Anesthesia anatomy practical training system based on virtual simulation

Abstract

The invention discloses an anesthesia anatomy practical training system based on virtual simulation, which relates to the technical field of medical simulation training and comprises a virtual anatomy modeling module, a physiological simulation module, a dynamic response and tactile feedback module, a multi-dimensional data acquisition and performance evaluation module and an intelligent clinical decision support and dynamic virtual case module. According to the invention, high-precision three-dimensional reconstruction and dynamic physiological simulation technologies are adopted, and real-time monitoring, tactile feedback and closed-loop adaptive optimization are combined, so that precise, real-time and personalized training of virtual simulation anesthesia anatomy practical training is realized. The system can dynamically simulate physiological changes of a human body, provides remote collaborative teaching and risk early warning, effectively improves training quality and clinical decision-making level, and has remarkable safety, practicability and popularization prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of medical simulation training, and particularly to an anesthesia anatomy training system based on virtual simulation. Background Art

[0002] In recent years, with the rapid development of computer image processing, three-dimensional reconstruction, virtual reality (VR) and augmented reality (AR) technologies, significant progress has been made in the field of medical simulation training. Multimodal medical image data (such as CT, MRI, ultrasound) provides a solid data foundation for constructing high-precision human anatomy models, and the application of artificial intelligence algorithms in image reconstruction and data fusion has been continuously matured. These technologies have promoted the gradual entry of virtual simulation systems into the fields of clinical teaching and skills training, providing a safe and non-invasive training method for medical staff and promoting the development of medical digitization and intelligence.

[0003] However, there are still many deficiencies in the existing technologies. First, when constructing virtual anatomy models based on multimodal image data, due to limitations in image resolution, noise, and algorithm limitations, it is often difficult to achieve precise restoration of details such as bones, blood vessels, nerves, and soft tissues, resulting in a deviation between the simulation effect and the actual situation. Second, in terms of dynamic physiological simulation, traditional methods are difficult to effectively simulate the instantaneous fluctuations of parameters such as heart rate, blood pressure, respiration, and blood oxygen under external interventions, resulting in a lag in simulation response and inaccurate feedback. Third, existing systems have problems such as discontinuous data updates and delayed interactive feedback in real-time monitoring, data collection, and tactile feedback, making it difficult for trainees to obtain a real and detailed experience during the operation training process. Finally, the comprehensive evaluation and risk warning functions are relatively primitive, unable to form a perfect closed-loop control system, and lacking a remote collaborative teaching platform, making it difficult to meet the needs of modern medical training for personalization, intelligence, and high-efficiency collaboration. Therefore, there is an urgent need for a new virtual simulation anesthesia anatomy training system to achieve high precision, real-time feedback, and remote collaboration by improving key technologies such as anatomical modeling, physiological simulation, real-time monitoring, dynamic response, tactile feedback, and data evaluation, so as to comprehensively improve the quality and safety of medical training. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing virtual simulation medical training methods have problems such as insufficient accuracy of anatomical models, lag in dynamic physiological responses, and imperfect data collection and risk warning, and the problem of how to implement an anesthesia anatomy training system with high precision, real-time feedback, and remote collaboration.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An anesthesia anatomy training system based on virtual simulation, including a virtual anatomy modeling module, a physiological simulation module, a dynamic response and tactile feedback module, a multi-dimensional data collection and performance evaluation module, and an intelligent clinical decision support and dynamic virtual case module; The three-dimensional human anatomy model constructed based on multi-modal medical image data provides anatomical structure parameters for the physiological simulation module and shares model information with the dynamic response and tactile feedback module; The physiological simulation module conducts virtual simulation of the dynamic physiological state of the virtual human body based on the virtual anatomy model of the virtual anatomy modeling module; The dynamic response and tactile feedback module is used to simulate the changes in the physiological state of the virtual patient in real time according to the influence of the trainee's operation and external intervention, adjust the physiological parameters of the virtual patient, simulate the hardness, elasticity and resistance of different tissues, and provide a tactile experience; The multi-dimensional data collection and performance evaluation module is used to comprehensively collect the operation trajectory, force application, angle, time and physiological parameters of the virtual patient during the trainee's operation, and output virtual cases and risk warnings; The intelligent clinical decision support and dynamic virtual case module is used to dynamically generate virtual clinical cases.

