Remote VR clinical medicine teaching system

Abstract

The invention relates to the technical field of VR teaching, in particular to a remote VR clinical medicine teaching system. The system comprises a first device, a second device and a server, the first equipment is used for enabling the student to enter the virtual medical teaching scene through the virtual reality equipment; the second equipment is used for the teacher to control the content and progress of the virtual medical teaching scene; the server is used for storing data of a virtual medical teaching scene and interaction information of students and teachers and communicating with the first equipment and the second equipment; the server further comprises a multi-modal data fusion module used for integrating various data types from the first device, including physiological data, voice data and video data, so as to generate a comprehensive student learning state report; the distributed edge computing node network is used for carrying out data preprocessing and preliminary analysis on edge nodes close to the first equipment; and the dynamic anatomical model generator is used for generating an interactive dynamic human anatomical model in real time according to teaching requirements.

Description

Technical Field

[0001] This invention relates to the field of VR teaching technology, and in particular to a remote VR clinical medical teaching system. Background Technology

[0002] With the continuous development of medical education, the traditional clinical medical teaching model faces many challenges. Traditional teaching methods mainly rely on theoretical lectures, laboratory practice, and clinical internships.

[0003] In recent years, the application of virtual reality (VR) technology in medical education has gradually attracted attention. VR technology can provide students with an immersive virtual learning environment, simulating real clinical scenarios, thereby overcoming the shortcomings of traditional teaching models. However, existing VR medical teaching systems still have the following problems:

[0004] Insufficient data integration: Existing systems mainly rely on single-modal data and lack the integration of multimodal data, thus failing to fully reflect students' learning status.

[0005] Low computational efficiency: Centralized computing architectures are less efficient when processing large-scale data, and are prone to latency, which affects the teaching experience.

[0006] To address this technical issue, a remote VR clinical medical teaching system is proposed. Summary of the Invention

[0007] To address the technical problems existing in the prior art, the present invention provides a remote VR clinical medical teaching system.

[0008] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0009] In a first aspect, in one embodiment of the present invention, a remote VR clinical medical teaching system is provided, the system comprising: a first device, a second device, and a server;

[0010] The first device is used by students to enter a virtual medical teaching scenario through virtual reality equipment;

[0011] The second device is used by teachers to control the content and pace of the virtual medical teaching scenario;

[0012] The server is used to store data from the virtual medical teaching scenario and interaction information between students and teachers, and to communicate with the first and second devices.

[0013] The server also includes:

[0014] The multimodal data fusion module is used to integrate multiple data types from the first device, including physiological data, operational data, voice data, and video data, to generate a comprehensive student learning status report;

[0015] A distributed edge computing node network is used for data preprocessing and preliminary analysis at edge nodes close to the first device;

[0016] The dynamic anatomy model generator is used to generate interactive dynamic human anatomy models in real time according to teaching needs. The model can dynamically change according to the students' operations and the teacher's instructions.

[0017] The virtual medical teaching scenario includes human anatomy models, pathology models, and surgical operation simulation medical teaching resources. Students can learn interactively in the virtual scenario, and teachers can monitor students' learning progress and provide guidance in real time.

[0018] As a further aspect of the present invention: the first device includes:

[0019] VR headsets are used to provide students with immersive virtual medical teaching scenarios;

[0020] Interactive controllers are used by students to operate and interact in virtual environments.

[0021] As a further embodiment of the present invention: the first device further includes:

[0022] Physiological data monitoring device, used to monitor students' physiological data in virtual medical teaching scenarios.

[0023] As a further aspect of the present invention: the second device includes:

[0024] The teacher control terminal is used by teachers to control the switching of virtual scenes, the display of teaching resources, and the feedback of student operations.

[0025] Display devices are used to show virtual medical teaching scenarios and students' operations.

[0026] As a further embodiment of the present invention: the second device further includes:

[0027] The real-time voice interaction module is used for teachers and students to conduct real-time voice communication in virtual medical teaching scenarios.

