation module is used to simulate the necrotizing fasciitis process, and obtain necrotizing fasciitis process simulation prediction data through necrotizing fasciitis process simulation.

Images