[0007] As a preferred solution of the anesthesia anatomy training system based on virtual simulation according to the present invention, wherein: The three-dimensional human anatomy model constructed during the construction of the three-dimensional human anatomy model based on multi-modal medical image data includes first collecting multi-modal medical image data, and the system uses the virtual anatomy modeling module to output a three-dimensional human anatomy model. The virtual anatomy modeling module converts the collected image data into a static anatomical structure through image processing and artificial intelligence reconstruction algorithms, and displays bone, blood vessel, nerve and soft tissue information.

[0008] As a preferred solution of the anesthesia anatomy training system based on virtual simulation according to the present invention, wherein: The virtual simulation of the dynamic physiological state of the virtual human body includes endowing the virtual human body with dynamic physiological parameters based on the static anatomical structure by using the physiological simulation module, including heart rate, blood pressure, respiration and blood oxygen saturation; The physiological simulation module simulates the physiological fluctuations of the human body in different states through physiological simulation algorithms and responds to the influence of external intervention.

[0009] As a preferred solution of the anesthesia anatomy training system based on virtual simulation according to the present invention, wherein: The simulation of the hardness, elasticity and resistance of different tissues and the provision of a tactile experience include that when the trainee starts the operation training, the system collects the physiological state of the virtual patient through real-time physiological parameter monitoring and monitors the immediate changes in heart rate, blood pressure and blood oxygen indexes; When the trainee performs operations such as acupuncture or catheter insertion, the system combines the real-time collected physiological data and operation instructions, and outputs and simulates the physiological changes caused by the operation, including instantaneous fluctuations in heart rate or blood pressure.

[0010] As a preferred solution of the virtual simulation-based anesthesia anatomy training system of the present invention, wherein: simulating the hardness, elasticity and resistance of different tissues to provide a tactile experience includes simulating the hardness, elasticity and resistance of different tissues according to the dynamic response data of the virtual anatomy modeling module and the dynamic response and tactile feedback module.

[0011] As a preferred solution of the virtual simulation-based anesthesia anatomy training system of the present invention, wherein: the dynamic generation of virtual clinical cases includes comprehensively collecting operation trajectories, applied forces, angles, operation durations, and physiological parameters and tactile feedback data of virtual patients throughout the operation process of trainees through the multi-dimensional data collection and performance evaluation module; Using data mining and analysis algorithms to conduct multi-dimensional evaluations on trainees' operations, quantifying operation accuracy, smoothness, and response timeliness, and generating evaluation reports.

[0012] As a preferred solution of the virtual simulation-based anesthesia anatomy training system of the present invention, wherein: the dynamic generation of virtual clinical cases includes automatically adjusting virtual environment parameters by the system using evaluation data and real-time physiological responses according to the evaluation reports output by the multi-dimensional data collection and performance evaluation module; The system dynamically generates virtual clinical cases that conform to the current operation situation through the intelligent clinical decision support and dynamic virtual case module, collects operation data and real-time physiological information, outputs risk warnings and operation suggestions using risk assessment algorithms, and assists trainees in clinical decision-making training.

[0013] Another object of the present invention is to provide a virtual simulation-based anesthesia anatomy training method, which can solve the problems of insufficient accuracy of anatomical models and lag in dynamic physiological responses in current virtual simulation medical training methods during the code development and quality monitoring stages of the virtual simulation-based anesthesia anatomy training process through the multi-dimensional data collection and performance evaluation module.

[0014] As a preferred solution of the virtual simulation-based anesthesia anatomy training method of the present invention, wherein: including the requirement analysis and resource allocation stage relying on the virtual anatomy modeling module and the physiological simulation module; the system first collects data from multi-modal medical image data, generates a three-dimensional human anatomical model through the virtual anatomy modeling module, and endows the model with dynamic physiological parameters using the physiological simulation module to monitor the physiological state of the virtual patient in real time and provide data support for requirement analysis; comprehensively monitoring through the physiological model basis provided by the physiological simulation module and the dynamic response and tactile feedback module, and outputting simulation data of clinical dynamics; based on the dynamic response and tactile feedback module, the multi-dimensional data collection and performance evaluation module, and intelligent clinical decision support, the testing and deployment stage in the virtual simulation-based anesthesia anatomy training process.