[0028] The video monitoring module allows teachers to monitor students' actions in a virtual environment via video, enabling them to provide timely guidance and correction.

[0029] As a further embodiment of the present invention: the multimodal data fusion module includes:

[0030] The physiological signal simulation unit is used to generate abnormal electrocardiogram and respiratory waveform data streams through bioelectric simulation algorithms;

[0031] The image 3D reconstruction unit is used to convert DICOM data into voxelized organ models that support force feedback penetration;

[0032] The operation trajectory comparison unit is used to perform spatiotemporal similarity analysis between trainees' actions and the expert database.

[0033] As a further embodiment of the present invention: the operation trajectory comparison unit further includes:

[0034] An expert motion feature database stores spatiotemporal encoded data of the motion trajectories of more than a set number of standard surgical instruments.

[0035] The Dynamic Time Warping (DTW) algorithm module eliminates comparison bias caused by different operation speeds;

[0036] The error heat map generator maps the deviation between the student's operation path and the expert data into a three-dimensional heat map.

[0037] As a further aspect of the present invention: the dynamic anatomical model generator includes: a real-time deformation physics engine and a hemodynamic simulator; the real-time deformation physics engine is used to calculate the critical value of tissue tearing based on the contact angle of the virtual instrument; the hemodynamic simulator is used to correlate vascular pressure parameters with a mathematical model of bleeding diffusion rate.

[0038] As a further embodiment of the present invention: the server further includes:

[0039] The data processing module is used to process and optimize the data in the virtual medical teaching scenario to improve the system's operating efficiency;

[0040] The student learning progress tracking module is used to record students' learning operations and progress in the virtual scene and generate learning reports.

[0041] The teacher teaching resource management module is used by teachers to upload, edit, and manage teaching resources in virtual medical teaching scenarios.

[0042] As a further aspect of the present invention, the virtual medical teaching scenario also includes:

[0043] The clinical case simulation module is used to simulate real clinical case scenarios, allowing students to perform diagnostic and treatment operations in a virtual environment.

[0044] The technical solution provided by this invention has the following beneficial effects:

[0045] This invention integrates multiple data types (physiological data, operational data, voice data, and video data, etc.) to provide teachers with a more comprehensive analysis of students' learning status, helping them to understand students' learning situations more accurately and thus provide more targeted guidance. Data preprocessing and preliminary analysis at edge nodes effectively reduce the server's computational burden, lower data transmission latency, and improve system response speed and operating efficiency, making it particularly suitable for maintaining system stability and smoothness when a large number of students are using the system simultaneously. Furthermore, it can generate interactive, dynamic human anatomy models in real time, simulating physiological processes such as organ movement and blood circulation, providing students with a more vivid and intuitive learning experience and enhancing their understanding and memorization of complex medical knowledge.

[0046] These or other aspects of the invention will become more apparent from the following description of embodiments. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a structural block diagram of a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0049] Figure 2 This is a structural block diagram of the first device in a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0050] Figure 3 This is a structural block diagram of the second device in a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0051] Figure 4 This is a block diagram of the server structure in a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0052] Figure 5 This is a block diagram of the multimodal data fusion module in a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0053] Figure 6 This is a block diagram of the dynamic anatomical model generator in a remote VR clinical medical teaching system according to an embodiment of the present invention.

[0054] In the diagram: First device-100, VR headset-101, interactive controller-102, physiological data monitoring device-103, Second device-200, teacher control terminal-201, display device-202, real-time voice interaction module-203, video monitoring module-204, server-300, multimodal data fusion module-301, distributed edge computing node network-302, dynamic anatomical model generator-303, data processing module-304, student learning progress tracking module-305, teacher teaching resource management module-306, physiological signal simulation unit-3011, image 3D reconstruction unit-3012, operation trajectory comparison unit-3013, real-time deformation physics engine-3031, hemodynamic simulator-3032. Detailed Implementation

[0055] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0057] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0058] Specifically, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0059] In one embodiment, see Figure 1 As shown, an embodiment of the present invention also provides a remote VR clinical medical teaching system, which includes a first device 100, a second device 200, and a server 300.