[0015] Advantages of the present invention: The virtual simulation-based anesthesia anatomy training system provided by the present invention utilizes the virtual anatomy modeling module (100). The system generates a high-precision three-dimensional human anatomy model from multi-modal medical image data, accurately displaying bone, blood vessel, nerve, and soft tissue structures, providing a static basis for subsequent steps; the physiological simulation module (200) endows the virtual human body with dynamic physiological parameters such as heart rate, blood pressure, respiration, and blood oxygen on this basis, and simulates the physiological fluctuations of the human body under different states through simulation algorithms to achieve a virtual "living body" effect; the dynamic response and tactile feedback module (300) combines the trainee's operation instructions with real-time data, quickly simulates the instantaneous changes of indicators such as heart rate or blood pressure, and realizes the real-time linkage between operation input and physiological response. At the same time, according to the virtual anatomy and dynamic response data, it simulates the hardness, elasticity, and resistance of different tissues, converts virtual operations into real tactile experiences, and enhances the operation immersion and safety; the multi-dimensional data acquisition and performance evaluation module (400) comprehensively records the trainee's operation trajectory, force application, angle, and duration, and conducts multi-dimensional evaluations in combination with physiological data, quantifying operation accuracy and smoothness, providing a scientific basis for subsequent feedback. The intelligent clinical decision support and dynamic virtual case module (500) integrates the collected operation data and physiological information, dynamically generates virtual cases that conform to the actual operation state, and uses risk assessment algorithms to output warnings and suggestions to assist trainees in improving their clinical decision-making abilities. Through the above steps, the present invention not only ensures the accurate reconstruction of the anatomical model and dynamic physiological simulation, but also realizes real-time monitoring, interactive feedback, data evaluation, environment adaptation, and clinical decision support, thereby significantly enhancing the realism, safety, and teaching effect of virtual simulation anesthesia anatomy training. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0017] Figure 1 It is the overall flowchart of a virtual simulation-based anesthesia anatomy training system provided by the first embodiment of the present invention.

[0018] Figure 2 It is the overall flowchart of a virtual simulation-based anesthesia anatomy training method provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0020] Example 1. Referring to Figure 1 , which is an embodiment of the present invention, provides an anesthesia anatomy training system based on virtual simulation, including: a virtual anatomy modeling module (100), a physiological simulation module (200), a dynamic response and tactile feedback module (300), a multi-dimensional data acquisition and performance evaluation module (400), and an intelligent clinical decision support and dynamic virtual case module (500).

[0021] Furthermore, the virtual anatomy modeling module (100) is used to generate a three-dimensional human anatomy model using multi-modal medical image data, display bone, blood vessel, nerve, and soft tissue structures, provide anatomical structure parameters for the physiological simulation module (200), share model information with the dynamic response and tactile feedback module (300), and support the feedback of real anatomical sensations during operation; the physiological simulation module (200) is used to simulate the dynamic physiological state of a virtual human based on the virtual anatomy model of the virtual anatomy modeling module (100); monitor changes in the physiological state, and transmit the collected data to the dynamic response and tactile feedback module (300) and the multi-dimensional data acquisition and performance evaluation module (400) for feedback and subsequent evaluation; the dynamic response and tactile feedback module (300) is used to simulate changes in the physiological state of a virtual patient in real time according to the influence of the trainee's operation and external intervention, adjust the physiological parameters of the virtual patient, and use the real-time physiological parameter monitoring data to feedback the updated physiological state to the dynamic response and tactile feedback module (300) and the intelligent clinical decision support and dynamic virtual case module (500); the dynamic response and tactile feedback module (300) is used to simulate the hardness, elasticity, and resistance of different tissues to provide a tactile experience; the multi-dimensional data acquisition and performance evaluation module (400) is used to comprehensively collect operation trajectories, applied forces, angles, times, and physiological parameters of the virtual patient during the trainee's operation, synchronously collect real-time physiological parameter monitoring data and real-time data of the dynamic response and tactile feedback module (300) to provide evaluation data, and at the same time, the data is used by the intelligent clinical decision support and dynamic virtual case module (500) to assist in generating virtual cases and risk warnings; use the evaluation data collected from the multi-dimensional data acquisition and performance evaluation module (400) to adjust the virtual environment parameters in real time; the intelligent clinical decision support and dynamic virtual case module (500) dynamically generates virtual clinical cases according to the real-time data and operation evaluation provided by the multi-dimensional data acquisition and performance evaluation module (400).