[0060] The first device 100 is used for students to enter a virtual medical teaching scenario through virtual reality (VR) devices.

[0061] See Figure 2 As shown, in some embodiments, the first device 100 includes:

[0062] VR Headset 101 is used to provide students with an immersive virtual medical teaching environment;

[0063] The interactive controller 102 is used by students to operate and interact in a virtual environment. It provides students with an immersive virtual medical teaching environment and convenient operation and interaction methods, enabling students to integrate more naturally into the virtual environment and enhance the fun and participation of learning.

[0064] In some embodiments, the first device 100 further includes:

[0065] The physiological data monitoring device 103 is used to monitor students' physiological data, such as heart rate and blood pressure, in the virtual medical teaching scenario and transmit the data to the server 300. Monitoring students' physiological data (such as heart rate and blood pressure) in the virtual medical teaching scenario and transmitting it to the server for analysis can promptly detect changes in students' physiological state during the learning process, prevent students from being affected by excessive tension or discomfort, and ensure students' learning safety.

[0066] The second device 200 is used by teachers to control the content and pace of the virtual medical teaching scenario.

[0067] See Figure 3 As shown, in some embodiments, the second device 200 includes:

[0068] The teacher control terminal 201 is used by teachers to control the switching of virtual scenes, the display of teaching resources, and the feedback of student operations.

[0069] Display device 202 is used to display the virtual medical teaching scenario and students' operation status. This allows teachers to flexibly control and monitor the virtual medical teaching scenario in real time, promptly identify students' learning problems and provide guidance, and facilitates the display of teaching content and feedback on student operations, thereby improving the interactivity and effectiveness of teaching.

[0070] In some embodiments, the second device 200 further includes:

[0071] The real-time voice interaction module 203 is used for real-time voice communication between teachers and students in a virtual medical teaching scenario. Real-time voice communication between teachers and students in a virtual medical teaching scenario can enhance the interaction and communication between teachers and students, enabling teachers to answer students' questions in a timely manner, and students to express their thoughts and confusions more clearly, thereby improving the interactivity and real-time nature of teaching.

[0072] The video monitoring module 204 allows teachers to monitor students' actions in a virtual environment via video, enabling them to provide timely guidance and correction. By monitoring students' actions in the virtual environment, teachers can promptly identify errors or deficiencies in their operations and provide corrections and guidance, ensuring that students learn under correct operating procedures and improving their practical skills.

[0073] See Figure 4 As shown, server 300 is used to store data of the virtual medical teaching scenario and interaction information between students and teachers, and communicates with the first device and the second device.

[0074] The server 300 also includes:

[0075] The multimodal data fusion module 301 is used to integrate multiple data types from the first device, including physiological data, operational data, voice data, and video data, to generate a comprehensive student learning status report.

[0076] The multimodal data fusion module 301 integrates various data types (physiological data, operational data, voice data, and video data, etc.) to provide teachers with a more comprehensive analysis of students' learning status, helping them to understand students' learning situation more accurately and thus provide more targeted guidance.

[0077] The distributed edge computing node network 302 is used to perform data preprocessing and preliminary analysis at edge nodes close to the first device, reducing the computational burden on the server 300, while reducing data transmission latency and improving system response speed. The distributed edge computing node network 302 performs data preprocessing and preliminary analysis at edge nodes, which can effectively reduce the computational burden on the server, reduce data transmission latency, and improve system response speed and operating efficiency. It is especially suitable for maintaining system stability and smoothness when a large number of students use it at the same time.

[0078] The dynamic anatomy model generator 303 is used to generate interactive dynamic human anatomy models in real time according to teaching needs. The model can dynamically change according to the student's operation and the teacher's instructions, such as simulating physiological processes such as organ movement and blood circulation. It can generate interactive dynamic human anatomy models in real time, simulating physiological processes such as organ movement and blood circulation, providing students with a more vivid and intuitive learning experience and enhancing their understanding and memory of complex medical knowledge.

[0079] The virtual medical teaching scenario includes medical teaching resources such as human anatomy models, pathology models, and surgical operation simulations. Students can learn interactively in the virtual scenario, and teachers can monitor students' learning progress and provide guidance in real time.

[0080] See Figure 5As shown, in some embodiments, the multimodal data fusion module 301 includes:

[0081] The physiological signal simulation unit 3011 is used to generate abnormal electrocardiogram and respiratory waveform data streams through bioelectric simulation algorithms.

[0082] The physiological signal simulation unit 3011 includes:

[0083] A bioelectric signal generator based on the Hodgkin-Huxley neuron model dynamically generates waveforms for arrhythmias such as atrial fibrillation and ventricular tachycardia.

[0084] The dynamic injection interface for pathological parameters allows the import of real patient ECG and PPG signals as training data sources.

[0085] A multi-physiological signal coupling engine was used to establish a nonlinear correlation model between respiratory rate and blood oxygen saturation fluctuations.

[0086] The image 3D reconstruction unit 3012 is used to convert DICOM data into voxelized organ models that support force feedback penetration.

[0087] Specifically, the image 3D reconstruction unit 3012 is implemented as follows:

[0088] The DICOM data deep learning segmentation module uses a 3D U-Net network to extract organ boundary features;

[0089] A voxel-to-mesh converter generates topology-optimized deformable surface models using the Marching Cubes algorithm;

[0090] Force feedback penetrates the computational layer, enabling real-time detection of tissue contact depth using GPU-accelerated Signed Distance Field instruments.

[0091] The operation trajectory comparison unit 3013 is used to perform spatiotemporal similarity analysis between the trainee's actions and the expert database.

[0092] Specifically, the operation trajectory comparison unit 3013 further includes:

[0093] An expert motion feature database stores spatiotemporal encoded data of the motion trajectories of more than a set number of standard surgical instruments.

[0094] The Dynamic Time Warping (DTW) algorithm module eliminates comparison bias caused by different operation speeds;

[0095] The error heat map generator maps the deviation between the student's operation path and the expert data into a three-dimensional heat map.

[0096] The multimodal data fusion module 301 also includes a newly added cross-modal synchronization controller, used to: establish a dynamic binding relationship between physiological signal frequencies and organ model motion phases; ensure millisecond-level synchronization of tactile feedback and visual distortion through a timestamp alignment mechanism; and trigger a 0.5-second virtual time dilation effect to prevent simulation distortion when the student's operation is too fast. This ensures that the virtual reality scene on the student's device and the teaching content on the teacher's device remain synchronized in real time during multimodal data interaction, including synchronization of multiple sensory modalities such as vision, hearing, and touch, to achieve a seamless interactive teaching experience.

[0097] The multimodal data fusion module 301 introduces a classic computational neuroscience model, enabling simulated waveforms to possess physiological reliability at the level of cell membrane ion channels. Combined with deep learning segmentation and GPU-accelerated SDF detection, it increases the speed of organ model generation to 3.2 times that of traditional methods. The DTW algorithm eliminates individual differences in operational rhythm, and the three-dimensional heat map intuitively presents the spatial distribution of technical defects. The time dilation mechanism resolves the inherent contradiction between the speed of physical simulation and human operational response.

[0098] The distributed edge computing node network 302 adopts: a bandwidth dynamic allocation protocol based on key surgical steps, prioritizing the transmission of force feedback and instrument collision data; and a breakpoint resume module that starts local motion pre-rendering cache when network latency exceeds 200ms.

[0099] Furthermore, the bandwidth dynamic allocation protocol is specifically implemented as follows:

[0100] In cardiac interventional procedures, catheter tip pressure feedback data (highest priority) and vessel wall deformation data are transmitted first.