[0022] It should be noted that, first, starting from multi-modal medical image data such as CT, MRI, and ultrasound, the virtual anatomy modeling module (100) performs image processing and three-dimensional reconstruction on the original image data to generate a high-precision three-dimensional human anatomy model. This model accurately displays detailed structures such as bones, blood vessels, nerves, and soft tissues, and serves as the basic data for the entire system, laying a solid static foundation for subsequent dynamic physiological simulation and interactive operations. To achieve the above goals, the present invention adopts a mathematical model for image segmentation and reconstruction based on energy minimization. Specifically expressed as: Let the input image data be expressed as: where, represents the gray value of the image at position . The image data can be output by multi-modal image fusion, represents the voxel coordinates, belonging to the domain and is a subset of the three-dimensional space .

[0023] Define the soft segmentation function (the value range is within ) to represent the probability that the voxel coordinates belong to the target anatomical structure. Construct the following energy function: where, and are the average gray values of the target region and the background region respectively, is the regularization parameter, and total variation regularization is adopted to ensure the smoothness of the segmentation boundary, represents the probability of belonging to the target anatomical structure.

[0024] Solve the minimization problem by the variational method: Obtain the optimal soft segmentation function . Subsequently, perform a simple thresholding operation on : where, represents converting the segmentation function into a binary image.

[0025] Thus, the boundary of the target anatomical structure is clearly extracted.

[0026] Use the Marching Cubes algorithm for the binary segmentation result Perform three-dimensional reconstruction. For each voxel, if there is a sign change between adjacent corner points, the intersection points are calculated by linear interpolation. Finally, all the intersection points are connected into a triangular mesh , where is the vertex set, is the face set, thus obtaining a visualized three-dimensional anatomical model.

[0027] It should also be noted that on the static anatomical model generated in the data acquisition and virtual anatomy modeling stage, physiological parameters are superimposed. Using physiological simulation algorithms, simulate the dynamic changes of heart rate, blood pressure, respiration, and blood oxygen saturation of the human body in different states, and at the same time respond to the effects of external interventions (such as drug injection or surgical operation). Let the state vector be expressed as: where, represents the heart rate at time (unit: bpm); represents the blood pressure at time (unit: mmHg); represents the respiratory rate at time (unit: times / minute); represents the blood oxygen saturation at time (unit: %).

[0028] Let the resting state be expressed as: where, represents the heart rate in the resting state, represents the blood pressure in the resting state, represents the respiratory rate in the resting state, represents the blood oxygen saturation in the resting state.

[0029] Define the external intervention input , which can represent the effects of drug injection, surgical operation, etc. on the patient's physiological state. In order to capture the non-linear saturation characteristics of the intervention effect, use to represent the excitation term of the intervention effect. The dynamic model of the system is described as: where, is the recovery rate matrix, indicating the speed at which each physiological parameter returns to the resting state; is the intervention influence coefficient vector, reflecting the sensitivity of external interventions to each physiological parameter.

[0030] It should also be noted that specifically, the model can be expanded as: Furthermore, when using the above mathematical model to simulate the dynamic changes of the human physiological state, the core idea is to regard each physiological index as a state variable that changes over time and describe its changing trend through differential equations. First, the recovery term is used to represent that in the absence of external intervention, each physiological index of the human body tends to return to the resting state. Here, each coefficient in the recovery rate matrix controls the speed at which the heart rate, blood pressure, respiration, and blood oxygen saturation return to the resting state respectively, ensuring the inherent stability of the system.