[0101] In orthopedic procedures, priority is given to transmitting bone drill vibration frequency data (>500Hz sampling rate) and bone chip splatter particle effects;

[0102] Dynamic QoS classification strategy, automatically switching between TCP / UDP transport protocol combinations according to the operation stage.

[0103] Furthermore, the local pre-rendering caching mechanism of the breakpoint resume module includes: a block preloading mechanism based on the surgical procedure tree, which pre-caches the 3D organ model block of the next operation step; a tactile signal prediction compensator, which uses an LSTM neural network to predict the force feedback waveform within the next 500ms; and an emergency degradation mode, which switches to a low-precision collision detection mode when the network jitter exceeds 3 times / second.

[0104] The distributed edge computing node network 302 also includes a dedicated edge computing data compression unit. This unit is used to apply wavelet transform compression algorithm to tactile feedback data to achieve an 85% reduction in data volume while maintaining tactile frequency domain characteristics; to perform keyframe extraction compression on instrument motion trajectory data, retaining key points with curvature changes greater than 15°; and to implement multi-node collaborative redundant coding, allowing complete recovery of organ texture mapping data with a loss rate of <5%.

[0105] The distributed edge computing node network 302 implements intelligent classification of key data types (pressure feedback / vibration frequency) for different procedures (cardiac intervention / orthopedics), reducing the latency of core tactile data to within 8ms; the TCP / UDP hybrid transmission strategy improves network bandwidth utilization by 37% and ensures zero loss of high-priority data packets; based on historical force feedback waveforms, it predicts data for the next 500ms, and maintains an operational continuity rate of >92% within 1 second of network interruption.

[0106] See Figure 6 As shown, the dynamic anatomy model generator 303 includes: a real-time deformation physics engine 3031 and a hemodynamic simulator 3032; the real-time deformation physics engine 3031 is used to calculate the critical value of tissue tearing based on the contact angle of the virtual instrument; the hemodynamic simulator 3032 is used to correlate the vascular pressure parameters with the mathematical model of bleeding diffusion rate.

[0107] Furthermore, the specific implementation of the real-time deformation physics engine 3031 is as follows:

[0108] A hybrid physics solver that combines Position-Based Dynamics with finite element analysis algorithms;

[0109] Tissue characteristics were modeled in layers: the superficial skin was modeled using the hyperelastic Ogden model (μ = 20 kPa, α = 4.5), the muscle layer was modeled using the anisotropic transverse isotropic model, and the bone was modeled using the elastoplastic fracture mechanics model (yield stress > 80 MPa).

[0110] Furthermore, the enhanced features of the hemodynamic simulator include: real-time calculation of non-Newtonian blood fluid based on the Navier-Stokes equations; a coagulation factor dynamic influence module that automatically adjusts the blood viscosity coefficient according to platelet concentration; and a student misoperation response subsystem that activates jet bleeding simulation when the vascular puncture depth is >2mm.

[0111] The dynamic anatomy model generator 303 also includes an organ state transfer mechanism. This mechanism is used for the pathological feature transfer interface, mapping calcification / tumor features from real patient CT images to the virtual model; a trauma response logic library, defining the mapping relationship between different sharp object angles (30°-90°) and tissue damage area; and a blood flow-pressure feedback closed loop, where for every 10% increase in the student's compression hemostasis force error, the simulated bleeding volume increases by 23%.

[0112] The server 300 also includes:

[0113] The data processing module 304 is used to process and optimize the data in the virtual medical teaching scenario in order to improve the system's operating efficiency.

[0114] The student learning progress tracking module 305 is used to record students' learning operations and progress in the virtual scene and generate learning reports. This allows teachers to understand students' learning situation and adjust teaching strategies in a timely manner, while also providing students with a basis for self-assessment.