[0031] At the same time, in order to simulate the immediate impact of external interventions (such as drug injection or surgical operation) on the physiological state, an intervention input is introduced. Considering that the physiological response has non-linear and saturation characteristics, the model uses as the intervention excitation term, so that even if the input signal is large, it can prevent the response from being infinitely amplified. The intervention term acts on each physiological index through the coefficient vector respectively, reflecting the different degrees of influence of the intervention on the heart rate, blood pressure, respiration, and blood oxygen.

[0032] In specific applications, when the external intervention signal changes, will immediately adjust the change rate of each index, resulting in fluctuations in the corresponding physiological indices; at the same time, due to the action of the recovery term, when the intervention signal ends, each index will gradually return to the resting state. In this way, the model can output a continuous physiological index curve, truly reflecting the dynamic response of the human body in different states.

[0033] It should also be noted that when the trainee conducts operation training, the system first calls the real-time physiological parameter monitoring, uses the built-in sensors and data acquisition technology to perform high-frequency sampling and real-time recording of the physiological indices such as the heart rate, blood pressure, and blood oxygen of the virtual patient, ensuring the accuracy of the physiological data in each operation link. At the same time, the system directly calls the dynamic response and tactile feedback module (300), and quickly calculates and simulates the impact of the operation on the physiological indices according to the trainee's operation instructions (such as acupuncture, catheter insertion, etc.) and the real-time data obtained from the real-time physiological parameter monitoring, immediately updating the state of the virtual patient. Through this direct call, each module closely cooperates, realizing the real-time linkage between the operation input and the physiological response, ensuring the continuity and accuracy of the data required for subsequent data evaluation and feedback regulation, thereby greatly improving the real-time performance and clinical simulation sense of the system.

[0034] It should also be noted that the trainee wears VR / AR devices and uses intelligent gloves and force feedback handles for actual operations. The system directly invokes the dynamic response and haptic feedback module (300), and based on the static anatomical data provided by the virtual anatomy modeling module (100) and the real-time physiological response data transmitted back by the dynamic response and haptic feedback module (300), generates haptic signals that match different tissue hardness, elasticity, and resistance. This direct invocation ensures that when the trainee performs operations such as acupuncture and catheter insertion, they can immediately feel haptic feedback highly consistent with the real clinical environment, thereby effectively reducing the operation risk and enhancing the authenticity of the immersive experience and skill training.

[0035] It should be noted that during the trainee's operation, the system synchronously collects the trainee's operation trajectory, applied force, angle, and operation duration by directly invoking multi-dimensional data acquisition and performance evaluation, while recording the physiological data of the virtual patient and the dynamic response and haptic feedback module (300). Using data mining and evaluation algorithms, multi-dimensional analysis is performed on the collected data to quantify the operation accuracy, smoothness, and response timeliness, and a detailed evaluation report is generated. The direct invocation of this module enables the data of the entire operation process to be accurately and real-time recorded and analyzed, providing a scientific and quantitative basis for subsequent adaptive feedback, thereby helping the trainee to promptly discover and improve operation deficiencies.

[0036] It should also be noted that let the actual operation trajectory be , and the ideal reference trajectory be . Define the accuracy index as the mean square error: where, represents the ideal or reference operation trajectory, that is, the best operation path that the trainee is expected to achieve, represents the total duration of the operation process, represents the operation accuracy index. The smaller this index is, the closer the trainee's operation is to the ideal trajectory and the higher the accuracy.

[0037] The operation smoothness reflects the continuity of the operation process and is commonly measured by the mean square value of the second derivative (acceleration) of the trajectory: where, represents the acceleration, represents the operation smoothness index, defined as the mean square value of the trajectory acceleration. A smaller value indicates a smoother operation.

[0038] Suppose there are key events (such as the moment of starting to apply force) during the operation process. For the th event, let be the moment when the operation instruction is issued, Let \(t\) be the moment when the system detects the corresponding physiological response, then the response delay is defined as: where \(D\) is the response delay index, representing the average delay of the system response in key operation events. The shorter the response delay, the more timely the system feedback.

[0039] The above indicators are weighted and fused according to the weight coefficients of operation accuracy, smoothness, and response delay to obtain the total evaluation score: where \(E\) represents the comprehensive operation evaluation index, which is the total score after weighting each individual index. To facilitate the classification discussion of operation performance, three thresholds \(T_1\), \(T_2\), \(T_3\) are set, and the classification is based on the value of \(E\): When \(E>T_1\), it is rated as excellent; When \(T_2 < E\leq T_1\), it is rated as good; When \(T_3 < E\leq T_2\), it is rated as average; When \(E\leq T_3\), it is rated as poor. When \(E\leq T_3\), it is rated as poor.

[0040] In addition, classification discussion can also be carried out separately for each individual index. For example: If \(A\) exceeds the preset threshold, the system will mark it as insufficient accuracy; If \(B\) is relatively high, it indicates that the operation is not smooth enough; If \(D\) is long, it indicates a large response delay.

[0041] It should also be noted that based on the evaluation report generated in the data collection and operation performance evaluation stage, the system directly calls real-time adaptive feedback and training optimization, and uses the evaluation data obtained from the multi-dimensional data collection and performance evaluation module (400) and the real-time physiological response information collected by real-time physiological parameter monitoring to automatically adjust the virtual environment parameters. Specifically, this module can automatically adjust the hardness of the virtual tissue, the complexity of the scene, or the intensity of tactile feedback according to the operation performance of the trainee, and provide instant improvement suggestions to the trainee in the form of graphics and voice.

[0042] It should also be noted that at this stage, the system comprehensively invokes the intelligent clinical decision support and dynamic virtual case module (500), and uses the real-time adjustment information fed back by the collected operation data to dynamically generate a virtual clinical case that conforms to the current operation state, such as an emergency anesthesia or complex surgical scenario. At the same time, this module outputs warnings and operation suggestions through a risk assessment algorithm to assist trainees in clinical decision-making training. Then, all training data, evaluation reports, and virtual case records are uploaded to the cloud platform to achieve remote real-time monitoring and online collaborative guidance. This enables teachers and experts to track the training progress of trainees in real time across regions and provide targeted guidance, thus constructing a long-term training closed-loop for continuous improvement and ultimately enhancing the overall quality and safety of medical training.

[0043] Embodiment 2, referring to Figure 2 , which is an embodiment of the present invention, provides a virtual simulation-based anesthesia anatomy training method, including a virtual anatomy modeling module (100), a physiological simulation module (200), a dynamic response and tactile feedback module (300), a multi-dimensional data acquisition and performance evaluation module (400), and an intelligent clinical decision support and dynamic virtual case module (500); the system first collects data from multi-modal medical image data, generates a three-dimensional human anatomy model through the virtual anatomy modeling module (100), and uses the physiological simulation module (200) to endow the model with dynamic physiological parameters, and monitors the physiological state of the virtual patient in real time to provide data support for requirement analysis; based on the physiological model provided by the physiological simulation module (200), the dynamic response and tactile feedback module (300) realizes real-time response and outputs simulation data of clinical dynamics; based on the dynamic response and tactile feedback module (300), the multi-dimensional data acquisition and performance evaluation module (400), and the intelligent clinical decision support and dynamic virtual case module (500), the test and deployment stage in the virtual simulation-based anesthesia anatomy training process.

[0044] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., all kinds of media that can store program codes.

[0045] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be embodied specifically in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in connection with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0046] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0047] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0048] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered by the scope of the claims of the present invention.

Claims

1. An anesthesia anatomy training system based on virtual simulation, characterized in that, including: A virtual anatomy modeling module (100) that constructs a three-dimensional human anatomy model based on multi-modal medical image data, provides anatomical structure parameters for a physiological simulation module (200), and shares model information with a dynamic response and haptic feedback module (300); A physiological simulation module (200) that simulates the dynamic physiological state of a virtual human based on the virtual anatomy model of the virtual anatomy modeling module (100); A dynamic response and haptic feedback module (300) that, according to the influence of the trainee's operation and external intervention, simulates in real time the changes in the physiological state of a virtual patient, adjusts the physiological parameters of the virtual patient, simulates the hardness, elasticity and resistance of different tissues, and provides a haptic experience; A multi-dimensional data acquisition and performance evaluation module (400) that comprehensively acquires operation trajectories, applied forces, angles, time, and the physiological parameters of a virtual patient during the trainee's operation, and outputs virtual cases and risk warnings; An intelligent clinical decision support and dynamic virtual case module (500) that dynamically generates virtual clinical cases.