[0115] The Teacher Teaching Resource Management Module 306 is used by teachers to upload, edit, and manage teaching resources in virtual medical teaching scenarios. It facilitates teachers' uploading, editing, and management of teaching resources within these scenarios, enabling them to flexibly adjust teaching content according to teaching needs, enrich the teaching resource library, and improve the diversity and adaptability of teaching.

[0116] The server 300 also includes:

[0117] The student group management module 307 is used to group students so that they can conduct group discussions and collaborative learning in a virtual medical teaching scenario;

[0118] The group learning evaluation module 308 is used to evaluate and record the learning outcomes of groups.

[0119] In some embodiments, the server 300 further includes:

[0120] The physiological data analysis module 309 is used to analyze students' physiological data to determine whether students are in a state of excessive tension or discomfort, and to alert teachers or students when necessary. This analysis enables teachers to adjust their teaching pace and methods in a timely manner, providing personalized learning support and improving the relevance and effectiveness of teaching.

[0121] The virtual medical teaching scenario also includes:

[0122] The clinical case simulation module is used to simulate real clinical case scenarios, allowing students to perform diagnostic and treatment procedures in a virtual environment. This simulation enhances students' clinical practice and problem-solving abilities, providing them with a learning experience that is closer to actual clinical work.

[0123] The medical knowledge Q&A module allows users to ask students medical questions in a virtual setting, and then score and provide feedback on their answers. Asking students medical questions in a virtual setting and providing feedback on their answers allows for timely assessment of their learning progress, reinforces their medical knowledge, and simultaneously motivates them to learn actively and proactively.

[0124] The virtual medical teaching scenario also includes:

[0125] The virtual surgical instrument library provides students with a variety of virtual surgical instruments for use in simulated surgical scenarios. This allows students to become familiar with the operation methods and usage skills of surgical instruments in a virtual environment, improving their surgical skills and laying a foundation for their future participation in actual surgical procedures.

[0126] The surgical procedure assessment module evaluates students' actions in simulated surgical scenarios, including accuracy and standardization, and generates assessment reports. This allows for timely feedback on students' strengths and weaknesses, helping them identify and improve their procedures, thereby enhancing the standardization and accuracy of their surgical operations.

[0127] The server 300 also includes a student feedback collection module and a teaching effectiveness evaluation module.

[0128] The student feedback collection module is used to collect student feedback on the virtual medical teaching scenarios and content, so that teachers can optimize and improve teaching resources. Collecting student feedback on the virtual medical teaching scenarios and content allows teachers to understand students' needs and suggestions in a timely manner, providing a reference for teachers to optimize teaching resources and improve teaching methods, thereby improving the pertinence and adaptability of teaching.

[0129] The teaching effectiveness evaluation module is used to assess the overall teaching effectiveness of the remote VR clinical medical teaching system based on data such as student learning progress, operational evaluations, and feedback, and generates an evaluation report. This system provides teachers and education administrators with a comprehensive evaluation of teaching effectiveness, helping them understand the system's operation, adjust and optimize teaching strategies in a timely manner, and improve teaching quality and effectiveness.

[0130] This invention integrates multiple data types (physiological data, operational data, voice data, and video data, etc.) to provide teachers with a more comprehensive analysis of students' learning status, helping them to understand students' learning situations more accurately and thus provide more targeted guidance. Data preprocessing and preliminary analysis at edge nodes effectively reduce the server's computational burden, lower data transmission latency, and improve system response speed and operating efficiency, making it particularly suitable for maintaining system stability and smoothness when a large number of students are using the system simultaneously. Furthermore, it can generate interactive, dynamic human anatomy models in real time, simulating physiological processes such as organ movement and blood circulation, providing students with a more vivid and intuitive learning experience and enhancing their understanding and memorization of complex medical knowledge.

[0131] It should be understood that, as used herein, the singular form "a" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the associatedly listed items. The embodiment numbers disclosed above are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0132] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples. Within the framework of the invention, technical features of the above embodiments or different embodiments can be combined, and many other variations of different aspects of the invention exist, which are not provided in the details for the sake of brevity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the invention should be included within the protection scope of the invention.

Claims

1. A remote VR clinical medical teaching system, characterized in that, The system includes: a first device, a second device, and a server; The first device is used by students to enter a virtual medical teaching scenario through virtual reality equipment; The second device is used by teachers to control the content and pace of the virtual medical teaching scenario; The server is used to store data from the virtual medical teaching scenario and interaction information between students and teachers, and to communicate with the first and second devices. The server also includes: The multimodal data fusion module is used to integrate multiple data types from the first device, including physiological data, operational data, voice data, and video data, to generate a comprehensive student learning status report; A distributed edge computing node network is used for data preprocessing and preliminary analysis at edge nodes close to the first device; A dynamic anatomy model generator is used to generate interactive dynamic human anatomy models in real time according to teaching needs. The virtual medical teaching scenario includes human anatomy models, pathology models, and surgical operation simulation medical teaching resources.

2. The remote VR clinical medical teaching system as described in claim 1, characterized in that, The first device includes: VR headsets are used to provide students with immersive virtual medical teaching scenarios; Interactive controllers are used by students to operate and interact in virtual environments.

3. The remote VR clinical medical teaching system as described in claim 2, characterized in that, The first device also includes: Physiological data monitoring device, used to monitor students' physiological data in virtual medical teaching scenarios.

4. The remote VR clinical medical teaching system as described in claim 3, characterized in that, The second device includes: The teacher control terminal is used by teachers to control the switching of virtual scenes, the display of teaching resources, and the feedback of student operations. Display devices are used to show virtual medical teaching scenarios and students' operations.

5. The remote VR clinical medical teaching system as described in claim 4, characterized in that, The second device also includes: The real-time voice interaction module is used for teachers and students to conduct real-time voice communication in virtual medical teaching scenarios. The video monitoring module allows teachers to monitor students' actions in a virtual environment via video, enabling them to provide timely guidance and correction.

6. The remote VR clinical medical teaching system as described in claim 1, characterized in that, The multimodal data fusion module includes: The physiological signal simulation unit is used to generate abnormal electrocardiogram and respiratory waveform data streams through bioelectric simulation algorithms; The image 3D reconstruction unit is used to convert DICOM data into voxelized organ models that support force feedback penetration; The operation trajectory comparison unit is used to perform spatiotemporal similarity analysis between trainees' actions and the expert database.

7. The remote VR clinical medical teaching system as described in claim 6, characterized in that, The operation trajectory comparison unit further includes: An expert motion feature database stores spatiotemporal encoded data of the motion trajectories of more than a set number of standard surgical instruments. The Dynamic Time Warping (DTW) algorithm module eliminates comparison bias caused by different operation speeds; The error heat map generator maps the deviation between the student's operation path and the expert data into a three-dimensional heat map.

8. The remote VR clinical medical teaching system as described in claim 7, characterized in that, The dynamic anatomical model generator includes a real-time deformation physics engine and a hemodynamic simulator. The real-time deformation physics engine is used to calculate the critical value of tissue tearing based on the contact angle of the virtual instrument. The hemodynamic simulator is used to correlate vascular pressure parameters with the mathematical model of bleeding diffusion rate.

9. The remote VR clinical medical teaching system as described in claim 1, characterized in that, The server also includes: The data processing module is used to process and optimize the data in the virtual medical teaching scenario to improve the system's operating efficiency; The student learning progress tracking module is used to record students' learning operations and progress in the virtual scene and generate learning reports; The teacher teaching resource management module is used by teachers to upload, edit, and manage teaching resources in virtual medical teaching scenarios.

10. The remote VR clinical medical teaching system as described in claim 1, characterized in that, The virtual medical teaching scenario also includes: The clinical case simulation module is used to simulate real clinical case scenarios, allowing students to perform diagnostic and treatment operations in a virtual environment.

Images