2. The virtual simulation-based anesthesia anatomy training system according to claim 1, wherein: The three-dimensional human anatomy model constructed during the process of constructing the three-dimensional human anatomy model based on multi-modal medical image data includes first acquiring multi-modal medical image data. The system uses the virtual anatomy modeling module (100) to output a three-dimensional human anatomy model. The virtual anatomy modeling module (100) converts the acquired image data into a static anatomical structure through image processing and artificial intelligence reconstruction algorithms, and displays bone, blood vessel, nerve, and soft tissue information.

3. The virtual simulation-based anesthesia anatomy training system according to claim 1, characterized in that: The simulation of the dynamic physiological state of a virtual human includes endowing the virtual human with dynamic physiological parameters, including heart rate, blood pressure, respiration, and blood oxygen saturation, by using the physiological simulation module (200) based on the static anatomical structure; The physiological simulation module (200) simulates the physiological fluctuations of the human body in different states through physiological simulation algorithms and responds to the influence of external intervention.

4. The virtual simulation-based anesthesia anatomy training system according to claim 1, wherein: The simulation of the hardness, elasticity and resistance of different tissues and the provision of a haptic experience include that when the trainee starts the operation training, the system acquires the physiological state of the virtual patient through real-time physiological parameter monitoring, and monitors the immediate changes in heart rate, blood pressure, and blood oxygen indicators; When the trainee performs operations such as acupuncture or catheter insertion, the system combines the real-time acquired physiological data and operation instructions, and outputs and simulates the physiological changes caused by the operation, including instantaneous fluctuations in heart rate or blood pressure.

5. The anesthesia anatomy training system based on virtual simulation according to claims 1 and 4, characterized in that: The simulation of the hardness, elasticity and resistance of different tissues and the provision of a haptic experience include simulating the hardness, elasticity and resistance of different tissues according to the dynamic response data of the virtual anatomy modeling module (100) and the dynamic response and haptic feedback module (300).

6. The virtual simulation-based anesthesia anatomy training system according to claim 1, wherein: The dynamic generation of virtual clinical cases includes comprehensively acquiring operation trajectories, applied forces, angles, operation durations, and the physiological parameters and haptic feedback data of a virtual patient throughout the trainee's operation through the multi-dimensional data acquisition and performance evaluation module (400); Using data mining and analysis algorithms to conduct multi-dimensional evaluations of the trainee's operations, quantify operation accuracy, smoothness, and response timeliness, and generate an evaluation report.

7. The virtual simulation-based anesthesia anatomy training system according to claim 1 and claim 6, characterized in that: The dynamically generated virtual clinical cases include automatically adjusting the virtual environment parameters by the system based on the evaluation report output by the multi-dimensional data acquisition and performance evaluation module (400), and then using the evaluation data and real-time physiological responses. Through the intelligent clinical decision support and dynamic virtual case module (500), the system collects the operation data and real-time physiological information, dynamically generates virtual clinical cases that conform to the current operation situation, and uses the risk assessment algorithm to output risk warnings and operation suggestions to assist trainees in clinical decision-making training.

8. A method of using the virtual simulation-based anesthesia anatomy training system according to any one of claims 1 to 7, characterized in that: It includes the requirement analysis and resource allocation phase relying on the virtual anatomy modeling module (100) and the physiological simulation module (200). The system first collects data from multi-modal medical image data, generates a three-dimensional human anatomy model through the virtual anatomy modeling module (100), and endows the model with dynamic physiological parameters using the physiological simulation module (200) to monitor the physiological state of the virtual patient in real time, providing data support for requirement analysis. Through the physiological model basis provided by the physiological simulation module (200) and the comprehensive monitoring of the dynamic response and tactile feedback module (300), the simulation data of clinical dynamics is output. Based on the dynamic response and tactile feedback module (300), the multi-dimensional data acquisition and performance evaluation module (400), and intelligent clinical decision support, it is the testing and deployment phase in the virtual simulation of anesthetic anatomy training.

Images